JP7647461B2 - Information processing device, control device, program, waste treatment facility, and method for operating a waste treatment facility - Google Patents

Description

The present invention relates to an information processing device, a control device, a program, a waste treatment facility, and a method for operating a waste treatment facility.

Conventionally, in an effort to ensure stable combustion of waste put into a waste incinerator, the waste piled up in the waste pit is mixed to make its properties uniform beforehand, and then the waste is put into the incinerator through a waste chute for incineration. The waste is mixed by a crane operated by an operator based on visual inspection, or by controlling the crane through automatic control. In recent years, various methods have been investigated for more effective mixing by converting the state of the mixed waste in the waste pit, i.e., the degree of mixing, into digital data to make it visible.

Patent Document 1 discloses a garbage agitation state measuring device that aims to recognize the garbage agitation state in a garbage pit. The technology disclosed in Patent Document 1 is a technology that creates an agitation degree map that stores the number of times garbage moves in an actual garbage pit in order to grasp the actual garbage agitation state.

Patent Document 2 discloses a display device for the garbage agitation state in a garbage pit, which attempts to grasp the garbage agitation state in the garbage pit overall and visually. The technology disclosed in Patent Document 2 is a technology that represents the garbage agitation state by the garbage agitation degree, and displays the garbage agitation degree in the garbage pit area as a three-dimensional bar-shaped figure. The technology described in Patent Document 2 aims to verify crane operation by grasping the agitation state in the garbage pit overall and visually, and displaying the bucket movement trajectory in three dimensions.

Patent Document 3 discloses technology related to a garbage mixing evaluation system that evaluates the mixing state of garbage quality. The technology disclosed in Patent Document 3 is a technology that captures images of garbage in a garbage pit, calculates three-dimensional height information, binarizes the captured image and an image corrected from the three-dimensional height information, and evaluates the garbage mixing degree of each evaluation area from the binarized image in order to grasp the mixing state of garbage quality.

Patent No. 6381395 Patent No. 6440374 Patent No. 6457137

However, in the technologies disclosed in Patent Documents 1 to 3, images are extracted and the degree of mixing of the waste is determined without considering the height (level) of the waste piled up in the waste storage pit. This poses the problem that when actually mixing the waste with a crane, the difference in height of the waste can be too great depending on the address (section). This can make it difficult for the crane to grasp the waste, and can cause the grasping part, such as a bucket, to tip over. Furthermore, if the difference in height in the piled state of the waste becomes large, blind spots will occur when the storage pit is imaged to grasp the state of the waste, reducing the accuracy of the degree of mixing determination.

Therefore, there was a need to develop technology that could make the height and degree of mixing of waste in a storage pit for garbage and other waste approximately uniform, and maintain the height and degree of mixing of waste in an approximately uniform state.

The present invention has been made in consideration of these circumstances, and its purpose is to provide an information processing device, a control device, a program, a waste treatment facility, and a method for operating a waste treatment facility that can maintain a substantially uniform level of waste height and mixing in a storage pit.

In order to solve the above-mentioned problems and achieve the object, an information processing device according to one aspect of the present invention is an information processing device that includes a control unit that manages waste stored in a storage pit configured to store waste, and the control unit derives the height of the waste corresponding to a predetermined position in the storage pit based on measurement information of the height of the waste obtained from a sensor unit capable of measuring the height of the waste, determines a degree of mixing that indicates the degree of mixing of the waste based on image information captured by an image capture unit capable of capturing an image of the waste stored in the storage pit, derives an elevation difference between the height of the waste in the section and the height of the waste in an adjacent section adjacent to the section, and selects and outputs a section for holding the waste and a section for dumping the waste based on the determined degree of mixing and the derived elevation difference.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit determines the degree of mixing for each of the sections, selects a grasping section that is a section for grasping the waste from among the multiple sections in the storage pit based on the degree of mixing, and sets the selected grasping section as the section for grasping the waste when the height difference in the selected grasping section is equal to or greater than a preset grasping threshold.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit determines the degree of mixing for each of the sections, selects a discharge section from among the multiple sections in the storage pit as a section into which the waste is discharged based on the degree of mixing, and sets the selected discharge section as a section that holds the waste when the elevation difference in the selected discharge section is equal to or less than a preset discharge threshold.

In the information processing device according to one aspect of the present invention, in these configurations, the control unit excludes the selected section from the selection if the height difference in the selected section is less than a preset grip threshold or greater than a preset drop threshold.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit determines the degree of mixing using a mixing degree determination model, and the mixing degree determination model is a learning model generated by machine learning using annotated imaging information obtained from an imaging unit that images the waste in the storage pit as a learning input parameter, and a mixing degree set by an operator from the imaging information as a learning output parameter.

In one aspect of the present invention, in the information processing device described above, the sensor unit includes a distance sensor that emits electromagnetic waves toward the waste and measures the time from when the electromagnetic waves are emitted to when the electromagnetic waves reflected by the waste are received.

In one aspect of the present invention, in the information processing device described above, the sensor unit has a plurality of distance measuring sensors, and each of the plurality of distance measuring sensors is installed at a position where at least one of the plurality of electromagnetic waves emitted from the plurality of distance measuring sensors can reach any position on the top surface of the waste stored in the storage pit.

A control device according to one aspect of the present invention is a control device including an information processing device according to the above invention and a gripping unit control unit that controls a gripping unit that moves the waste stored in the storage pit by gripping and releasing, and the gripping unit control unit outputs an instruction signal to grip the waste in a section for gripping the waste output by the information processing device and to release the waste in a section for releasing the waste.

A program according to one aspect of the present invention causes a control unit of an information processing device that includes a control unit for managing waste stored in a storage pit configured to store waste to derive the height of the waste in correspondence with a predetermined position in the storage pit based on measurement information of the height of the waste obtained from a sensor unit capable of measuring the height of the waste, determine a degree of mixing that indicates the degree of mixing of the waste based on image information captured by an image capture unit capable of capturing an image of the waste stored in the storage pit, derive an elevation difference between the height of the waste in the section and the height of the waste in an adjacent section adjacent to the section, for each section set by dividing the area in the storage pit into a plurality of sections, and select and output a section for holding the waste and a section for dumping the waste based on the determined degree of mixing and the derived elevation difference.

A waste treatment facility according to one aspect of the present invention includes a control device according to the above invention, a storage pit for storing waste, and a gripping unit that can move the waste by gripping and releasing it under the control of the control device.

A method for operating a waste treatment facility according to one aspect of the present invention is a method for operating a waste treatment facility comprising: a storage pit configured to store waste and equipped with a sensor unit capable of measuring the height of the waste at a predetermined position and an imaging unit capable of imaging the waste; an information processing device equipped with a control unit for managing the waste stored in the storage pit; and a control device equipped with a gripping unit control unit for controlling a gripping unit that moves the waste stored in the storage pit by gripping and releasing, wherein the control unit controls the waste to correspond to a predetermined position in the storage pit based on measurement information of the height of the waste obtained from the sensor unit capable of measuring the height of the waste. The height of the objects is derived, and a degree of mixing indicating the degree of mixing of the waste is determined based on imaging information captured by an imaging unit capable of capturing images of the waste stored in the storage pit. For each section in which the area in the storage pit is divided into a number of sections, the height difference between the height of the waste in the section and the height of the waste in the adjacent section adjacent to the section is derived, and a section for holding the waste and a section for dumping the waste are selected and output based on the determined degree of mixing and the derived height difference, and the gripping unit control unit moves the waste based on the section for holding and the section for dumping output by the control unit.

The information processing device, control device, program, waste treatment facility, and waste treatment facility operation method according to the present invention make it possible to maintain the height and degree of mixing of waste in the storage pit at a substantially uniform level.

FIG. 1 is a block diagram showing a pit management system according to one embodiment of the present invention. FIG. 2 is a block diagram showing a pit management device according to an embodiment of the present invention. FIG. 3 is a plan view of a retention pit according to one embodiment of the present invention. FIG. 4 is a cross-sectional view of the storage pit taken along line IV-IV in FIG. FIG. 5 is a cross-sectional view of the storage pit taken along line VV in FIG. FIG. 6 is a plan view illustrating the compartments of a storage pit according to one embodiment of the present invention. FIG. 7 is a diagram for explaining the definition of the elevation difference for each divided area according to an embodiment of the present invention. FIG. 8 is a flow chart for explaining a method for operating a waste storage facility controlled by a management device according to an embodiment of the present invention. FIG. 9 is a cross-sectional view of a storage pit taken along line IV-IV in FIG. 3, in which four sensor units are provided.

One embodiment of the present invention will be described below with reference to the drawings. Note that in all the drawings of the embodiment below, the same or corresponding parts are given the same reference numerals. Furthermore, the present invention is not limited to the embodiment described below.

(Pit management system)
Fig. 1 shows a pit management system to which an information processing device according to an embodiment of the present invention is applied. As shown in Fig. 1, the pit management system 1 includes a pit management device 10, a waste storage facility 20, and a waste incineration facility 30, which are capable of communicating with each other via a network 2. The waste treatment facility 3 includes at least the waste storage facility 20 and the waste incineration facility 30. The pit management device 10 may be provided outside the waste treatment facility 3 and capable of communicating with the waste treatment facility 3 via the network 2, or may be a part of the waste treatment facility 3. The pit management device 10 may also be provided inside the waste storage facility 20, and the installation location is not limited.

Network 2 is configured by appropriately combining wired and wireless communications, and is composed of communication networks such as the Internet network and mobile phone network. Network 2 is composed of one or more combinations of, for example, dedicated lines, public communication networks such as the Internet, for example, LANs (Local Area Networks), WANs (Wide Area Networks), telephone communication networks such as mobile phones, public lines, and VPNs (Virtual Private Networks). The pit management device 10, waste storage facility 20, and waste incineration facility 30 are connected via network 2.

(Waste storage facility)
The waste storage facility 20 as a waste storage section includes a control section 21, a communication section 22, an imaging section 23, a sensor section 24, a gripping section 25, and a storage pit 26. The gripping section 25 is movably provided in the storage pit 26, and the imaging section 23 and the sensor section 24 are also provided therein. The gripping section 25 is controlled by the control section 21 based on a control signal transmitted from the control section 11 of the pit management device 10. The control section 21 may control the imaging section 23 and the sensor section 24 based on a control signal transmitted from the control section 11. Note that the control section 11 of the pit management device 10 may directly control the imaging section 23, the sensor section 24, and the gripping section 25.

Specifically, the control unit 21 includes a processor having hardware such as a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and an FPGA (Field-Programmable Gate Array), and a main memory unit such as a RAM (Random Access Memory) and a ROM (Read Only Memory) (none of which are shown). The control unit 21 controls the imaging unit 23, the sensor unit 24, and the grip unit 25 based on control signals input from the pit management device 10 via the communication units 13 and 22, in accordance with various programs stored in the main memory unit such as the RAM or ROM.

The communication unit 22 is, for example, a LAN interface board, a wired communication circuit for wired communication, or a wireless communication circuit for wireless communication. The LAN interface board, the wired communication circuit, and the wireless communication circuit are connected to the network 2. The communication unit 22, which functions as a transmitter and receiver, is connected to the network 2 and communicates with the pit management device 10.

The imaging unit 23 has, for example, imaging cameras 231 and 232. The imaging unit 23 is configured to be able to image the waste 26a in the storage pit 26, particularly the surface, using the imaging cameras 231 and 232. The imaging unit 23 may be configured to be able to image the waste 26a gripped by the bucket 253, for example, by imaging the bucket 253 of the gripping unit 25. The imaging unit 23 images the state of the waste 26a in the storage pit 26, i.e., the state of the waste 26a, and transmits the captured image data as imaging information to the pit management device 10 via the communication unit 22. The imaging unit 23 may transmit the captured image data of the waste 26a as imaging information to the pit management device 10 via the communication unit 22.

The sensor unit 24 is configured to include multiple distance measuring sensors, for example, two distance measuring sensors 241, 242 such as LiDAR (Laser Imaging Detection and Ranging). In addition to distance measuring sensors, the sensor unit 24 may also be configured to include, for example, a laser sensor, an infrared sensor, or a combination of these sensors. The distance measuring sensors 241, 242 are configured to be able to measure the distance from the installed position to the surface of the waste 26a in the storage pit 26. The distance measuring sensors 241, 242 can measure the distance from the distance measuring sensors 241, 242 to the waste 26a in association with two-dimensional position information (x, y) in the horizontal plane of the storage pit 26. The sensor unit 24 having the distance measuring sensors 241, 242 transmits the measured distance to the pit management device 10 via the communication unit 22.

The gripping unit 25 grips and moves the waste 26a stored in the storage pit 26. The bucket 253, which serves as an opening/closing unit, is capable of gripping the waste 26a. The crane 252, which serves as a moving unit, is configured to be movable by connecting the bucket 253. The crane 252 is provided with a load meter 251. The load meter 251 is configured to be capable of measuring the weight of the waste 26a gripped by the bucket 253. Data on the weight of the waste 26a measured by the load meter 251 (load data) is transmitted to the pit management device 10 via the communication unit 22.

Parameters related to the work operation of the crane 252, such as the current position of the crane 252 in the two dimensions (x, y) in the horizontal plane of the storage pit 26 above the storage pit 26, the movement path, the movement range, and the movement speed, are sequentially transmitted from the gripping unit 25 to the pit management device 10 via the control unit 21 and the communication unit 22. Similarly, parameters related to the work operation of the bucket 253, such as the current position of the bucket 253 in three dimensions (x, y, z), the open time, the closed time, the number of times it is opened and closed, and the amount of opening, are sequentially transmitted from the gripping unit 25 to the pit management device 10 via the control unit 21 and the communication unit 22.

The storage pit 26 is a pit that can temporarily store waste 26a. The waste 26a in the storage pit 26 is grasped by the grasping part 25 and supplied to the incinerator 33 of the waste incineration facility 30, where it is incinerated.

(Waste incineration facility)
The waste incineration facility 30 as the waste incineration unit includes a combustion control device (ACC) 31, a sensor unit 32, and an incinerator 33. The combustion control device 31 controls the combustion air amount, the cooling air amount, the waste feeder feed speed, and the grate feed speed as the operation amounts of the respective operation terminals based on the setting of a predetermined operation amount reference value. The incinerator 33 as the waste incinerator includes a furnace in which the waste 26a is burned, a waste inlet into which the waste 26a is input, and a boiler (none of which are shown). The sensor unit 32 is composed of, for example, a thermometer and a pressure gauge provided at various locations. The internal state of the incinerator 33 and various physical quantities such as pressure and speed in the facilities related to the incinerator 33, specifically, in the power generation facilities for generating electricity, measured by the sensor unit 32, are output from the sensor unit 32 as sensor information. The sensor information output from the sensor unit 32 is supplied to the combustion control device 31 as a parameter. The combustion control device 31 controls the combustion of the incinerator 33 based on the input parameters.

(Pit management device)
Fig. 2 shows details of the pit management device 10 in Fig. 1. The pit management device 10 as an information processing device shown in Fig. 2 includes a control unit 11, a storage unit 12, a communication unit 13, and an input/output unit 14. The control unit 11 and the communication unit 13 are physically similar to the control unit 21 and the communication unit 22 described above, respectively.

The storage unit 12 is composed of a storage medium selected from a volatile memory such as RAM, a non-volatile memory such as ROM, an erasable programmable ROM (EPROM), a hard disk drive (HDD, Hard Disk Drive), and a removable medium. Note that the removable medium is, for example, a Universal Serial Bus (USB) memory, or a disk recording medium such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray (registered trademark) disc (BD). The storage unit 12 may also be composed of a computer-readable recording medium such as an externally attachable memory card.

The memory unit 12 can store an operating system (OS), various programs, various tables, various databases, and the like for executing the operations of the pit management device 10. These various programs can also be recorded on computer-readable recording media such as hard disks, flash memory, CD-ROMs, DVD-ROMs, and flexible disks for widespread distribution. The control unit 11 loads the programs stored in the memory unit 12 into the working area of the main memory unit, executes them, and can realize functions that meet a specified purpose by controlling each component through the execution of the programs.

The memory unit 12 stores waste level information 121, type information 122, pile information 123, and a mixture degree determination model 124. The waste level information 121, type information 122, and pile information 123 are all stored in the memory unit 12 as a searchable database.

The waste level information 121 is information on the level of the waste 26a stored in the storage pit 26. The waste level information 121 includes measurement information such as the level (height, waste level z) of the waste 26a associated with a two-dimensional coordinate in the storage pit 26, i.e., a predetermined position (x, y) such as an address. The waste level information 121 may include mapping data including point cloud data representing the shape of the surface of the waste 26a. When the waste 26a in the storage pit 26 is managed as a plurality of units divided into, for example, a predetermined rectangular parallelepiped shape, specifically, for example, a cube shape of 500 mm square, the waste level information 121 may include history information such as the volume, bulk density, weight, and storage days of each unit.

The type information 122 includes information on the type of waste 26a in the storage pit 26. The type information 122 includes, for example, but is not limited to, information on the type determined by assuming that the waste 26a carried in is one type when the waste collection vehicle carries the waste 26a into the storage pit 26. The type information 122 includes type information for each predetermined position defined by three-dimensional coordinates (x, y, z) in the storage pit 26 after the waste 26a is transferred by the gripper 25. In other words, the type information 122 includes information on the type of waste 26a determined in association with the three-dimensional position coordinates (x, y, z) of the surface of the waste 26a when the surface shape of the waste 26a is measured.

The deposition information 123 is information generated by associating the waste level information 121 obtained as described above with the type information 122 of the determined waste 26a. In other words, the deposition information 123 is three-dimensional map information generated by associating the type information 122 captured by the imaging unit 23 and determined by the type determination unit 112 with three-dimensional coordinates (x, y, z) based on the waste level information 121 of the stored waste 26a. This allows the control unit 11 to accumulate, as deposition information 123, information on not only the surface of the waste 26a stored in the storage pit 26, but also information on the waste 26a buried below the surface.

The deposition information 123 may include work area information regarding the work area in the storage pit 26. The work area information includes information regarding areas such as the carry-in area (carry-in area), the transfer area (transfer area), and the input area (input area). The work area information may also include information on the crushing area (crushing area), which is an area where the waste 26a is crushed by the bucket 253 or the like. This makes it possible for the control unit 11 to separate the deposition information for each of the carry-in area, transfer area, input area, and crushing area.

The mixture degree determination model 124 is composed of a learning model in which the image information acquired from the imaging unit 23 that images the waste 26a in the storage pit 26 is used as an input parameter, and the mixture degree indicating the degree of the mixed state of the waste 26a is used as an output parameter. The learning model is also called a learned model or simply a model. The mixture degree may be a discontinuous numerical value or rank, or a continuous numerical value or level. The mixture degree determination model 124 is generated by machine learning such as supervised learning in which the image information acquired and annotated from the imaging unit 23 that images the waste 26a in the storage pit 26 is used as an input parameter for learning, and the mixture degree set by the worker based on the image information is used as an output parameter for learning. Note that various types of machine learning, such as deep learning using a neural network, can be used for the machine learning.

In this embodiment, the functions of the level derivation unit 111, type determination unit 112, pile information generation unit 113, crane control unit 114, mixture degree determination unit 115, and learning unit 116 are performed by executing the various programs loaded by the control unit 11. The various programs also include programs that realize artificial intelligence and learned models that can realize the processing according to this embodiment.

The level derivation unit 111 can set an area representing the position of the waste 26a stored in the storage pit 26. Specifically, for example, the horizontal size of the bucket 253 can be used as a reference to divide the area on a plane parallel to the bottom surface of the storage pit 26 and set an address (x, y). It is also possible to set areas such as a carrying-in area, a transfer area, and a throw-in area based on the address. The carrying-in area 261 is an area where garbage is carried in from a garbage collection vehicle (packer vehicle), and may be divided by a partition wall. The transfer area is a transfer area where the waste 26a is transferred from the carrying-in area by a crane installed in the storage pit 26. The throw-in area is an throw-in area where the waste 26a to be thrown into the incinerator 33 is stored.

The level derivation unit 111 can calculate or determine the height (waste level z) of the waste 26a in the storage pit 26 based on at least one, preferably multiple, pieces of distance information supplied from the sensor unit 24. That is, the level derivation unit 111 derives the height of the waste 26a, i.e., the waste level z, based on the distance to the waste 26a at a predetermined position (x, y) input from the sensor unit 24. This allows the level derivation unit 111 to map at least the surface of the waste 26a in the storage pit 26 in three-dimensional coordinates (x, y, z). In addition to the sensor unit 24, the crane rope length of the bucket 253 can be used to accumulate information on the height of the waste 26a at a predetermined position (x, y), thereby making it possible to derive the waste level z as the waste level z associated with the predetermined position (x, y). The method of deriving the waste level z is not necessarily limited to the above-mentioned method, and various methods can be adopted.

Next, a method for deriving the waste level z by the level deriving unit 111 will be described. Figures 3, 4, and 5 are diagrams showing the storage pit 26 according to this embodiment. Figure 3 is a plan view of the storage pit 26 from above. Figures 4 and 5 are cross-sectional views of the storage pit 26 taken along lines IV-IV and V-V in Figure 3, respectively.

In the example shown in FIG. 3, for example, the horizontal size of the bucket 253 is used as a reference, and the plane parallel to the bottom surface of the storage pit 26 is divided and the addresses (x, y) are set. Note that various methods of division within the storage pit 26 can be adopted, and are not limited to the example shown in FIG. 3. Furthermore, for the address (x, y), when the size of the bucket 253 is used as a reference, both variables x and y become discrete, but they may be set continuously. Note that the waste 26a is put into the storage pit 26 toward the carry-in area 261 after opening the carry-in door arranged in the storage pit 26. The carry-in door is, for example, an openable/closable type, and multiple doors are arranged at predetermined intervals along the side wall of the storage pit 26. The waste 26a brought into the waste storage equipment 20 of the waste treatment facility 3 is put into the storage pit 26 through one of the carry-in doors. The waste 26a in the storage pit 26 is transferred, stirred, and dumped into the dump hopper 331 by the three-axis drive of the crane 252.

At least one imaging camera, preferably multiple cameras, is disposed as the imaging unit 23 near the upper waist wall of the storage pit 26. When multiple cameras are installed, it is preferable to install them in a position where there is a low possibility of a blind spot occurring, for example, on the side of the waste 26a loading area 261, in order to suppress the occurrence of blind spots of the cameras. In Figs. 3 and 4, two imaging cameras 231 and 232 are provided. The imaging cameras 231 and 232 are configured to have a camera such as a CCD camera or a CMOS camera, but are not necessarily limited to these. The imaging cameras 231 and 232 are configured to be able to identify the color tone of the waste 26a, which changes depending on the type of waste 26a. The imaging cameras 231 and 232 may be installed, for example, on the upper part of the inner wall of the storage pit 26, on a wall that can capture the waste 26a in the storage pit 26. The imaging cameras 231 and 232 may be one, or three or more. The imaging unit 23 can use various devices as long as they are capable of detecting the type of waste 26a.

In the storage pit 26, a plurality of distance measuring sensors, for example two distance measuring sensors 241, 242, which constitute the sensor unit 24, are installed. It is preferable, but not limited to, that each of the distance measuring sensors 241, 242 is installed at a position where at least one of the emitted electromagnetic waves can reach any position on the surface of the waste 26a stored in the storage pit 26. Specifically, for example, the distance measuring sensors 241, 242 are installed near the upper waist wall of the storage pit 26, near the respective imaging cameras 231, 232. Note that the installation locations of the distance measuring sensors 241, 242 are not necessarily limited, but the installation positions and the number of sensors to be installed can be set based on the directivity of the distance measuring sensors 241, 242 and the reach of the light.

As shown in Fig. 4, in the storage pit 26, the waste level z can be measured by the distance measuring sensors 241, 242 when the waste 26a is stored. That is, the distance from each of the distance measuring sensors 241, 242 installed at the upper part of the two corners on the carry-in area 261 side of the storage pit 26 to a predetermined position P on the surface of the waste 26a can be measured. In this case, the waste level z at a predetermined position (x, y) can be measured by the distance l ₁ between the distance measuring sensor 241 and the predetermined position P and the emission angle θ ₁ of the electromagnetic wave from the distance measuring sensor 241. On the other hand, the waste level z at a predetermined position (x, y) can be measured by the distance l ₂ between the distance measuring sensor 242 and the predetermined position P and the emission angle θ ₂ of the electromagnetic wave from the distance measuring sensor 242. The level deriving unit 111 of the pit management device 10 can derive the waste level z at a given location (x, y) in the storage pit 26 based on the position information acquired from these distance measuring sensors 241 , 242 .

5, the distance from each of the distance measuring sensors 241, 242 to a predetermined position _P0 on the surface of the waste 26a can be measured in the storage pit 26. The distance measuring sensor 241 measures the waste level z at a predetermined location (x, y) based on the distance _l10 to the predetermined position _P0 and the emission angle _θ1 of the electromagnetic wave from the distance measuring sensor 241, and can acquire point cloud data of the predetermined position _P0 . It is also possible to derive the waste level z based on the distances _l10 and _l20 from the distance measuring sensors 241, 242 to the predetermined position _P0 of the waste 26a. In this way, the level derivation unit 111 can instantly and continuously derive the waste level z of the waste 26a at the predetermined position P in the storage pit 26 based on the distance information and angle information from the distance measuring sensors 241, 242.

As shown in FIG. 5, the crane 252 used in the waste storage facility 20 is provided above the storage pit 26 equipped with the input hopper 331 of the incinerator 33. The crane 252 is arranged so that it can travel along the traveling rails 256 on the crane girder 254. The crane 252 is arranged so that a bucket 253 capable of holding a predetermined amount of waste 26a can be raised and lowered by winding up and down a wire rope on a crab 255 arranged so that it can move laterally on the crane girder 254.

5, for example, the electromagnetic waves emitted from the distance sensor 241 may be blocked by the waste 26a piled up high, resulting in a blind spot. In this case, the level derivation unit ₁₁₁ of the control unit ₁₁ can perform a masking process on the blocked portion. That is, when the level derivation unit 111 determines that the position of the object measured by the sensor unit 24 is not the predetermined position of the waste 26a to be measured, it can perform a masking process to mask the portion that is not the predetermined position.

When determining whether or not to perform masking processing, for example, the following method can be adopted. That is, when electromagnetic waves are emitted from the distance measuring sensors 241, 242 toward the waste 26a, and the electromagnetic waves are used to scan the surface of the waste 26a piled up in the storage pit 26 to measure the distance, if the measured distance during scanning changes by a predetermined threshold or more, masking processing can be performed on that part. In this case, the object irradiated with the electromagnetic waves after the distance changes by a predetermined threshold or more is likely not the waste 26a at the predetermined position to be measured, but the blocked waste 26a or another object. This allows the level derivation unit 111 to determine the part to be masked based on the information on the distance from the sensor unit 24. The level derivation unit 111 may determine whether or not to perform masking processing and the range of the masking processing by reading a learning model or a learned model obtained by machine learning using teacher data.

After the masking process is performed, the waste level z1 at the predetermined location ( _x1 , _y1 ) can be measured _based on the distance _l21 between the distance measuring sensor 242 and the predetermined position P1 and the emission angle _θ2 of the electromagnetic wave from the distance measuring sensor _242. That is, the point cloud data of the predetermined position _P1 can be acquired by the distance measuring sensor 242. Note that the above-mentioned case where the electromagnetic wave emitted from the distance measuring sensor 241 is blocked before reaching the predetermined position P is not limited to the case where it is blocked by the waste 26a. That is, even when it is blocked by various objects present in the storage pit 26, such as the bucket 253, the level derivation unit 111 performs the masking process on the obtained point cloud data.

When the distance measuring sensors 241 and 242 according to this embodiment are composed of LiDAR, for example, the electromagnetic waves used are typically near-infrared or infrared. As a result, although it is difficult for cameras to capture images in dark places, the distance measuring sensors 241 and 242 can measure distances even in dark places. In addition, the dimensions of objects that can be detected by the distance measuring sensors 241 and 242 are greater than or equal to the wavelength. The electromagnetic waves emitted from the distance measuring sensors 241 and 242 have a high light flux density, high coherence, and an extremely short wavelength, so that they are easily reflected even when irradiated on a small object. Therefore, the distance measuring sensors 241 and 242 can easily measure the time from the time the electromagnetic waves are emitted toward the waste 26a to the time the electromagnetic waves are reflected by the waste 26a. As a result, the distance measuring sensors 241 and 242 can easily measure the distance to the surface or surface layer of the waste 26a stored in the storage pit 26 with high accuracy. In addition, by measuring distances using distance measuring sensors 241, 242 such as LiDAR, time response can be made on the order of milliseconds, shortening the measurement interval and allowing the distance from the distance measuring sensors 241, 242 to the waste 26a to be measured almost continuously. Therefore, for example, the movement and swing of the bucket 253 can be tracked, so that the swing prevention of the bucket 253 can be optimized.

In addition, when the bucket 253 is moving in the storage pit 26, if there is only one distance measuring sensor, the electromagnetic waves of one of the distance measuring sensors 241, 242 may be blocked by the bucket 253 and not irradiated to the waste 26a at the specified position. Even in this case, the electromagnetic waves emitted from one of the distance measuring sensors 241, 242 can be irradiated to the waste 26a without being blocked by the bucket 253. Therefore, even when the bucket 253 is moving in the storage pit 26, the distance to the waste 26a can be measured from at least one of the distance measuring sensors 241, 242, so that the possibility of measuring the waste level z at the specified position is improved compared to the case where only one distance measuring sensor is used. In other words, even when the bucket 253 is moving, the height of the waste 26a in the storage pit 26 can be measured instantly with a higher probability by the sensor unit 24.

As described above, the upper layer of waste 26a can be measured by at least one of distance measuring sensors 241, 242. This allows the waste level z to be measured over the entire surface of waste 26a in storage pit 26 along the horizontal plane of storage pit 26, i.e., over all addresses (x, y).

The type determination unit 112 determines the type (also called classification) of the waste 26a brought into the receiving area 261. In addition, when the waste 26a is mixed or reloaded by the crane 252, the type determination unit 112 determines the type and state of the waste 26a after mixing or reloading based on the imaging information provided by the imaging cameras 231, 232. In this way, the type determination unit 112 generates type information. The type information includes information on the type and state of the waste 26a.

The deposition information generating unit 113 associates the type information 122 of the waste 26a determined by the type determining unit 112 with three-dimensional coordinates (x, y, z) based on the waste level information 121 of the waste 26a at a predetermined position obtained based on the measurement by the sensor unit 24. This allows the three-dimensional map of the waste 26a to be continuously generated. In addition, since the point cloud data of the waste 26a in the storage pit 26 can be obtained from the distance measuring sensors 241 and 242, the shape of the surface of the waste 26a can be obtained instantly or intermittently. This allows the deposition information generating unit 113 to generate deposition information 123 including point cloud data that maps the surface shape of the waste 26a. The deposition information 123 includes three-dimensional mapping information of the surface shape of the waste 26a. The generated deposition information is stored in the deposition information 123 of the storage unit 12. The deposition information generating unit 113 may generate the deposition information 123 discontinuously and intermittently at predetermined time intervals.

The mixture degree determination unit 115, which serves as a mixture degree determination means, determines the mixture degree of the waste 26a stored in the storage pit 26 based on the type and state of the waste 26a acquired from the type determination unit 112 and the image information acquired from the imaging cameras 231 and 232. The mixture degree of the waste 26a is determined by inputting the image information of the waste 26a in the storage pit 26 captured as an input parameter to the mixture degree determination model 124, and outputting the mixture degree as an output parameter. The mixture degree is a degree that is defined in advance by, for example, the color and fineness of the waste 26a and is comparable to each other. The mixture degree determination unit 115 can measure the mixture degree of the waste 26a for each predetermined section based on the position coordinates (x, y) along the horizontal plane of the storage pit 26, for example, for each rectangular area (hereinafter, section) divided at a predetermined interval along the x direction and a predetermined interval along the y direction. The information on the mixture degree for each output position coordinate (x, y) is stored in the memory unit 12 as the pile information 123.

The learning unit 116, which serves as a learning means, can derive a mixture degree determination model 124 by machine learning using image information of the waste 26a captured in the storage pit 26 as a learning input parameter and a mixture degree set for the acquired image information as a learning output parameter. The generated mixture degree determination model 124 is supplied to the learning unit 116 from the computer that performed the machine learning and is stored in the memory unit 12.

In this embodiment, the crane control unit 114, which serves as the gripping unit control unit, outputs instruction signals to drive the crane 252 on three axes to grip the waste material 26a at the desired position with the bucket 253, and to scatter the gripped waste material 26a, and transmits these to the control unit 21. The control unit 21 controls the crane 252 and bucket 253 of the gripping unit 25 based on the received instruction signals. Note that the crane 252 may also be controlled directly by the crane control unit 114.

The crane control unit 114 can perform transfer based on the acquired waste level information 121 and pile information 123 including information on the degree of mixing. Here, the control of the gripper 25 by the crane control unit 114 according to this embodiment, in particular the control of transfer, is described. Figure 6 is a plan view for explaining the compartments of the storage pit 26 according to this embodiment. Figure 7 is a diagram for explaining the definition of the elevation difference for each compartment according to this embodiment.

As shown in FIG. 6, in this embodiment, sections S are set at predetermined positions (x, y) along the horizontal plane (xy plane) of the storage pit 26, which is divided at predetermined intervals in the x direction and at predetermined intervals in the y direction. In the example shown in FIG. 6, the storage pit 26 is divided into 11 sections in the x direction and 20 sections in the y direction, resulting in a total of 220 rectangular sections S. In addition, to define the position of the section S, the center of the section S can be set as a predetermined position P (x, y), but the vertex of the section S may also be set at the predetermined position P, and is not limited thereto.

Section S is an area of the storage pit 26 along a horizontal plane, and can be set based on, for example, the horizontal size of the bucket 253 driven by the crane 252 of the gripper 25, but is not limited to this. Here, the adjacent section adjacent to section S is section _S1 . The adjacent section _S1 is three surrounding sections when section S is in a corner, five surrounding sections when section S is located along an outer wall, and eight surrounding sections in other cases.

As shown in Fig. 7, waste 26a is piled up in each of the sections S and _S1 . When waste 26a is carried in or transferred, a height difference Δh occurs between the amount of piled up waste 26a in the section S, for example, between the waste level Z of the section S and the waste level _Z1 of the adjacent section S1. In this embodiment, the height difference Δh is defined by the following formula (1) based on the waste level Z in the section S and the waste level _Z1 in the section _S1 .
Δh=Z−Z ₁ …(1)

From formula (1), Δh>0 (positive) when Z> _Z1 , and Δh<0 (negative) when Z< _Z1 . The waste level Z of the section S and the waste level _Z1 of the section _S1 can each be selected as a representative value of the waste level z in the sections S and _S1 . Here, as the representative value, for example, the largest or smallest waste level z in each of the sections S and _S1 can be adopted, the average value of the waste level z in the sections S and _S1 can be adopted, or the smallest waste level z can be adopted when the pile-up state is concave and the largest waste level z can be adopted when the pile-up state is convex. It is also possible to adopt the waste levels Z and _Z1 that have the largest absolute value of Δh (|Δh|=|Z- _Z1 |) as the representative value of the waste level _z in the adjacent sections S and S1. The crane control unit 114 can perform the transshipment of the waste 26a based on the height difference Δh and the degree of mixing defined as above. The control of the transfer of waste material 26a by the crane control unit 114 will be described in detail later.

In addition, for example, when moving from a predetermined position _P0 to a predetermined position _P1 (see FIG. 5), it is also possible to derive a moving path that allows the bucket 253 to avoid the top of the waste 26a. The crane control unit 114 moves the crane 252 based on the derived moving path. This makes it possible to shorten the lifting length of the bucket 253 and improve the moving efficiency of the crane 252 compared to the conventional method in which, for example, when moving from a predetermined position _P0 to a predetermined position _P1 , the bucket 253 of the gripper 25 is lifted to a position higher than the top of the waste 26a before moving it. For example, when the waste 26a is only to be moved sideways, the waste 26a can be moved by minimizing the winding of the wire rope that lifts the bucket 253. This makes it possible to move the bucket 253 at an optimal height according to the purpose of processing the waste 26a, such as mixing or reloading.

In addition, when waste 26a is discharged from the bucket 253, the discharge height can be changed to match the waste level z at the address (x, y) where waste 26a is to be discharged, so that the bucket 253 is not hoisted up more than necessary. In other words, when the control unit 21 automatically operates the gripping unit 25, the crane 252 and bucket 253 can be moved at a height that can avoid the pile of waste 26a that is created when the gripping unit 25 is piled up. Therefore, unnecessary operations of the gripping unit 25 can be reduced, so that the automatic operation of the gripping unit 25 can be performed efficiently and the operating rate can be reduced.

Furthermore, by accumulating and updating the pile information 123, the control units 11 and 21 can always derive and control the necessary height for the bucket 253 to grasp and dump the waste 26a based on the latest pile information 123. By constructing a learning model to be applied to the crane control unit 114 through machine learning by the control units 11 and 21, particularly the learning unit 116, it becomes possible to automatically control the gripping unit 25 including the crane 252 and bucket 253. Therefore, the crane control unit 114 can move the crane 252 and bucket 253 to an appropriate height and along an appropriate movement path in accordance with the purpose of the operation of the gripping unit 25. Note that various types of machine learning can be adopted for the machine learning, such as deep learning using a neural network, reinforcement learning, or deep reinforcement learning.

The input/output unit 14 can be composed of, for example, a touch panel display or a speaker microphone. The input/output unit 14 as an input means includes an interface that inputs various information transmitted from, for example, the imaging unit 23 or the sensor unit 24 installed in the waste storage facility 20 through the communication unit 22 and outputs the information to the control unit 11. The information may be transmitted from the imaging unit 23 or the sensor unit 24 to the input/output unit 14 by wired communication or wireless communication. The input/output unit 14 also includes a user interface such as a keyboard, input buttons, a lever, a touch panel for manual input superimposed on a display such as a liquid crystal display, or a microphone for voice recognition. The input/output unit 14 is configured to be able to input predetermined information to the control unit 11 by an operator or the like operating the input/output unit 14. The input/output unit 14 as an output means displays an image of the waste storage facility 20 in the storage pit 26 on the display monitor, displays characters and figures on the screen of the touch panel display, and outputs sound from the speaker, according to the control by the control unit 11. That is, the input/output unit 14 is configured to be able to notify predetermined information to the outside. The input and output sections of the input/output unit 14 may be configured separately.

(Operation method of waste treatment facility)
Next, a method of operating the waste storage facility 20, which is a waste treatment facility according to this embodiment, will be described. Figure 8 is a flow chart for explaining a method of operating the waste storage facility 20 controlled by the pit management device 10 according to this embodiment. Note that step ST1 is a process performed by an operator, and steps ST2 to ST15 are processes based on the control of the pit management device 10. Note that in the following description, information is transmitted and received between the respective components via the communication units 13, 22 and the network 2, but a detailed description of this point will be omitted.

As shown in FIG. 8, first, in step ST1, the worker performs preparations. That is, in step ST1, the worker installs at least one imaging camera 231, and preferably multiple imaging cameras 231, 232 as shown in FIG. 3, in a predetermined position in the storage pit 26, for example, near the upper waist wall of the storage pit 26. Note that it is preferable to install the imaging cameras 231, 232 in a location that avoids blind spots as much as possible.

Next, the process proceeds to step ST2, where the control unit 11 of the pit management device 10 controls the imaging unit 23 via the control unit 21 of the waste storage facility 20 to capture an image of the waste 26a in the storage pit 26. The imaging unit 23 generates imaging information of the waste 26a and transmits it to the pit management device 10. The level derivation unit 111 identifies the position (x, y) of the captured waste 26a based on the imaging information provided by the imaging unit 23.

Next, proceeding to step ST3, the type determination unit 112 of the control unit 11 determines the type and state of the captured waste 26a based on the imaging information supplied from the imaging unit 23, and stores the type information 122 in the storage unit 12. In addition, the pile information generation unit 113 generates pile information 123 by corresponding the generated type information 122 to the position (x, y) of the section S (hereinafter referred to as the address (x, y)) and stores the pile information 123 in the storage unit 12. This allows the control unit 11 to distinguish the type and state of the waste 26a by corresponding it to the address (x, y) of the section S. After the pile information 123 is generated, the mixture degree determination unit 115 of the control unit 11 inputs the imaging information acquired from the imaging unit 23 to the mixture degree determination model 124 to generate pile information 123 including the mixture degree corresponding to the address (x, y) of the section S. The mixture degree determination unit 115 stores the pile information 123 including the mixture degree corresponding to the address (x, y) of the section S in the storage unit 12.

Next, the process proceeds to step ST4, where the level derivation unit 111 measures the waste level z of the waste 26a. It is preferable to measure the waste level z continuously, but it may be intermittently. The control unit 21 controls the sensor unit 24 to measure the irradiation angle θ and irradiation distance l when irradiating the waste 26a in the storage pit 26 with electromagnetic waves from the distance measurement sensor 241, etc., to measure the waste level z of the waste 26a. The level derivation unit 111 acquires the measured waste level z and associates it with the address (x, y). The pile information generation unit 113 performs mapping processing of the upper surface of the waste 26a in the storage pit 26 based on the measurement value of the waste level z associated with the address (x, y), and generates point cloud data P (x, y, z) of the waste 26a. The pile information generating unit 113 associates the point cloud data P(x, y, z) with the type and state of the waste 26a to generate pile information 123 and store it in the storage unit 12. Note that the processes of steps ST2 to ST4 described above are continuously and repeatedly executed.

Next, the process proceeds to step ST5, where the level derivation unit 111 of the control unit 11 acquires the deposition information 123 including the degree of mixing, and selects the section S (address (x, y)) (see FIG. 7) in the storage pit 26 that has the lowest degree of mixing. Note that if there are multiple sections S with the lowest degree of mixing, the level derivation unit 111 selects any one of the multiple sections S.

Next, the process proceeds to step ST6, where the level derivation unit 111 derives the height difference Δh between the waste level Z of the selected section S and the waste level _Z1 of the section _S1 adjacent to the section S. The height difference Δh of the section S is derived for one section S by the number of adjacent sections _S1 . That is, the height difference Δh is derived in three, five, or eight ways according to the position (x, y) of the section S, but is not limited thereto. The level derivation unit 111 selects the height difference Δh having the largest absolute value (|Δh|) of the height difference Δh from among the derived multiple height differences Δh. Next, the level derivation unit 111 compares the selected height difference Δh with a gripping threshold. Here, the gripping threshold is a preset threshold at which the waste 26a can be gripped, and is a negative value.

The process proceeds to step ST7, where the level derivation unit 111 determines whether the selected height difference Δh is less than the gripping threshold. If the level derivation unit 111 determines that the selected height difference Δh is less than the gripping threshold (step ST7: Yes), the process proceeds to step ST8. If the height difference Δh is less than the gripping threshold, the absolute value of the height difference Δh (|Δh|) is greater than the absolute value of the gripping threshold. That is, the waste level z in the selected section S is lower than the absolute value of the gripping threshold compared to the waste level z of the adjacent section S _1. In other words, the pile state of the waste 26a is such that the selected section S is more depressed than the adjacent section S ₁ by the absolute value of the gripping threshold, and it is not preferable to transfer the waste 26a to another section by reloading. Therefore, the process proceeds to step ST8, where the level derivation unit 111 executes a process of excluding the section S selected in step ST5 from the gripping section. Then, the process returns to step ST5.

In step ST5, the level derivation unit 111 selects the least mixed section from among the sections in the storage pit 26 other than section S that was excluded from the gripping section in the same manner as described above, and executes steps ST6 and ST7. Steps ST5 to ST8 are repeatedly executed until the level derivation unit 111 determines in step ST7 that the selected height difference Δh is equal to or greater than the gripping threshold.

On the other hand, if the level derivation unit 111 determines in step ST7 that the selected height difference Δh is not less than the gripping threshold (step ST7: No), the process proceeds to step ST9. If the height difference Δh is not less than the gripping threshold, i.e., is equal to or greater than the gripping threshold, the absolute value of the height difference Δh (|Δh|) is smaller than the absolute value of the gripping threshold. That is, the waste level z in the selected section S is lower than the waste level z in the adjacent section S ₁ , but is not lower than the absolute value of the gripping threshold. In other words, the pile state of the waste 26a is such that the selected section S is not recessed to a depth equal to the absolute value of the gripping threshold compared to the adjacent section S _1. In step ST9, the level derivation unit 111 sets the section S selected in step ST5 as the gripping section S. The level derivation unit 111 stores information on the selected gripping section S as waste level information 121 in the storage unit 12. In addition, the level derivation unit 111 excludes the set gripping section S from the dropping section.

Next, the process proceeds to step ST10, where the level derivation unit 111 of the control unit 11 acquires the pile information 123 including the degree of mixing, and selects the section S (address (x, y)) with the lowest degree of mixing other than the gripping section S set in step ST9 in the storage pit 26. Thereafter, the process proceeds to step ST11, where the level derivation unit 111 derives the height difference Δh between the waste level Z of the selected section S and the waste level _Z1 of the section _S1 adjacent to the section S, as in step ST6. The level derivation unit 111 selects the height difference Δh with the largest absolute value (|Δh|) of the height difference Δh from among the derived multiple height differences Δh. Next, the level derivation unit 111 compares the selected height difference Δh with the discharge threshold. Here, the discharge threshold is a threshold based on a pre-set convex pile state, and is a threshold that can be judged to be undesirable as a section S for discharging waste 26a when the height difference Δh with the adjacent section _S1 is greater than the discharge threshold.

The process proceeds to step ST12, where the level derivation unit 111 determines whether the selected height difference Δh is greater than the discharge threshold. If the level derivation unit 111 determines that the selected height difference Δh is greater than the discharge threshold (step ST12: Yes), the process proceeds to step ST13. If the height difference Δh is greater than the discharge threshold, the absolute value of the height difference Δh (|Δh|) is also greater than the absolute value of the discharge threshold. That is, the waste level z in the selected section S is higher than the discharge threshold and its absolute value compared to the waste level z of the adjacent section S _1. In other words, the piled-up state of the waste 26a in the selected section S is piled up more than the absolute value of the discharge threshold and is convex compared to the adjacent section S _1. If the waste 26a is dumped into this section S, it will pile up even more, so that the piled-up state of the waste 26a in the storage pit 26 will become more uneven, and dumping the waste 26a is not preferable. Therefore, in step ST13, the level derivation unit 111 executes a process of excluding the section S selected in step ST10 from the released sections, and then returns to step ST10.

In step ST10, the level derivation unit 111 selects the least mixed section from among the sections other than section S that was excluded from the gripping section in the storage pit 26 in the same manner as described above, and executes steps ST11 and ST12. Steps ST9 to ST13 are repeatedly executed until the level derivation unit 111 determines in step ST12 that the selected height difference Δh is equal to or less than the release threshold.

On the other hand, if the level derivation unit 111 determines in step ST12 that the selected height difference Δh is equal to or less than the discharge threshold (step ST12: No), the process proceeds to step ST14. If the height difference Δh is equal to or less than the discharge threshold, the waste level z in the selected discharge section S is not higher than the waste level z of the adjacent section _S1 by the discharge threshold and its absolute value. Therefore, in step ST14, the level derivation unit 111 sets the section S selected in step ST10 as the discharge section S. The level derivation unit 111 stores information about the selected discharge section S in the memory unit 12 as waste level information 121.

Next, proceeding to step ST15, the crane control unit 114 reads out the waste level information 121 from the memory unit 12 and acquires information on the gripping section S and the release section S selected by the level derivation unit 111. The crane control unit 114 controls the gripping unit 25 to grip the waste 26a in the acquired gripping section S with the bucket 253, moves the bucket 253 to the position of the release section S, and releases the waste 26a. As a result, the crane control unit 114 can transfer the waste 26a from the section S with a low degree of mixing to another section S with a low degree of mixing to substantially equalize the degree of mixing, and can perform the task of transferring the waste 26a from the section S with a relatively high waste level z to the section S with a relatively low waste level z. In this way, the operation of the waste storage facility 20 is performed by the pit management device 10. Steps ST2 to ST15 are repeatedly performed while the waste storage facility 20 is in operation.

(Modification)
9, four imaging cameras 231, 232, 233, and 234 are provided at the four corners of the upper part of the storage pit 26, while four distance measurement sensors 241, 242, 243, and 244 can be provided near the imaging cameras 231 to 234. In this case, the blind spot of the imaging camera 231 can be imaged by the imaging camera 234, and the blind spot of the imaging camera 234 can be imaged by the imaging camera 231. In addition, the blind spot of the distance measurement sensor 241 can be measured by the distance measurement sensor 244, and the blind spot of the distance measurement sensor 244 can be measured by the distance measurement sensor 241.

5, the waste level z at a given location (x, y) is measured by the distance measuring sensor 243 _based on the distance _l30 to the given position P0 and the emission angle _θ2 of the electromagnetic wave from the distance measuring sensor 243, and the point cloud data of the given position _P0 can be acquired by the distance measuring sensor 243. It is also possible to derive the waste level z based on the distances _l30 and _l40 from the distance measuring sensors 243 and 244 to the given position _P0 of the waste 26a. In other words, the point cloud data P(x, y, z) of the given position P can be acquired with high accuracy by the distance measuring sensors 243 and 244.

In the modified example, imaging cameras 231-234 are provided at the four corners of the upper part of the outer wall of the storage pit 26, and distance measurement sensors 241-244 are provided at the four corners of the upper part of the outer wall of the storage pit 26, thereby making it possible to reduce the occurrence of areas that cannot be imaged, so-called blind spots, caused by waste 26a.

By installing the distance measuring sensors 241-244 at the top of the four corners of the storage pit 26, the upper layer of the waste 26a can be measured by at least one of the distance measuring sensors 241-244. This makes it possible to measure the waste level z of the surface of the waste 26a stored in the storage pit 26 over the entire surface along the horizontal plane of the storage pit 26, i.e., across all addresses (x, y). In addition, since point cloud data of the waste 26a in the storage pit 26 can be obtained, it is possible to instantly measure the surface shape of the waste 26a and generate deposition information 123 including point cloud data in which the surface shape of the waste 26a is mapped.

5, the waste level z1 at a given location ( _x1 , _y1 ) can be measured by the distance measuring sensor 243 based on the distance _{l31 between} the distance measuring sensor 243 and the given position _P0 and the emission angle θ2 of the electromagnetic wave from the distance measuring sensor 243, thereby obtaining point cloud data _for the given position _P1 . In this case, even if the electromagnetic wave emitted from the distance measuring sensor 244 does not reach the given position _P1 , the waste level _z1 at the given position _P1 can be derived based on the distance _l31 , and point cloud data can be obtained.

In addition, by providing the distance measuring sensors 241-244 at the four corners of the planar rectangular storage pit 26, the likelihood that the electromagnetic waves emitted from at least one of the distance measuring sensors 241-244 can be irradiated onto the waste 26a without being blocked by the bucket 253 is further improved. This further improves the accuracy of the measurement of the waste level z by the sensor unit 24, and further improves the accuracy of the generation of point cloud data.

According to the embodiment described above, blind spots can be reduced in the image information of the waste 26a in the storage pit 26 captured and generated by the imaging unit 23, improving the accuracy of measuring the degree of mixing of the waste 26a. When the accuracy of the degree of mixing is improved, it becomes easier to select a method of transferring waste 26a in the storage pit 26 to make the degree of mixing of the waste 26a approximately uniform, so that the so-called garbage quality can be made uniform, and stable combustion can be achieved when the waste 26a is fed into the incinerator 33 and burned. This makes it easier to control the amount of boiler steam, thereby realizing a stable supply of electricity.

In addition, according to one embodiment, the waste 26a can be easily grasped by the bucket 253 and tipping over of the bucket 253 can be suppressed, which leads to a reduction in the operating time of the gripping unit 25 and realizes efficient operation. Furthermore, the waste level z of the waste 26a can be made substantially uniform within the storage pit 26, which reduces the movement of the bucket 253 in the gripping unit 25 in the vertical direction (z direction) and reduces energy consumption in the waste treatment facility 3. In other words, the waste level z of the waste 26a in the storage pit 26 can be made substantially uniform, and the degree of mixing of the waste 26a can be maintained substantially uniform within the storage pit 26.

Although one embodiment of the present invention has been specifically described above, the present invention is not limited to the above-described embodiment, and various modifications based on the technical concept of the present invention are possible. For example, the numerical values given in the above-described embodiment are merely examples, and numerical values different from these may be used as necessary, and the present invention is not limited by the description and drawings that form part of the disclosure of the present invention according to this embodiment.

For example, in the embodiment described above, at least one of the at least one, preferably multiple, imaging cameras 231-234 constituting the imaging unit 23 may be provided, for example, at the bottom of the crane girder 254. It is preferable that at least one imaging camera 231-234 is configured to be able to capture an image of the entire surface of the waste 26a. In this case, it is also possible to dispose the camera, for example, in approximately the center of the storage pit 26 excluding the input hopper 331.

For example, in the embodiment described above, the section S in the storage pit 26, which is the reference for transfer and is selected by the level derivation unit 111 to derive the elevation difference Δh, and the section S in which the degree of mixing is measured are made to be a common section, but this is not necessarily limited to being a common section. For example, it is possible to make the size of the section in which the degree of mixing is measured smaller than the size of the section S in which the elevation difference Δh is derived, or conversely, to make the size of the section S in which the elevation difference Δh is derived smaller than the size of the section in which the degree of mixing is measured.

In addition, when artificial intelligence is used in the above-described embodiment, deep learning using a neural network is used as an example of machine learning, but machine learning based on other methods may be performed. For example, other supervised learning such as support vector machines, decision trees, naive Bayes, and k-nearest neighbors may be used. Also, semi-supervised learning may be used instead of supervised learning.

In addition, in one embodiment, the "unit" described above can be read as a "circuit" or the like. For example, a control unit can be read as a control circuit.

Note that in the explanation of the flowcharts in this specification, the order of processing between steps is clearly indicated using expressions such as "first," "then," and "continue." However, the order of processing required to implement this embodiment is not uniquely determined by these expressions. In other words, the order of processing in the flowcharts described in this specification can be changed as long as there are no contradictions.

Further advantages and modifications may be readily derived by those skilled in the art. The broader aspects of the disclosure are not limited to the specific details and representative embodiments shown and described above. Thus, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and equivalents thereof.

1 Pit management system 2 Network 3 Waste treatment facility 10 Pit management device 11, 21 Control unit 12 Memory unit 13, 22 Communication unit 14 Input/output unit 20 Waste storage facility 23 Imaging unit 24, 32 Sensor unit 25 Grip unit 26 Storage pit 26a Waste 30 Waste incineration facility 31 Combustion control device 33 Incinerator 111 Level derivation unit 112 Type determination unit 113 Heap information generation unit 114 Crane control unit 115 Mixing degree determination unit 116 Learning unit 121 Waste level information 122 Type information 123 Heaping information 124 Mixing degree determination model 231, 232, 233, 234 Imaging camera 241, 242, 243, 244 Distance measurement sensor 251 Load meter 252 Crane 253 Bucket 254 Crane girder 255 Crab 256 Travel rail 261 Loading area 331: Input hopper

Claims (9)

An information processing device including a control unit for managing waste stored in a storage pit configured to store the waste,
The control unit is
deriving a height of the waste in correspondence with a predetermined position of the storage pit based on measurement information of the height of the waste obtained from a sensor unit capable of measuring the height of the waste;
A degree of mixing indicating a degree of mixing state of the waste is determined based on imaging information captured by an imaging unit capable of capturing an image of the waste stored in the storage pit;
The area within the storage pit is divided into a plurality of sections, and for each section, a height difference between the height of the waste in the section and the height of the waste in an adjacent section adjacent to the section is derived;
The degree of mixing is determined for each of the sections, and a holding section which is a section for holding the waste and a release section which is a section for releasing the waste are selected from a plurality of sections in the storage pit based on the degree of mixing;
When the height difference in the selected gripping section is equal to or greater than a preset gripping threshold, the selected gripping section is selected as a section for gripping the waste, and is output;
When the elevation difference in the selected dump section is equal to or less than a preset dump threshold, the selected dump section is selected as a section for dumping the waste and output.
Information processing device. The control unit is
The information processing device of claim 1, wherein if the elevation difference in the gripping section is less than a predetermined gripping threshold, the gripping section is excluded from the section in which the waste is gripped, and if the elevation difference in the release section is greater than a predetermined release threshold , the release section is excluded from the section in which the waste is released . The control unit is
determining the degree of mixing using a mixing degree determination model;
The information processing device according to claim 1 or 2, wherein the mixing degree determination model is a learning model generated by machine learning using annotated imaging information obtained from an imaging unit that images the waste in the storage pit as a learning input parameter, and a mixing degree set by an operator from the imaging information as a learning output parameter . The information processing device according to claim 1 , wherein the sensor unit includes a distance measuring sensor that emits electromagnetic waves toward the waste and measures the time from when the electromagnetic waves are emitted to when the electromagnetic waves reflected by the waste are received. the sensor unit has a plurality of distance measuring sensors,
An information processing device as described in any one of claims 1 to 4, wherein each of the multiple distance measuring sensors is installed at a position where at least one of the multiple electromagnetic waves emitted from the multiple distance measuring sensors can reach any position on the top surface of the waste stored in the storage pit. An information processing device according to any one of claims 1 to 5 ;
A control device comprising: a gripping unit control unit that controls a gripping unit that moves the waste stored in the storage pit by gripping and releasing the waste;
The gripping unit control unit is
a control device that outputs an instruction signal to grip the waste in a section for gripping the waste output by the information processing device, and to release the waste in a section for releasing the waste. A control unit of an information processing device includes a control unit for managing waste stored in a storage pit configured to be able to store the waste,
deriving a height of the waste in correspondence with a predetermined position of the storage pit based on measurement information of the height of the waste obtained from a sensor unit capable of measuring the height of the waste;
A degree of mixing indicating a degree of mixing state of the waste is determined based on imaging information captured by an imaging unit capable of capturing an image of the waste stored in the storage pit;
The area within the storage pit is divided into a plurality of sections, and for each section, a height difference between the height of the waste in the section and the height of the waste in an adjacent section adjacent to the section is derived;
The degree of mixing is determined for each of the sections, and a holding section which is a section for holding the waste and a release section which is a section for releasing the waste are selected from a plurality of sections in the storage pit based on the degree of mixing;
When the height difference in the selected gripping section is equal to or greater than a preset gripping threshold, the selected gripping section is selected as a section for gripping the waste, and is output;
When the elevation difference in the selected dump section is equal to or less than a preset dump threshold, the selected dump section is selected as a section for dumping the waste and output.
A program to make that happen. A control device according to claim 6 ;
a storage pit for storing waste;
a gripping unit that is capable of moving by gripping and releasing the waste under the control of the control device. a storage pit configured to store waste and equipped with a sensor unit capable of measuring the height of the waste at a predetermined position and an imaging unit capable of imaging the waste;
an information processing device including a control unit that manages the waste stored in the storage pit, and a control device including a gripping unit control unit that controls a gripping unit that moves the waste stored in the storage pit by gripping and releasing the waste;
A method for operating a waste treatment facility comprising:
The control unit:
deriving a height of the waste in correspondence with a predetermined position of the storage pit based on measurement information of the height of the waste obtained from a sensor unit capable of measuring the height of the waste;
A degree of mixing indicating a degree of mixing state of the waste is determined based on imaging information captured by an imaging unit capable of capturing an image of the waste stored in the storage pit;
The area within the storage pit is divided into a plurality of sections, and for each section, a height difference between the height of the waste in the section and the height of the waste in an adjacent section adjacent to the section is derived;
The degree of mixing is determined for each of the sections, and a holding section which is a section for holding the waste and a release section which is a section for releasing the waste are selected from a plurality of sections in the storage pit based on the degree of mixing;
When the height difference in the selected gripping section is equal to or greater than a preset gripping threshold, the selected gripping section is selected as a section for gripping the waste, and is output;
When the elevation difference in the selected discharge section is equal to or less than a preset discharge threshold, the selected discharge section is selected as a section for discharging the waste and outputted;
The gripping portion control portion is
A method for operating a waste treatment facility, comprising the steps of: moving the waste based on the section to be grasped and the section to be released output by the control unit.

Images