JP7499347B2 - Condition monitoring system, condition monitoring device, condition monitoring method, and computer program - Google Patents

Description

The present invention relates to a condition monitoring system, a condition monitoring device, a condition monitoring method, and a computer program.

In recent years, blowers have been used for aeration purposes in wastewater treatment facilities, etc., for transporting powder in powder processing equipment, etc. A turbo blower, which is one type of blower, includes an impeller and a motor that drives the impeller to rotate, and is configured to transport gas such as air by rotating the impeller when driven by the motor (see, for example, Patent Documents 1 to 3).

JP 2012-236164 A JP 2015-182036 A JP 2016-185513 A

A turbo blower includes components such as a motor that rotates an impeller, an inverter that supplies driving power to drive the motor, and a cooling fan that cools the inverter, and has a mechanism that automatically stops operation of the turbo blower if an abnormality caused by a component failure is detected. For example, if the cooling fan that cools the inverter fails, the inverter cannot be cooled and a temperature abnormality occurs in the inverter. If the turbo blower detects a temperature abnormality in the inverter, it stops operation of the device itself.

As described above, in the past, if an abnormality associated with a component failure was detected, it was possible to stop the operation of the blower, but there was no way to infer failure or deterioration of the component.

An object of the present invention is to provide a condition monitoring system, a condition monitoring device, a condition monitoring method, and a computer program that are capable of estimating failure or deterioration of a component that constitutes a blower.

A status monitoring system according to one embodiment of the present invention comprises a communication device that transmits operating data of a blower, and a status monitoring device that acquires the operating data of the blower transmitted from the communication device and monitors the status of the blower based on the acquired operating data, in which the communication device comprises a first transmission unit that transmits the operating data of the blower recorded in a first period, and a second transmission unit that transmits the operating data of the blower recorded in a second period shorter than the first period in response to the occurrence of an event, and the status monitoring device comprises an acquisition unit that acquires the operating data of the first period and the operating data of the second period transmitted from the communication device, an estimation unit that analyzes the acquired operating data of the second period and estimates the status of the blower, and an output unit that outputs the estimation result by the estimation unit.

A status monitoring device according to one embodiment of the present invention acquires operation data of a blower transmitted from a communication device and estimates a status of the blower based on the acquired operation data.The status monitoring device comprises an acquisition unit that acquires operation data of the blower recorded in a first period transmitted from the communication device and operation data of the blower recorded in a second period shorter than the first period and transmitted from the communication device in response to the occurrence of an event, an estimation unit that analyzes the acquired operation data of the second period and estimates the status of the blower, and an output unit that outputs the estimation result by the estimation unit.

A status monitoring method according to one aspect of the present invention monitors the status of a blower based on operation data of the blower, by using a computer to acquire operation data of the blower recorded in a first period and operation data of the blower recorded in a second period shorter than the first period and transmitted in response to the occurrence of an event, analyzing the acquired operation data of the second period to estimate the status of the blower, and outputting the estimated result.

A computer program according to one embodiment of the present invention causes a computer to execute a process of acquiring blower operation data recorded in a first period and blower operation data recorded in a second period shorter than the first period and sent in response to an event occurrence trigger, analyzing the acquired second period operation data to estimate the state of the blower, and outputting the estimated result.

According to the present application, it is possible to estimate failure or deterioration of a component that constitutes a blower.

FIG. 1 is a schematic diagram showing a configuration of a status monitoring system. FIG. 2 is a schematic diagram showing a configuration of a blower. FIG. 2 is an explanatory diagram illustrating a configuration of a measurement system in the blower. FIG. 2 is a block diagram showing an internal configuration of a control device. 10 is a conceptual diagram illustrating an example of a driving history table provided in the cloud server. 2 is a block diagram showing an internal configuration of the state monitoring device; FIG. FIG. 4 is a schematic diagram showing an example of display of operation data. FIG. 11 is an explanatory diagram illustrating an example of an analysis method. 4 is a flowchart illustrating a procedure of a process executed by a control device. 4 is a flowchart illustrating a procedure of a process executed by a state monitor. FIG. 13 is a schematic diagram showing an example of output of an estimation result. FIG. 2 is a schematic diagram illustrating an example of the configuration of a learning model. 11 is a flowchart illustrating an estimation procedure using a learning model.

Hereinafter, the present invention will be described in detail with reference to the drawings showing embodiments thereof.
(Embodiment 1)
FIG. 1 is a schematic diagram showing the configuration of a status monitoring system. The status monitoring system according to the embodiment is a system for monitoring the status of a blower 1 based on operation data of the blower 1. The blower 1 is used for aeration purposes in a wastewater treatment facility, for example. Alternatively, the blower 1 may be used for transporting powder in a powder treatment device, or for drying or cooling an item. The status monitoring system includes a control device 100 mounted on the blower 1, and a status monitoring device 200 provided outside the blower 1. The control device 100 and the status monitoring device 200 are configured to be able to access a cloud server 300 via a communication network N such as the Internet.

The control device 100 controls the operation of the blower 1 and transmits (uploads) operation data obtained during operation of the blower 1 to the cloud server 300. In this embodiment, the control device 100 transmits operation data recorded at a first period (e.g., one-minute intervals) to the cloud server 300, and transmits operation data recorded at a second period (e.g., 0.1-second intervals) to the cloud server 300 when an event occurs, triggering the transmission of operation data recorded at a second period (e.g., 0.1-second intervals). Here, the events include a start event, a stop event, an abnormal stop event, and the like of the blower 1. When an event occurs, the control device 100 transmits to the cloud server 300 not only operation data obtained after the event occurs, but also operation data of a second period obtained during a predetermined period before and after the event occurs.

Note that starting the blower 1 refers to operating the motor 12 (see FIG. 2 ), which will be described later, to start the rotational drive of the impeller 11 (see FIG. 2 ). Stopping the blower 1 refers to stopping the operation of the motor 12 to stop the rotational drive of the impeller 11. In contrast, being in operation of the blower 1 refers to being in a state in which operation data can be transmitted to the cloud server 300, regardless of whether the motor 12 is operating (i.e., regardless of whether the impeller 11 is being rotationally driven).

The status monitoring device 200 appropriately acquires and analyzes the operation data of the blower 1 transmitted to the cloud server 300, and presents information based on the analysis results to the manager or the like of the blower 1. For example, the status monitoring device 200 generates a trend graph based on the operation data of a first period (e.g., at one-minute intervals) and presents the generated trend graph to the manager or the like. The status monitoring device 200 also estimates the cause of deterioration of the components that make up the blower 1 and the cause of an abnormal stop that has occurred in the blower 1 based on the operation data of a second period (e.g., at 0.1-second intervals), and presents the estimated result to the manager or the like.

In the present embodiment, the control device 100 transmits operation data to the cloud server 300, and the state monitoring device 200 acquires the operation data transmitted to the cloud server 300, but the control device 100 of the blower 1 may transmit operation data directly to the state monitoring device 200 without going through the cloud server 300. Also, in the present embodiment, the control device 100 mounted on the blower 1 and the state monitoring device 200 provided outside the blower 1 are used to monitor the state of the blower 1, but the control device 100 mounted on the blower 1 may analyze the operation data and present information based on the analysis results to an administrator, etc. In other words, the control device 100 and the state monitoring device 200 do not need to be separate entities, and may be integrally configured and mounted on the blower 1.

FIG. 2 is a schematic diagram showing the configuration of the blower 1. In this embodiment, the blower 1 is a turbo type blower (turbo blower). A turbo blower is a blower for sending gas such as air by the rotational motion of an impeller (blade). Such blowers are roughly classified into turbo type and positive displacement type. The turbo type includes axial type and centrifugal type, and the positive displacement type includes Roots type. In an axial type blower, the suction direction and the discharge direction are aligned in a straight line. Axial type blowers are suitable for low pressure and large volume of air, and are used for tunnel blowers and the like. On the other hand, in a centrifugal type blower, the suction direction and the discharge direction intersect at a right angle, and the blower sends gas such as air by utilizing centrifugal force. In a Roots type blower, two rotors are rotated in opposite directions in a housing in synchronization with each other, and the volume of the space surrounded by the housing and the rotors increases and decreases to send gas, and the blower is characterized by a stable air volume relative to the rotation speed because of the positive displacement type. Centrifugal and roots type blowers are used for aeration in wastewater treatment facilities, etc. The blower 1 shown as an example in Fig. 2 is a centrifugal type blower among turbo blowers, and the suction direction and the discharge direction intersect at approximately right angles. The blower 1 is not limited to a centrifugal type blower, and may be an axial type blower or a roots type blower.

The blower 1 includes an impeller 11 housed in an impeller housing 10, and a motor 12 that rotates and drives the impeller 11. In order to achieve high reliability and low maintenance, the blower 1 according to the embodiment employs an airfoil bearing (air bearing) 13 for a motor shaft 12A. The airfoil bearing 13 supports the motor shaft 12A without contacting it, but when the rotation speed of the motor 12 falls to 3000 min ^-1 or less during start-up or stop, the motor shaft 12A may come into contact with a top foil (not shown), which is a part of the airfoil bearing 13.

The blower 1 discharges gas introduced into the impeller housing 10 through the suction port 10A in a direction substantially perpendicular to the gas suction direction (upward in the example of FIG. 2) by centrifugal force generated by the rotational motion of the impeller 11. The gas discharged from the impeller housing 10 is discharged to the outside of the blower 1 through a discharge passage L1. The gas discharged to the outside of the blower 1 is sent to a predetermined supply destination such as a water tank through a gas supply line L2, which is partially shown in FIG. 2.

A bypass line L3 is connected to the middle of the discharge line L1, which allows a portion of the gas to be discharged to bypass. A blow-off line L4 and a cooling gas discharge line L5 are connected to this bypass line L3 via a blow-off valve BOV. A filter F is provided on the side of the blower 1 facing the suction port 10A of the impeller housing 10 to remove foreign matter such as dust and dirt contained in the gas to be sucked. The filter F is made of, for example, nonwoven fabric.

3 is an explanatory diagram illustrating the configuration of a measurement system in the blower 1. The blower 1 includes a drive device 120 that drives the motor 12 described above, and a control device 100 that controls the operation of the entire blower including the drive device 120.

The driving device 120 includes a converter 121 that converts a three-phase AC voltage or the like supplied from a commercial power source into a DC voltage and outputs the DC voltage, and an inverter 122 that converts the DC voltage input from the converter 121 into a voltage with a PWM (Pulse Width Modulation) waveform and outputs the voltage. The driving device 120 changes the voltage waveform of the inverter 122 in accordance with the required rotation speed of the motor 12, and adjusts the magnitude of the current supplied to the motor 12. Note that the driving device 120 may be configured to input the commercial power source directly to the inverter 122 without including the converter 121.

The blower 1 includes a current sensor S1 that measures the current supplied to the motor 12 (the output current of the inverter 122), and measures the output current of the inverter 122 as one piece of operation data for the blower 1. The measurement data of the current sensor S1 is provided to the control device 100. The blower 1 also includes a rotation speed sensor S2 that measures the rotation speed of the motor 12, and measures the rotation speed of the motor 12 as one piece of operation data for the blower 1. The measurement data of the rotation speed sensor S2 is provided to the control device 100. The output current of the inverter 122 may be calculated from the power consumption of the inverter 122, and the rotation speed of the motor 12 may be calculated from the output frequency of the inverter 122 and the number of poles of the motor 12.

The motor 12 of the blower 1 is driven by a current supplied from an inverter 122 of the drive unit 120 to rotate the impeller 11. The blower 1 is equipped with a temperature sensor S3 for measuring the temperature (suction temperature) of the gas sucked from the suction port 10A of the impeller housing 10, a flow rate sensor S4 for measuring the flow rate (suction gas amount) of the sucked gas, and a pressure sensor S5 for measuring the pressure (discharge pressure) of the gas discharged to the discharge passage L1, and these values may be measured as the operating data of the blower 1. The measurement data of the temperature sensor S3, the flow rate sensor S4, and the pressure sensor S5 are provided to the control device 100. The suction gas amount represents the amount of gas sucked from the suction port 10A per unit time. The gas amount may be a converted value under conditions of a temperature of 20°C, a humidity of 65%, and atmospheric pressure (industrial standard conditions), or a value converted into the gas amount under specific conditions, such as a converted value under conditions of a temperature of 0°C, a humidity of 0%, and atmospheric pressure (academic standard conditions).

The measurement data measured as the operation data of the blower 1 is not limited to the above. For example, the temperature of the motor 12, the temperature of the drive device 120, the power consumption of the blower 1, the filter loss in the filter F, the accumulated operation time, the accumulated startup time, etc. may be measured, and these measurement data may be provided to the control device 100.

4 is a block diagram showing the internal configuration of the control device 100. The control device 100 includes a control unit 101, a storage unit 102, an input unit 103, and a communication unit 104, and controls the operation of the blower 1 and outputs operation data obtained during operation of the blower 1 to the cloud server 300.

The control unit 101 includes, for example, a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM).
A control program that controls the operation of each of the above-mentioned hardware components is stored in the ROM. A CPU in the control unit 101 executes the control program stored in the ROM to cause at least a part of the control device 100 to function as a communication device in the present invention. Data generated during execution of the control program is temporarily stored in the RAM. The control unit 101 may also be equipped with functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when an instruction to start measurement is given until when an instruction to end measurement is given, and a counter that counts numbers.

The storage unit 102 includes a storage device using a hard disk, a flash memory, or the like. The storage unit 102 stores data necessary for various controls, driving data input through the input unit 103, and the like. In this embodiment, the driving data is periodically uploaded to the cloud server 300, so the storage unit 102 does not need to accumulate all the input driving data, and only needs to store driving data for a period going back a certain time (for example, one day or several minutes) from the latest time. For example, the storage unit 102 includes a first storage area (ROM) that stores one day's worth of driving data for a first cycle, and a second storage area (RAM) that stores several minutes' worth of driving data for a second cycle while overwriting it.

The input unit 103 includes a connection interface for connecting various sensors. The connection interface included in the input unit 103 may be a wired interface or a wireless interface. The sensors connected to the input unit 103 include, for example, a current sensor S1 that measures the output current of the inverter 122, a rotation speed sensor S2 that measures the rotation speed of the motor 12, a temperature sensor S3 that measures the suction temperature, a flow rate sensor S4 that measures the amount of suction gas, and a pressure sensor S5 that measures the discharge pressure. The control unit 101 acquires measurement data from the various sensors S1 to S5 through the input unit 103.

The communication unit 104 includes a communication interface for communicating with an external device. The communication interface included in the communication unit 104 is, for example, a communication interface conforming to a communication standard of a LAN (Local Area Network) used in WiFi (registered trademark) or Ethernet (registered trademark). Alternatively, the communication interface may be a communication interface conforming to a communication standard such as Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, or LTE (Long Term Evolution). In this embodiment, the control device 100 is connected to a communication network N through the communication unit 104 and is configured to be able to communicate with the cloud server 300 via the communication network N.

Furthermore, the control device 100 may include an operation unit that receives instructions or operations from a manager of the blower 1, a display unit that displays information to be notified to the manager of the blower 1, and the like.

In this embodiment, the control device 100 transmits the operation data of the blower 1 (measurement data of various sensors S1 to S5) to the cloud server 300. More specifically, after the operation of the blower 1 starts, the control device 100 records the operation data at a first period (e.g., one-minute intervals) and transmits the recorded operation data to the cloud server 300 at an appropriate timing. The control device 100 may transmit the operation data to the cloud server 300 every time it records the operation data at the first period, or may transmit the operation data of the first period for a predetermined time period to the cloud server 300 all at once. In addition, when an event occurs, the control device 100 transmits the operation data of a predetermined period (e.g., three minutes) including the start time of the event out of the data recorded at the second period (e.g., 0.1 second intervals) to the cloud server 300. The control device 100 transmits the operation data to the cloud server 300 after completing the recording of the operation data of the second period related to the event, for example. The start time of the event may be given by an administrator of the blower 1 or may be determined by the control unit 101 based on, for example, the output of the current sensor S1.

The cloud server 300 stores in a driving history table the driving data of the first cycle and the driving data of the second cycle received from the control device 100 via the communication network N. Fig. 5 is a conceptual diagram showing an example of a driving history table provided in the cloud server 300. The driving history table provided in the cloud server 300 is composed of a first driving history table 301A that stores the driving data of the first cycle and a second driving history table 301B that stores the driving data of the second cycle.

The first operation history table 301A stores operation data of a first period (e.g., 1 minute intervals) of the blower 1. The second operation history table 301B stores operation data of a second period (e.g., 0.1 second intervals) of the blower 1, which is transmitted in response to the occurrence of an event as a trigger. The operation data includes the current supplied to the motor 12 (the output current of the inverter 122), the rotation speed of the motor 12, the suction temperature of the blower 1, the amount of suction gas of the blower 1, the discharge pressure of the blower 1, etc.

The first operation history table 301A stores long-term operation data measured during operation of the blower 1, whereas the second operation history table 301B stores short-term and detailed operation data for a predetermined period for each event (e.g., 3 minutes before and after the event occurs). For example, if a startup event occurs in the blower 1 at 12:00 on August 1, 2020, operation data at 0.1 second intervals from 11:59 to 12:02 is stored in the second operation history table 301B.

6 is a block diagram showing the internal configuration of the status monitoring device 200. The status monitoring device 200 is a dedicated or general-purpose computer, and includes a control unit 201, a storage unit 202, a communication unit 203, an operation unit 204, and a display unit 205. The status monitoring device 200 acquires operation data from the cloud server 300, and estimates the status of the blower 1 by analyzing the acquired operation data.

The control unit 201 includes, for example, a CPU, a ROM, and a RAM. The ROM included in the control unit 201 stores a control program that controls the operation of each of the above-mentioned hardware components. The CPU in the control unit 201 executes the control program stored in the ROM and various computer programs stored in a storage unit 202 (described later) to control the operation of each of the hardware components, thereby causing the status monitoring device 200 to function as the status monitoring device of the present invention. The RAM included in the control unit 201 temporarily stores data used during the execution of calculations.

In the present embodiment, the control unit 201 is configured to include a CPU, a ROM, and a RAM, but is not necessarily limited to such a configuration. The control unit 201 may be one or more arithmetic circuits or control circuits including a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, a volatile or non-volatile memory, etc. The control unit 201 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given to when a measurement end instruction is given, and a counter that counts numbers.

The storage unit 202 includes a storage device such as a hard disk drive (HDD), a solid state drive (SSD), etc. The storage unit 202 stores various computer programs executed by the control unit 201 and various data used by the control unit 201.

The computer programs stored in the storage unit 202 include a state estimation program PG for estimating a state of the blower 1 based on operation data of the blower 1. The state estimation program PG is a computer program for causing a computer to execute a process of acquiring operation data of the blower 1 recorded in a first period and operation data of the blower 1 recorded in a second period, estimating a state of the blower 1 by analyzing the acquired operation data of the second period, and outputting the estimation result.

The computer program stored in the storage unit 202 is provided by a non-transitory storage medium M on which the computer program is readably recorded. The storage medium M is, for example, a portable memory such as a CD-ROM, a USB memory, a Secure Digital (SD) card, or a Compact Flash (registered trademark). The control unit 201 reads the computer program recorded on the storage medium M using a reading device not shown in the figure, and stores the read computer program in the storage unit 202. Alternatively, the computer program stored in the storage unit 202 may be provided by communication. In this case, the control unit 201 may obtain the computer program through the communication unit 203, and store the obtained computer program in the storage unit 202.

The communication unit 203 includes a communication interface for transmitting and receiving various data. The communication interface included in the communication unit 203 is, for example, a communication interface conforming to a communication standard of a LAN (Local Area Network) used in WiFi (registered trademark) or Ethernet (registered trademark). In this embodiment, the communication unit 203 accesses the cloud server 300 via the communication network N, and acquires the driving data of the first period stored in the first driving history table 301A and the driving data of the second period stored in the second driving history table 301B.

The operation unit 204 includes operation devices such as a keyboard, a mouse, and a touch panel, and receives various operations and settings from an administrator, etc. The control unit 201 performs appropriate control based on various operation information provided by the operation unit 204, and stores setting information in the storage unit 202 as necessary.

The display unit 205 includes a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence) display, and displays information to be notified to a manager or the like in response to an instruction from the control unit 201 .

The state monitoring device 200 does not have to be a single computer, but may be a computer system including a plurality of computers and peripheral devices. Furthermore, the state monitoring device 200 may be a virtual machine that is virtually constructed by software.

The status monitoring device 200 acquires the first cycle of operating data and the second cycle of operating data from the cloud server 300, so that, for example, when an event occurs, it can present the operating data before and after the event to a manager, etc.

Fig. 7 is a schematic diagram showing an example of the display of the operating data. Fig. 7 shows an example of the display of the operating data when a startup event occurs. When an instruction from a manager or the like is received through the operation unit 204, when a predetermined event occurs in the blower 1, etc., the control unit 201 of the status monitoring device 200 generates screen data for the display screen 220 and displays it on the display unit 205.

The display screen 220 includes, for example, an event type selection field 221, an event date and time specification field 222, a display item selection field 223, an item group selection field 224, and a graph display field 225. The event type selection field 221 is a selection field in the form of a pull-down menu, and accepts the selection of an event type. The event types include start, stop, and abnormal stop. The event date and time specification field 222 is a specification field in the form of a pull-down menu, and accepts the specification of the occurrence date and time for the event selected in the event type selection field 221. The example of FIG. 7 shows that a start event that occurred at 0.863 seconds and 9:26 on August 20, 2020 has been selected.

The display item selection field 223 is a selection field in the form of check boxes, and accepts the selection of the operating data (measurement values) to be displayed. The item group selection field 224 is composed of selection buttons, and accepts the selection of the item group to be displayed. For example, when the selection button labeled "power" is selected, the display item selection field 223 is configured to automatically select items related to power (power consumption, input current, and output current in the example of FIG. 7).

In the graph display field 225, the operation data of the items selected in the display item selection field 223 for the event selected in the event type selection field 221 and the event date and time specification field 222 are displayed as a graph. In the example of FIG. 7, "motor rotation speed", "suction air volume", "discharge pressure", "power consumption", and "output current" are selected in the display item selection field 223, so that graphs showing the time changes of these measured values are displayed in the graph display field 225. The horizontal axis of the graph indicates time, and the vertical axis indicates the magnitude of each measured value as a ratio to a previously assumed maximum value. The display range of the horizontal axis (time) is a predetermined period including the event occurrence time. In the start event, the operation data of the second period (e.g., 0.1 second intervals) of 1 minute before the event starts and 2 minutes after the event starts is displayed. On the other hand, in the stop event and the abnormal stop event, the operation data of the second period (e.g., 0.1 second intervals) of 2 minutes before the event starts and 1 minute after the event starts is displayed.

In this manner, in the present embodiment, the operation data before and after the start of the event occurrence can be displayed in detail, so that the behavior (waveform) of each measurement value can be analyzed in detail. For example, the control unit 201 can estimate the deterioration of the airfoil bearing 13 by analyzing the behavior of the rotation speed of the motor 12 and the output current of the inverter 122 immediately after the start of the blower 1 (for example, from the start of the start to 30 seconds). In addition, the control unit 201 can estimate the efficiency reduction due to the adhesion of dust to the impeller 11 and the deterioration of the airfoil bearing 13 by analyzing the behavior of the rotation speed of the motor 12, the output current of the inverter 122, the discharge pressure of the blower 1, and the amount of air sucked into the blower 1 during constant speed operation after the start of the blower (for example, from the time when 30 seconds have elapsed to the time when 45 seconds have elapsed after the start of the blower).

FIG. 8 is an explanatory diagram for explaining an example of an analysis method. The graph shown in FIG. 8 shows the time change of the output current of the inverter 122 immediately after startup. The horizontal axis of the graph is time, and the vertical axis is the value of the output current. The control unit 201 derives, in advance, for example, a linear approximation formula and deviation regarding the time change of the output current of the inverter 122 from the waveform of the output current immediately after startup collected in the past. In FIG. 8, the derived linear approximation formula is indicated by a solid line, and the confidence interval (deviation) is indicated by a dashed line.

When the control unit 201 newly acquires operation data at the time of startup, it judges whether or not the value of the output current of the inverter 122 included in the operation data is included in the confidence interval. If it is included in the confidence interval, the control unit 201 estimates that there is no deterioration of the airfoil bearing 13. On the other hand, if it is outside the confidence interval, the control unit 201 estimates that there is deterioration of the airfoil bearing 13. Note that in order to eliminate the possibility of measurement error, it may be estimated that there is deterioration only when multiple measurement values consecutively fall outside the confidence interval.

In the example of Fig. 8, the output current waveform of the inverter 122 is linearly approximated and a confidence interval is set, but curve approximation may be performed and a confidence interval may be set for the obtained approximation formula. Also, in the example of Fig. 8, one confidence interval is set, but a confidence interval for estimating deterioration and a confidence interval for estimating a sign of deterioration may be set.

8 is configured to estimate the deterioration of the airfoil bearing 13 based on the output current of the inverter 122, but it is also possible to estimate the deterioration of the airfoil bearing 13 based on the rotational speed of the motor 12 instead of the output current of the inverter. Also, it is also possible to estimate the deterioration of the airfoil bearing 13 based on the rotational speed of the motor 12 and the output current of the inverter 122.

Similarly, the control unit 201 may estimate the deterioration of the airfoil bearing 13 by analyzing the behavior of the rotational speed of the motor 12 and the output current of the inverter 122 immediately after a stop command is given to the blower 1 (for example, within 10 seconds after the stop command is given).

Furthermore, the control unit 201 may estimate the efficiency reduction due to the adhesion of dust to the impeller 11 by analyzing the behavior of the rotation speed of the motor 12, the output current of the inverter 122, the discharge pressure of the blower 1, and the amount of air sucked into the blower during constant speed operation after the start of the blower 1 (for example, from 30 seconds to 45 seconds after start-up). The analysis method is the same as that for estimating the deterioration of the airfoil bearing 13, and the judgment may be made based on the presence or absence of deviation from the confidence interval.

Furthermore, when an abnormal stop event occurs, the control unit 201 may estimate the cause of the abnormal stop by analyzing operation data before and after the abnormal stop. The analysis method may be to determine the presence or absence of deviation from the confidence interval, similar to the estimation of deterioration of the airfoil bearing 13, and to identify the measurement value that has deviated from the confidence interval, thereby estimating the cause of the abnormal stop. For example, when an abnormal stop event occurs, if the output current of the inverter 122 is outside the confidence interval, while other measurement values are within the confidence interval, the control unit 201 can estimate that the cause of the abnormal stop is an abnormality in the inverter 122.

The operation of the status monitoring system according to this embodiment will be described below.
9 is a flowchart explaining the procedure of the process executed by the control device 100. After the operation of the blower 1 starts, the control unit 101 of the control device 100 acquires measurement data output from the various sensors S1 to S5 from the input unit 103 at any time. The control unit 101 refers to the output of the built-in clock, records the acquired measurement data in a first storage area of the storage unit 102 in a first cycle, and records the data in a second storage area of the storage unit 102 in a second cycle. In this embodiment, the measurement data from the sensors S1 to S5 is operation data of the blower 1.

The control unit 101 judges whether or not to transmit the operating data of the first period to the cloud server 300 (step S101). For example, the control unit 101 judges to transmit the measurement data to the cloud server 300 every time the measurement data is recorded in the first period. Alternatively, the control unit 101 may judge to transmit the measurement data at a predetermined period (for example, an interval of several minutes to an interval of several hours) different from the first period, or may judge to transmit the measurement data at a predetermined time. When it is judged not to transmit the measurement data in step S101 (S101: NO), the control unit 101 executes the process of step S103 and subsequent steps.

When it is determined in step S101 that the driving data should be transmitted (S101: YES), the control unit 101 transmits the driving data of the first period recorded in the first storage area of the storage unit 102 to the cloud server 300 (step S102). At this time, the control unit 101 may transmit the driving data of the first period recorded between the previous transmission and the current transmission to the cloud server 300. The transmitted driving data of the first period is stored in the first driving history table 301A in the cloud server 300.

Next, the control unit 101 determines whether an event has occurred (step S103). In step S103, it is sufficient to determine a start event, a stop event, an abnormal stop event, etc. of the blower 1. The occurrence of an event is determined based on the operation data of the first period. For example, the control unit 101 can specify the timing when the blower 1 started, stopped, or abnormally stopped by monitoring the output current of the inverter 122. The control unit 101 may also determine that an event has occurred when a start instruction or a stop instruction is given to the blower 1. If no event has occurred (S103: NO), the control unit 101 returns the process to step S101.

When it is determined that an event has occurred (S103: YES), the control unit 101 determines whether or not to transmit the second cycle of driving data related to the event (step S104). When the event that has occurred is a stop event or an abnormal stop event, the control unit 101 determines that the second cycle of driving data should be transmitted, for example, when one minute has elapsed since the event occurred. When the event that has occurred is a start event, the control unit 101 determines that the second cycle of driving data should be transmitted, for example, when two minutes have elapsed since the event occurred.

When it is determined in step S104 that the data should not be transmitted (S104: NO), the control unit 101 waits until the transmission timing. During this waiting period, the control unit 101 continuously records the driving data. That is, the control unit 101 records the driving data acquired through the input unit 103 in the first storage area of the storage unit 102 in the first cycle, and records the data in the second storage area of the storage unit 102 in the second cycle.

When it is determined in step S104 that the data is to be transmitted (S104: YES), the control unit 101 transmits the second period of driving data recorded in the second storage area of the storage unit 102 to the cloud server 300 (step S105). When the event that has occurred is a stop event or an abnormal stop event, the control unit 101 reads out driving data for a total of three minutes, for example, from two minutes before the event occurrence to one minute after the event occurrence, from the second storage area of the storage unit 102, and transmits the read driving data to the cloud server 300 via the communication unit 104. When the event that has occurred is a start event, the control unit 101 reads out driving data for a total of three minutes, for example, from one minute before the event occurrence to two minutes after the event occurrence, from the second storage area of the storage unit 102, and transmits the read driving data to the cloud server 300 via the communication unit 104. The transmitted driving data for the second period is stored in the second driving history table 301B in the cloud server 300.

10 is a flowchart explaining the procedure of the process executed by the state monitoring device 200. The control unit 201 of the state monitoring device 200 executes the following process by reading and executing the state estimation program PG stored in the storage unit 202. The control unit 201 accesses the cloud server 300 via the communication unit 203 and acquires the operating data of the first period (step S121). At this time, the state monitoring device 200 may accept user authentication and permit access to the cloud server 300 only if the authentication is successful.

The control unit 201 judges whether an event has occurred (step S122). In step S122, it is sufficient to judge whether the blower 1 has started, stopped, or stopped due to an abnormality. The occurrence of an event is judged based on the operation data of the first period. For example, the control unit 201 can specify the timing at which the blower 1 started, stopped, or stopped due to an abnormality by monitoring the output current of the inverter 122. Alternatively, the control unit 201 may obtain information from the control device 100 indicating that a start instruction or a stop instruction has been given to the blower 1, and judge whether an event has occurred. If no event has occurred (S122: NO), the control unit 201 returns the process to step S121.

When it is determined that an event has occurred (S122: YES), the control unit 201 accesses the cloud server 300 via the communication unit 203 and acquires the operating data of the second period (step S123).

Next, the control unit 201 analyzes the acquired operation data of the second period and estimates the state of the blower 1 (step S124). The control unit 201 can estimate the deterioration of the airfoil bearing 13, for example, by determining whether the output current of the inverter 122 and the rotation speed of the motor 12 are within a previously obtained confidence interval. The control unit 201 can also estimate the efficiency reduction due to the adhesion of dust to the impeller 11 by determining whether the rotation speed of the motor 12, the output current of the inverter 122, the discharge pressure of the blower 1, and the amount of air sucked by the blower during constant speed operation after the start of the blower 1 (for example, from 30 seconds to 45 seconds after the start) are within a previously obtained confidence interval. Furthermore, when an abnormal stop event occurs, the control unit 201 can estimate the cause of the abnormal stop by analyzing the operation data before and after the abnormal stop.

Next, the control unit 201 outputs the estimation result (step S125). FIG. 11 is a schematic diagram showing an example of the output of the estimation result. The output example of FIG. 11 shows an example in which text information indicating that the airfoil bearing 13 has deteriorated is displayed on the display unit 205 together with a graph of each measurement value. At this time, the control unit 201 may highlight a graph of an estimated value (e.g., an output current of the inverter 122) used for estimating the deterioration of the airfoil bearing 13. FIG. 11 shows an example in which text information indicating that the airfoil bearing 13 has deteriorated is displayed. Similarly, the control unit 201 may cause the display unit 205 to display text information indicating that a decrease in efficiency has occurred due to the adhesion of dust to the impeller 11, text information indicating the cause of the abnormal stop, and the like. Moreover, instead of displaying the information on the display unit 205, the control unit 201 may notify a terminal device used by an administrator or the like through the communication unit 203.

As described above, in this embodiment, the second cycle of operating data transmitted when an event occurs is analyzed and the state of blower 1 is estimated, so that the behavior of each component constituting blower 1 can be grasped in detail, and for example, deterioration of airfoil bearings 13, reduced efficiency due to dust adhesion to impeller 11, the cause of abnormal stoppage, etc. can be grasped.

(Embodiment 2)
In the second embodiment, a configuration for estimating the state of the blower 1 using a learning model will be described.

In the second embodiment, the state of the blower 1 is estimated using a learning model MD (see FIG. 12 ) that has learned the relationship between the measurement data of the output current of the inverter 122 measured by the current sensor S1, the rotation speed of the motor 12 measured by the rotation speed sensor S2, the suction temperature of the blower 1 measured by the temperature sensor S3, the suction flow rate measured by the flow rate sensor S4, and the discharge pressure measured by the pressure sensor S5, and the state of the blower 1. The learning model MD is stored, for example, in the storage unit 202 of the state monitoring device 200. Alternatively, the learning model MD may be stored in an external device (for example, the cloud server 300) accessible from the state monitoring device 200.

FIG. 12 is a schematic diagram for explaining a configuration example of the learning model MD. The learning model MD is, for example, a machine learning learning model including deep learning, and is configured by a neural network. The learning model MD includes an input layer LY1, intermediate layers LY2 and LY3, and an output layer LY4. In the example of FIG. 12, two intermediate layers LY2 and LY3 are described, but the number of intermediate layers is not limited to two and may be three or more.

The input layer LY1, the intermediate layers LY2 and LY3, and the output layer LY4 each have one or more nodes, and the nodes of each layer are connected in one direction to the nodes in the previous and next layers with desired weights and biases. The input layer LY1 of the learning model MD receives the same number of data as the number of nodes in the input layer LY1. In this embodiment, the data input to the nodes of the input layer LY1 is the second period of operation data obtained for the blower 1. That is, the data input to the nodes of the input layer LY1 includes the measurement data of the output current of the inverter 122, the rotation speed of the motor 12, the suction temperature, suction flow rate, and discharge pressure of the blower 1 in the second period.

The input measurement data is output to the nodes in the first intermediate layer LY2 through the nodes in the input layer LY1. The data input to the first intermediate layer LY2 is output to the nodes in the next intermediate layer LY3 through the nodes in the intermediate layer LY2. At this time, the output is calculated using an activation function including weights and biases set between the nodes. In the same manner, calculations are performed using activation functions including weights and biases set between the nodes, and are transmitted to the subsequent layers one after another until a calculation result is obtained by the output layer LY4.

Here, parameters such as weights and biases connecting nodes are learned by a predetermined learning algorithm. For example, a deep learning learning algorithm including backpropagation is used as the learning algorithm for learning various parameters. In this embodiment, the above-mentioned measurement data and label data indicating the state of the blower 1 (presence or absence of deterioration, cause of abnormality, etc.) are collected as training data, and using the collected training data, various parameters including weights and biases between nodes are learned by a predetermined learning algorithm so that a calculation result regarding the state of the blower 1 is output when measurement data is input. The learning model MD may be generated inside the state monitoring device 200 or may be generated by an external server (for example, the cloud server 300).

The output layer LY4 outputs the calculation results regarding the state of the blower 1. For example, the output layer LY4 is configured with three nodes, from the first node to the third node, and the first node outputs the possibility that a component of the blower 1 has deteriorated (probability P1), the second node outputs the possibility that there is a sign of deterioration (probability P2), and the third node outputs the possibility that there is no deterioration (probability P3).

The number of nodes constituting the output layer LY4 and the calculation results assigned to each node are not limited to the above example, and can be designed as appropriate. For example, the first node of the output layer LY4 may output the possibility that the cause of the abnormal stop is an inverter abnormality (probability P1), the second node may output the possibility that the cause of the abnormal stop is a malfunction of the motor 12 (probability P2), and the third node may output the possibility that the cause of the abnormal stop is a malfunction of the airfoil bearing 13 (probability P3).

In addition, the learning model MD may be prepared for each event type, or for each type of input measurement data.

13 is a flowchart for explaining an estimation procedure using the learning model MD. The control unit 201 of the state monitoring device 200 executes the state estimation program PG stored in the storage unit 202 to perform the following processes.

The control unit 201 inputs the second period operation data acquired from the cloud server 300 to the learning model MD through the communication unit 203 (step S201), and executes a calculation by the learning model MD (step S202). The data provided to the nodes of the input layer LY1 is output to the adjacent nodes of the intermediate layer LY2. In the intermediate layer LY2, a calculation is performed using an activation function including weights and biases between the nodes, and the calculation result is output to the subsequent intermediate layer LY3. In the intermediate layer LY3, a calculation is further performed using an activation function including weights and biases between the nodes, and the calculation result is output to each node of the output layer LY4. Each node of the output layer LY4 outputs the calculation result regarding the state of the blower 1.

The control unit 201 estimates the state of the blower 1 based on the calculation results of the learning model MD (step S203). When the output layer LY4 of the learning model MD outputs the possibility that the components of the blower 1 are degraded, that there are signs of degradation, and that there is no degradation as probabilities P1 to P3, the control unit 201 can estimate the degradation of the components by identifying the node that outputs the highest probability among these probabilities P1 to P3. In addition, when the output layer LY4 of the learning model MD outputs information regarding the cause of the abnormal stop, the control unit 201 may estimate the cause of the abnormal stop based on the output from the output layer LY4.

The control unit 201 outputs information based on the estimation result (step S204). For example, the control unit 201 displays information on the degradation of the component or information on the cause of the abnormal stop on the display unit 205. The control unit 201 may also notify a terminal device of an administrator or the like of the information on the degradation of the component or information on the cause of the abnormal stop via the communication unit 203. Note that, in order to avoid erroneous judgment based on single measurement data, the control unit 201 may output information that the component is degraded only when the number of times that it has been estimated that there is degradation (or a sign of degradation) is consecutively equal to or more than a predetermined number of times (e.g., 10 times).

As described above, in embodiment 2, the machine learning learning model MD including deep learning can be used to estimate the state of the blower 1 and output information based on the estimation result, so that the user can be prompted to replace or maintain the components that make up the blower 1 as necessary.

In this embodiment 2, a configuration has been described in which a calculation result regarding the state of the blower 1 is obtained using a machine learning learning model MD configured by a neural network, but the learning model MD is not limited to a model obtained using a specific method.

For example, instead of a neural network based on deep learning, a learning model based on a perceptron, a convolutional neural network, a recurrent neural network, a residual network, a self-organizing map, or the like may be used.

In addition, instead of the learning model using the above neural network, the learning model may be a model trained using other methods including regression analysis methods including linear regression, logistic regression, support vector machines, etc.; methods using search trees such as decision trees, regression trees, random forests, gradient boosting trees, etc.; Bayesian estimation methods including naive Bayes, etc.; time series prediction methods including AR (Auto Regressive), MA (Moving Average), ARIMA (Auto Regressive Integrated Moving Average), state space models, etc.; clustering methods including K-nearest neighbor methods, etc.; methods using ensemble learning including boosting, bagging, etc.; clustering methods including hierarchical clustering, non-hierarchical clustering, topic models, etc.; association analysis, emphasis filtering, etc.

In addition, PLS (Partial Least Squares) regression, multiple regression analysis, principal component analysis, factor analysis,
A learning model may be constructed using multivariate analysis including cluster analysis.

In the present embodiment, the measurement data obtained from the sensors S1 to S5 are input to the learning model MD, but instead of inputting the measurement data, a graph (image) showing the time series change of the measurement value may be input. In this case, the learning model MD may be a CNN (Convolutional Neural Networks), R-CNN (Region-based CNN), YOLO (Young Lonely Planets), or a CNN (Convolutional Neural Networks).
A learning model constructed using a Single Look Once (SSD), a Single Shot Detector (SSD), a Generative Adversarial Network (GAN), or the like may be used.

Further, in this embodiment, the data is based on the measurement data obtained from the sensors S1 to S5, but the types of sensors are not limited to S1 to S5, and measurement data such as motor temperature and inverter temperature shown in the display item selection field 223 in Figure 7 may also be used.

In this embodiment, the blower 1 is based on an airfoil bearing (air bearing) 13, but it is not limited to an airfoil bearing, and the blower may use a sliding bearing other than an airfoil bearing, such as a magnetic bearing or a tilting pad bearing.

REFERENCE SIGNS LIST 1 Blower 11 Impeller 12 Motor 100 Control device 101 Control unit 102 Memory unit 103 Input unit 104 Communication unit 120 Drive device 121 Converter 122 Inverter 200 Status monitoring device 201 Control unit 202 Memory unit 203 Communication unit 204 Operation unit 205 Display unit 300 Cloud server

Claims (14)

1. A status monitoring system comprising: a communication device that transmits operation data of a blower; and a status monitoring device that acquires the operation data of the blower transmitted from the communication device and monitors a status of the blower based on the acquired operation data,
The communication device includes:
a first transmission unit that transmits the operation data of the blower recorded in a first period;
a second transmission unit that transmits the operation data of the blower recorded at a second period that is shorter than the first period, using the occurrence of an event as a trigger,
The condition monitoring device includes:
an acquisition unit that acquires the first periodic operating data and the second periodic operating data transmitted from the communication device;
an estimation unit that analyzes the acquired operation data of the second period and estimates a state of the blower;
and an output unit that outputs an estimation result by the estimation unit. 1. A status monitoring device that acquires operation data of a blower transmitted from a communication device and estimates a status of the blower based on the acquired operation data,
an acquisition unit that acquires operation data of the blower recorded in a first period transmitted from the communication device and operation data of the blower recorded in a second period shorter than the first period and transmitted from the communication device using the occurrence of an event as a trigger;
an estimation unit that analyzes the acquired operation data of the second period and estimates a state of the blower;
and an output unit that outputs an estimation result by the estimation unit. The state monitoring device according to claim 2 , wherein the second cycle of operating data is operating data for a period from a point in time before the event occurs to a point in time after the event occurs. The event includes a start event or a stop event of the blower;
The condition monitoring device according to claim 2 or 3, wherein the estimation unit estimates deterioration of a component included in the blower based on the second period of operational data obtained when the blower is started or stopped. The blower includes an impeller, a motor that rotates the impeller, and an air bearing that supports a rotating shaft of the motor in a non-contact manner,
the acquisition unit acquires, as the operation data for the second period, measurement data including at least one of a current supplied to the motor and a rotation speed of the motor;
The condition monitoring device according to claim 4 , wherein the estimation unit estimates the deterioration of the air bearing based on the acquired measurement data. The blower includes an impeller, a motor that rotates the impeller, and an air bearing that supports a rotating shaft of the motor in a non-contact manner,
the acquisition unit acquires, as the operation data for the second period, measurement data including at least one of a current supplied to the motor, a rotation speed of the motor, a discharge pressure of the blower, and an amount of air suctioned by the blower;
The condition monitoring device according to claim 4 , wherein the estimation unit estimates a decrease in efficiency caused by adhesion of dust to the impeller based on the acquired measurement data. The condition monitoring device according to any one of claims 4 to 6, wherein the estimation unit estimates the deterioration of the component using a learning model configured to output information regarding the deterioration of the component when a second period of operating data is input. the event includes an abnormal stop event of the blower;
The condition monitoring device according to claim 2 or 3, wherein the estimation unit estimates a cause of an abnormality based on the second period of operational data obtained when the blower stops abnormally. The blower includes an impeller, a motor that rotates the impeller, and an air bearing that supports a rotating shaft of the motor in a non-contact manner,
the acquisition unit acquires, as the operation data for the second period, measurement data including at least one of a current supplied to the motor, a rotational speed of the rotary shaft, a discharge pressure of the blower, and an amount of air suctioned by the blower;
The condition monitoring device according to claim 8 , wherein the estimation unit estimates a cause of the occurrence of the abnormality based on the acquired measurement data. 10. The condition monitoring device according to claim 8, wherein the estimation unit estimates a cause of the occurrence of an abnormality in the blower by using a learning model configured to output information regarding a cause of the occurrence of an abnormality in the blower when the second cycle of operating data is input. The state monitoring device according to claim 2 , wherein the output unit highlights a graph of the driving data used to estimate the state together with the estimation result. The status monitoring device according to claim 2 , further comprising a determination unit that determines whether an event has occurred based on the acquired operating data of the first period. 1. A status monitoring method for monitoring a status of a blower based on operation data of the blower, comprising:
Using a computer,
Acquire operation data of the blower recorded in a first period and operation data of the blower recorded in a second period shorter than the first period, the second period being transmitted in response to an occurrence of an event;
Analyzing the acquired operation data of the second period to estimate a state of the blower;
A condition monitoring method that outputs an estimation result. On the computer,
Acquire operation data of the blower recorded in a first period and operation data of the blower recorded in a second period shorter than the first period, the second period being transmitted in response to an occurrence of an event as a trigger;
Analyzing the acquired operation data of the second period to estimate a state of the blower;
A computer program for executing a process to output an estimation result.

Images