JP6899766B2 - Information processing device and information processing method - Google Patents

Description

The present invention relates to an information processing device or the like capable of outputting information that can be used for operation control of the incinerator using data on the operating state of the incinerator.

In recent years, garbage incinerators use steam generated by using waste heat generated from garbage incinerators to generate electricity and effectively use energy. In order to generate electricity efficiently, it is desired to generate a stable amount of steam. On the other hand, in an incinerator, the combustion state of the incinerator changes due to various factors such as fluctuations in the quality and quantity of waste to be incinerated and fluctuations in the amount of operation with respect to the incinerator. For this reason, various control methods for incinerators have been conventionally developed to stably generate steam while responding to such changes in the combustion state of the incinerator.

For example, in Patent Document 1, the steam amount is predicted from the past fluctuation of the steam amount of the incinerator, the prediction accuracy is evaluated by a stabilization analysis method or statistical processing, and the ratio of prediction control is calculated from the evaluation result. A technique for stabilizing the amount of steam in an incinerator while adjusting is disclosed.

Japanese Unexamined Patent Publication No. 2001-289401 (published on October 19, 2001)

However, there are various factors for reducing the amount of steam, and the control to be performed in order to prevent the decrease in the amount of steam differs depending on the factors. Therefore, there is a problem that it is not possible to determine an appropriate control for preventing the decrease in the amount of steam only by predicting that the amount of steam will decrease as in the above-mentioned prior art. In addition to the decrease in the amount of steam, there are known events that should be avoided by appropriate control in advance in garbage incinerators and the like, and such events also have the same problems as described above.

One aspect of the present invention has been made in view of such problems, and an object of the present invention makes it possible to determine appropriate control for preventing the occurrence of a predetermined event in an incineration facility. The purpose is to realize an information processing device and the like.

In order to solve the above problems, the information processing device according to one aspect of the present invention is an information processing device that performs information processing related to the incinerator facility, and acquires a plurality of types of predetermined data relating to the operating state of the incinerator facility. With respect to the data acquisition unit and the predetermined event predicted to occur in the incinerator, at least a part of the predetermined data is combined with the predetermined data when the predetermined event occurred in the incinerator in the past. It is characterized by having a factor prediction unit that identifies the cause of the predetermined event by using it for a factor prediction model constructed based on the correspondence with the cause of the predetermined event. To do.

In order to solve the above problems, the information processing method according to one aspect of the present invention is an information processing method by an information processing apparatus that performs information processing on the incineration facility, and a plurality of types of predetermined information on the operating state of the incineration facility. With respect to the data acquisition step for acquiring the data of the above and the predetermined event predicted to occur at the incineration facility, at least a part of the predetermined data is obtained when the predetermined event has occurred at the incineration facility in the past. Includes a factor prediction step that identifies the cause of the predetermined event by using it for a factor prediction model constructed based on the correspondence between the predetermined data and the cause of the predetermined event. It is a feature.

According to one aspect of the present invention, it is possible to determine an appropriate control for preventing the occurrence of a predetermined event.

It is a block diagram which shows an example of the main part structure of the information processing apparatus which concerns on Embodiment 1 of this invention. It is a schematic block diagram of the garbage incinerator equipped with the said information processing apparatus. It is a figure which shows an example of the factor prediction using the factor prediction model. It is a flowchart which shows an example of the processing of the said information processing apparatus. It is a flowchart which shows the other example of the processing of the said information processing apparatus.

[Embodiment 1]
Embodiment 1 of the present invention will be described with reference to FIGS. 1 to 4. FIG. 1 is a block diagram showing an example of a main configuration of the information processing apparatus 1 according to the first embodiment of the present invention. FIG. 2 is a schematic configuration diagram of a garbage incinerator 100 including an information processing device 1. Although the information processing device of the garbage incinerator 100 will be described in the present embodiment, the present invention can be applied to an incinerator that incinerates an arbitrary incinerator. For example, it can be applied not only to a general waste incinerator, but also to an industrial waste incinerator, a sludge incinerator, and the like. These incinerators may use the heat generated by incineration to generate electricity. In addition, facilities that incinerate mainly for the purpose of power generation, such as biomass power generation facilities, are also included in the category of the above incinerator facilities.

[Structure of garbage incinerator]
The garbage incineration facility 100 is a facility for collecting and incinerating garbage, and includes an information processing device 1, a central control device 50, and an incinerator 60 as shown in FIG. The details will be described later, but if the garbage incinerator 100 is provided with the information processing device 1 to predict whether or not an abnormality will occur during garbage incineration, and if it is predicted that an abnormality will occur, The cause of the abnormality can be identified. Then, by causing the central control device 50 to perform control according to the above-mentioned occurrence factor, it is possible to prevent the occurrence of an abnormality.

The incinerator 60 is a furnace for incinerating the thrown-in garbage and is provided with a generator. A garbage pit (not shown) is attached to the incinerator 60, and the garbage accumulated in the garbage pit is transported by a crane and put into the incinerator 60. A boiler is provided in the incinerator 60, and the heat obtained by burning garbage is supplied to the boiler, and the steam generated from the boiler turns the turbine of the generator to generate electricity.

Information on the operating status of the incinerator 60, including the amount of steam generated from the boiler, is detected by sensors and the like provided at various locations in the garbage incinerator 100, and is output to the information processing device 1 and the central control device 50.

The central control device 50 controls the operation of various devices included in the garbage incinerator 100. The central control device 50 and the information processing device 1 may be configured as an integrated device. Further, the information processing device 1 may be arranged outside the site of the garbage incinerator 100 as long as it can acquire data regarding the operating state of the garbage incinerator 100 and can communicate with the central control device 50.

[Configuration of information processing device]
The information processing device 1 performs information processing on the garbage incinerator 100. Specifically, the information processing device 1 predicts whether or not an abnormality occurs in the amount of steam generated during garbage incineration based on a plurality of predetermined data D regarding the operating state of the garbage incinerator 100. Further, the information processing apparatus 1 identifies the cause of the abnormality in the amount of steam and the amount of steam when the abnormality occurs when the abnormality is predicted to occur in the amount of steam. Further, the information processing apparatus 1 determines the control for preventing the occurrence of an abnormality in the amount of steam according to the above-mentioned generation factor and the amount of steam.

In this embodiment, among the events that can occur in the garbage incinerator 100, an example of predicting the occurrence of an event in which the amount of steam decreases (hereinafter, simply referred to as a decrease in the amount of steam) will be described, but other events will also be described. Similar predictions are possible. A typical example of an event to be predicted is an event in which a predetermined parameter relating to the operating state of the garbage incinerator 100 becomes an abnormal value. For example, an event in which the temperature inside the incinerator 60 is below the threshold value, an event in which the concentration of harmful substances (carbon monoxide, nitrogen oxides, etc.) in the exhaust gas from the incinerator 60 is above the threshold value, etc. are to be predicted. It can also be.

The definition of the decrease in the amount of steam may be based on the actual situation such as the operation of the garbage incinerator 100. For example, a decrease in the amount of steam exceeding an allowable range (for example, 5 to 10% of the set value) with respect to the set value of the amount of steam may be defined as a decrease in the amount of steam. Further, for example, a decrease exceeding a predetermined volatility (for example, a decrease in steam amount of 5% in 10 minutes) may be regarded as a decrease in steam amount, and a decrease in steam amount below the minimum amount of steam required for stable power generation may be defined as a decrease in steam amount. The amount may be reduced.

The information processing device 1 includes a control unit 11, a storage unit 12, an input unit 13, and a communication unit 14. The hardware such as the storage unit 12, the input unit 13, and the communication unit 14 may be an external device of the information processing device 1 externally attached to the information processing device 1. Further, these hardwares (including the control unit 11) may be one or a plurality.

The storage unit 12 stores various data used by the information processing device 1. The storage unit 12 stores, in particular, the probability prediction model 121, the factor prediction model 122, the steam amount prediction model 123, and the control decision information 124. Each of the above models will be described in detail later.

The input unit 13 receives input of a plurality of predetermined data D relating to the operating state of the garbage incinerator 100 and outputs the input to the data acquisition unit 111.

The communication unit 14 is for the information processing device 1 to communicate with another device. For example, the information processing device 1 outputs to the central control device 50 the control and the control amount regarding the operation of the garbage incinerator 100 determined by the control unit 11 by communication via the communication unit 14. Further, it is also possible to have a configuration in which a part or all of the data D is acquired via the communication unit 14.

The control unit 11 controls the functions of the information processing device 1 in an integrated manner. The control unit 11 includes a data acquisition unit 111, a probability prediction unit 112, a factor prediction unit 113, a control determination unit 114, a steam amount prediction unit (parameter value prediction unit) 115, and a control amount determination unit 116.

The data acquisition unit 111 acquires a plurality of types of predetermined data D relating to the operating state of the garbage incinerator 100 from the input unit 13, and stores the data for the time required for making a prediction with each of the above prediction models in the storage unit 12. accumulate. Since the predetermined data D is sequentially acquired, the storage unit 12 stores the predetermined data D acquired at a plurality of different time points in time series. The predetermined data D is, for example, sensor data indicating a sensor detection value and input dust information regarding dust charged into the incinerator 60. The sensor data includes the dust supply device / grate speed (speed of supplying dust to the incinerator 60), air flow rate, exhaust gas flow rate, various exhaust gas concentrations, furnace temperature, grate temperature, combustion air temperature, and in the furnace. The amount of dust, the thickness of the dust layer, etc. The input dust information includes the water content of the dust, the bulk specific gravity of the dust, the number of times the dust is agitated in the dust pit, the type of dust, the calorific value of the dust, and the like. The acquisition destination of the data D is not particularly limited, and for example, the data D input by the user to the input unit 13 may be acquired, or may be acquired from another device via the input unit 13. Further, the data D may be acquired from a plurality of acquisition destinations.

The probability prediction unit 112 identifies the probability of occurrence of a decrease in the amount of steam by using at least a part of the data D and the probability prediction model 121. The probability prediction model 121 includes data D regarding the operating state of the garbage incinerator 100 in the past for a predetermined time (for example, several hours) immediately before a certain time point, and a decrease in the amount of steam after a predetermined time from that time point. It is a model constructed based on the correspondence with the occurrence probability of. By using such a probability prediction model 121 and the data D acquired by the data acquisition unit 111, the probability prediction unit 112 can specify the probability that an abnormality in which the amount of steam decreases in the future will occur.

For example, among the data D acquired and accumulated when the garbage incinerator 100 was operated in the past, the data D for one hour immediately before a certain point in time and the probability that the amount of steam decreased in the 30 minutes immediately after that. The correspondence relationship may be specified and the probability prediction model 121 may be used. By using such a probability prediction model 121, it is possible to specify the probability that the amount of vapor decreases in the 30 minutes immediately after that from the data D acquired in 1 hour immediately before the time of prediction.

In the construction of the probability prediction model 121, it is not necessary to use all the data D for one hour, and among the data D for one hour, the data D sufficient to secure the required prediction accuracy may be used. For example, the sensor values (part of data D) acquired at one time point, 40 minutes before, 20 minutes before, and at that time point, and the amount of steam decreased in 30 minutes immediately after that time point. It is also possible to construct the probability prediction model 121 from the correspondence relationship with the obtained probability. In this case, by using the sensor values acquired at the time of prediction 1 hour, 40 minutes, 20 minutes, and the time of prediction for the probability prediction model 121, immediately after the time of prediction. The probability that the amount of steam will decrease in 30 minutes can be specified.

Further, for example, the probability prediction model 121 may be constructed only from the data D (which may include a plurality of types of data) acquired at a certain time point. When such a probability prediction model 121 is used, prediction is possible only from the data D acquired at the time of prediction. Therefore, in this case, it is possible to predict the probability of decrease in the amount of steam by using the data acquired by the data acquisition unit 111 as it is without temporarily storing it in the storage unit 12.

The probability prediction model 121 may be any one that can predict the probability that a decrease in the amount of steam will occur from the data D. For example, the probability prediction model 121 may be a decision tree model generated by decision tree analysis or a regression model generated by regression analysis.

The factor prediction unit 113 identifies the cause of the decrease in the amount of steam by using at least a part of the data D and the factor prediction model 122. When the factor prediction unit 113 predicts that a decrease in the amount of steam will occur in the waste incinerator from at least a part of a plurality of predetermined data, for example, the probability of occurrence specified by the probability prediction unit 112 is equal to or higher than a predetermined threshold value. In some cases, identify the cause.

The factor prediction model 122 includes data D of a predetermined time (for example, several hours) immediately before a certain time point when the garbage incinerator 100 was operated in the past, and data D when the amount of steam decreases after a predetermined time from that time point. This model was constructed based on the correspondence with the factors that cause the decrease in steam volume. By using such a factor prediction model 122 and the data D acquired and accumulated by the data acquisition unit 111, the factor prediction unit 113 identifies the cause of the decrease in the amount of steam expected to be generated in the future. be able to. For example, among the data D acquired and accumulated when the garbage incinerator 100 was operated in the past, the data D for one hour immediately before a certain point in time and the data D for 30 minutes immediately after that when the amount of steam decreased. The factor prediction model 122 may be used by specifying the correspondence relationship with the cause of the decrease in steam amount. By using such a factor prediction model 122, it is possible to identify the cause of occurrence when the amount of vapor decreases 30 minutes after the data D for one hour immediately before the time of prediction.

In the construction of the factor prediction model 122, it is not necessary to use all the data D for the predetermined time, and among the data D for the predetermined time, the data D sufficient to secure the required prediction accuracy may be used. Factor prediction using the factor prediction model 122 will be described later based on FIG.

The factor prediction model 122 may be any one that can predict the cause of the decrease in the amount of steam from the data D. For example, the factor prediction model 122 may be a decision tree generated by decision tree learning. In this case, the factor prediction unit 113 analyzes by the decision tree analysis which of the predetermined plurality of generation factors is classified as the cause of the decrease in the amount of steam.

The cause of occurrence, which is the classification destination, may be set manually in advance, or may be automatically set by information processing. For example, the data D (the value of each element included in the data D and the pattern of the combination of those values) acquired during the past operation of the garbage incinerator 100 is classified by clustering analysis (K-means method, etc.) and they are classified. Each classification of may be used as an occurrence factor.

The control determination unit 114 uses the control determination information 124 to determine the control (type of control) to be performed in the waste incinerator 100 in order to prevent the occurrence of a decrease in the amount of steam according to the generation factor specified by the factor prediction unit 113. To do. Further, the control amount determination unit 116 uses the control determination information 124 to determine the control amount (degree of control) according to the steam amount specified by the steam amount prediction unit 115.

The control decision information 124 includes information in which the generation factor and the type of control to be performed in the garbage incinerator 100 corresponding to the generation factor are associated with each other. Further, the control decision information 124 includes information in which the fluctuation amount of the steam amount and the control amount of various devices included in the garbage incinerator 100 corresponding to the fluctuation amount of the steam amount are associated with each other.

For example, the control decision information 124 corresponds to the dust supply device of the incinerator 60 and the control for increasing the grate speed for the dust supply failure, which is one of the causes of the decrease in the amount of steam, and the decrease in the amount of steam. The information may be associated with the increment of the dust supply device / grate speed according to the degree. As a result, in a situation where a decrease in steam amount due to poor dust supply is predicted, it is possible to perform appropriate control by increasing the speed of the dust supply device and grate, and prevent the decrease in steam amount due to poor dust supply. Becomes possible. In addition, when the range of decrease in steam amount is expected to be large, it is possible to increase the amount of increase in the dust supply device / grate speed to more reliably prevent the decrease in steam amount due to poor dust supply. .. Then, when the extent of the decrease in the amount of steam is expected to be small, the amount of steam can be stabilized by minimizing the increase in the dust supply device / grate speed.

The steam amount prediction unit 115 identifies the future steam amount by using at least a part of the data D and the steam amount prediction model 123.

The steam amount prediction model 123 includes data D regarding the operating state of the garbage incinerator 100 at a predetermined time immediately before a certain time point (for example, several hours) when the garbage incinerator 100 is operated in the past, and a predetermined time from that time point. It is a model constructed based on the correspondence with the value of the amount of steam later. The steam amount prediction unit 115 uses such a steam amount prediction model 123 and the data D acquired by the data acquisition unit 111 to specify the value of the steam amount after a predetermined time from which the data D is acquired. Can be done. For example, a steam amount prediction model based on the correspondence between the sensor values (part of data D) acquired 1.5 hours, 1 hour, and 30 minutes before a certain point in time and the amount of steam at that certain point in time. You can also build 123. In this case, by using the sensor values acquired 1.5 hours, 1 hour, and 30 minutes before the prediction time for the steam amount prediction model 123, 30 minutes after the prediction time. The amount of steam can be specified.

In the construction of the steam amount prediction model 123, it is not necessary to use all the data D for the predetermined time, and among the data D for the predetermined time, the data D sufficient to secure the required prediction accuracy may be used. .. For example, the steam amount prediction model 123 may be constructed only from the data D (which may include a plurality of types of data) acquired at a certain time point. When such a steam amount prediction model 123 is used, prediction is possible only from the data D acquired at the time of prediction. Therefore, in this case, it is possible to predict the amount of steam by using the data acquired by the data acquisition unit 111 as it is without temporarily storing it in the storage unit 12.

The steam amount prediction model 123 may be any one that can predict the steam amount from the data D. For example, the vapor quantity prediction model 123 may be a model based on multiple regression analysis, neural network analysis, decision tree analysis, or generalized linear analysis. The predetermined time may be several minutes to several tens of minutes, or may be a relatively long time (for example, one hour). By using the above model, it is possible to accurately predict the amount of steam after such a relatively long time.

[Example of factor prediction]
An example of factor prediction using the factor prediction model 122 will be described with reference to FIG. FIG. 3 is a diagram showing an example of factor prediction using the factor prediction model 122.

As described above, the factor prediction unit 113 identifies the cause of the decrease in the amount of steam by using at least a part of the data D for the factor prediction model 122. The data D used by the factor prediction unit 113 is the data acquired for the prediction. As shown in FIG. 3, in this data D, in addition to the data D acquired at the prediction time point, the data D is acquired at a predetermined time in the past at the prediction time point (for example, from several hours before the prediction time point to the prediction time point) and is stored in the storage unit. The data D accumulated in 12 is included.

Further, as described above, the factor prediction model 122 is a prediction model constructed based on the data D acquired and accumulated when the past decrease in steam amount occurs in the waste incinerator 100. When the factor prediction model 122 is used as a decision tree model, its data structure may be as shown in FIG. 3, for example.

The factor prediction model 122 shown in FIG. 3 has a value of the sensor A at the time of prediction, a value of the sensor B 20 minutes before the prediction time, and a value of the sensor B 10 minutes before the prediction time among a plurality of types of data included in the data D. It is a model that identifies the cause of the decrease in the amount of steam using the value of the sensor C. This factor prediction model 122 can be constructed by using the data D acquired and accumulated when the past decrease in steam amount occurs. More specifically, among the above data D, the value of the sensor A before a predetermined time from the occurrence of the decrease in the amount of steam, the value of the sensor B 20 minutes before the acquisition of the value of the sensor A, and the value of the sensor A are acquired. It can be constructed using the value of the sensor C 10 minutes before the time point. The predetermined time may be set according to how much the factor for the decrease in the amount of steam is predicted. For example, when predicting the cause of the decrease in the amount of steam that is expected to occur 30 minutes before the prediction time, the predetermined time may be 30 minutes.

The first branch of the factor prediction model 122 shown in FIG. 3 is a branch based on the value of the sensor A at the time of prediction. If the value of the sensor A is X or more, it advances to the left at this branch, and if it is less than X, it advances to the left. Go to the right.

When the branching based on the value of the sensor A proceeds to the left, that is, when the value of the sensor A is X or more, the branching is further performed based on the value of the sensor B 20 minutes before the prediction time. Here, if the value of the sensor B is Y or more, the branch is advanced to the left, and the factor (1): poor dust supply is identified. On the other hand, if the value of the sensor B is less than Y, the branch is advanced to the right, and the factor (2): insufficient air flow rate is identified.

On the other hand, when the branching based on the value of the sensor A proceeds to the right, that is, when the value of the sensor A is less than X, the branching is further performed based on the value of the sensor C 10 minutes before the prediction time. Here, if the value of the sensor C is Z or more, the branch is advanced to the left, and the factor (3) is identified. On the other hand, if the value of the sensor C is less than Z, the branch is advanced to the right, and the factor (1) is identified.

In FIG. 3, a dashed arrow indicates a specific flow of factors when the value of the sensor A at the time of prediction is X or more and the value of the sensor B 20 minutes before the prediction time is Y or more. In this case, as shown in the figure, the branch based on the value of the sensor A advances to the left, and the branch based on the value of the sensor B 20 minutes before the prediction time also proceeds to the left. As a result, the factor of the decrease in the amount of steam predicted to be generated is identified as the factor (1).

The factor prediction model 122 in FIG. 3 is an example. When the decision tree model is used as the factor prediction model 122, the number of nodes, the number of branches at each node, the branch conditions at each node, etc. correspond to the type and value of the acquired data D, the target event, etc. It should be. Further, in the above example, the factor prediction model 122 constructed from the data D acquired at a plurality of time points is used, but only the data D acquired at a certain time point (may include a plurality of types of data). The factor prediction model 122 may be constructed from. When such a factor prediction model 122 is used, prediction is possible only from the data D acquired at the time of prediction. Therefore, in this case, it is possible to predict the cause of the decrease in the amount of steam by using the data acquired by the data acquisition unit 111 as it is without temporarily storing it in the storage unit 12.

[Processing flow]
FIG. 4 is a flowchart showing an example of processing performed by the information processing device 1 during the operation of the garbage incinerator 100.

First, the data acquisition unit 111 acquires and stores the data D via the input unit 13 (S1, data acquisition step). Next, the probability prediction unit 112 uses at least a part of the data D with respect to the probability prediction model 121 to specify the probability of occurrence of a decrease in the amount of steam (S2). Further, the factor prediction unit 113 determines whether or not the occurrence probability specified in S2 is equal to or higher than a predetermined threshold value (S3).

When it is determined in S3 that the probability of occurrence is less than a predetermined threshold value (NO in S3), the process returns to S1. On the other hand, when it is determined that the probability of occurrence is equal to or higher than a predetermined threshold value (YES in S3), the factor prediction unit 113 uses at least a part of the data D acquired in S1 for the factor prediction model 122 and the amount of steam. (S4, factor prediction step).

Subsequently, the control determination unit 114 determines the type of control according to the occurrence factor specified by the factor prediction unit 113 using the control determination information 124 (S5). Further, the steam amount prediction unit 115 uses at least a part of the data D acquired in S1 for the steam amount prediction model 123 to specify the steam amount at the time of decrease (S6).

After that, the control amount determination unit 116 determines the control amount in the type of control determined in S5 according to the amount of steam specified in S6 (S7). Then, the control amount determination unit 116 notifies the central control device 50 of the determined control contents. As a result, the central control device 50 controls the garbage incinerator 100 (S8).

The degree of decrease in steam amount may be predicted based on the factor of decrease in steam amount specified in S4 and the value of the predicted future factor (in this example, the amount of steam). Then, in S7, the controlled amount may be determined according to the prediction result of the degree of decrease in the amount of steam.

[Other examples of processing flow]
FIG. 5 is a flowchart showing another example of the processing of the information processing device 1. Since S11, S12, and S15 to S18 in FIG. 5 are the same processes as S1, S2, S4, S5, S7, and S8 in FIG. 4, detailed description of these processes will be omitted.

In the flowchart of FIG. 5, the data acquisition unit 111 acquires the data D (S11), and the probability prediction unit 112 specifies the probability of occurrence of a decrease in the amount of steam (S12). Further, the steam amount prediction unit 115 specifies the amount of steam at the time of decrease (S13).

Next, the factor prediction unit 113 determines whether or not to control the garbage incinerator 100 (S14). Specifically, the factor prediction unit 113 has a small value of the amount of steam specified in S13 (the predicted value of the amount of steam is an abnormal value), but the occurrence probability specified in S12 is less than a predetermined threshold value. In that case, that is, when the prediction result of the steam amount prediction unit 115 does not match the prediction result of the probability prediction unit 112, it is determined that the control is not performed. In this case, the determination in S14 becomes NO, and the process returns to S11. Further, although the value of the amount of vapor specified in S13 is not small, it is determined that control is not performed even when the probability of occurrence specified in S12 is equal to or greater than a predetermined threshold value. On the other hand, when the value of the amount of steam specified in S13 is small and the probability of occurrence specified in S12 is equal to or greater than a predetermined threshold value, that is, the prediction result of the steam amount prediction unit 115 matches the prediction result of the probability prediction unit 112. If so, it is determined that control is to be performed. In this case, the determination in S14 is YES, and the process proceeds to S15. Whether or not the value of the amount of steam is small may be determined by comparing the value of the amount of steam with a predetermined threshold value.

In S15, the factor prediction unit 113 identifies the cause of the decrease in the amount of steam, in S16 the control determination unit 114 determines the type of control according to the generating factor, and in S17, the control determination unit 114 determines the control amount according to the amount of steam. To determine. Then, in S18, the central control device 50 controls the garbage incinerator 100.

In S14, it is determined that the waste incinerator 100 is controlled when at least one of the conditions that the value of the amount of steam specified in S13 is small and the probability of occurrence specified in S12 is high is satisfied. You may. Further, in this case, the value of the amount of vapor specified in S13 is not small, but if the probability of occurrence specified in S12 is high, the value of the amount of vapor specified in S13 may not be used for control. .. That is, in this case, the processing of S17 is omitted, and in S18, the waste incinerator 100 is controlled by a predetermined control amount (for example, 1.5 times the current control amount) set in advance for each factor in the central control device 50. May be executed.

[Embodiment 2]
In the present embodiment, the information processing device 1 causes an event in which the concentration of carbon monoxide (hereinafter referred to as CO) generated during garbage incineration exceeds a threshold value from a plurality of predetermined data regarding the operating state of the garbage incinerator 100. An example of predicting whether or not it will occur will be described. Further, the information processing apparatus 1 of the present embodiment identifies the cause of the CO concentration when it is predicted to exceed the threshold value, and prevents the CO concentration from exceeding the threshold value according to the cause of the CO concentration. Determine control to prevent. The same reference numerals are added to the members having the same functions as the members described in the above embodiment, and the description is not repeated. Further, since the flow of processing executed by the information processing apparatus 1 of the present embodiment is the same as that of the first embodiment, the description will not be repeated.

In the present embodiment, the data acquisition unit 111 replaces or in addition to the various data described in the above embodiment, the operating state of the grate, the rate of change in the temperature inside the furnace, the combustion air pressure, and the amount of steam. , Data such as oxygen concentration at the incinerator outlet and secondary air flow rate may be acquired. The operating state of the grate indicates, for example, whether the grate is operating or stopped. Further, the secondary air is air supplied above the combustion position in order to burn (secondary combustion) the gas generated by the combustion of dust (primary combustion). In addition to this, the data acquisition unit 111 obtains an image of the inside of the furnace (which may be a moving image or a still image) or data showing the result obtained by analyzing the image. You may get it. For example, the data acquisition unit 111 may acquire an image of the dust burning in the furnace, data indicating the burning state of the dust obtained by analyzing the image, and the like.

The probability prediction unit 112 of the present embodiment identifies the probability of occurrence of an event in which the CO concentration exceeds the threshold value by using at least a part of the data acquired by the data acquisition unit 111 and the probability prediction model 121. The probability prediction model 121 includes data on the operating state of the garbage incinerator 100 at a predetermined time immediately before a certain point in time and the probability of occurrence of an event in which the CO concentration exceeds the threshold value after a predetermined time from that point. It is a model constructed based on the correspondence with. The predetermined time may be a time corresponding to an event to be predicted and a timing for performing control for preventing the occurrence of the event. In the case of an event in which the CO concentration exceeds the threshold value, the predetermined time may be, for example, several minutes to several tens of minutes. Of course, this predetermined time may be set as appropriate, and may be a time shorter than a few minutes to a few tens of minutes (for example, immediately after the prediction time point) or a longer time. Even if the target of prediction is an event other than an event in which the CO concentration exceeds the threshold value (for example, an event in which the amount of vapor illustrated in the first embodiment drops to an unacceptable range or other event), the predetermined time should be appropriately set. The same is true.

The factor prediction unit 113 of the present embodiment identifies the cause of the event in which the CO concentration exceeds the threshold value by using at least a part of the data acquired by the data acquisition unit 111 and the factor prediction model 122. In the factor prediction model 122 of the present embodiment, when the garbage incinerator 100 was operated in the past, data of a predetermined time immediately before a certain time point and an event in which the CO concentration exceeded the threshold value occurred after a predetermined time from that time point. It is a model constructed based on the correspondence with the cause of the event. The predetermined time may be a time corresponding to an event to be predicted and a timing for performing control for preventing the occurrence of the event. In the case of an event in which the CO concentration exceeds the threshold value, the predetermined time may be, for example, several minutes to several tens of minutes. This predetermined time may be appropriately set, and may be a time shorter than several minutes to several tens of minutes (for example, immediately after the prediction time point) or a longer time. Even if the target of prediction is an event other than an event in which the CO concentration exceeds the threshold value (for example, an event in which the amount of vapor illustrated in the first embodiment drops to an unacceptable range or other event), the predetermined time should be appropriately set. The same is true.

The control determination unit 114 of the present embodiment uses the control determination information 124, and controls to be performed at the garbage incinerator 100 in order to prevent the occurrence of an event in which the CO concentration exceeds the threshold value according to the occurrence factor specified by the factor prediction unit 113. (Type of control) is determined. Further, the control amount determination unit 116 uses the control determination information 124 to determine the control amount (degree of control) according to the predicted value of the CO concentration. The control amount may be determined according to the probability specified by the probability prediction unit 112.

The control decision information 124 of the present embodiment includes information in which the cause of the event in which the CO concentration exceeds the threshold value and the type of control to be performed in the garbage incinerator 100 corresponding to the cause are associated with each other. In this information, for example, a control for increasing the secondary air amount may be associated with a cause of insufficient secondary air amount. The CO concentration can be lowered by supplying a sufficient amount of secondary air. Further, the control decision information 124 of the present embodiment includes information in which the amount of increase in CO concentration and the amount of control of various devices included in the garbage incinerator 100 corresponding to the increase amount are associated with each other.

The information processing device 1 of the present embodiment does not need to include the vapor amount prediction unit 115, and may include a CO concentration prediction unit (parameter value prediction unit) instead. The CO concentration prediction unit identifies the future CO concentration by using at least a part of the data acquired by the data acquisition unit 111 and the CO concentration prediction model. The CO concentration prediction model corresponds to the correspondence between the data on the operating state of the garbage incinerator 100 at a predetermined time immediately before a certain point in time when the garbage incinerator 100 was operated in the past and the CO concentration after a predetermined time from that point. It is a model built on the basis of relationships. The predetermined time may be a time corresponding to an event to be predicted and a timing for performing control for preventing the occurrence of the event. In the case of an event in which the CO concentration exceeds the threshold value, the predetermined time may be, for example, several minutes to several tens of minutes. This predetermined time may be appropriately set, and may be a time shorter than several minutes to several tens of minutes (for example, immediately after the prediction time point) or a longer time. Even if the target of prediction is other than the CO concentration (for example, the amount of vapor and other parameters exemplified in the first embodiment), the above-mentioned predetermined time may be appropriately set in the same manner.

According to the information processing apparatus 1 of the present embodiment having the above configuration, it is possible to predict whether or not an event in which the CO concentration exceeds the threshold value will occur. Then, when the CO concentration is predicted to exceed the threshold value, it is possible to identify the cause of the occurrence and determine the control for preventing the CO concentration from exceeding the threshold value according to the cause of the occurrence. it can.

[Other examples of events to be predicted]
According to the information processing device 1, in addition to the above-mentioned amount of steam and CO concentration, for example, an event in which _{the concentration of nitrogen oxides (NO x} ) and hydrogen chloride generated during garbage incineration exceeds the threshold value is predicted. It is also possible to target. It is possible to predict the occurrence of these events and determine appropriate control according to the cause of the occurrence by the same processing as in each of the above-described embodiments.

Further, for example, it is possible to predict an abnormality in the combustion position of garbage. This combustion position is a position from the ignition position where the dust conveyed by the grate or the like is ignited to the burnout position where the dust burns out. The combustion position is required to be properly controlled, especially in a stoker-type incinerator. This is because if the combustion position (particularly the burnout position) is too close to the downstream side in the dust transport direction, problems such as unburned residue will occur. According to the information processing apparatus 1, it is also possible to predict an abnormality in the combustion position and determine an appropriate control according to the cause of the abnormality by the same processing as in each of the above-described embodiments.

[Other examples of predictive models]
Each of the above-mentioned prediction models may be any prediction model constructed based on the correspondence between the predetermined data when a predetermined event occurred in the incineration facility in the past and the cause of the predetermined event. For example, in addition to the above-mentioned decision tree model, a prediction model constructed using a support vector machine or a prediction model constructed using a neural network may be used.

[Modification example]
Instead of determining the control content according to the specified generation factor, the information processing device 1 may notify the user by displaying the specified generation factor on the display device or the like. Even with such a configuration, it is possible to prevent the occurrence of an event such as a decrease in the amount of steam by performing control according to the generating factor by the user who recognizes the generating factor. Further, the control content may be determined according to the cause of occurrence, and the determined control content may be notified to the user. In this case, after confirming the validity of the notified control content, the user can have the central control device 50 control the control content if appropriate.

Further, in the above embodiment, an example of determining the control amount according to the predicted value of the steam amount has been described, but it is also possible to use a parameter value other than the steam amount to determine the control amount. That is, if the information processing apparatus 1 includes a parameter value prediction unit that predicts a parameter value that correlates with the appropriate control amount, the appropriate control amount can be determined. And this parameter value may be other than the amount of vapor. It is also possible to predict the parameter values for a plurality of types of parameters and determine the control amount using the prediction results.

Further, in the above embodiment, the example of specifying the cause of one event such as a decrease in the amount of steam has been described, but the cause of occurrence may be specified for a plurality of events. In this case, among a plurality of events, the cause of occurrence or the like may be specified for an event that is highly likely to occur (can be determined by at least one of probability prediction and parameter value prediction).

[Example of realization by software]
The control block of the information processing unit 1 (particularly, the data acquisition unit 111, the probability prediction unit 112, the factor prediction unit 113, the control determination unit 114, the steam amount prediction unit 115, and the control amount determination unit 116) is an integrated circuit (IC chip). It may be realized by a logic circuit (hardware) formed in the above, or it may be realized by software using a CPU (Central Processing Unit).

In the latter case, the information processing unit 1 is a CPU that executes instructions of a program that is software that realizes each function, and a ROM (Read Only Memory) in which the program and various data are readablely recorded by a computer (or CPU). Alternatively, it is equipped with a storage device (referred to as a "recording medium"), a RAM (Random Access Memory) for developing the above program, and the like. Then, the object of the present invention is achieved by the computer (or CPU) reading the program from the recording medium and executing the program. As the recording medium, a "non-temporary tangible medium", for example, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, the program may be supplied to the computer via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. It should be noted that one aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

[Additional notes]
The information processing device according to one aspect of the present invention is an information processing device that performs information processing related to an incineration facility, and includes a data acquisition unit that acquires a plurality of types of predetermined data regarding the operating state of the incineration facility, and the incineration facility. With respect to the predetermined event predicted to occur in the above, at least a part of the above-mentioned predetermined data is obtained from the above-mentioned predetermined data when the above-mentioned predetermined event occurred in the above-mentioned incineration facility in the past and the cause of the predetermined event. It is provided with a factor prediction unit that identifies the cause of the predetermined event by using it for a factor prediction model constructed based on a correspondence relationship.

The control to be performed in order to prevent the occurrence of a predetermined event may differ depending on the cause of the occurrence. Therefore, according to the above configuration, when a predetermined event is predicted to occur in the incinerator, the cause of the occurrence is specified. This makes it possible to determine appropriate control according to the cause of occurrence.

The data acquisition unit acquires the predetermined data at a plurality of different time points and stores the predetermined data in the storage unit, and the factor prediction unit uses each of the predetermined data acquired at the plurality of time points as the factor prediction model. On the other hand, it is preferable to identify the cause of the above-mentioned predetermined event that is predicted to occur.

According to the above configuration, since the cause of the occurrence of the predetermined event is specified by using the predetermined data having different acquisition time points, highly accurate prediction in consideration of the predetermined data at each time point becomes possible. The predetermined data at each time point may be the same type of data or different types of data. For example, the cause may be specified by using the value of the sensor A acquired at a certain time point and the value of the sensor B acquired 10 minutes before that, or the value of the sensor A acquired at a certain time point. And the value of the sensor A acquired 20 minutes before that may be used to identify the cause.

The information processing apparatus includes a probability prediction unit that specifies the probability of occurrence of the predetermined event using at least a part of the predetermined data, and the factor prediction unit is the predetermined event specified by the probability prediction unit. It is preferable to identify the cause of occurrence of the above-mentioned predetermined event in which the probability of occurrence of is equal to or higher than a predetermined threshold.

According to the above configuration, since the occurrence factor is specified when the occurrence probability of the predetermined event is high, the occurrence factor is not specified even when the occurrence probability of the predetermined event is low. Therefore, the amount of information processing can be reduced as compared with the configuration in which the cause of occurrence is specified regardless of the probability of occurrence of a predetermined event.

In the information processing apparatus, when the predetermined event is an event in which the predetermined parameter relating to the operating state of the incineration facility becomes an abnormal value, the predetermined data is used to describe the above when the predetermined event occurs. A parameter value prediction unit that specifies a parameter value is provided, and the factor prediction unit has an occurrence probability specified by the probability prediction unit that is equal to or higher than a predetermined threshold value, and the parameter value specified by the parameter value prediction unit is abnormal. When it is a value, it is preferable to specify the cause of the above-mentioned predetermined event.

According to the above configuration, even if the predetermined parameter specified by the parameter value prediction unit is an abnormal value, the factor prediction unit does not identify the cause unless the probability of occurrence of the event is high. As a result, it is possible to reduce the processing of the information processing apparatus and prevent improper control from being performed in the unlikely event that the prediction is wrong.

It is preferable that the information processing apparatus includes a control determination unit that determines the control to be performed in the incineration facility in order to prevent the occurrence of the predetermined event according to the occurrence factor specified by the factor prediction unit.

According to the above configuration, since the control to be performed in the waste incinerator is determined based on the identified cause, it is possible to control the incinerator appropriately.

In the information processing apparatus, when the predetermined event is an event in which a predetermined parameter relating to the operating state of the incineration facility becomes an abnormal value, at least a part of the predetermined data is used to perform the predetermined event. A parameter value prediction unit that specifies the value of the parameter at the time of occurrence, and a control amount determination unit that determines the control amount in the control determined by the control determination unit according to the value of the parameter specified by the parameter value prediction unit. And, it is preferable to have.

According to the above configuration, the control amount in the control determined by the control determination unit can be determined based on the value of the parameter specified by the parameter value prediction unit. As a result, the incineration facility can be appropriately controlled.

The information processing method according to one aspect of the present invention is an information processing method by an information processing apparatus that performs information processing related to an incineration facility, and includes a data acquisition step of acquiring a plurality of types of predetermined data relating to the operating state of the incineration facility. For a predetermined event that is predicted to occur at the incineration facility, at least a part of the predetermined data is obtained from the predetermined data when the predetermined event occurred at the incineration facility in the past and the predetermined event. It includes a factor prediction step for identifying the cause of the predetermined event by using it for a factor prediction model constructed based on a correspondence relationship with the occurrence factor.

According to the above configuration, the same effect as that of the first aspect is obtained.

The information processing device according to each aspect of the present invention may be realized by a computer. In this case, the information processing device is made into a computer by operating the computer as each part (software element) included in the information processing device. The control program of the information processing device to be realized and the computer-readable recording medium on which the control program is recorded also fall within the scope of the present invention.

The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims, and the embodiments obtained by appropriately combining the technical means disclosed in the different embodiments. Is also included in the technical scope of the present invention. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment.

1 Information processing device 100 Garbage incinerator (incinerator)
111 Data acquisition unit 112 Probability prediction unit 113 Factor prediction unit 114 Control decision unit 115 Steam amount prediction unit (parameter value prediction unit)
116 Control amount determination unit 121 Probability prediction model 122 Factor prediction model 123 Steam amount prediction model

Claims (7)

An information processing device that processes information about incineration facilities.
A data acquisition unit that acquires multiple types of predetermined data related to the operating status of the incinerator,
Regarding a predetermined event that is expected to occur at the incineration facility, at least a part of the predetermined data is used as the predetermined data when the predetermined event occurred at the incineration facility in the past and the occurrence of the predetermined event. By using it for a factor prediction model constructed based on a correspondence relationship with a factor, it is provided with a factor prediction unit that identifies the cause of the predetermined event before the occurrence of the predetermined event. An information processing device characterized by being present. The data acquisition unit acquires the predetermined data at a plurality of different time points and stores the data in the storage unit.
The factor prediction unit is characterized in that it identifies the cause of the predetermined event that is predicted to occur by using each of the predetermined data acquired at a plurality of time points for the factor prediction model. The information processing apparatus according to claim 1. An information processing device that processes information about incineration facilities.
A data acquisition unit that acquires multiple types of predetermined data related to the operating status of the incinerator,
Regarding a predetermined event that is predicted to occur at the incineration facility, at least a part of the predetermined data is used as the predetermined data when the predetermined event occurred at the incineration facility in the past and the occurrence of the predetermined event. A factor prediction unit that identifies the cause of the above-mentioned predetermined event by using it for a factor prediction model constructed based on the correspondence with the factors.
A probability prediction unit for specifying the probability of occurrence of the predetermined event using at least a part of the predetermined data is provided.
The factor prediction unit, information processing apparatus characterized in that the probability of occurrence of the predetermined event the probability prediction unit has identified identifies the cause for the above predetermined event is above a predetermined threshold value. When the predetermined event is an event in which the predetermined parameter relating to the operating state of the incinerator becomes an abnormal value, the parameter for specifying the parameter value at the time of occurrence of the predetermined event using the predetermined data. Equipped with a value prediction unit
The factor prediction unit generates the predetermined event when the probability of occurrence specified by the probability prediction unit is equal to or higher than a predetermined threshold value and the parameter value specified by the parameter value prediction unit is an abnormal value. The information processing apparatus according to claim 3, wherein a factor is specified. An information processing device that processes information about incineration facilities.
A data acquisition unit that acquires multiple types of predetermined data related to the operating status of the incinerator,
Regarding a predetermined event that is predicted to occur at the incineration facility, at least a part of the predetermined data is used as the predetermined data when the predetermined event occurred at the incineration facility in the past and the occurrence of the predetermined event. A factor prediction unit that identifies the cause of the above-mentioned predetermined event by using it for a factor prediction model constructed based on the correspondence with the factors.
In response to the occurrence factors above factor prediction unit has identified, it information processing you said that and a control determination unit that determines control to be performed by the incinerator in order to prevent the occurrence of the predetermined event apparatus. When the predetermined event is an event in which the predetermined parameter relating to the operating state of the incinerator becomes an abnormal value, at least a part of the predetermined data is used to determine the parameter at the time of occurrence of the predetermined event. Parameter value prediction unit that specifies the value, and
The fifth aspect of claim 5, wherein the control amount determination unit that determines the control amount in the control determined by the control determination unit according to the value of the parameter specified by the parameter value prediction unit is provided. Information processing equipment. It is an information processing method using an information processing device that processes information about the incinerator.
A data acquisition step to acquire multiple types of predetermined data related to the operating status of the incineration facility, and
Regarding a predetermined event that is expected to occur at the incineration facility, at least a part of the predetermined data is used as the predetermined data when the predetermined event occurred at the incineration facility in the past and the occurrence of the predetermined event. Includes a factor prediction step that identifies the cause of the predetermined event before the occurrence of the predetermined event by using it for a factor prediction model constructed based on the correspondence with the factors. An information processing method characterized by.

Images