JP7443683B2 - Automatic combustion control method and monitoring center - Google Patents

Description

The present invention relates to an automatic combustion control method and monitoring center for a waste incinerator.

Conventionally, various demands have been made in the field of waste treatment in order to realize a low-carbon society and a recycling-oriented society. Waste incinerators are required not only to efficiently recover heat from combustion exhaust gas, but also to suppress harmful substances such as dioxins and nitrogen oxides (NO _x ) released into the atmosphere. Therefore, automatic waste combustion control is employed in waste incinerators in order to stabilize the combustion of garbage, which is waste (see Patent Documents 1 and 2).

In automatic combustion control performed in a waste incinerator, the automatic combustion control device that controls combustion calculates the set values for operation items, and the monitoring control device performs control based on the calculated set values. . In a waste incinerator, the calorie provided for combustion varies depending on the calorie of the received waste and the stirring condition in the garbage pit where the waste is received and agitated, and the combustion state changes. Therefore, operators and others use a monitoring and control device in a central control room to constantly monitor data obtained from various sensors, alarms accompanying the data, and images taken of combustion conditions. Then, in order to perform operational management that further stabilizes combustion in the waste incinerator and maintains operational control values at predetermined values, the operator manually adjusts the settings of the main operation items from the automatic combustion control device. A so-called driving intervention operation (hereinafter referred to as "intervention operation") is performed. In operation management, factory operators perform manual intervention several times to dozens of times per day to correct combustion control values using various control values to ensure safe and stable operation. ing. In addition to control data and current operating data, operators also consider combustion conditions when deciding whether to intervene manually.

Japanese Patent Application Publication No. 2017-180971 Japanese Patent Application Publication No. 2015-114040

In the prior art waste incinerators described above, manual intervention by an experienced operator is generally performed. It is also necessary to ensure the number of operators so that they can perform intervention operations at all times during operation. However, in recent years, there has been a shortage of experienced operators in waste incinerators, and there has been an increasing need for them to be managed and operated by a small number of people. For these reasons, in the future, it may become difficult to appropriately perform a manual intervention operation even in a state where an intervention operation is required. Even in this case, it was necessary to strictly stabilize combustion and maintain operational control values in the waste incinerator. Therefore, there has been a need to reduce the frequency of manual intervention.

The present invention has been made in view of the above, and an object thereof is to provide an automatic combustion control method and a monitoring center that can significantly reduce the frequency of manual intervention operations by an operator in a waste incinerator. There is a particular thing.

In order to solve the above-mentioned problems and achieve the purpose, an automatic combustion control method according to one aspect of the present invention sets the operating amount reference value of a plurality of operating terminals of a waste incinerator to a preset setting value. an automatic combustion control method executed by an automatic combustion control device that controls combustion of waste inside the waste incinerator based on the manipulated variable reference value; a parameter acquisition step of acquiring sensor information regarding the state of the waste incinerator and facilities related to the waste incinerator, and a control value of the operating end controlled by the automatic combustion control device as input parameters; and a model that has been trained to operate the input parameters. a control step of correcting and controlling the operation amount reference value of the operation end obtained based on the type of the operation end and the correction value of the operation amount reference value; The completed model uses learning sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and learning control values of the operating end controlled by the automatic combustion control device. The type of operating end and the correction value for the operating amount reference value, which correspond to the learning sensor information and the learning control value, are used as input parameters and are set in advance by at least one of machine learning and statistical methods as learning output parameters. It is characterized by being a generated trained model.

In the automatic combustion control method according to one aspect of the present invention, in the above invention, the learning sensor information and the learning control value of the learning input parameter are data used to determine a manual intervention operation by an operator. The correction value for the type of operating end and the reference value of the operating amount included in the learning output parameter is a correction value for the type of operating end and the reference value of the operating amount operated by the operator in the manual intervention operation, The operation-trained model is characterized in that it is a trained model generated by cluster analysis using the learning input parameters and the learning output parameters. In the automatic combustion control method according to one aspect of the present invention, in this configuration, the data used for determining the manual intervention operation by the operator is a control value, an operating value, or It is characterized by including instantaneous value data, data derived based on a plurality of pieces of sensor information, data on fluctuation trends of the sensor information over a predetermined period of time, and data on an hourly moving average of the control value of the operating end. do.

In the automatic combustion control method according to one aspect of the present invention, in the above invention, the sensor information uses learning combustion image data as a learning input parameter and a numerical value corresponding to the learning combustion image data as a learning output parameter. The method is characterized in that the combustion image learned model generated in advance by machine learning includes a numerical value obtained by inputting combustion image data obtained by capturing a combustion state in the waste incinerator.

An automatic combustion control method according to an aspect of the present invention is characterized in that, in the above invention, the learning output parameter includes data for determining the start of the control step and data for determining the end of the control step. shall be.

The automatic combustion control device according to one aspect of the present invention sets a manipulated variable reference value of a plurality of operating ends of a waste incinerator based on a preset setting value, and An automatic combustion control device that controls combustion of waste inside a waste incinerator, the automatic combustion control device comprising sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and the automatic combustion control device. a storage unit that stores the control value of the operating end to be controlled as an input parameter; and inputting the input parameter read from the storage unit into an operation-trained model, and correcting the type of the operating end and the operating amount reference value. a control unit that corrects and controls the operation amount reference value of the operation end obtained based on the operation amount reference value, and the operation learned model is configured to control the internal state of the waste incinerator and the waste Learning sensor information regarding a facility related to an incinerator and a learning control value of the operating end controlled by the automatic combustion control device are used as learning input parameters, and correspond to the learning sensor information and the learning control value. The model is characterized in that it is a learned model generated in advance by at least one of machine learning and statistical methods, using the type of operating end and the correction value for the operating amount reference value as learning output parameters.

According to the automatic combustion control method and monitoring center according to the present invention, it is possible to significantly reduce the frequency of manual intervention operations by an operator in a waste incinerator.

FIG. 1 is an overall configuration diagram schematically showing an incineration facility to which an automatic combustion control device according to an embodiment of the present invention is applied. FIG. 2 is a block diagram showing the configuration of an automatic combustion control device according to an embodiment of the present invention. FIG. 3 is a flowchart for explaining an automatic combustion control method according to an embodiment of the present invention. FIG. 4 is a flowchart for explaining an intervention operation in an automatic combustion control method according to an embodiment of the present invention. FIG. 5 is a graph showing the conventional manual intervention frequency (a) and the manual intervention frequency (b) of the automatic combustion control method according to an embodiment of the present invention.

Hereinafter, one embodiment of the present invention will be described with reference to the drawings. In addition, in all the drawings of one embodiment below, the same or corresponding parts are given the same reference numerals. Moreover, the present invention is not limited to one embodiment described below.

FIG. 1 shows a grate-type garbage incinerator to which an automatic combustion control device according to an embodiment of the present invention is applied. As shown in FIG. 1, a garbage incinerator that is a waste incinerator includes a furnace 1 in which garbage is burned, a garbage inlet 2 into which garbage is input, and a boiler 9. Note that the boiler 9 includes a heat exchanger 9a and a steam drum 9b installed downstream of the furnace outlet 7 of the furnace 1.

Garbage input from the garbage input port 2 is conveyed to the grate 4 by the garbage supply device 3. The reciprocating motion of the grate 4 causes the garbage to be stirred and moved. The garbage on the grate 4 is burned while being dried by blowing combustion air supplied by the combustion air blower 6 into the wind box below the grate 4, thereby producing exhaust gas and ash. The generated ash falls through the ash drop port 5 and is discharged to the outside of the furnace 1.

The total amount of combustion air supplied into the furnace 1 from below the grate 4 is regulated by a combustion air damper 14 provided in the immediate vicinity of the combustion air blower 6. The flow rate of combustion air supplied to each wind box is adjusted by under-grate combustion air dampers 14a, 14b, 14c, and 14d, which are respectively provided in piping that supplies combustion air to each wind box. Ru. That is, the ratio of the flow rate of combustion air supplied to each wind box is adjusted by the under-grate combustion air dampers 14a to 14d. In Fig. 1, the area below the grate 4 is divided into four air boxes along the garbage transport direction, and combustion air is supplied through each air box. The numbers of the wind boxes 14a to 14d and the wind boxes are not necessarily limited to four, and can be changed as appropriate depending on the scale and purpose of the waste incinerator.

Cooling air is blown into the furnace 1 by a cooling air blower 11 from a cooling air inlet 10 provided in the furnace wall. By blowing the cooling air into the furnace 1, unburned components in the combustion gas are further combusted, and the temperature of the furnace wall is prevented from rising excessively. The flow rate of the cooling air supplied into the furnace 1 from the cooling air inlet 10 is adjusted by a cooling air damper 15 provided in the immediate vicinity of the cooling air blower 11.

Along the conveyance direction of the waste in the grate 4, the combustible gas generated during the waste drying process and the main combustion process on the upstream side and the combustion exhaust gas generated during the post-combustion process on the downstream side are separated from the furnace outlet 7 of the furnace 1. The gases merge at a gas mixing section provided on the side. The combustible gas and the combustion exhaust gas that have joined together in the gas mixing section are stirred and mixed again, and then secondary combustion is performed by supplying secondary combustion air. The boiler 9 is installed on the downstream side along the waste transport direction with respect to a portion where secondary combustion is performed (hereinafter referred to as a secondary combustion section). The combustion gas that has undergone secondary combustion is exhausted to the outside from the chimney 8 after its thermal energy is recovered by the heat exchanger 9a of the boiler 9.

Inside the furnace 1, an intermediate ceiling 16 is provided at an upper position along the height direction of the furnace 1. The gas flowing in the furnace 1 is separated by the intermediate ceiling 16 into gas containing a large amount of combustible gas generated during the waste drying process and main combustion process on the upstream side, and combustion exhaust gas generated during the post-combustion process on the downstream side. Can be divided and discharged. Specifically, combustion exhaust gas flows through the flue (main flue) below the intermediate ceiling 16, while gas containing a large amount of flammable gas flows through the flue (sub-flue) above the intermediate ceiling 16. . By combining the combustion exhaust gas and the gas containing a large amount of combustible gas in the gas mixing section, stirring and mixing of the gases in the gas mixing section is further promoted. This makes combustion in the secondary combustion section more stable, suppresses the generation of dioxins during the combustion process, and suppresses the generation of unburned waste. Note that the furnace 1 may have a configuration in which the intermediate ceiling 16 is not provided.

Thermometers serving as sensors for measuring the gas temperature within the furnace 1 are provided at multiple locations within the furnace 1 . Specifically, along the height direction of the furnace 1, a combustion chamber gas thermometer 17 is provided at an intermediate position between the grate 4 and the cooling air inlet 10. A main flue gas thermometer 18 is provided along the height direction of the furnace 1 at a position below the furnace outlet 7. A furnace outlet lower gas thermometer 19 is provided at a lower position of the furnace outlet 7 along the height direction of the furnace 1 . Along the height direction of the furnace 1, a furnace outlet central gas thermometer 20 is provided at a central position of the furnace outlet 7. Along the height direction of the furnace 1, a furnace outlet gas thermometer 21 is provided downstream of the furnace outlet 7 to measure the combustion control temperature. The temperature values measured by the combustion chamber gas thermometer 17, the main flue gas thermometer 18, the furnace outlet lower gas thermometer 19, the furnace outlet middle gas thermometer 20, and the furnace outlet gas thermometer 21 are based on the combustion process. The measured value is stored in the storage unit 34 (see FIG. 2) of the combustion control device 30. The measured temperature value stored in the storage unit 34 is transmitted from the combustion control device 30 to the monitoring center 40 and stored in the storage unit 44 .

The boiler 9 is provided with a boiler outlet oxygen concentration meter 22 on the outlet side that measures the concentration of oxygen (O ₂ ) in the exhaust gas. A gas concentration meter 23 is provided at the entrance of the chimney 8 to measure the concentration of carbon monoxide (CO) and nitrogen oxides (NO _x ) in the exhaust gas. A pipe connecting the outlet of the boiler 9 and the chimney 8 is provided with an exhaust gas flow meter 24 for measuring the amount of exhaust gas. Measured values of gas concentration and flow rate measured by the boiler outlet oxygen concentration meter 22, gas concentration meter 23, and exhaust gas flow meter 24 are stored in the storage unit 34 of the combustion control device 30 as combustion process measurement values. The measured values of the gas concentration and flow rate are transmitted from the combustion control device 30 to the monitoring center 40 and stored in the storage unit 44.

A combustion image capturing section 25 is provided inside the furnace 1 on the downstream side in the transport direction of the waste. The combustion image capturing section 25 captures an image of the combustion state of the garbage on the grate 4 and stores the captured combustion image data in the storage section 34 of the combustion control device 30 . The combustion image data stored in the storage unit 34 is transmitted from the combustion control device 30 to the monitoring center 40 at predetermined time intervals.

The combustion control device 30 is connected to, for example, a private line, a public communication network such as the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), a telephone communication network such as a mobile phone, a public line, or a VPN (Virtual Private Network). ), etc., is connected to the monitoring center 40 via a network (not shown) consisting of one or more combinations of the following.

FIG. 2 is a block diagram showing the configuration of the combustion control device 30 and the monitoring center 40. As shown in FIG. 2, the combustion control device 30 as an automatic combustion control device includes a garbage quality calculation section 31, a manipulated variable reference value adjustment section 32, a manipulated variable standard value correction section 33, a storage section 34, and a manipulated variable adjustment section. 35. Specifically, the waste quality calculation unit 31, the operation amount reference value adjustment unit 32, the operation amount reference value correction unit 33, and the operation amount adjustment unit 35 are A processor such as a Field-Programmable Gate Array (Field-Programmable Gate Array), and a main memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory) (none of which are shown). The storage unit 34 is composed of a storage medium selected from volatile memory such as RAM, non-volatile memory such as ROM, EPROM (Erasable Programmable ROM), hard disk drive (HDD), removable media, etc. . Note that the removable media is, for example, a USB (Universal Serial Bus) memory, or a disc recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a BD (Blu-ray (registered trademark) Disc). be. Furthermore, the storage unit 34 may be configured using a computer-readable recording medium such as an externally attachable memory card.

The storage unit 34 can store an operating system (OS), various programs, various tables, various databases, etc. for executing the operations of the combustion control device 30. Here, the various programs also include an automatic combustion control program that implements processing based on the learned model according to this embodiment. These various programs can also be widely distributed by being recorded on computer-readable recording media such as hard disks, flash memories, CD-ROMs, DVD-ROMs, and flexible disks.

The combustion control device 30 sets the amount of combustion air, the amount of cooling air, the feed rate of the garbage supply device, and Control the grate feed rate. Note that the combustion control device 30 also controls the stoppage and operation of the garbage supply device feed rate and the grate feed rate. The manipulated variable reference value setting relational expression is a relational expression between the waste incineration amount set value or the waste quality set value and the manipulated variable reference value (target value of the manipulated variable), and includes a control parameter as a correction coefficient. The control parameters are adjusted by the manipulated variable reference value adjustment section 32 so as to match the waste incineration amount set value and the waste quality set value. The adjusted control parameters are adjusted by the manipulated variable standard value adjustment unit 32 in response to the changed setting value when at least one of the waste incineration amount setting value and the waste quality setting value is changed. Be changed. By changing the control parameters, the preset manipulated variable reference value is corrected.

The garbage quality calculation unit 31 calculates the garbage quality (lower calorific value of garbage) according to the garbage incineration amount setting value. The manipulated variable reference value adjustment section 32 adjusts the manipulated variable reference value by adjusting the control parameters included in the manipulated variable reference value setting relational expression. The manipulated variable reference value corrector 33 corrects the manipulated variable reference value adjusted by the manipulated variable reference value adjuster 32 based on a predetermined control algorithm (PID control, fuzzy calculation, etc.). The storage unit 34 stores data referenced by the waste quality calculation unit 31, the operation amount reference value adjustment unit 32, and the operation amount reference value correction unit 33. The storage unit 34 stores predetermined operation amount reference value setting relational expressions and control algorithms, as well as preset incineration amount set values and combustion process measurement values obtained as combustion state quantities in the furnace. There is.

The operation amount adjustment unit 35 adjusts the operation amount of each operation end so as to follow the operation amount reference value. Specifically, the operation amount adjustment section 35 includes a combustion air amount adjustment section 36, an air amount ratio adjustment section 36A, a cooling air amount adjustment section 37, a garbage supply device feed speed adjustment section 38, and a grate feed speed adjustment section 39. has. The combustion air amount adjustment section 36 adjusts the manipulated variable so that the combustion air amount follows the manipulated variable reference value (hereinafter referred to as corrected manipulated variable reference value) corrected by the manipulated variable reference value correction section 33. The air amount ratio adjustment section 36A controls each of the under-grate combustion air dampers 14a to 14d to adjust the mutual ratio of flow rates in each wind box. The cooling air amount adjustment section 37 adjusts the amount of operation so that the amount of cooling air follows the corrected amount of operation amount reference value. Here, the amount of combustion air and the amount of cooling air are adjusted by controlling the opening degrees of each of the combustion air damper 14, the under-grate combustion air dampers 14a to 14d, and the cooling air damper 15. . The garbage supply device feed speed adjustment unit 38 adjusts the manipulated variable so that the garbage feed device feed speed follows the corrected manipulated variable reference value. The grate feed speed adjustment section 39 adjusts the manipulated variable so that the grate feed speed follows the corrected manipulated variable reference value. If the manipulated variable reference value is not corrected by the manipulated variable reference value corrector 33, the manipulated variable adjustment section 35 adjusts each manipulated variable based on the uncorrected manipulated variable reference value.

The monitoring center 40 includes a control section 41, an output section 42, an input section 43, and a storage section 44. The control unit 41 specifically includes a processor such as a CPU, a DSP, or an FPGA, and a main storage unit such as a RAM or ROM (none of which is shown). The output unit 42 as an output means displays images of combustion inside the furnace 1 on a display monitor, displays characters and figures on a touch panel display screen, and outputs audio from a speaker under the control of the control unit 41. It is configured to be able to notify the outside of predetermined information by outputting it. The input unit 43 as an input means uses a user interface such as a keyboard, input buttons, levers, a touch panel for manual input provided superimposed on a display such as a liquid crystal display, or a microphone for voice recognition. It consists of The control unit 41 is configured to be able to input predetermined information to the control unit 41 by a user or the like operating the input unit 43 . Note that the output section 42 and the input section 43 may be integrated into an input/output section, and the input/output section may be configured from a touch panel display, a speaker microphone, or the like.

The storage unit 44 is composed of a storage medium selected from volatile memory such as RAM, nonvolatile memory such as ROM, EPROM, HDD, removable media, and the like. Note that the removable medium is, for example, a USB memory, or a disk recording medium such as a CD, DVD, or BD. Furthermore, the storage unit 44 may be configured using a computer-readable recording medium such as a memory card that can be loaded from the outside. The storage unit 44 can store an OS, various programs, various tables, various databases, etc. for executing operations of the monitoring center 40. Here, the various programs include an automatic combustion control program that implements control using the operation-trained model according to the present embodiment, and an automatic determination processing program that implements determination processing using the combustion image-trained model. Specifically, the storage unit 44 stores an operation learned model 44a and a combustion image learned model 44b. Note that the storage unit 44 may be provided in another server that can communicate via various networks, or may be provided in the combustion control device 30. Further, these various programs can also be widely distributed by being recorded on computer-readable recording media such as hard disks, flash memories, CD-ROMs, DVD-ROMs, and flexible disks.

The control unit 41 loads the program stored in the storage unit 44 into the work area of the main storage unit and executes it, and controls each component through the execution of the program to realize functions that meet a predetermined purpose. can. In this embodiment, the function of the learning section 41a is executed by the execution of the program by the control section 41, and the processing of the operation learned model 44a and combustion image learned model 44b, which are the programs, is executed.

Here, a method for generating the operationally learned model 44a, which is a program stored in the storage unit 44, will be described. That is, the operation learned model 44a determines the conditions for determining an intervention operation, the amount of operation at the time of the intervention operation, and the return to automatic combustion control from the intervention operation in the intervention operation control acquired from the operator's experience in the operation management work of the incinerator. It is generated by deriving the return conditions etc. when doing so through cluster analysis. For example, the points at which the speed of the grate 4 is increased or decreased by operator operations can be extracted by cluster analysis from the relationship between the combustion control temperature and the combustion chamber temperature, or the points at which the speed of the grate 4 is increased or decreased by the operator's operation can be extracted from the relationship between the combustion control temperature and the NO _x concentration. It can be extracted from relationships using cluster analysis.

In addition to the speed of the grate 4, the data used to generate the operation-trained model 44a includes process values obtained from sensors related to combustion control as learning sensor information, and operation management calculated from the process values. This includes values used in the control of combustion, numerical combustion data, etc. The combustion quantification data is combustion quantification data obtained by digitizing the combustion state obtained by the combustion image learned model 44b from combustion images periodically obtained by the combustion image capturing section 25. The data used to generate the operationally learned model 44a further includes a control value by the combustion control device 30 as a learning control value. These learning sensor information and learning control values become learning input parameters when generating the operation-trained model 44a.

The learning output parameter when generating the operation-trained model 44a is a correction amount obtained from the control value operated by the operator. In addition, the learning output parameters include the start timing of switching the control mode between automatic combustion control by the combustion control device 30 and control by the monitoring center 40 when the operator performs an intervention operation, and the timing at which the control mode is switched between automatic combustion control by the combustion control device 30 and control by the monitoring center 40 after switching the control mode. It includes parameters for the duration of control and the timing at which control by the monitoring center 40 ends.

Further, the learning unit 41a of the control unit 41 of the monitoring center uses machine learning such as cluster analysis to derive data correlations when an operator performs an intervention operation from the above-described learning input parameters and learning output parameters. As a result, a driving operation pattern in which the operator performs an intervention operation is generated as the operation learned model 44a. The generated operationally learned model 44a is stored in the storage unit 44. The control unit 41 executes control of various intervention operations according to the driving movement pattern based on the operation learned model 44a generated by the learning unit 41a. Note that the operation learned model 44a may be generated by performing machine learning such as cluster analysis on another computer or the like to derive the correlation of data when an operator performs an intervention operation. In this case, the generated operationally learned model 44a is supplied from the computer that performed the machine learning to the learning section 41a and stored in the storage section 44. In addition to machine learning, the operation-trained model 44a may be generated by deriving correlations using statistical methods such as average, quartile, and correlation analysis. That is, by analyzing multiple conditions related to complex intervention operations that differ depending on each operator using at least one of machine learning and statistical methods, it is possible to determine the starting and ending points of intervention operations performed by multiple operators; It is possible to extract the amount of correction for each operating end set by the operator. Note that the trained model is also referred to as a model.

Furthermore, the above-described combustion image trained model 44b uses a plurality of learning combustion image data captured by the combustion image capturing section 25 as learning input parameters. In addition, the combustion image trained model 44b provides, as learning output parameters, data that quantifies the strength of the combustion state, data that quantifies the position of the burnout point of combustion, and digitizes the degree of occurrence of unburned matter. Use the data obtained. The combustion image trained model 44b is generated by machine learning such as deep learning using the above-described learning input parameters and learning output parameters as teacher data. When a combustion image is input, the combustion image trained model 44b digitizes the combustion state based on the input combustion image. Specifically, the combustion image trained model 44b classifies the combustion state into multiple types, for example, 8 types, determines the confidence level for each of the 8 types, and converts it into a numerical value based on each confidence level. I do. Note that it may be classified into seven or fewer types or more than eight types.

Table 1 shows examples of measurement targets and operation targets used in the operation-trained model 44a described above, and parameters used.

In Table 1, the instantaneous value is a measured value at a predetermined point in time, and the 1-hour average value is a 1-hour moving average value from the instantaneous value to 1 hour before. The difference from the target value is the difference between the instantaneous value and the preset target value. The slope of several minutes to several tens of minutes means any slope of the instantaneous value from several minutes to several tens of minutes. The average value over several minutes to several tens of minutes means any one of the average values of instantaneous values over several minutes to the average value over several tens of minutes. Here, several minutes may be any value from 1 to 9 minutes, and several tens of minutes may be any value from 10 minutes to 60 minutes. The one-hour average value, the slope of several minutes to several tens of minutes, and the average value of several minutes to several tens of minutes are indicators that indicate a tendency of fluctuation over a predetermined period of time. The control value is a control value for each type of operating end controlled by the combustion control device 30, and the operating value is an actual value for the type of operating end being operated.

Next, an automatic combustion control method according to an embodiment of the present invention will be described. FIG. 3 is a flowchart showing control operations by the combustion control device 30 and the monitoring center 40 to explain the automatic combustion control method according to the present embodiment. In the flowchart shown in FIG. 3, steps ST1 to ST3 and ST5 are executed by the combustion control device 30, and step ST4 is a process executed by the monitoring center 40.

As shown in FIG. 3, in step ST1 executed by the combustion control device 30, the operator sets a target waste incineration amount as an incineration amount setting value. Note that instead of the incineration amount setting value, the operator may set a target waste incineration amount as the evaporation amount setting value. The set incineration amount setting value is stored in the storage unit 34. As a result, automatic combustion control for the incinerator is started.

Next, proceeding to step ST2, the waste quality calculation unit 31 calculates the amount of heat input other than waste, such as the amount of heat of combustion heated air, and the amount of heat input into the furnace The waste quality, which is the lower calorific value of the waste, is calculated based on the planned value of the amount of heat discharged from the waste and the amount of heat recovered as steam, and is set as the waste quality setting value. The waste quality setting value is stored in the storage unit 34.

Next, proceeding to step ST3, the operation amount reference value adjustment section 32 sets the values stored in the storage section 34 based on the setting values including the incineration amount setting value and the waste quality setting value stored in the storage section 34. The reference value of each manipulated variable is calculated by referring to the manipulated variable reference value setting relational expression. After the operating amount reference value is set in this manner, the operating amount of each operating end is controlled to follow the operating amount reference value, and the waste incinerator is operated.

Next, the process moves to step ST4 executed by the monitoring center 40. In step ST4, the instantaneous values of the measurement targets shown in Table 1 are input as sensor information to the monitoring center 40 while the furnace 1 is in operation. The sensor information is sensor information measured on the internal state of the furnace 1 and a facility related to the furnace 1, specifically, for example, a power generation facility for generating electric power. The input sensor information is stored in the storage unit 44 as a parameter (parameter acquisition step). The control unit 41 of the monitoring center 40 monitors fluctuations in the instantaneous values of the measurement targets stored in the storage unit 44 , and also monitors changes in the instantaneous values of the measurement targets input from the combustion control device 30 and read out from the storage unit 44 . , calculate the parameters used. The learning unit 41a of the control unit 41 uses the operation-trained model 44a to determine whether or not an intervention operation by the monitoring center 40 is necessary based on the input instantaneous value of the measurement target and the calculated usage parameters.

FIG. 4 is a flowchart for explaining the judgment of intervention operation and the derivation of the correction amount by the monitoring center 40 in step ST4 of FIG. Control steps are executed according to the flowchart shown in FIG. As shown in FIG. 4, in step ST21, the learning unit 41a of the control unit 41 inputs the usage parameters shown in Table 1 as input parameters to the operation-trained model 44a. The learning unit 41a determines whether or not it is necessary to correct the operation amount reference value, that is, whether or not an intervention operation is necessary, based on the operation learned model 44a. If the learning unit 41a determines in step ST21 that an intervention operation is necessary, the process moves to step ST22.

In step ST22, the control unit 41 of the monitoring center 40 switches the operation of the incinerator from automatic combustion control (ACC) by the combustion control device 30 to control based on the operation learned model 44a by the learning unit 41a. The learning unit 41a derives a correction amount (corrected operation amount reference value) for correcting the operation amount reference value based on the input usage parameter.

In step ST23, the control unit 41 of the monitoring center 40 outputs the corrected manipulated variable reference value. Proceeding to step ST24, as shown in FIG. 2, the correction operation amount reference value derived by the learning section 41a is adjusted to 38 and a manipulated variable adjustment section 35 including a grate feed speed adjustment section 39 . As a result, the control unit 41 controls the combustion air damper 14, the cooling air damper 15, the under-grate combustion air dampers 14a to 14d, the waste supply device 3, and the grate 4, which are the operation ends.

As shown in FIG. 4, the learning unit 41a determines, based on the operation learned model 44a, when the upper limit of the time to end the intervention operation has been reached (step ST25), or when the usage parameters have reached the condition for ending the intervention. If so (step ST26), the process moves to step ST27. In step ST27, the control unit 41 changes the operation control of the incinerator from control based on the operation learned model 44a by the learning unit 41a to automatic combustion control (ACC) by the combustion control device 30 by ending the intervention operation. Switch.

In step ST27, when the process is switched from the processing by the monitoring center 40 to the automatic combustion control by the combustion control device 30, the process returns to FIG. 3 and proceeds to step ST5. In step ST5, the waste quality calculation unit 31 of the combustion control device 30 determines whether or not waste is input. When the waste quality calculation unit 31 determines that waste has been thrown in (step ST5: Yes), the process returns to step ST2. When the waste quality calculation unit 31 determines that no waste has been input (step ST5: No), the process returns to step ST4. As described above, automatic combustion control of the incinerator using the learned model by machine learning is executed.

(Example)
Next, the effects obtained when the automatic combustion control method using the combustion control device 30 and the monitoring center 40 configured as described above are executed will be described. FIG. 5 is a graph showing the frequency of manual intervention operations performed by an operator in two different furnaces, a first furnace and a second furnace. FIG. 5(a) is a graph showing the average number of operations per day in which the operator performed intervention operations in the first furnace and the second furnace in the case of the conventional automatic combustion control method. FIG. 5(b) shows one day when the operator performs intervention operations in the first furnace and the second furnace when the automatic combustion control method according to the above-described embodiment is applied to the waste supply system, the ventilation system, etc. It is a graph showing the average number of operations. Note that the garbage supply system is an intervention operation performed on the garbage supply device 3 by the garbage supply device feed speed adjustment section 38 and on the grate 4 by the grate feed speed adjustment section 39. Further, the ventilation system and the like refers to intervention operations performed by the combustion air amount adjustment section 36 on the combustion air damper 14 and the cooling air amount adjustment section 37 on the cooling air damper 15. FIG. 5B also shows the average number of operations per day in which the control unit 41 of the monitoring center 40 performs intervention operations based on the operation learned model 44a.

As shown in FIG. 5, the operator's manual intervention operations on the waste supply system of the first furnace were an average of 10.2 times per day in the conventional automatic combustion control method, compared to 10.2 times per day in the conventional automatic combustion control method. It can be seen that the automatic combustion control method has reduced the number of combustions to 0.3 times per day on average. Similarly, the automatic combustion control method according to one embodiment requires manual operator intervention on the waste supply system of the second furnace, compared to an average of 18.3 times per day in the conventional automatic combustion control method. It can be seen that this has decreased to 0.2 times per day on average. In addition, in the automatic combustion control method according to one embodiment, the average number of operations per day in which the monitoring center 40 performs an intervention operation on the waste supply system based on the operation learned model 44a is 17.3 times in the first furnace. , and 16.3 times in the second furnace.

Furthermore, from FIG. 5, when the automatic combustion control method according to one embodiment is executed on the blower system, etc., the average number of manual intervention operations per day is 5.9 times in the first furnace, compared to 5.9 times in the conventional case. It can be seen that the number of times in the second furnace was reduced to 0.5 times compared to 12.2 times in the conventional furnace, and to 0.0 times in the second furnace. That is, it can be seen that in the automatic combustion control method according to the above-described embodiment, the number of intervention operations can be reduced for the ventilation system as well as for the waste supply system.

According to the embodiment described above, in a waste incinerator, intervention operations that were previously performed by skilled or experienced operators (hereinafter referred to as skilled operators) based on their own judgment can be performed using, for example, cluster analysis instead of skilled operators. By executing the learning unit 41a based on the operation learned model 44a, which is a program generated by machine learning, the control unit 41 of the monitoring center 40 can perform stable combustion control. This can be significantly reduced, and the operation management of waste incinerators can be automated.

In other words, while conventional automatic combustion control was performed based only on process values, automatic combustion control according to one embodiment adds control that incorporates combustion state judgments similar to those made by a skilled operator. can do. This makes it possible to establish a technology that uses artificial intelligence using a trained model to replace the human eye and skilled technology in determining combustion conditions. Therefore, combustion control that includes the combustion state in addition to process signals becomes possible.

The present invention makes it possible to determine intervention conditions by analyzing a large amount of performance data to determine whether to start driving intervention, to correct a reference operation amount value in driving intervention, to end driving intervention, or to set an average intervention time.

Although one embodiment of the present invention has been specifically described above, the present invention is not limited to the above-described one embodiment, and various modifications based on the technical idea of the present invention are possible. For example, the numerical values listed in the above-mentioned embodiment are merely examples, and different numerical values may be used as necessary. The invention is not limited.

For example, the input parameters and output parameters listed in the above-described embodiments are merely examples, and input parameters and output parameters different from these may be used as necessary.

For example, although the storage unit 44 stores the operation trained model 44a and the combustion image trained model 44b, the combustion image trained model 44b can be communicated with the monitoring center 40 via a network such as a public network. It is also possible to store it in the storage unit of a combustion image determination server that performs combustion image determination. In this case, the combustion image data captured by the combustion image capturing section 25 is transmitted to the combustion image determination server via the network and stored in the storage section. After that, the control unit of the combustion image judgment server discriminates and classifies the combustion state based on the combustion image learned model 44b, derives a numerical value corresponding to the combustion state as a result of the discrimination and classification, and sends the result to the monitoring center. Send to 40. In the monitoring center 40, the received numerical values are input into the operation learned model 44a of the control unit 41, and each operating end is controlled based on the obtained correction amount.

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

1 Furnace 2 Inlet 3 Supply device 4 Grate 5 Ash falling port 6 Combustion air blower 7 Furnace outlet 8 Chimney 9 Boiler 9a Heat exchanger 9b Steam drum 10 Cooling air inlet 11 Cooling air blower 14 Combustion air damper 14a, 14b, 14c, 14d Combustion air damper under the grate 15 Cooling air damper 16 Intermediate ceiling 17 Combustion chamber gas thermometer 18 Main flue gas thermometer 19 Furnace outlet lower gas thermometer 20 Furnace outlet middle gas thermometer 21 Furnace outlet gas thermometer 22 Boiler outlet oxygen concentration meter 23 Gas concentration meter 24 Exhaust gas flow meter 25 Combustion image capturing section 30 Combustion control device 31 Refuse quality calculation section 32 Manipulated variable reference value adjustment section 33 Manipulated variable standard value correction section 34 Storage section 35 Operation amount adjustment section 36 Combustion air amount adjustment section 37 Cooling air amount adjustment section 38 Supply device feed speed adjustment section 39 Grate feed speed adjustment section 40 Monitoring center 41 Control section 41a Learning section 42 Output section 43 Input section 44 Memory Part 44a Operation trained model 44b Combustion image trained model

Claims (6)

Setting operating amount reference values of a plurality of operating ends of the waste incinerator based on preset setting values, and controlling combustion of waste inside the waste incinerator based on the operating amount reference values. An automatic combustion control method executed by a monitoring center capable of communicating with an automatic combustion control device,
Sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and a control value of the operating end controlled by automatic combustion control by the automatic combustion control device are acquired as input parameters. a parameter acquisition step;
It is determined whether or not an intervention operation is required to correct the operation amount reference value, and when it is determined that the intervention operation is necessary, the operation end value obtained by inputting the input parameters into the operation learned model is determined. The intervention operation for correcting the operation amount reference value of the operating end is performed according to the type and the correction value of the operation amount reference value, and the result obtained by inputting the input parameters to the operation learned model is a control step of performing control to end the intervention operation and return to the automatic combustion control when a return condition is reached to end the operation and return to the automatic combustion control;
The operation-trained model includes learning sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator and the automatic combustion, which have been acquired in advance to generate the operation-learned model. A learning control value of the operating end controlled by a control device is used as a learning input parameter, and a correction value for the operating end type and operating amount reference value corresponding to the learning sensor information and the learning control value. is a trained model generated in advance by machine learning with as the learning output parameter,
The learning sensor information and the learning control value of the learning input parameter are data used to determine whether to start the manual intervention operation by the operator, and the learning output parameter is the data used to determine whether the operator should start the manual intervention operation. including the type of operating end operated in the operation, a correction value for the operating amount reference value, and data used to determine the end of the manual intervention operation by the operator,
The operation learned model uses the learning input parameters and the learning output parameters to determine a judgment condition for the intervention operation, a correction amount for the operating end, and a method for returning to the automatic combustion control from the intervention operation. An automatic combustion control method characterized in that the model is a trained model generated by cluster analysis to derive the return condition. The data used for determining the start of the operator's manual intervention operation is derived based on the control value, operating value, or instantaneous value data of the operating end in the waste incinerator, and the plurality of sensor information. 2. The automatic combustion control method according to claim 1, further comprising data on a fluctuation trend of the sensor information over a predetermined period of time, and data on a one-hour moving average of the control value of the operating end. The data used to determine the end of the manual intervention operation by the operator includes data on the operating value or instantaneous value of the operating end in the waste incinerator, data derived based on the plurality of sensor information, The automatic combustion control method according to claim 2, further comprising data on a fluctuation trend of sensor information over a predetermined period of time, and data on a one-hour moving average of the control value of the operating end. Setting operating amount reference values of a plurality of operating ends of the waste incinerator based on preset setting values, and controlling combustion of waste inside the waste incinerator based on the operating amount reference values. An automatic combustion control method executed by a monitoring center capable of communicating with an automatic combustion control device, the method comprising:
a parameter acquisition step of acquiring sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and a control value of the operating end controlled by the automatic combustion control device as input parameters;
a control step of correcting and controlling the operation amount reference value of the operation end based on the type of the operation end and the correction value of the operation amount reference value obtained by inputting the input parameter into the operation learning model; , including;
The operation-trained model includes learning sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator and the automatic combustion, which have been acquired in advance to generate the operation-learned model. A learning control value of the operating end controlled by a control device is used as a learning input parameter, and a correction value for the operating end type and operating amount reference value corresponding to the learning sensor information and the learning control value. is a trained model generated in advance by at least one of machine learning and statistical methods, with
The sensor information is applied to the combustion image learned model generated in advance by machine learning, with the combustion image data for learning as the input parameter for learning and the numerical value corresponding to the combustion image data for learning as the output parameter for learning. An automatic combustion control method characterized by including a numerical value obtained by inputting combustion image data obtained by capturing a combustion state in an incinerator. Setting operating amount reference values of a plurality of operating ends of the waste incinerator based on preset setting values, and controlling combustion of waste inside the waste incinerator based on the operating amount reference values. A monitoring center capable of communicating with an automatic combustion control device,
Sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and the control value of the operating end controlled by automatic combustion control by the automatic combustion control device are stored as input parameters. storage section and
Determining whether or not an intervention operation for correcting the operation amount reference value is necessary, and when determining that the intervention operation is necessary, inputting the input parameters read from the storage unit into the operation learned model. Further, the intervention operation for correcting the operation amount reference value of the operation end is performed according to the type of the operation end and the correction value of the operation amount reference value, and the input parameters are input to the operation learned model to obtain the obtained results. a control unit that performs control to end the intervention operation and return to the automatic combustion control when the result of the intervention becomes a return condition for ending the intervention operation and returning to the automatic combustion control. ,
The operation-trained model includes learning sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator and the automatic combustion, which have been acquired in advance to generate the operation-learned model. A learning control value of the operating end controlled by a control device is used as a learning input parameter, and a correction value for the operating end type and operating amount reference value corresponding to the learning sensor information and the learning control value. is a trained model generated in advance by machine learning with as the learning output parameter,
The learning sensor information and the learning control value of the learning input parameter are data used to determine whether to start the manual intervention operation by the operator, and the learning output parameter is the data used to determine whether the operator should start the manual intervention operation. including the type of operating end operated in the operation, a correction value for the operating amount reference value, and data used to determine the end of the manual intervention operation by the operator,
The operation learned model uses the learning input parameters and the learning output parameters to determine the conditions for determining the intervention operation, the amount of correction of the operating end, and the method for returning to the automatic combustion control from the intervention operation. A monitoring center characterized in that the model is a trained model generated by cluster analysis to derive the return condition. Setting operating amount reference values of a plurality of operating ends of the waste incinerator based on preset setting values, and controlling combustion of waste inside the waste incinerator based on the operating amount reference values. A monitoring center capable of communicating with an automatic combustion control device,
a storage unit that stores sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator, and a control value of the operating end controlled by the automatic combustion control device as input parameters;
Correcting the operation amount reference value of the operation end based on the type of the operation end and the correction value of the operation amount reference value obtained by inputting the input parameter read from the storage unit into the operation-trained model. a control unit for controlling the
The operation-trained model includes learning sensor information regarding the internal state of the waste incinerator and facilities related to the waste incinerator and the automatic combustion acquired in advance to generate the operation-learned model. A learning control value of the operating end controlled by a control device is used as a learning input parameter, and a correction value for the operating end type and operating amount reference value corresponding to the learning sensor information and the learning control value. is a trained model generated in advance by at least one of machine learning and statistical methods, with
The sensor information is applied to the combustion image learned model generated in advance by machine learning, with the combustion image data for learning as the input parameter for learning and the numerical value corresponding to the combustion image data for learning as the output parameter for learning. A monitoring center characterized by including numerical values obtained by inputting combustion image data obtained by capturing combustion conditions in an incinerator.

Images