JP2023005444A - Controller of incinerator facility - Google Patents

Abstract

To improve delay of control depending on change in a supply amount of an object to be burned, such as waste.SOLUTION: A controller of an incinerator facility has a furnace body that conveys an object to be incinerated while burning it, and a feeder that supplies the object to be incinerated to the furnace body. The controller comprises: an image information acquisition unit that periodically acquires image information including a feeder vicinity area; an image information recognition unit that recognizes whether or not the object to be incinerated in the feeder vicinity area protrudes from the furnace body based on image information; and a supply state determination unit that when it is continuously recognized for a predetermined time that the object to be incinerated protrudes from the furnace body, determines that there is a sign that the object to be incinerated is being excessively supplied to the furnace body.SELECTED DRAWING: Figure 4

Description

The present disclosure relates to a controller for an incinerator installation.

Patent Document 1 discloses the following waste incinerator. That is, in the waste incinerator described in Patent Document 1, based on the difference image between the image of the waste before falling into the furnace and the image of the waste after falling into the furnace, the waste actually supplied to the furnace The amount of waste supplied is sensed. Further, in the waste incinerator described in Patent Document 1, when the current value of the waste supply amount is higher than the predetermined supply amount range, the waste supply speed is reduced to the dust collector and the waste is transferred to the grate. Decrease the amount of waste supplied to the grate by issuing a command to reduce the amount of waste supplied to the furnace, and a command to increase the amount of primary air for combustion to promote waste combustion and change the operating conditions. At the same time, control is performed to promote the combustion of waste on the grate and reduce the amount of waste on the grate.

JP 2020-128837 A

However, in the waste incinerator described in Patent Document 1, the operating conditions and the like are changed based on the current value of the waste supply amount. There was a problem that there was a delay in

The present disclosure has been made to solve the above problems, and provides a control device for an incinerator facility that can improve control delays in response to changes in the supply amount of combustible materials such as waste. intended to

In order to solve the above problems, an incinerator facility control device according to the present disclosure includes a furnace body for burning and conveying materials to be incinerated, and a feeder for supplying the materials to be incinerated to the furnace body. A control device for equipment, comprising: an image information acquiring unit that periodically acquires image information including the area near the feeder; an image information recognition unit for recognizing whether or not the object to be incinerated is in a protruding state; and a supply state determination unit that determines that there is a sign of excessive supply of the gas to the furnace body.

According to the control device for the incinerator facility of the present disclosure, it is possible to improve the delay in the control according to the change in the supply amount of the combustible material such as waste.

1 is a schematic diagram showing a configuration example of incinerator equipment according to an embodiment of the present disclosure; FIG. 1 is a block diagram showing a configuration example of a control device according to an embodiment of the present disclosure; FIG. FIG. 2 illustrates an example infrared image according to an embodiment of the present disclosure; 4 is a flow chart showing an operation example of the control device according to the embodiment of the present disclosure; FIG. 4 is a schematic diagram for explaining an operation example of the control device according to the embodiment of the present disclosure; FIG. 4 is a schematic diagram for explaining an operation example of the control device according to the embodiment of the present disclosure; FIG. 4 is a schematic diagram for explaining an operation example of the control device according to the embodiment of the present disclosure; FIG. 4 is a schematic diagram for explaining an operation example of the control device according to the embodiment of the present disclosure; FIG. 4 is a schematic diagram for explaining an operation example of the control device according to the embodiment of the present disclosure; 1 is a schematic block diagram showing the configuration of a computer according to an embodiment of the present disclosure; FIG.

(Configuration of control device for incinerator equipment)
An incinerator facility control device according to an embodiment of the present disclosure will be described below with reference to FIGS. 1 to 10. FIG. FIG. 1 is a schematic diagram showing a configuration example of incinerator equipment according to an embodiment of the present disclosure. FIG. 2 is a block diagram illustrating a configuration example of a control device according to an embodiment of the present disclosure; FIG. 3 is a diagram illustrating an example of an infrared image according to an embodiment of the present disclosure; FIG. 4 is a flow chart showing an operation example of the control device according to the embodiment of the present disclosure. 5 to 9 are schematic diagrams for explaining an operation example of the control device according to the embodiment of the present disclosure. FIG. 10 is a schematic block diagram showing the configuration of a computer according to an embodiment of the present disclosure; In each figure, the same reference numerals are used for the same or corresponding configurations, and the description thereof will be omitted as appropriate.

(Composition of incinerator equipment)
FIG. 1 shows a configuration example of an incinerator facility 100 according to an embodiment of the present disclosure. In the exemplary form shown in FIG. 1, the incinerator installation 100 is a stoker-type refuse incinerator with solid fuel Fg such as municipal solid waste, industrial waste, or biomass. Note that the incinerator facility 100 is not limited to a stoker-type garbage incinerator.

As shown in FIG. 1, the incinerator facility 100 includes a hopper 102, a feeder section 104, a combustion chamber 108, an extrusion device 110 (dust supply device), an air supply device 112, a heat recovery boiler 114, and an attenuator. It includes a warm tower 116 , a dust collector 118 and a chimney 120 . The combustion chamber 108 is an example of a furnace body that burns and conveys the incinerator according to the present disclosure. The extrusion device 110 is an example of a feeder that supplies incinerators to the furnace body according to the present disclosure.

Feeder section 104 is a passageway that extends toward combustion chamber 108 . The feeder section 104 is configured such that the solid fuel Fg, which is a combustible material such as waste (garbage) thrown into the hopper 102, accumulates. Assuming that the direction in which the solid fuel Fg moves in the incinerator facility 100 is the movement direction W1, the downstream end 121 of the feeder section 104 on the downstream side in the movement direction W1 (the end of the feeder section 104 on the combustion chamber 108 side) is It connects with the inlet 122 of the combustion chamber 108 .

The pushing device 110 has a pushing arm 124 for pushing out the solid fuel Fg accumulated in the feeder section 104 through the inlet 122 into the combustion chamber 108 . The pushing arm 124 is configured to be movable in the feeder section 104 from the upstream side to the downstream side in the moving direction W1 and from the downstream side to the upstream side. That is, the pushing arm 124 reciprocates in the feeder section 104 along the extending direction (horizontal direction) of the feeder section 104 .

Combustion chamber 108 includes a grate 126 (stoker) onto which solid fuel Fg pushed into combustion chamber 108 via inlet 122 falls. This grate 126 corresponds to the floor of the combustion chamber 108 . The grate 126 is configured to move the solid fuel Fg on the grate 126 away from the inlet 122 (from the upstream side to the downstream side in the movement direction W1). Combustion chamber 108 also includes a drying zone 128, a combustion zone 130, and a post-combustion zone 132, which are arranged in order from upstream to downstream in movement direction W1. The drying zone 128 dries the solid fuel Fg with heat within the combustion chamber 108 . Combustion zone 130 raises flame 131 to burn solid fuel Fg. The post-combustion zone 132 completely burns the burnt-out that was not burned out in the combustion zone 130 . The solid fuel Fg dried, burned, and post-burned in the combustion chamber 108 becomes ash 135 and discharged outside the incinerator facility 100 .

The air supply device 112 supplies primary air used for burning the solid fuel Fg and secondary air used for reducing the concentration of unburned gas such as carbon monoxide generated by burning the solid fuel Fg to the combustion chamber 108 . configured to supply to In the exemplary form shown in FIG. 1, the air supply device 112 includes an air supply tube 136 and a blower 138 mounted on the air supply tube 136 . A portion of the air flowing through the air supply pipe 136 is supplied as primary air from the fire grate 126 to the lower portion of the combustion chamber 108 via the first flow control valve 140, and the remaining portion is supplied as secondary air. The fuel is supplied from the side wall of the combustion chamber 108 to the upper portion of the combustion chamber 108 via the second flow control valve 142 . The air supply device 112 functions as a secondary air supply device that supplies secondary air to the upper portion of the combustion chamber 108 . It should be noted that in the exemplary configuration shown in FIG. 1, primary air is provided to each of the dry zone 128, the combustion zone 130, and the post-combustion zone 132 of the combustion chamber 108. As shown in FIG.

Heat recovery boiler 114, cooling tower 116, dust collector 118, and chimney 120 are each provided in flue 144 of incinerator facility 100 through which exhaust gas 143 produced by burning solid fuel Fg flows. The exhaust gas 143 flows through the heat recovery boiler 114, the cooling tower 116, the dust collector 118, and the stack 120 in this order. The heat recovery boiler 114 produces steam from the thermal energy of the exhaust gas 143 . The temperature reducing tower 116 lowers the temperature of the exhaust gas 143 that has passed through the heat recovery boiler 114 . The dust collector 118 collects fly ash contained in the flue gas 143 that has passed through the temperature reducing tower 116 . The chimney 120 discharges the exhaust gas 143 that has passed through the dust collector 118 to the outside of the incinerator facility 100 . Note that the steam generated by the heat recovery boiler 114 may be configured to be supplied to a steam turbine (not shown).

(Configuration of control device)
The control device 4 applied to the incinerator facility 100 described above is a control device of the incinerator facility 100 having a combustion chamber 108 for burning and conveying the materials to be incinerated, and an extrusion device 110 for supplying the materials to be incinerated to the combustion chamber 108. It is a control device. The control device 4 has the following units as a functional configuration composed of a combination of a computer, hardware such as peripheral devices of the computer, and software such as programs executed by the computer. That is, the control device 4 includes an image information acquisition unit 41, an image information recognition unit 42, a supply state determination unit 43, a combustion air amount control unit 44, a feeder control unit 45, an excess supply detection unit 46, A protrusion amount detection unit 47 , a model learning unit 48 , and a storage unit 49 are provided. The storage unit 49 also stores a plurality of trained models 491 and a plurality of image information 492 .

The image information acquisition unit 41 periodically acquires image information including an image signal representing a feeder vicinity area, which is an area including the feeder unit 104 and the like photographed by the imaging device 2 . In the present embodiment, the image information includes an image signal representing a captured image, information representing the date and time when the image signal was captured, information representing the total stroke length of the pushing arm 124 at the time of shooting (total pushing length of the feeder), and the like. may contain. The total stroke length of the push arm 124 is the total length of the push arm 124 moved from upstream to downstream in the W1 direction, starting from the time when an excessive supply of incinerators (also called "dumping") occurs. is. The feeder vicinity area is, for example, an area including the front surface Fr of the solid fuel Fg as a target area.

The imaging device 2 is configured to capture an infrared image (thermal image) of the solid fuel Fg deposited in the feeder section 104 of the incinerator facility 100 before it falls into the combustion chamber 108. ing. An infrared image of the solid fuel Fg captured by the imaging device 2 is sent to the control device 4 in real time. In the exemplary form shown in FIG. 1, the imaging device 2 captures an infrared image of the front surface Fr facing the combustion chamber 108 among the surfaces of the solid fuel Fg before falling into the combustion chamber 108. It is provided at the bottom 145 of the combustion chamber 108 located downstream of the post-combustion region 132 of the combustion chamber 108 in the movement direction W1. The imaging device 2 can capture an infrared image of the front surface Fr of the solid fuel Fg protruding from the inlet 122 of the combustion chamber 108 . Note that the imaging device 2 may be provided at a location other than the furnace bottom 145 of the combustion chamber 108 as long as the infrared image of the front surface Fr of the solid fuel Fg can be captured.

Also, the imaging device 2 is, for example, an infrared camera, and detects infrared rays in a predetermined wavelength range with little radiation from the flame 131 . In this case, the range of the predetermined wavelength band is, for example, 2 μm or more and 5 μm or less. In order to capture an infrared image of the front surface Fr of the solid fuel Fg while suppressing the influence of the flame 131, the predetermined wavelength range is 3.8 μm or more and 4.2 μm or less. Note that the target wavelength range for imaging as an infrared image is 0.8 μm to 1000 μm. By passing this wavelength band through a band-pass filter or the like, it is possible to use only a part of the wavelengths as necessary.

Further, the imaging device 2 is not limited to an infrared camera as long as it can capture an infrared image of the front surface Fr of the solid fuel Fg beyond the flame 131 . In some embodiments, imaging device 2 includes a visible light camera and a filter device that limits transmitted wavelengths incident on the visible light camera to a predetermined wavelength band.

The image information recognition unit 42 recognizes whether or not the solid fuel Fg in the feeder vicinity area protrudes from the combustion chamber 108 based on the image information acquired by the image information acquisition unit 41 . In the present embodiment, the image information recognition unit 42 uses the learned model 491 to recognize whether or not the solid fuel Fg in the feeder vicinity region protrudes from the combustion chamber 108 . In the present embodiment, the image information recognition unit 42 recognizes whether or not the solid fuel Fg protrudes from the combustion chamber 108 for each divided area obtained by dividing the feeder vicinity area into a plurality of areas. In this case, the learned model 491 is learned for each divided region.

The learned model 491 is, for example, a deep learning model, and is a model that has been learned in advance by supervised learning with at least image information as an explanatory variable and presence/absence of protrusion of the solid fuel Fg and poor visibility as objective variables. be. The learned model 491, for example, inputs at least image information as an explanatory variable, and outputs the presence or absence of protrusion of the solid fuel Fg and poor visibility as objective variables. The trained model 491 has, for example, a neural network as an element, and weighting coefficients between neurons in each layer of the neural network are optimized by machine learning so that desired solutions are output for a large amount of input data. The trained model 491 is composed of, for example, a combination of a program for performing calculations from input to output and weighting coefficients (parameters) used for the calculations. Also, the learned model 491 is learned for each divided area obtained by dividing the infrared image captured by the imaging device 2 into arbitrary areas, for example.

FIG. 3 shows an example of an infrared image 201 captured by the imaging device 2 . The image information recognition unit 42 divides the infrared image 201 into three regions, the left region RL, the central region RC, and the right region RR, in a direction orthogonal to the movement direction W1 (the X1 direction), and divides each divided region into , with or without protrusion, or with poor visibility. In the example shown in FIG. 3, the center region RC is classified as having protrusion, and the left region RL and right region RR are classified as having no protrusion. It should be noted that poor visibility corresponds to, for example, an image captured when ash or the like is interposed between the imaging device 2 and the feeder vicinity area. In addition, although it is set as 3 divisions in this embodiment, it is not limited to 3 divisions. The solid fuel Fg is evenly pushed by the extruder 110, but does not drop uniformly into the furnace due to entanglement of dust. In addition, when the dust falls, the dust at the back may get entangled and fall together, and the surface of the dust is not uniform. Therefore, multiple attention areas are provided.

The learned model 491 can be a determination model based on deep learning that classifies each divided region into whether the dust sticks out, does not, or has poor visibility based on the image information. Driving data may also be used as an explanatory variable for learning. The image information may be the image information 492 during actual driving, or may be the past image information 492 .

When it is continuously recognized that the solid fuel Fg protrudes from the combustion chamber 108 for a predetermined time, the supply state determination unit 43 determines that the solid fuel Fg is excessively supplied to the combustion chamber 108 ( It is determined that there is an omen. Further, when the supply state determination unit 43 continuously recognizes that the solid fuel Fg protrudes from the combustion chamber 108 at least in a plurality of divided regions for a predetermined time, the solid fuel Fg is combusted. It is determined that there is a sign of excessive supply to the chamber 108 . Furthermore, the image information recognizing unit 42 uses a learned model 491 that uses at least the image information as an explanatory variable, and obtains whether or not the solid fuel Fg protrudes, and low visibility as objective variables. When recognizing whether it is in a state protruding from 108, the supply state determination unit 43 determines as follows. That is, the supply state determination unit 43 continuously recognizes at least that the solid fuel Fg protrudes from the combustion chamber 108 for a predetermined period of time, and the pushing device 110 is pushing the solid fuel Fg. If there is, it is determined that there is an indication that the solid fuel Fg will be excessively supplied to the combustion chamber 108 .

For example, the supply state determination unit 43 determines whether or not all of the following conditions are met in the drop sign determination. (Condition 1) From the image information divided into 3, there are 2 or more of the 3 divisions with protrusions. (Condition 2) Occurs continuously for 5 seconds. (Condition 3) Feeder operation is pushing. It should be noted that the detection time is, for example, continued for a predetermined time (for example, 60 seconds). This detection time is a standby time until the next predictive determination is performed after the conditions for the predictive determination are met, if a drop (oversupply) does not actually occur. After the conditions for predictive judgment are established, when a drop in supply (oversupply) actually occurs, the next predictive judgment can be performed immediately. The predetermined time can be adjusted, for example, according to the average pressing time of one time.

In this embodiment, the supply state determination unit 43 continuously recognizes that the solid fuel Fg protrudes from the combustion chamber 108 for a predetermined period of time, length) is equal to or greater than a predetermined threshold value, it is determined that there is a sign that the solid fuel Fg will be excessively supplied to the combustion chamber 108 . FIG. 5 shows an example of overfeed occurrence probability based on the total stroke length of the extruder 110 . FIG. 5 shows an example of the drop occurrence probability with respect to the total stroke length, with the horizontal axis representing the total stroke length and the vertical axis representing the drop occurrence probability. In the example shown in FIG. 5, when the total stroke length is L1, the occurrence probability is 10%, when the total stroke length is L2, the occurrence probability is 40%, and when the total stroke length is L3, the occurrence probability is 70%, and the total stroke length is is L4, the probability of occurrence is 90%. The solid line indicates the case where the feeder is pushed in and the feeder falls off, and the dashed line indicates the cases where the feeder falls off during the backward movement or stoppage. The example (plant) shown in FIG. 5 is an example in which the stroke length per stroke is generally controlled between L2 and L3.

In the present embodiment, the supply state determination unit 43 determines that the probability of occurrence of excessive supply based on the total stroke length of the extrusion device 110 is less than a predetermined threshold value (for example, 70%) even when all the conditions for the sign determination described above are satisfied. Occasionally, it determines that there are no signs of oversupply. The probability of occurrence of oversupply can be approximated by a quadratic function with the total stroke length as a parameter, or can be obtained using a map that defines the correspondence relationship between the total stroke length and the probability of occurrence of oversupply. In the confirmation with the actual machine of the present embodiment, it was not always the case that the dropout occurred after the sign was detected. Therefore, as shown in FIG. 5, the probability of occurrence of a thumping drop with respect to the total stroke length of the feeder is calculated, and this occurrence probability is also used for the prediction judgment, thereby further improving the accuracy of the prediction judgment.

It should be noted that the threshold for the probability of occurrence of excess supply may be changed, for example, by the supply state determination unit 43 according to the operating conditions, for example, every predetermined time during operation. Since the probability of occurrence of dizziness changes depending on the quality of dust (dryness, shape, hardness, etc.), the threshold value is changed automatically or manually based on the actual values of detection rate and correct answer rate (wrong answer rate), for example. be able to. Control for suppressing the generation of carbon monoxide at the time of sign detection, which will be described later, is performed, for example, by increasing the supply of secondary air before the drop occurs at the time of sign detection. In this case, if the dropout actually occurs, it is possible to prevent incomplete combustion and suppress the generation of carbon monoxide by increasing the supply of oxygen. However, in the event that the dropout does not actually occur, there is a risk that oxygen will become excessive and the generation of nitrogen oxides will increase. Therefore, the threshold value may be changed according to the actual driving conditions by balancing the demand for carbon monoxide reduction and the increased risk of nitrogen oxide generation. Here, the information indicating the operating conditions is not limited to the information indicating the amount of carbon monoxide generated and the information indicating the amount of nitrogen oxides generated, and includes, for example, information indicating the type of waste, temperature, humidity, and the like. good too. In this case, the threshold for the probability of occurrence of oversupply changes based on information related to the actual combustion state of the incinerator, including at least information indicating the amount of carbon monoxide generated and information indicating the amount of nitrogen oxides generated. is the value to be set. By changing the threshold value in this manner, for example, the upper limit value for the amount of carbon monoxide generated and the upper limit value for the amount of nitrogen oxides generated can be controlled with high accuracy. FIG. 6 shows the relationship between the false response rate and the detection rate of the predictor determination when the threshold is changed when the predictor determination based on image recognition and the comparison of the oversupply occurrence probability based on the total stroke length and the threshold are combined. show. The wrong answer rate is the ratio of the number of times that no thunder occurs with respect to the total number of predictive judgments. The detection rate is the ratio of the number of times the occurrence was predicted to the number of times the drop occurred. When the threshold was made smaller, the detection rate increased, but the false response rate also increased. Increasing the threshold reduced the error rate, but also decreased the detection rate.

The combustion air amount control unit 44 controls the air supply device 112 so as to change the supply amount of combustion air based on the determination result of the sign of excessive supply by the supply state determination unit 43 . With this control, for example, it is possible to suppress a rapid increase in carbon monoxide that occurs when a sudden drop occurs. For example, when the supply state determination unit 43 determines that there is a sign of oversupply, the combustion air amount control unit 44 performs control to increase the supply amount of the secondary combustion air, thereby reducing oxygen in the furnace. Concentration can be increased. This makes it possible to suppress a rapid increase in the CO concentration.

The feeder control unit 45 changes at least one of the operating speed and the stroke of the extrusion device 110 based on the determination result of the sign of oversupply by the supply state determination unit 43 . For example, when the supply state determination unit 43 determines that there is a sign of oversupply, the feeder control unit 45 slows down the operation speed of the extrusion device 110 and shortens the stroke (moving stroke of the extrusion arm 124). Extruder 110 is controlled as follows. With this control, it is possible to buy (postpone) the time until the next thump occurs, and even if the thump occurs, it is not necessary to stop the dust supply device, so the fuel supply can be continued, and the amount of evaporation is reduced. It becomes possible to suppress the decrease.

Both the control by the combustion air amount control unit 44 and the control by the feeder control unit 45 may be performed, or only one of them may be performed. The control by the combustion air amount control unit 44 and the control by the feeder control unit 45 when it is determined that there is a sign of oversupply is referred to as sign control.

The oversupply detection unit 46 detects the occurrence of oversupply by monitoring the brightness of the infrared image of the front surface Fr of the solid fuel Fg based on the plurality of infrared images acquired by the image information acquisition unit 41 . FIG. 7 is a graph showing the brightness of the infrared image of the front face Fr of the solid fuel Fg before falling into the combustion chamber 108, where the vertical axis represents brightness and the horizontal axis represents time. t1 and t2 are the times when the oversupply actually occurred. As shown in FIG. 7, at times t1 and t2 when oversupply actually occurs, the brightness of the infrared image of the front surface Fr of the solid fuel Fg is significantly reduced. Therefore, by monitoring the brightness of the infrared image of the front surface Fr of the solid fuel Fg, it is possible to quickly detect the occurrence of excessive supply. When the excessive supply detection unit 46 detects the occurrence of excessive supply, it instructs the extrusion device 110 to stop the operation of the extrusion arm 124 via the feeder control unit 45 . The extrusion device 110 stops the operation of the extrusion arm 124 upon receiving the instruction from the feeder control unit 45 . As a result, the supply of solid fuel Fg to combustion chamber 108 is stopped.

Further, when the oversupply detection unit 46 detects the occurrence of oversupply, the secondary air supply device 112 (secondary air supply device) supplies the secondary air to the combustion chamber 108 via the combustion air amount control unit 44 . Increase air volume.

The protrusion amount detection unit 47 detects the protrusion length Lr of the solid fuel Fg that protrudes from the inlet 122 of the combustion chamber 108 toward the combustion chamber 108, as shown in FIG. In the exemplary embodiment shown in FIG. 8, the protrusion amount detection unit 47 detects a portion Fr1 located on the most downstream side of the front surface Fr of the front surface Fr of the combustion chamber 108 and the inlet 122 of the combustion chamber 108 in the moving direction W1. The size is detected as the protrusion length Lr. The protrusion amount detection unit 47 detects, for example, the protrusion length Lr for each divided area based on the imaging information of the protrusion amount detection imaging device 28 capable of photographing the solid fuel Fg from above.

The model learning unit 48 performs image processing such as pattern recognition for each divided area on the infrared image acquired by the image information acquiring unit 41, recognizes whether or not visibility is poor, and determines whether visibility is poor. Then, the divided area is classified as poor visibility. In addition, when the infrared image acquired by the image information acquisition unit 41 is not recognized as having poor visibility, the model learning unit 48 calculates the following for each divided region based on the protrusion length Lr detected by the protrusion amount detection unit 47. Then, the partial area is classified as having protrusion or without protrusion. Then, the model learning unit 48 saves the recognition result as image information 492 , and re-learns the trained model 491 using the image information 492 when, for example, a predetermined amount of image information 492 is accumulated.

(Example of control device operation)
Next, an operation example of the control device 4 will be described with reference to FIG. The processing shown in FIG. 4 is repeatedly executed, for example, at intervals of one second. When the process shown in FIG. 4 is started, the control device 4 determines whether or not the predictive time control is being performed (S1). If the predictive time control is not being performed (S1: NO), the image information acquisition unit 41 acquires image information by photographing the inside of the furnace with the imaging device 2 (infrared camera) (S2). Next, the image information recognition unit 42 divides the image of the feeder vicinity area into meshes (S3). Next, the image information recognizing unit 42 determines whether or not there is protrusion or poor visibility for each divided area using a deep learning determination model (S4). Next, the supply state determination unit 43 performs a drop sign determination (S5).

The supply state determination unit 43 determines that there is a sign when all of the above-described (conditions 1) to (conditions 3) are met (S5: Yes), and determines that there is no sign when any one of them is not met ( S5: No). When it is determined that there is a sign (S5: Yes), the supply state determination unit 43 determines whether or not the drop occurrence probability based on the total stroke length is equal to or greater than a predetermined threshold (S6). If it is equal to or greater than the threshold value (S6: Yes), the combustion air amount control unit 44 and the feeder control unit 45 start the predictive time control (S7). Next, the control device 4 determines whether or not conditions for ending the predictive time control are satisfied (S8).

The end condition of the predictive time control is, for example, when the excessive supply detection unit 46 detects that a slowdown has actually occurred, or when the slowdown does not occur after the start of the predictive time control and a predetermined duration (for example, 60 seconds) ) has passed. If the end condition for the control at the time of indication is satisfied (S8: Yes), the control device 4 terminates the control at the time of indication and shifts to control for actual sluggishness, or simply ends the control at the time of indication (S9).

If the predictive time control is being performed (S1: Yes), the control device 4 determines whether or not the ending condition of the predictive time control is satisfied (S8). Further, when the predictive time control is ended (S9), when there is no predictive sign in the predictive judgment judgment (S5: No), when it is not equal to or greater than the threshold value (S6: No), or when the termination condition of the predictive time control is not satisfied If so (S8: No), the control device 4 terminates the processing shown in FIG.

FIG. 9 shows an example of an operation pattern when a sign detection is established. The T1 time is, for example, 5 seconds, and the T2 time is, for example, 60 seconds. At time t11, the feeding of the feeder is started, and at time t12, the conditions 1 and 3 and the threshold determination are established. Further, when T1 time has passed, the sign is detected at time t13, and the time until the time t14 when the drop occurs. In TC1, predictive time control is performed. At time t11, the feeding of the feeder is started, and at time t22, conditions 1 and 3 and the threshold determination are established. Further, when T1 time elapses, an omen is detected at time t23, and until time t25 when the thunder occurs. At time TC2 of , predictive time control is performed. In this case, at time t24, the feeder has moved backward from being pushed. At time t11, the feeding of the feeder is started, and at time t22, the conditions 1 and 3 and the threshold determination are established, and when T1 time elapses, a sign is detected at time t23, and until the time t32 when the drop occurs. At time TC3 of , predictive time control is performed. In this case, at time t24, the feeder has moved backward from being pushed. Also, at time t31, the feeder is stopped.

(action/effect)
As described above, according to the present embodiment, it is possible to improve control delays in response to changes in the supply amount of combustible materials such as wastes, such as excessive supply.

(Other embodiments)
As described above, the embodiments of the present disclosure have been described in detail with reference to the drawings, but the specific configuration is not limited to these embodiments, and design changes etc. within the scope of the present disclosure are also included. .
In the above embodiment, the trained model 491 is used to perform image recognition processing, but the present invention is not limited to this. You can
In addition, when the supply state determination unit 43 detects a sign, the combustion air amount control unit 44 opens the OFA (Over Fire Air) in advance to eliminate the lack of air and prevent an increase in the CO concentration. Therefore, the damper opening of the post-combustion region 132 may be minimized. In addition, when the feeder control unit 45 detects a sign during a drop target, the feeder control unit 45 reduces the stoker speed to gain time until the next occurrence, thereby suppressing fluctuations in the amount of evaporation due to continuous drop. good too.

<Computer configuration>
FIG. 10 is a schematic block diagram showing the configuration of a computer according to at least one embodiment;
Computer 90 comprises processor 91 , main memory 92 , storage 93 and interface 94 .
The control device 4 described above is implemented in the computer 90 . The operation of each processing unit described above is stored in the storage 93 in the form of a program. The processor 91 reads out the program from the storage 93, develops it in the main memory 92, and executes the above processes according to the program. In addition, the processor 91 secures storage areas corresponding to the storage units described above in the main memory 92 according to the program.

The program may be for realizing part of the functions that the computer 90 is caused to exhibit. For example, the program may function in combination with another program already stored in the storage or in combination with another program installed in another device. Note that in other embodiments, the computer may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or instead of the above configuration. Examples of PLD include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), FPGA (Field Programmable Gate Array), and the like. In this case, part or all of the functions implemented by the processor may be implemented by the integrated circuit.

Examples of the storage 93 include HDD (Hard Disk Drive), SSD (Solid State Drive), magnetic disk, magneto-optical disk, CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory). , semiconductor memory, and the like. The storage 93 may be an internal medium directly connected to the bus of the computer 90, or an external medium connected to the computer 90 via an interface 94 or communication line. Further, when this program is distributed to the computer 90 via a communication line, the computer 90 receiving the distribution may develop the program in the main memory 92 and execute the above process. In at least one embodiment, storage 93 is a non-transitory, tangible storage medium.

<Appendix>
The control device 4 of the incinerator facility described in each embodiment is grasped, for example, as follows.

(1) A control device 4 for an incinerator facility according to a first aspect is an incinerator facility having a furnace body for burning and conveying materials to be incinerated, and a feeder for supplying the materials to be incinerated to the furnace body. A control device comprising: an image information acquisition unit 41 for periodically acquiring image information including the area near the feeder; and an image information recognition unit 42 for recognizing whether or not the object to be incinerated is in a protruding state with respect to the main body of the furnace. and a supply state determination unit 43 for determining that there is a sign of excessive supply of the gas to the furnace body. According to this aspect and the following aspects, it is possible to improve control delays in response to changes in the supply amount of combustible materials such as waste, such as oversupply.

(2) The control device 4 for the incinerator equipment according to the second aspect is the control device 4 for the incinerator equipment according to the aspect (1) above, and the supply state determination unit 43 determines that the incinerator equipment When the state of protruding from the furnace body is continuously recognized for a predetermined time and the probability of occurrence of excessive supply based on the total extrusion length of the feeder is equal to or greater than a predetermined threshold, the incinerator It is determined that there is a sign that is excessively supplied to the furnace body.

(3) A control device 4 for an incinerator facility according to a third aspect is the control device 4 for an incinerator facility according to the above aspect (2), wherein the threshold is information indicating the amount of carbon monoxide generated. and information indicating the amount of nitrogen oxides generated.

(4) A control device 4 for incinerator equipment according to a fourth aspect is the control device 4 for incinerator equipment according to aspects (1) to (3) above, wherein the image information recognition unit 42 includes the The feeder vicinity area is divided into a plurality of divided areas, each of which recognizes whether or not the incinerator protrudes from the furnace main body. When it is continuously recognized for a predetermined period of time that the incinerator protrudes from the furnace main body in the divided area, it is a sign that the incinerator is excessively supplied to the furnace main body. It is determined that there is

(5) A control device 4 for incinerator equipment according to a fifth aspect is the control device 4 for incinerator equipment according to aspects (1) to (4) above, wherein the image information recognition unit 42 includes at least Using a trained model 491 that uses the image information as an explanatory variable and determines whether or not the object to be incinerated protrudes, as well as poor visibility as objective variables, it is determined whether or not the object to be incinerated protrudes. The supply state determination unit 43 continuously recognizes that at least the incineration material protrudes from the furnace main body for a predetermined period of time, and the feeder keeps the incineration material protruding from the furnace main body. If it is being pushed in, it is determined that there is a sign that the incinerator body will be oversupplied with the incinerator body.

(6) The control device 4 for the incinerator equipment according to the sixth aspect is the control device 4 for the incinerator equipment according to the above aspects (1) to (5), and determines that there is a sign of the oversupply a combustion air amount control unit that controls to increase the amount of combustion air supplied when the It further comprises at least one feeder control unit that controls the stroke to be shortened.

DESCRIPTION OF SYMBOLS 100... Incinerator equipment 108... Combustion chamber 110... Pusher 4... Control device 41... Image information acquisition part 42... Image information recognition part 43... Supply state determination part 44... Combustion air amount control part 45... Feeder control part 49... Storage unit 491: learned model 492: image information

Claims (6)

A control device for an incinerator facility having a furnace body for burning and conveying materials to be incinerated, and a feeder for supplying the materials to be incinerated to the furnace body,
an image information acquisition unit that periodically acquires image information including the feeder vicinity area;
an image information recognition unit that recognizes whether or not the incineration material in the feeder vicinity area protrudes from the furnace body based on the image information;
When it is continuously recognized for a predetermined time that the materials to be incinerated protrude from the main body of the furnace, it is determined that there is a sign that the materials to be incinerated are excessively supplied to the main body of the furnace. A control device for an incinerator facility, comprising: a supply state determination unit; The supply state determination unit continuously recognizes that the incinerator protrudes from the furnace main body for a predetermined time, and the probability of occurrence of excess supply based on the total extrusion length of the feeder is reduced. 2. The control device for incinerator equipment according to claim 1, wherein, if it is equal to or greater than a predetermined threshold value, it is determined that there is a sign that the incinerator body will be oversupplied with the incinerator body. The threshold value is a value that is changed based on information relating to the actual combustion state of the incinerator including at least information indicating the amount of carbon monoxide generated and information indicating the amount of nitrogen oxides generated. 3. The control device for the incinerator facility according to 2. The image information recognition unit recognizes whether or not the incinerator protrudes from the furnace body for each divided region obtained by dividing the feeder vicinity region into a plurality of regions,
The supply state judging unit detects that the incineration material protrudes from the furnace body continuously for a predetermined time, at least in the plurality of divided regions, when the incineration material is 4. The control device for incinerator equipment according to any one of claims 1 to 3, wherein it is determined that there is a sign of excessive supply to the incinerator body. The image information recognizing unit uses a learned model that uses at least the image information as an explanatory variable, and determines whether or not the incineration object protrudes, and low visibility as objective variables, so that the incineration object protrudes. recognizing whether the state is
The supply state determination unit continuously recognizes at least that the incineration material protrudes from the furnace main body for a predetermined time, and the feeder is pushing the incineration material. 5. The control device for incinerator equipment according to any one of claims 1 to 4, wherein it is determined that there is a sign that the incinerator body will be oversupplied with the incinerator body if the incinerator body is oversupplied. A combustion air amount control unit that changes the supply amount of combustion air based on the determination result of the sign of oversupply, or at least one of the operating speed or the stroke of the feeder based on the determination result of the sign of oversupply. The control device for incinerator equipment according to any one of claims 1 to 5, further comprising at least one feeder control unit that changes the .

Images