CN117321339A

CN117321339A - Control device for incinerator equipment

Info

Publication number: CN117321339A
Application number: CN202280035667.8A
Authority: CN
Inventors: 岩下信治; 草加浩都; 濑户口稔彦; 今田润司; 大丸卓一郎; 滑泽幸司; 林庆一; 江草知通
Original assignee: Mitsubishi Heavy Industries Environmental and Chemical Engineering Co Ltd
Current assignee: Mitsubishi Heavy Industries Environmental and Chemical Engineering Co Ltd
Priority date: 2021-06-29
Filing date: 2022-04-21
Publication date: 2023-12-29
Also published as: KR20230172551A; JP6998485B1; TWI823354B; TW202303044A; WO2023276423A1; JP2023005444A

Abstract

A control device for an incinerator apparatus having a furnace main body for transporting an object to be incinerated while burning the object, and a feeder for feeding the object to be incinerated to the furnace main body, the control device comprising: an image information acquisition unit that periodically acquires image information including a receiving port of a furnace main body, the receiving port of the furnace main body being connected to an end of a feeder; an image information identification unit for identifying whether the burned object at the receiving port is in a state of protruding toward the furnace body based on the image information; and a supply state determination unit that determines that there is a sign that the burnt material is excessively supplied to the furnace main body when the burnt material is recognized as being in a state of protruding to the furnace main body for a predetermined time.

Description

Control device for incinerator equipment

Technical Field

The present invention relates to a control device for incinerator equipment.

The present application claims priority from 2021, 6, 29 to japanese patent application No. 2021-107370, and the contents thereof are incorporated herein by reference.

Background

Patent document 1 discloses a waste incineration apparatus as follows. That is, in the waste incineration apparatus described in patent document 1, the amount of waste actually supplied to the furnace is detected from a difference image between an image of waste before falling into the furnace and an image of waste after falling into the furnace. In the waste incineration apparatus described in patent document 1, when the current value of the waste supply amount is higher than the predetermined supply amount range, control is performed such that an instruction to reduce the supply amount of waste supplied to the grate by reducing the waste supply speed, an instruction to promote combustion of waste by increasing the amount of primary air for combustion, or the like is issued to the feeder to change the operation conditions, thereby reducing the supply amount of waste supplied to the grate and promoting combustion of waste on the grate, and the amount of waste on the grate is reduced.

Prior art literature

Patent literature

Patent document 1: japanese patent laid-open No. 2020-128837

Disclosure of Invention

Problems to be solved by the invention

However, in the waste incineration apparatus described in patent document 1, there is a problem that since the operation condition is changed according to the current value of the waste supply amount, for example, a delay occurs in control of increasing the amount of air for combustion and the like according to the change of the supply amount.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a control device for an incinerator facility capable of improving delay in control in response to a change in the amount of the objects to be burned such as waste.

Means for solving the problems

To solve the above problems, a control device for an incinerator apparatus including a furnace main body for transporting an object to be incinerated while combusting the object to be incinerated, and a feeder for feeding the object to be incinerated to the furnace main body according to the present invention includes: an image information acquisition unit that periodically acquires image information including a receiving port of the furnace main body, the receiving port of the furnace main body being connected to an end of the feeder; an image information identifying unit that identifies, based on the image information, whether or not the object to be incinerated at the receiving port is in a state of protruding toward the furnace main body; and a supply state determination unit that determines that there is a sign that the material to be incinerated is excessively supplied to the furnace main body when it is recognized that the material to be incinerated is in a state of being projected to the furnace main body for a predetermined time.

Effects of the invention

According to the control device of the incinerator equipment of the present invention, it is possible to improve the delay in control which is made in response to the change in the supply amount of the objects to be burned such as waste.

Drawings

Fig. 1 is a schematic diagram showing a configuration example of an incinerator facility according to an embodiment of the present invention.

Fig. 2 is a block diagram showing a configuration example of a control device according to an embodiment of the present invention.

Fig. 3 is a diagram showing an example of an infrared image according to an embodiment of the present invention.

Fig. 4 is a flowchart showing an example of the operation of the control device according to the embodiment of the present invention.

Fig. 5 is a schematic diagram for explaining an example of the operation of the control device according to the embodiment of the present invention.

Fig. 6 is a schematic diagram for explaining an example of the operation of the control device according to the embodiment of the present invention.

Fig. 7 is a schematic diagram for explaining an example of the operation of the control device according to the embodiment of the present invention.

Fig. 8 is a schematic diagram for explaining an example of the operation of the control device according to the embodiment of the present invention.

Fig. 9 is a schematic diagram for explaining an example of the operation of the control device according to the embodiment of the present invention.

Fig. 10 is a schematic block diagram showing a configuration of a computer according to an embodiment of the present invention.

Detailed Description

(Structure of control device of incinerator facility)

A control device for an incinerator apparatus according to an embodiment of the present invention will be described below with reference to fig. 1 to 10. Fig. 1 is a schematic diagram showing a configuration example of an incinerator facility according to an embodiment of the present invention. Fig. 2 is a block diagram showing a configuration example of a control device according to an embodiment of the present invention. Fig. 3 is a diagram showing an example of an infrared image according to an embodiment of the present invention. Fig. 4 is a flowchart showing an example of the operation of the control device according to the embodiment of the present invention. Fig. 5 to 9 are schematic diagrams for explaining an example of the operation of the control device according to the embodiment of the present invention. Fig. 10 is a schematic block diagram showing a configuration of a computer according to an embodiment of the present invention. In the drawings, the same or corresponding structures are denoted by the same reference numerals, and description thereof is omitted as appropriate.

(construction of incinerator apparatus)

Fig. 1 shows a configuration example of an incinerator facility 100 according to an embodiment of the present invention. In the illustrative manner shown in fig. 1, the incinerator apparatus 100 is a stoker type refuse incinerator using municipal waste, industrial waste, biomass, or the like as a solid fuel Fg. The incinerator apparatus 100 is not limited to a grate type garbage incinerator.

As shown in fig. 1, the incinerator apparatus 100 includes a hopper 102, a feeder section 104, a combustion chamber 108, an extrusion device 110 (feeding device), an air supply device 112, a heat recovery boiler 114, a desuperheating tower 116, a dust collection device 118, and a chimney 120. The combustion chamber 108 is an example of a furnace body for transporting an object to be burned while burning the object to be burned according to the present invention. The extrusion device 110 is an example of a feeder for feeding an object to be incinerated to a furnace body according to the present invention.

The feeder portion 104 is a passage extending toward the combustion chamber 108. The feeder unit 104 is configured to accumulate solid fuel Fg, which is an object to be burned such as waste (refuse) charged into the hopper 102. When the direction in which the solid fuel Fg moves in the incinerator 100 is the moving direction W1, the downstream end 121 of the feeder unit 104 (the end of the feeder unit 104 on the combustion chamber 108 side) located downstream in the moving direction W1 is connected to the receiving port 122 of the combustion chamber 108.

The extrusion device 110 has an extrusion arm 124 for extruding the solid fuel Fg deposited on the feeder portion 104 to the combustion chamber 108 via a receiving opening 122. The extrusion arm 124 is configured to be movable in the feeder unit 104 from the upstream side toward the downstream side in the movement direction W1, and from the downstream side toward the upstream side. That is, the extrusion arm 124 reciprocates in the feeder portion 104 along the extending direction (horizontal direction) of the feeder portion 104.

The combustion chamber 108 includes a grate 126 (grate), and the solid fuel Fg extruded into the combustion chamber 108 through the receiving port 122 falls down to the grate 126. The grate 126 corresponds to the hearth portion of the combustion chamber 108. The grate 126 is configured such that the solid fuel Fg on the grate 126 is moved in a direction gradually away from the receiving port 122 (from the upstream side to the downstream side in the moving direction W1). The combustion chamber 108 includes a drying region 128, a combustion region 130, and a post-combustion region 132 arranged in this order from the upstream side toward the downstream side in the moving direction W1. The drying zone 128 dries the solid fuel Fg by heat within the combustion chamber 108. The combustion zone 130 ignites the flame 131 to burn the solid fuel Fg. The post-combustion zone 132 completely combusts combustion debris that is not completely combusted in the combustion zone 130. The solid fuel Fg dried, burned, and post-burned in the combustion chamber 108 is converted into ash 135, and discharged to the outside of the incinerator apparatus 100.

The air supply device 112 is configured to supply 1 st air used for combustion of the solid fuel Fg and 2 nd air for reducing the concentration of unburned gas such as carbon monoxide generated by combustion of the solid fuel Fg to the combustion chamber 108. In the illustrative manner shown in FIG. 1, the air supply 112 includes an air supply tube 136 and a sootblower 138 disposed in the air supply tube 136. A part of the air flowing through the air supply pipe 136 is supplied as 1 st air from the grate 126 to the lower portion of the combustion chamber 108 via the 1 st flow rate adjustment valve 140, and the remaining part is supplied as 2 nd air from the side wall of the combustion chamber 108 to the upper portion of the combustion chamber 108 via the 2 nd flow rate adjustment valve 142. The air supply device 112 functions as a 2-time air supply device that supplies 2-time air to the upper portion of the combustion chamber 108. In the exemplary embodiment shown in fig. 1, 1 time of air is supplied to each of the drying region 128, the combustion region 130, and the post-combustion region 132 of the combustion chamber 108.

The heat recovery boiler 114, the temperature reduction tower 116, the dust collector 118, and the stack 120 are provided in a flue 144 of the incinerator facility 100 through which an exhaust gas 143 generated by burning the solid fuel Fg flows. The exhaust gas 143 flows through the heat recovery boiler 114, the temperature reduction tower 116, the dust collector 118, and the stack 120 in this order. The heat recovery boiler 114 generates steam from the thermal energy of the exhaust gas 143. The attemperator 116 reduces the temperature of the exhaust gas 143 passing through the heat recovery boiler 114. The dust collector 118 captures fly ash contained in the exhaust gas 143 passing through the temperature reduction tower 116. The stack 120 discharges the exhaust gas 143 having passed through the dust collecting device 118 to the outside of the incinerator apparatus 100. The steam generated in the heat recovery boiler 114 may be supplied to a steam turbine, not shown.

(Structure of control device)

The control device 4 applied to the above-described incinerator apparatus 100 is a control device of the incinerator apparatus 100 having a combustion chamber 108 for transporting the objects to be incinerated while burning the objects to be incinerated, and an extrusion device 110 for supplying the objects to be incinerated to the combustion chamber 108. The control device 4 has the following functional configuration as a combination of hardware such as a computer and a peripheral device of the computer, and software such as a program executed by the computer. That is, the control device 4 includes an image information acquisition unit 41, an image information identification unit 42, a supply state determination unit 43, a combustion air amount control unit 44, a feeder control unit 45, a rich spike detection unit 46, a rich spike detection unit 47, a model training unit 48, and a storage unit 49. The storage unit 49 stores a plurality of pre-training models 491 and a plurality of pieces of image information 492.

The image information acquisition section 41 periodically acquires image information including an image signal indicating a feeder vicinity area, which is an area including the feeder section 104 and the like, captured by the imaging device 2. In the present embodiment, the image information may include an image signal indicating an image to be captured, information indicating a capturing date and time of the image signal, information indicating the total length of travel of the extrusion arm 124 at the time of capturing (total extrusion length of feeder), and the like. The total length of the stroke of the extrusion arm 124 is a total value of lengths of the extrusion arm 124 moving from the upstream side to the downstream side in the moving direction W1 with a point of time when oversupply of the burned object (also referred to as "drop" or the like) occurs as a starting point. The feeder vicinity area is, for example, an area including the front surface Fr of the solid fuel Fg as a region of interest.

The imaging device 2 is configured to capture an infrared image (thermal image) of the solid fuel Fg deposited on the feeder portion 104 of the incinerator apparatus 100 before the solid fuel Fg falls to the combustion chamber 108. The infrared image of the solid fuel Fg taken by the image pickup device 2 is transmitted to the control device 4 in real time. In the exemplary embodiment shown in fig. 1, the imaging device 2 is provided at the tail 145 of the combustion chamber 108 on the downstream side in the moving direction W1 from the post-combustion region 132 of the combustion chamber 108 so as to capture an infrared image of the front surface Fr facing the combustion chamber 108 out of the surfaces of the solid fuel Fg before falling into the combustion chamber 108. The image pickup device 2 is capable of picking up an infrared image of the front surface Fr of the solid fuel Fg that protrudes from the receiving port 122 of the combustion chamber 108. The imaging device 2 may be provided at a position other than the tail 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.

The imaging device 2 is, for example, an infrared camera that detects infrared rays in a predetermined wavelength region in which the radiation from the flame 131 is small. In this case, the range of the predetermined wavelength region is, for example, 2 μm or more and 5 μm or less. To further suppress the influence of the flame 131, an infrared image of the front surface Fr of the solid fuel Fg is captured, and the predetermined wavelength range is 3.8 μm or more and 4.2 μm or less. The wavelength range of the object to be imaged as an infrared image is 0.8 μm to 1000 μm. By passing a band-pass filter or the like through this wavelength region, the device can be operated so that only a part of wavelengths are used as needed.

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 via the flame 131. In some embodiments, the imaging device 2 includes a visible light camera and a filter device that limits the transmission wavelength incident on the visible light camera to a predetermined wavelength region.

The image information identifying section 42 identifies whether the solid fuel Fg in the feeder vicinity is in a state of protruding toward the combustion chamber 108, based on the image information acquired by the image information acquiring section 41. In the present embodiment, the image information identifying unit 42 uses the pre-training model 491 to identify whether or not the solid fuel Fg in the feeder vicinity is in a state of protruding toward the combustion chamber 108. In the present embodiment, the image information identifying unit 42 identifies whether or not the solid fuel Fg is in a state of protruding into the combustion chamber 108 for each divided area in which the feeder vicinity area is divided into a plurality of areas. In this case, the pre-training model 491 is trained for each divided region.

The pre-training model 491 is, for example, a deep learning model, which is trained by performing a supervision training in advance using at least image information as an explanatory variable and the presence or absence of protrusion of the solid fuel Fg and the visual field defect as target variables. The pre-training model 491 is input with at least image information as an explanatory variable, and outputs the presence or absence of protrusion of the solid fuel Fg and the poor visual field as target variables, for example. The pre-training model 491 uses a neural network as an element, and by machine learning, weighting coefficients between neurons of each layer of the neural network are optimized so as to output a solution obtained for a plurality of data to be input. The pre-training model 491 is composed of, for example, a combination of a program for performing an operation from input to output and a weighting coefficient (parameter) used for the operation. The pre-training model 491 trains, for example, an infrared image captured by the imaging device 2 for each divided region obtained by dividing the infrared image into arbitrary regions.

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 a left region RL, a center region RC, and a right region RR in a direction (X1 direction) orthogonal to the moving direction W1, and classifies each divided region as either the presence or absence of extension or poor visual field. In the example shown in fig. 3, the center region RC is classified as having a protrusion, and the left region RL and the right region RR are classified as having no protrusion. The poor view corresponds to an image or the like captured when, for example, ash or the like is interposed between the imaging device 2 and the feeder adjacent region. In the present embodiment, the 3-division is used, but the present invention is not limited to the 3-division. Although the extruding device 110 uniformly pushes the solid fuel Fg, the solid fuel Fg does not uniformly drop into the furnace due to the entanglement of the garbage. Furthermore, when falling, the garbage in the depth may be entangled and fall together, so that the surface of the garbage is not uniform, and thus a plurality of regions of interest are provided.

The pre-training model 491 can be a deep learning-based determination model that classifies the presence or absence of protrusion of garbage and poor visibility into regions of the division based on image information, and can be trained by using operational data such as the total length of the journey as an explanatory variable in the course of producing the determination model. The image information may be image information 492 in actual operation, or past image information 492 may be used.

When it is recognized that the solid fuel Fg is in a state of being projected into the combustion chamber 108 for a predetermined period of time, the supply state determination unit 43 determines that there is a sign of the solid fuel Fg being excessively supplied to the combustion chamber 108 (falling). Further, at least when the state where the solid fuel Fg is projected into the combustion chamber 108 in the plurality of divided regions is recognized for a predetermined period of time, the supply state determination unit 43 determines that there is a sign that the solid fuel Fg is excessively supplied to the combustion chamber 108. Further, when the image information identifying unit 42 identifies whether or not the solid fuel Fg is in a state of protruding into the combustion chamber 108 using the pre-training model 491 obtained by using at least the image information as an explanatory variable and the presence or absence of protruding of the solid fuel Fg and the visual field defect as target variables, the supply state determining unit 43 determines as follows. That is, at least when the solid fuel Fg is recognized as being in a state of being projected into the combustion chamber 108 for a predetermined period of time and the solid fuel Fg is being pushed by the extruding device 110, the supply state determining unit 43 determines that there is a sign that the solid fuel Fg is excessively supplied to the combustion chamber 108.

For example, in the fall warning judgment, the supply state judgment unit 43 makes warning judgment as to whether or not all of the following conditions are satisfied. (condition 1) from the 3-division image information, there is a stretch out of 2 or more of the 3-division. (condition 2) continuously occurs for 5 seconds. (condition 3) the feeder acts as a pushing. The detection time is set to be a predetermined time (for example, 60 seconds), for example. In the detection time, when a fall (oversupply) does not actually occur after the sign determination condition is established, the detection time is a standby time until the next sign determination is performed. When a drop (oversupply) occurs in practice after the sign determination condition is established, the next sign determination can be performed immediately. The predetermined time can be adjusted in accordance with an average pushing time of 1 time, for example.

In the present embodiment, when the solid fuel Fg is recognized as being in a state of being fed to the combustion chamber 108 for a predetermined time and the probability of occurrence of the rich spike based on the total stroke length (total extrusion length) of the extrusion device 110 is equal to or greater than a predetermined threshold, the supply state determining unit 43 determines that there is a sign of the solid fuel Fg being rich-fed to the combustion chamber 108. Fig. 5 shows an example of the possibility of occurrence of the rich spike based on the total stroke length of the extruding apparatus 110. In fig. 5, an example of the probability of occurrence of a fall with respect to the total stroke length is shown with the horizontal axis being the total stroke length and the vertical axis being the probability of occurrence of a fall. In the example shown in fig. 5, the occurrence probability is approximately 10% when the stroke total length is L1, 40% when the stroke total length is L2, 70% when the stroke total length is L3, and 90% when the stroke total length is L4. In addition, the solid line indicates the case where a fall occurs during the pushing of the feeder, and the broken line indicates the case where a fall occurs during the backward or stop of the feeder. The example (apparatus) shown in fig. 5 is a typical example in which the stroke length is controlled between L2 and L3 for every 1 time.

In the present embodiment, even when all the conditions for the sign determination described above are satisfied, if the possibility of occurrence of the rich spike based on the total stroke length of the extrusion device 110 does not reach a predetermined threshold (for example, 70%), the feed state determining unit 43 determines that there is no sign of the rich spike. The rich spike occurrence probability can be approximated by, for example, a 2-degree function using the stroke total length as a parameter, or can be obtained using a map in which a correspondence relationship between the stroke total length and the rich spike occurrence probability is set. In the confirmation of the actual machine of the present embodiment, it is not necessary to fall after the sign is detected. In view of this, as shown in fig. 5, the probability of occurrence of a fall with respect to the total stroke length of the feeder is calculated, and the probability of occurrence is also used for the precursor determination, whereby the accuracy of the precursor determination is further improved.

In addition, the threshold value of the oversupply occurrence probability may be changed by the supply state determination unit 43, for example, at predetermined time intervals in accordance with the operation condition at the time of operation. Since the probability of occurrence of a fall varies depending on the texture (dryness, shape, hardness, etc.) of the refuse, the threshold value can be automatically or manually changed, for example, according to the actual result value of the detection rate or the answer rate (answer error rate). The control for suppressing the generation of carbon monoxide at the time of the warning detection described later is performed by, for example, increasing the supply of air 2 times before the fall occurs at the time of warning detection. In this case, if a fall actually occurs, incomplete combustion is prevented by the increased supply of oxygen, and the generation of carbon monoxide can be suppressed. However, in the case where a fall does not actually occur, oxygen may be excessive, which may lead to an increase in the production of nitrogen oxides. Therefore, it is also possible to change the threshold value according to the actual operating condition by a trade-off between a demand for reducing carbon monoxide and an increase in the possibility of generating nitrogen oxides. Here, the information indicating the operating condition is not limited to the information indicating the amount of carbon monoxide generated and the information indicating the amount of nitrogen oxide generated, and may include, for example, information indicating the texture, temperature, humidity, and the like of garbage. In this case, the threshold value of the probability of occurrence of the rich spike is changed based on information related to the actual combustion state of the burned object, which includes at least information indicating the amount of carbon monoxide generated and information indicating the amount of nitrogen oxide generated. By changing the threshold in this way, for example, the upper limit value of the carbon monoxide generation amount and the upper limit value of the nitrogen oxide generation amount can be accurately controlled. Fig. 6 shows a relationship between the error rate and the detection rate of the precursor determination when the threshold value is changed in the case where the precursor determination based on the image recognition and the comparison of the oversupply occurrence probability based on the total stroke length are combined with the threshold value. The error rate is the ratio of the number of times a fall has not occurred to all the number of times the precursor decision has been made. The detection rate is the ratio of the number of occurrences of a success precursor to the number of occurrences of a fall. If the threshold value is reduced, the detection rate increases, but the error rate also increases. If the threshold value is increased, the error rate can be reduced, but the detection rate is also reduced.

The combustion air amount control unit 44 controls the control air supply device 112 so as to change the supply amount of the combustion air in accordance with the determination result of the rich spike determined by the supply state determination unit 43. By this control, for example, a sudden increase in carbon monoxide generated when a fall occurs can be suppressed. The combustion air amount control unit 44 can increase the oxygen concentration in the furnace by performing control to increase the supply amount of the post-combustion air when the supply state determination unit 43 determines that there is a rich spike, for example. Thus, a sharp increase in the CO concentration can be suppressed.

The feeder control unit 45 changes at least one of the operation speed and the stroke of the extrusion device 110 according to the determination result of the rich spike precursor determined by the supply state determination unit 43. For example, if the feed state determination unit 43 determines that there is a rich spike, the feeder control unit 45 slows down the operation speed of the extrusion device 110 and controls the extrusion device 110 so that the stroke (the movement stroke of the extrusion arm 124) becomes shorter. By this control, the time for the next fall to occur is delayed (delayed), and the feeder does not need to be stopped even when a fall occurs, so that the fuel supply can be continued, and the evaporation amount can be suppressed from decreasing.

The control by the combustion air amount control unit 44 and the control by the feeder control unit 45 may be performed both or only one of them. In addition, when it is determined that there is a rich spike, the control by the combustion air amount control unit 44 and the control by the feeder control unit 45 are referred to as a spike time control.

The rich spike detection section 46 monitors 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 section 41, thereby detecting the occurrence of rich spike. Fig. 7 is a graph showing the brightness of an infrared image of the front surface Fr of the solid fuel Fg before it falls into the combustion chamber 108, with the vertical axis showing the brightness and the horizontal axis showing the time. t1 and t2 are the times when the rich spike actually occurs. As shown in fig. 7, at t1 and t2 when the rich spike 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, the occurrence of the rich spike can be promptly detected. When it is detected that the oversupply has occurred, the oversupply detecting unit 46 instructs the extrusion device 110 to stop the operation of the extrusion arm 124 via the feeder control unit 45. When instructed by the feeder control unit 45, the extrusion device 110 stops the operation of the extrusion arm 124.

Thereby, the supply of the solid fuel Fg to the combustion chamber 108 is stopped.

When it is detected that the oversupply has occurred, the oversupply detecting unit 46 increases the amount of 2-time air supplied from the air supply device 112 (2-time air supply device) to the combustion chamber 108 via the combustion air amount control unit 44.

As shown in fig. 8, the protrusion amount detection unit 47 detects the protrusion length Lr of the solid fuel Fg that protrudes from the receiving port 122 of the combustion chamber 108 toward the combustion chamber 108. In the exemplary embodiment shown in fig. 8, the protrusion amount detection section 47 detects the size between the receiving port 122 of the combustion chamber 108 and the portion Fr1 located on the most downstream side in the front surface Fr of the solid fuel Fg in the moving direction W1 as the protrusion length Lr. The extension amount detection unit 47 detects the extension length Lr for each divided region based on, for example, imaging information of the extension amount detection imaging device 28 capable of imaging the solid fuel Fg from above.

The model training unit 48 performs image processing such as pattern recognition on the infrared image acquired by the image information acquisition unit 41 for each divided region, and identifies whether or not the visual field is poor, and classifies the divided region as poor when the visual field is poor. When the infrared image acquired by the image information acquisition unit 41 is not recognized as having a poor visual field by the model training unit 48, the partial region is classified into the presence or absence of extension for each divided region according to the extension length Lr detected by the extension amount detection unit 47. Then, the model training unit 48 stores the result of the recognition as image information 492, and, for example, when a predetermined amount of image information 492 is stored, retrains the pre-training model 491 using the image information 492.

(operation example of control device)

Next, an operation example of the control device 4 will be described with reference to fig. 4. The process shown in fig. 4 is repeatedly performed at 1 second intervals, for example. When the process shown in fig. 4 starts, the control device 4 determines whether or not the control is in the precursor time control (S1). If the control is not in the warning state (S1: NO), the image information acquisition unit 41 acquires image information by capturing an image of the inside of the furnace with the imaging device 2 (infrared camera) (S2). Next, the image information identifying unit 42 performs mesh division on the image of the feeder vicinity (S3). Next, the image information identifying unit 42 determines whether or not the protrusion or the visual field defect is present for each divided region using the deep learning determination model (S4). Next, the supply state determination unit 43 performs fall warning determination (S5).

The supply state determination unit 43 determines that there is a sign when all of the above (conditions 1) to (condition 3) are satisfied (yes in S5), and determines that there is no sign when any of them is not satisfied (no in S5). When it is determined that there is a sign (yes in S5), the supply state determination unit 43 determines whether or not the probability of occurrence of a fall based on the total length of the stroke is equal to or greater than a predetermined threshold (S6). When the temperature is equal to or higher than the threshold value (S6: yes), the combustion air quantity control unit 44 and the feeder control unit 45 start the predictive time control (S7). Next, the control device 4 determines whether or not the end condition of the precursor time control is satisfied (S8).

The end condition of the warning-time control is, for example, that the oversupply detecting unit 46 detects that a fall has actually occurred or that a predetermined time (for example, 60 seconds) has elapsed since the start of the warning-time control. When the end condition of the warning-time control is satisfied (yes in S8), the control device 4 ends the warning-time control and shifts to the control of the actual fall, or simply ends the warning-time control (S9).

If the control is in the warning-time control (yes in S1), the control device 4 determines whether or not the end condition of the warning-time control is satisfied (S8). When the warning-time control is ended (S9), when there is no warning in the falling warning judgment (S5: no), when the warning is not equal to or greater than the threshold value (S6: no), or when the warning-time control ending condition is not satisfied (S8: no), the control device 4 ends the processing shown in fig. 4.

Fig. 9 shows an example of an operation mode when the sign detection is established. The T1 time is, for example, 5 seconds, and the T2 time is, for example, 60 seconds. At time T11, pushing of the feeder is started, at time T12, conditions 1 and 3 and the threshold value are determined to be satisfied, and after the time T1 has elapsed, a warning detection is made at time T13, and a warning time control is performed at time TC1 until time T14 when the fall occurs. Then, at time T11, pushing of the feeder is started, at time T22, conditions 1 and 3 and threshold value determination are established, and after the lapse of time T1, a warning detection is made at time T23, and warning time control is performed at time TC2 until time T25 when the fall occurs. In this case, the feeder is pushed from the time t24 to the time of backward movement. Then, at time T11, pushing of the feeder is started, at time T22, conditions 1 and 3 and threshold value determination are established, and after the lapse of time T1, a warning detection is made at time T23, and warning time control is performed at time TC3 up to time T32 when the fall occurs. In this case, the feeder is pushed from the time t24 to the time of backward movement. Also, at time t31 the feeder stops.

(action and Effect)

As described above, according to the present embodiment, it is possible to improve the delay in control that is made in response to the change in the supply amount of the objects to be burned, such as waste, such as oversupplied.

(other embodiments)

Although the embodiments of the present invention have been described above with reference to the drawings, specific configurations are not limited to the embodiments, and design changes and the like without departing from the scope of the gist of the present invention are also included.

In the above embodiment, the image recognition processing was performed using the pre-training model 491, but the image recognition processing is not limited thereto, and may be performed using, for example, an Optical Flow method (Optical Flow) or a cubic high-order local autocorrelation feature method (CHLAC; cubic higher-order local autocorrelation).

The combustion Air amount control unit 44 may be configured to, when the supply state determination unit 43 detects a precursor, first turn on an OFA (Over Fire Air) to eliminate insufficient Air to prevent an increase in CO concentration, and to minimize the damper opening of the post combustion region 132 to cope with an increase in NOx. Further, the feeder control unit 45 may be configured to reduce the grate speed and delay the next occurrence time when the sign is detected in the falling object, thereby suppressing the variation in the evaporation amount due to the continuous falling.

< computer Structure >

Fig. 10 is a schematic block diagram showing a configuration of a computer according to at least one embodiment.

The computer 90 includes a processor 91, a main memory 92, a storage device 93, and an interface 94.

The control device 4 is mounted on a computer 90. The operations of the respective processing units are stored in the storage device 93 in the form of a program. After the processor 91 reads the program from the storage device 93, it expands it in the main memory 92, and executes the above-described processing according to the program. The processor 91 secures a storage area corresponding to each storage unit in the main memory 92 according to a program.

The program may be used to realize a part of the functions that the computer 90 performs. For example, the program may function by being combined with another program stored in a storage device or by being combined with another program installed in another device. In other embodiments, the computer may include a custom LSI (Large Scale Integrated Circuit: large scale integrated circuit) such as a PLD (Programmable Logic Device: programmable logic device) in addition to or instead of the above configuration. Examples of PLDs include PAL (Programmable Array Logic: programmable array logic), GAL (Generic Array Logic: general-purpose array logic), CPLD (Complex Programmable Logic Device: complex programmable logic device), and FPGA (Field Programmable Gate Array: field programmable gate array). In this case, part or all of the functions implemented by the processor may be implemented by the integrated circuit.

Examples of the storage device 93 include an HDD (Hard Disk Drive), an SSD (Solid State Drive: solid state Drive), a magnetic Disk, an optical Disk, a CD-ROM (Compact Disc Read Only Memory: compact Disk read only memory), a DVD-ROM (Digital Versatile Disc Read Only Memory: digital versatile Disk read only memory), and a semiconductor memory. The storage device 93 may be an internal medium directly connected to the bus of the computer 90, or may be an external medium connected to the computer 90 via the interface 94 or a communication line. Further, in the case where the program is distributed to the computer 90 via a communication line, the computer 90 having received the distribution can expand the program in the main memory 92 to execute the above-described processing. In at least one embodiment, the storage 93 is a non-transitory tangible storage medium.

< by-note >

The control device 4 of the incinerator apparatus according to each embodiment is grasped as follows, for example.

(1) The control device 4 of the incinerator apparatus according to claim 1, which has a furnace main body that conveys an object to be incinerated while burning the object to be incinerated, and a feeder that supplies the object to be incinerated to the furnace main body, comprises: an image information acquisition unit 41 that periodically acquires image information including a receiving port 122 of the furnace main body, the receiving port 122 of the furnace main body being connected to an end of the feeder; an image information identifying unit 42 that identifies whether or not the incineration object at the receiving opening 122 is in a state of protruding toward the furnace main body, based on the image information; and a supply state determination unit 43 that determines that there is a sign that the material to be incinerated is excessively supplied to the furnace main body when it is recognized that the material to be incinerated is in a state of being projected to the furnace main body for a predetermined time. According to the present embodiment and the following embodiments, it is possible to improve control delay that is made in response to a change in the supply amount of the objects to be burned, such as waste, such as oversupplied.

(2) The control device 4 of the incinerator apparatus according to claim 2 is the control device 4 of the incinerator apparatus according to claim (1), wherein the image information acquisition unit 41 may acquire the image information including at least a part of the receiving port 122 and the inner wall of the drying area.

(3) The control device 4 of the incinerator apparatus according to claim 3 is the control device 4 of the incinerator apparatus according to the above (1) or (2), wherein the supply state determination unit 43 may determine that there is a sign that the material to be incinerated is oversupplied to the furnace main body when the material to be incinerated is recognized as being in a state of being projected to the furnace main body for a predetermined time and when the probability of occurrence of oversupply based on the total extrusion length of the feeder is equal to or greater than a predetermined threshold.

(4) The control device 4 of the incinerator equipment according to claim 4 is the control device 4 of the incinerator equipment according to claim 3, wherein the threshold value may be a value that is changed based on information related to the actual combustion state of the object to be incinerated including at least information indicating the amount of carbon monoxide generated and information indicating the amount of nitrogen oxide generated.

(5) The control device 4 of the incinerator apparatus according to claim 5 is the control device 4 of the incinerator apparatus according to any one of the above (1) to (4), wherein the image information identifying unit 42 may identify whether or not the material to be incinerated is in a state of being projected toward the main body of the incinerator for each of the divided regions in which the receiving port 122 is divided, and the supply state determining unit 43 may determine that there is a sign that the material to be incinerated is excessively supplied to the main body of the incinerator at least when it is identified that the material to be incinerated is projected toward the main body of the incinerator in the plurality of divided regions for a predetermined period of time.

(6) The control device 4 of the incinerator apparatus according to claim 6 is the control device 4 of the incinerator apparatus according to any one of the above (1) to (5), wherein the image information identifying unit 42 may identify whether or not the incineration object is in an extended state by using a pre-training model 491 which is obtained by using at least the image information as an explanatory variable and using the presence or absence of extension of the incineration object and a visual field defect as target variables, and the supply state determining unit 43 may determine that there is a sign that the incineration object is excessively supplied to the incinerator body when it is at least for a predetermined time that the incineration object is in an extended state toward the incinerator body and the feeder is pushing the incineration object.

(7) The control device 4 of the incinerator apparatus according to claim 7 is the control device 4 of the incinerator apparatus according to any one of the above (1) to (6), wherein at least one of a combustion air amount control unit that changes a supply amount of the combustion air based on a determination result of the excess supply precursor and a feeder control unit that changes at least one of an operation speed and a stroke of the feeder based on a determination result of the excess supply precursor may be further provided.

Industrial applicability

Symbol description

100-incinerator equipment, 108-combustion chamber, 110-extrusion device, 4-control device, 41-image information acquisition unit, 42-image information identification unit, 43-supply state determination unit, 44-combustion air amount control unit, 45-feeder control unit, 49-storage unit, 491-pre-training model, 492-image information.

Claims

1. A control device for an incinerator apparatus having a furnace main body for transporting an object to be incinerated while combusting the object to be incinerated, and a feeder for feeding the object to be incinerated to the furnace main body, the control device comprising:

an image information acquisition unit that periodically acquires image information including a receiving port of the furnace main body, the receiving port of the furnace main body being connected to an end of the feeder;

an image information identifying unit that identifies, based on the image information, whether or not the object to be incinerated at the receiving port is in a state of protruding toward the furnace main body; a kind of electronic device with high-pressure air-conditioning system

And a supply state determination unit configured to determine that there is a sign that the material to be incinerated is excessively supplied to the furnace main body when the material to be incinerated is recognized as being in a state of being projected toward the furnace main body for a predetermined time.

2. The control device of an incinerator apparatus according to claim 1, wherein,

the image information acquisition unit acquires the image information including at least a part of the inner wall of the receiving port and the drying area.

3. The control device of an incinerator apparatus according to claim 1 or 2, wherein,

when the status of the burnt objects extending toward the furnace main body is recognized for a predetermined time and the probability of occurrence of oversupply based on the total extrusion length of the feeder is equal to or greater than a predetermined threshold, the supply status determination unit determines that there is a sign that the burnt objects are oversupplied to the furnace main body.

4. A control device for an incinerator apparatus according to claim 3, wherein,

the threshold value is a value that is changed based on information related to the actual combustion state of the burned object, which includes at least information indicating the amount of carbon monoxide generated and information indicating the amount of nitrogen oxide generated.

5. The control device of an incinerator apparatus according to any one of claims 1 to 4, wherein,

the image information identifying unit identifies whether or not the object to be incinerated is in a state of protruding toward the furnace main body for each divided region in which the receiving port is divided into a plurality of regions,

at least when the state that the objects to be burned extend toward the furnace main body in the plurality of divided areas is recognized for a predetermined period of time, the supply state determination unit determines that there is a sign that the objects to be burned are excessively supplied to the furnace main body.

6. The control device of an incinerator apparatus according to any one of claims 1 to 5, wherein,

the image information identifying unit identifies whether or not the object to be incinerated is in a state of being projected using a pre-trained model obtained by using at least the image information as an explanatory variable and the presence or absence of projection of the object to be incinerated and a visual field defect as target variables,

the supply state determination unit determines that there is a sign that the material to be incinerated is excessively supplied to the furnace main body at least when the material to be incinerated is recognized as being in a state of being projected toward the furnace main body for a predetermined time and the feeder is pushing the material to be incinerated.

7. The control device of an incinerator apparatus according to any one of claims 1 to 6, further comprising at least one of a combustion air amount control unit that changes a supply amount of combustion air according to a determination result of the excess supply precursor, and a feeder control unit that changes at least one of an operation speed and a stroke of the feeder according to a determination result of the excess supply precursor.