Management device, management method, and program

Abstract

To easily derive the volume of waste on a stoker, according to thermal image data obtained by imaging the inside of an incinerator.SOLUTION: There is provided a management device comprising a controller for acquiring image data relating to thermal image information obtained by imaging an area including waste in a furnace provided with a stoker, so as to perform image processing. The controller causes a memory unit to memorize the acquired image data, identifies a boundary between an area where waste is present and an area where a substance other than waste is present on the stoker to generate a boundary line and generate boundary image data including the boundary line from the image data having been read out, sets up a prescribed cross section corresponding to a prescribed axis concerning the waste present on the stoker according to the boundary image data, and sets up a closed curve connecting three peaks, i.e., an upper position of the boundary line in the prescribed cross section, a lower position of the boundary line therein, and the position of the stoker where the waste is to be fed, to derive the area of the closed curve from the plurality of positions along the prescribed axis and derive the volume of the waste on the stoker, according to the area of the closed curve.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to a management device, a management method, and a program. [Background technology]

[0002] In order to improve the efficiency of stoker-type incinerator operation, there has been a demand for a technology that can derive the amount of waste on the grate from thermal imaging data of waste burning inside the incinerator. In Patent Document 1, the pile height of waste on the wall surface is derived by detecting the boundary lines with the inner wall surfaces on both sides inside the incinerator, and the volume of waste is estimated based on the value of the pile height. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6472035 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the technology described in Patent Document 1, the volume of waste is calculated based only on the height of the left and right walls, making it difficult to accurately estimate the amount of waste piled up. Therefore, there has been a demand for a technology that can easily calculate the volume of waste on the grate based on thermal imaging data captured inside the incinerator.

[0005] The present invention has been made in consideration of the above, and its object is to provide a management device, management method, and program that can easily derive the volume of waste on the grate based on thermal imaging data taken inside an incinerator. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, one embodiment of the present invention provides a management device that includes a control unit that acquires image data generated from thermal image information of an area containing waste in a waste incinerator equipped with a grate for moving the waste, and performs image processing on the image data. The control unit acquires the image data and stores it in a memory unit, and for the image data read from the memory unit, identifies the boundary between the area on the grate where the waste is present and the area other than the waste, generates a boundary line that defines at least a portion of the boundary, and generates boundary image data including the boundary line. Based on the boundary image data, a specified cross section corresponding to a specified axis for the waste present on the grate is set, a closed curve is set that connects three vertices, the vertices of which are the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate, and the area of ​​the closed curve is calculated for multiple positions along the specified axis. The control unit calculates the volume of waste on the grate based on the area of ​​the closed curve.

[0007] In one aspect of the present invention, in the management device of the above invention, the control unit acquires the image data from the memory unit as an input parameter, inputs the image data into a boundary identification learning model, and outputs the boundary image data as an output parameter, and the boundary identification learning model is a learning model generated by machine learning using the image data as a learning input parameter and processed image data in which the boundary line is drawn on the image data as a learning output parameter.

[0008] In one embodiment of the management device of the present invention, in the above invention, the specified axis is set parallel to the intersection between the grate and the step wall onto which the waste falls, the specified cross section is a plane perpendicular to the specified axis, and a closed curve connecting the three vertices is set within the plane.

[0009] A management method according to one embodiment of the present invention is a management method executed by a management device that acquires image data generated from thermal image information of an area containing waste within a waste incinerator equipped with a grate for moving the waste, and performs image processing on the image data.The management method acquires the image data and stores it in a memory unit.For the image data read from the memory unit, the boundary between the area where the waste is present on the grate and the area other than the waste is identified, a boundary line that defines at least a portion of the boundary is generated, and boundary image data including the boundary line is generated.Based on the boundary image data, a specified cross section corresponding to a specified axis for the waste present on the grate is set, a closed curve is set that connects three vertices, the vertices of which are the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate.The area of ​​the closed curve is derived for multiple positions along the specified axis, and the volume of waste on the grate is derived based on the area of ​​the closed curve.

[0010] A program according to one embodiment of the present invention is a management device having a control unit that acquires image data generated from thermal image information of an area containing waste in a waste incinerator equipped with a grate for moving the waste and performs image processing on the image data. The program causes the control unit of the management device to acquire the image data and store it in a memory unit, identify the boundary between the area on the grate where the waste is present and the area other than the waste for the image data read from the memory unit, generate a boundary line that defines at least a portion of the boundary, generate boundary image data including the boundary line, set a specified cross section corresponding to a specified axis for the waste present on the grate based on the boundary image data, set a closed curve connecting three vertices, the vertices of which are the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate, derive the area of ​​the closed curve for multiple positions along the specified axis, and derive the volume of the waste on the grate based on the area of ​​the closed curve. [Effects of the Invention]

[0011] According to the management device, management method, and program of the present invention, it is possible to easily derive the volume of waste on the grate based on thermal imaging data obtained by capturing an image of the inside of an incinerator. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a schematic diagram showing the overall configuration of a waste incineration facility to which a waste management apparatus according to one embodiment of the present invention is applied. [Figure 2] FIG. 2 is a side view showing waste, a portion where the waste is fed onto a fire grate, and an imaging unit in an incinerator according to an embodiment of the present invention. [Figure 3] FIG. 3 is a block diagram showing the configuration of a combustion control device according to one embodiment of the present invention. [Figure 4] FIG. 4 is a block diagram showing the configuration of a waste management apparatus in a management system according to an embodiment of the present invention. [Figure 5] FIG. 5 is a diagram showing an example of transmission image data of waste being burned, captured by the imaging section according to one embodiment of the present invention. [Figure 6] FIG. 6 is a diagram showing an example in which a longitudinal cross section of waste is set on boundary image data in which a boundary line is set on transmission image data captured by the imaging section according to one embodiment of the present invention. [Figure 7] FIG. 7 is a flowchart illustrating a management method according to an embodiment of the present invention. [Figure 8] FIG. 8 is a front view for explaining coordinates (grid lines) on the fire grate in an incinerator according to one embodiment of the present invention. [Figure 9] FIG. 9 is a diagram schematically illustrating an example of setting a closed curve with three vertices according to an embodiment of the present invention, viewed in the x direction. [Figure 10] FIG. 10 is a diagram showing an example of setting a partial volume of waste that is set for transmission image data captured by an imaging section according to an embodiment of the present invention. [Figure 11A] FIG. 11A is a diagram schematically illustrating a first modified example of a setting example of a closed curve with three vertices according to an embodiment of the present invention, as viewed in the x direction. [Figure 11B] FIG. 11B is a diagram schematically showing a second modified example of a setting example of a closed curve with three vertices according to an embodiment of the present invention, as viewed in the x direction. [Figure 11C] FIG. 11C is a diagram schematically illustrating a third modified example of a setting example of a closed curve with three vertices according to an embodiment of the present invention, as viewed in the x direction. [Figure 11D] FIG. 11D is a diagram schematically illustrating a fourth modified example of a setting example of a closed curve with three vertices according to an embodiment of the present invention, as viewed in the x direction. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all the drawings of the embodiment below, the same or corresponding parts are designated by the same reference numerals. Furthermore, the present invention is not limited to the embodiment described below.

[0014] As described above, in order to improve the efficiency of incinerator operation, there has been a need for technology that can determine the amount of waste on the grate from thermal imaging data captured inside the incinerator. However, it has been difficult to accurately estimate the amount of waste by image processing of thermal imaging data captured inside the incinerator. In this regard, the inventors have found that in stoker-type incinerators (hereinafter referred to as grate-type incinerators), waste is supplied from the supply port by dropping down a step wall and being burned while being moved by the grate. Therefore, the cross-sectional shape of the waste piled up on the grate can be approximated by a simple closed curve (also called a single closed curve or Jordan curve) with vertices at the intersection of the step wall and the grate, the top of the waste, and the combustion point of the waste on the grate. In this specification, various triangles and simple closed curves connecting three vertices are referred to as three-vertex closed curves. On the other hand, by detecting the boundary line of the outer edge of the waste piled up on the grate using image signal processing such as deep learning and applying a closed curve model, it is possible to accurately estimate the distribution shape of the waste. This led the inventor to conceive that if the boundary line of the waste on the grate is detected, the amount of waste can be derived. The embodiment described below was devised based on the inventor's diligent investigation.

[0015] (Waste Management System) Figure 1 is an overall configuration diagram showing a waste incineration facility as an incineration facility to which a waste management apparatus according to one embodiment of the present invention is applied. As shown in Figure 1, a waste management system 1 according to one embodiment has a monitoring and combustion control device 30 and a waste management apparatus 40 that can communicate with each other via a network 2. The monitoring and combustion control device 30 is configured to be able to control a waste incinerator 100 as a predetermined facility.

[0016] The network 2 is composed of an internet network, a mobile phone network, or the like. The network 2 is, for example, a public communication network such as the internet, and may also include other communication networks such as a wide area network (WAN), a telephone communication network such as a mobile phone, or a wireless communication network such as Wi-Fi. Note that data transmitted and received in communication between the monitoring and combustion control device 30 and the waste management device 40 may include operational management indicators important for the operation of the waste incinerator 100. In this case, considering the security of the transmitted and received data, the communication line between the monitoring and combustion control device 30 and the waste management device 40 may be a dedicated line or a VPN line. The monitoring and combustion control device 30 and the waste management device 40 may be integrated, and may be installed in the same facility as the waste incinerator 100 or in separate facilities. When the waste incinerator 100, the monitoring and combustion control device 30, and the waste management device 40 are installed in separate facilities, various information and data are communicated via the network 2.

[0017] (Waste incinerator) 1, a waste incinerator 100, such as a grate-type waste incinerator, includes a furnace 101 in which waste is burned, a waste inlet 102 through which the waste is introduced, and a boiler 109. The boiler 109 includes a heat exchanger 109a and a steam drum 109b installed downstream of a furnace outlet 107 of the furnace 101.

[0018] Waste thrown in through the waste inlet 102 is transported to the grate 104 by a waste feeder 103. The reciprocating motion of the grate 104 agitates and moves the waste. The waste on the grate 104 is burned while being dried by the blowing of combustion air supplied by a combustion air blower 106 into a wind box below the grate 104, producing exhaust gas and ash. The produced ash falls through an ash drop port 105 and is discharged outside the furnace 101.

[0019] The total amount of combustion air supplied to the furnace 101 from below the grate 104 is adjusted by a combustion air damper 114 located immediately adjacent to the combustion air blower 106. The flow rate of combustion air supplied to each wind box is adjusted by under-grate combustion air dampers 114a, 114b, 114c, and 114d, which are respectively installed in the pipes supplying combustion air to each wind box. In other words, the under-grate combustion air dampers 114a-114d adjust the ratio of the flow rate of combustion air supplied to each wind box. Note that in FIG. 1, the area below the grate 104 is divided into four wind boxes along the waste transport direction, and combustion air is supplied through each wind box. However, the number of under-grate combustion air dampers 114a-114d and wind boxes is not necessarily limited to four and can be changed as appropriate depending on the size and purpose of the waste incinerator.

[0020] Furthermore, for example, a combustion air temperature damper 126a connected in series and a combustion air temperature damper 126b connected in parallel are connected to the combustion air damper 114. These combustion air temperature dampers 126a and 126b adjust the temperature of the combustion air supplied from below the grate 104 into the furnace 101.

[0021] Cooling air is blown into the furnace 101 by a cooling air blower 111 through cooling air inlets 110 provided on the furnace wall or ceiling of the furnace 101. Blowing cooling air into the furnace 101 further burns unburned components in the combustion gas and prevents the furnace wall temperature from rising excessively. The flow rate of the cooling air supplied into the furnace 101 from the cooling air inlets 110 is adjusted by a cooling air damper 115 provided immediately adjacent to the cooling air blower 111. An exhaust gas recirculation air damper 128 is provided on the ceiling or other part of the furnace 101. This damper adjusts the flow rates of the exhaust gas and combustion air when a recirculation blower 127 mixes exhaust gas from the outlet of an exhaust gas treatment device (not shown) with the combustion air and recirculates it into the furnace 101. Low-air-ratio combustion achieved by the exhaust gas recirculation air damper 128 makes it possible to suppress NOx generation during combustion.

[0022] Along the direction of waste transport in the grate 104, combustible gases generated in the upstream waste drying process and main combustion process and combustion exhaust gases generated in the downstream post-combustion process join together in a gas mixing section located on the furnace outlet 107 side of the furnace 101. The combustible gases and combustion exhaust gases joined in the gas mixing section are agitated and mixed again, and then secondary combustion is carried out by supplying secondary combustion air. The boiler 109 is installed downstream of the section where secondary combustion takes place (hereinafter referred to as the secondary combustion section) along the direction of waste transport. The combustion gases from the secondary combustion have their thermal energy recovered by the heat exchanger 109a of the boiler 109 and are then exhausted to the outside through the chimney 108.

[0023] An intermediate ceiling 116 is installed in the furnace 101 at an upper position along the height direction of the furnace 101. The intermediate ceiling 116 separates the gas flowing within the furnace 101 into gas containing a large amount of combustible gas generated during the waste drying process and main combustion process on the upstream side, and combustion exhaust gas generated during the post-combustion process on the downstream side, and then discharges the separated gases. Specifically, the combustion exhaust gas flows through a flue (main flue) below the intermediate ceiling 116, while the gas containing a large amount of combustible gas flows through a flue (secondary flue) above the intermediate ceiling 116. The combustion exhaust gas and the gas containing a large amount of combustible gas merge in the gas mixing section, further promoting gas agitation and mixing in the gas mixing section. This further stabilizes combustion in the secondary combustion section, suppresses the generation of dioxins during the combustion process, and reduces the generation of unburned waste. The furnace 101 may also be configured without the intermediate ceiling 116.

[0024] Thermometers serving as sensors for measuring the gas temperature inside the furnace 101 are provided at multiple positions inside the furnace 101. Specifically, a combustion chamber gas thermometer 117 is provided along the height direction of the furnace 101 at an intermediate position between the fire grate 104 and the cooling air inlet 110.

[0025] A main flue gas thermometer 118 is provided below the furnace outlet 107 along the height of the furnace 101. A furnace outlet lower gas thermometer 119 is provided below the furnace outlet 107 along the height of the furnace 101. A furnace outlet middle gas thermometer 120 is provided at the center of the furnace outlet 107 along the height of the furnace 101. A furnace outlet gas thermometer 121 is provided downstream of the furnace outlet 107 along the height of the furnace 101 to measure the combustion control temperature. The temperature measurement values ​​measured by the combustion chamber gas thermometer 117, main flue gas thermometer 118, furnace outlet lower gas thermometer 119, furnace outlet middle gas thermometer 120, and furnace outlet gas thermometer 121 are stored as combustion process measurement values ​​in the memory unit 34 (see FIG. 3 ) of the monitoring and combustion control device 30. The temperature measurement value data stored in the memory unit 34 may be transmitted from the monitoring and combustion control device 30 to the waste management device 40 as measurement data.

[0026] The boiler 109 is provided with a boiler outlet oxygen concentration meter 122 on the outlet side to measure the concentration of oxygen (O2) in the exhaust gas. At the inlet of the chimney 108, a boiler outlet oxygen concentration meter 122 is provided to measure the concentration of carbon monoxide (CO) and nitrogen oxides (NO x ) is provided. An exhaust gas flow meter 124 for measuring the amount of exhaust gas is provided in the pipe connecting the outlet of the boiler 109 to the chimney 108. The measurement values ​​of the gas concentration and flow rate measured by the boiler outlet oxygen concentration meter 122, gas concentration meter 123, and exhaust gas flow meter 124 are stored in the memory unit 34 of the monitoring combustion control device 30 as combustion process measurement values. The combustion process measurement values ​​are also simply referred to as measurement values.

[0027] An imaging unit 125 is provided downstream in the waste transport direction in the furnace 101. The imaging unit 125 is configured to include a flame transmission camera, for example, an infrared camera, and an image processing unit that processes the captured image data. The imaging unit 125 captures an image of the burning state of the waste on the grate 104 and stores transmission image data, which is thermal image data generated from the captured thermal image information, in the memory unit 34 of the monitoring and combustion control device 30. Furthermore, the imaging unit 125 may capture an image of the burning state of the waste on the grate 104 and store the captured transmission image data in, for example, an captured image database 421 (see FIG. 4) in the memory unit 42 of the waste management apparatus 40.

[0028] FIG. 2 is a side view showing the installation state of the imaging unit 125. In this embodiment, the imaging unit 125 is installed, for example, in a position substantially directly facing the waste supply unit 112 and the step wall 113, as shown in FIG. 2. Note that the installation of the imaging unit 125 is not limited to a position substantially directly facing the waste supply unit 112 and the step wall 113. The imaging unit 125 can be installed in various positions as long as it can capture an image of at least the boundary between the waste 52 on the grate and another object, in this case, the step wall 113 and the grate 104. The imaging unit 125 may be installed outside the furnace near a monitoring window provided in the furnace wall 101a, or may be installed inside the furnace 101 with a water-cooled structure. As shown in FIG. 2, the waste 50 falls from the waste supply unit 112 onto the grate 104 at the step wall 113. The waste 50 that has fallen onto the grate 104 is stirred by the reciprocating motion that accompanies the back and forth movement of the grate 104, and is moved forward toward the imaging unit 125 side.

[0029] (Monitoring and combustion control device) Fig. 3 is a block diagram showing the configuration of the monitoring and combustion control device 30. As shown in Fig. 3, the monitoring and combustion control device 30 includes a calculation control unit 31, an operated variable reference value adjustment unit 32, an operated variable reference value correction unit 33, a storage unit 34, an operated variable adjustment unit 35, and a communication unit 36. The calculation control unit 31, the operated variable reference value adjustment unit 32, the operated variable reference value correction unit 33, and the operated variable adjustment unit 35 specifically include a processor having hardware such as a CPU (Central Processing Unit), a DSP (Digital Signal Processor), or an FPGA (Field-Programmable Gate Array), and a main storage unit such as a RAM (Random Access Memory) or a ROM (Read Only Memory) (none of which are shown).

[0030] The storage unit 34 is configured with a storage medium selected from volatile memory such as RAM, non-volatile memory such as ROM, erasable programmable ROM (EPROM), hard disk drive (HDD), and removable media. The removable media is, for example, a universal serial bus (USB) memory or a disc storage medium such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray (registered trademark) disc (BD). Alternatively, the storage unit 34 may be configured with a computer-readable storage medium such as an externally attachable memory card.

[0031] The memory unit 34 can store an operating system (OS), various programs, various tables, various databases, and the like for executing the operation of the monitoring and combustion control device 30. The various programs include information processing programs that implement processing based on models such as the learning model and the trained model according to this embodiment. These various programs can also be recorded on computer-readable recording media such as a hard disk, flash memory, CD-ROM, DVD-ROM, or flexible disk for widespread distribution. The memory unit 34 includes a set value database 341 that stores externally input incineration volume set values ​​and evaporation volume set values ​​as information, and a measurement value database 342 that stores combustion-related process measurement values ​​acquired from the waste incinerator 100 as information. The memory unit 34 may also be provided in another server that can communicate via various networks.

[0032] The monitoring and combustion control device 30 controls the combustion air volume, cooling air volume, waste feeder feed rate, and grate feed rate as the manipulated variables of each control element based on a predetermined manipulated variable reference value setting relational expression. The monitoring and combustion control device 30 also controls the shutdown and operation of the waste feeder feed rate and grate feed rate. The manipulated variable reference value setting relational expression is a relational expression between the waste incineration volume set value or waste quality set value and the manipulated variable reference value (the target value of the manipulated variable), and includes a control parameter as a correction coefficient. The control parameter is adjusted by the manipulated variable reference value adjustment unit 32 to match the waste incineration volume set value and the waste quality set value. When at least one of the waste incineration volume set value and the waste quality set value is changed, the adjusted control parameter is changed by the manipulated variable reference value adjustment unit 32 in accordance with the changed set value. By changing the control parameter, the previously set manipulated variable reference value is corrected.

[0033] The calculation control unit 31 performs various controls and calculations. Specifically, for example, the calculation control unit 31 derives the amount of evaporation per hour generated by the combustion of waste in the waste incinerator 100 over a predetermined period, for example, one day (24 hours), as the evaporation amount setting value. Furthermore, for example, when functioning as a waste calculation unit, the calculation control unit 31 calculates the waste quality (lower heating value of the waste) according to the waste incineration amount setting value. The manipulated variable reference value adjustment unit 32 adjusts the manipulated variable reference value by adjusting control parameters included in the manipulated variable reference value setting relational expression. The manipulated variable reference value correction unit 33 corrects the manipulated variable reference value adjusted by the manipulated variable reference value adjustment unit 32 based on a predetermined control algorithm (PID control, fuzzy calculation, etc.). Note that data referenced by the calculation control unit 31, manipulated variable reference value adjustment unit 32, and manipulated variable reference value correction unit 33 is readably stored in the memory unit 34. The memory unit 34 stores predetermined operation quantity reference value setting relational expressions and control algorithms, daily evaporation amount setting values ​​and incineration amount setting values ​​transmitted from the waste management device 40, and combustion process measurement values ​​transmitted from the waste incinerator 100 and acquired as combustion state quantities within the furnace 101.

[0034] The manipulated variable adjustment unit 35 adjusts the manipulated variable of each manipulated variable so that it follows the manipulated variable reference value. Specifically, the manipulated variable adjustment unit 35 has a combustion air amount adjustment unit 351, an air amount ratio adjustment unit 352, a cooling air amount adjustment unit 353, a garbage feeder feed rate adjustment unit 354, a grate feed rate adjustment unit 355, a combustion air temperature adjustment unit 356, and an exhaust gas recirculation air flow rate adjustment unit 357.

[0035] The combustion air volume adjustment unit 351 adjusts the operation volume so that the combustion air volume follows the operation volume reference value (hereinafter, the corrected operation volume reference value) corrected by the operation volume reference value correction unit 33. The air volume ratio adjustment unit 352 controls each of the under-grate combustion air dampers 114a-114d to adjust the relative ratio of the flow rates in each wind box. The cooling air volume adjustment unit 353 adjusts the operation volume so that the cooling air volume follows the corrected operation volume reference value. Here, the combustion air volume and the cooling air volume are adjusted by controlling the opening degrees of the combustion air damper 114, the under-grate combustion air dampers 114a-114d, and the cooling air damper 115. The garbage feeder feed rate adjustment unit 354 adjusts the operation volume so that the garbage feeder feed rate follows the corrected operation volume reference value. The grate feed rate adjustment unit 355 adjusts the operation volume so that the grate feed rate follows the corrected operation volume reference value. The combustion air temperature adjusting unit 356 controls the combustion air temperature dampers 126a and 126b so that the temperature of the combustion air follows the corrected manipulated variable reference value. The exhaust gas recirculation air flow rate adjusting unit 357 controls the exhaust gas recirculation air damper 128 so that the flow rates of the recirculated exhaust gas and air follow the corrected manipulated variable reference value. If the manipulated variable reference value correcting unit 33 has not corrected the manipulated variable reference value, the manipulated variable adjusting unit 35 adjusts each manipulated variable based on the uncorrected manipulated variable reference value.

[0036] The communication unit 36 ​​is, for example, a LAN (Local Area Network) interface board or a wireless communication circuit for wireless communication. The LAN interface board or wireless communication circuit is connected to a network 2 such as the Internet, which is a public communication network. The communication unit 36 ​​is configured to be connected to the network 2 and to be able to communicate with the waste management device 40, other devices, and servers.

[0037] (Waste Management Equipment) FIG. 4 is a block diagram showing a schematic configuration of the waste management apparatus 40. As shown in FIG. 4, the waste management apparatus 40 has the configuration of a typical computer capable of communicating via the network 2. The waste management apparatus 40 includes a control unit 41, a memory unit 42, a communication unit 43, and an input / output unit 44. The control unit 41, the memory unit 42, and the communication unit 43 are physically and functionally similar to the calculation control unit 31, the memory unit 34, and the communication unit 36 ​​described above, respectively. The waste management apparatus 40 functions as a volume estimation device for waste 50 that derives or estimates the volume of waste 50, and as a combustion point position measurement device that measures the position of the combustion point.

[0038] The control unit 41 loads a program stored in the storage unit 42 into a working area of ​​the main storage unit, executes the program, and controls each component through the execution of the program, thereby realizing functions that meet a predetermined purpose. In this embodiment, the control unit 41 executes the functions of a boundary generation unit 411, a volume calculation unit 412, and a learning unit 413 by executing the program stored in the storage unit 42. Specifically, for example, the control unit 41 executes the function of the boundary generation unit 411 by reading a boundary identification learning model 423, which is a program, from the storage unit 42. The control unit 41 also executes the function of the volume calculation unit 412 by reading a volume calculation program from the storage unit 42. Details of the functions of the boundary generation unit 411, the volume calculation unit 412, and the learning unit 413 will be described later.

[0039] The storage unit 42 has the same functional and physical configuration as the storage unit 34 described above, and is composed of a storage medium selected from volatile memory such as RAM, non-volatile memory such as ROM, EPROM, HDD, and removable media. The removable media is, for example, a USB memory or a disc storage medium such as a CD, DVD, or BD. Alternatively, the storage unit 42 may be composed of a computer-readable storage medium such as an externally attachable memory card.

[0040] The storage unit 42 can store an OS, various programs, various tables, various databases, and the like for executing the operations of the waste management apparatus 40. Here, the various programs include an information processing program that realizes control using the learning model or the trained model according to this embodiment. The storage unit 42 may be provided in another server that can communicate via various networks, or may be provided in the monitoring and combustion control device 30.

[0041] Specifically, the storage unit 42 stores a captured image database 421, a volume information database 422, and a boundary identification learning model 423. The database (DB) described in this embodiment is constructed by a database management system (DBMS) program executed by the above-mentioned processor managing data stored in the storage unit 42. The captured image database 421 stores searchable captured image data of the inside of the furnace 101, such as transmission image data captured by the imaging unit 125 and boundary image data generated by the boundary generation unit 411. The volume information database 422 stores searchable volume information of the waste 50 on the grate 104 in the furnace 101 calculated by the volume calculation unit 412 from boundary image data obtained based on the transmission image data captured by the imaging unit 125. These databases 421 and 422 are, for example, relational databases (RDB). The databases stored in the storage unit 42 are not limited to the above databases.

[0042] The boundary discrimination learning model 423 is an updatable model including at least one learning model. If the learning model is not updated, it is stored in the storage unit 42 as a trained model. The boundary discrimination learning model 423 may include a combustion state learning model, which is a learning model capable of extracting a combustion region based on image data of the interior of the furnace 101, such as transmission image data and boundary image data. Instead of the boundary discrimination learning model 423, a rule-based information processing program created without learning or the like, which performs predetermined information processing on input data, may be used. Furthermore, the boundary discrimination learning model 423 may include an automatic judgment processing program that realizes judgment processing using a combustion image learning model, which can make predetermined judgments based on data of the combustion image of the luminous flame itself captured by the imaging unit 125. These various programs may be recorded on computer-readable recording media such as hard disks, flash memories, CD-ROMs, DVD-ROMs, and flexible disks, and widely distributed.

[0043] The input / output unit 44, serving as an output means, displays images of the waste 50 in the furnace 101 on a display monitor, such as an organic electroluminescence (EL) panel or a liquid crystal display (LCD) panel, displays text and graphics on a touchscreen display, and outputs audio from a speaker, under the control of the control unit 41. The input / output unit 44, serving as an input means, is configured using a user interface, such as a keyboard, input buttons, levers, a touchscreen for manual input superimposed on a display such as an LCD, or a microphone for voice recognition. A user can input predetermined information to the control unit 41 by operating the input / output unit 44. That is, the input / output unit 44 can be configured, for example, as a touchscreen keyboard incorporated into the keyboard or display unit to detect touch operations on the display panel, or as a voice input device that enables external communication. The input / output unit 44 may also be configured as a separate output unit and input unit.

[0044] (Boundary discrimination learning model) Next, we will explain the boundary discrimination learning model 423 stored in the storage unit 42 used in the waste management apparatus 40 in the management method by the waste management system 1 configured as described above, and the method for generating the boundary discrimination learning model 423. Fig. 5 is a diagram showing an example of transmission image data of burning waste captured by the imaging unit 125 of this embodiment. Fig. 6 is a diagram showing an example of boundary image data in which a boundary line is generated from the transmission image data captured by the imaging unit 125 of this embodiment.

[0045] As shown in FIG. 5, the imaging unit 125 captures images of the waste 51 before it is supplied onto the waste supply unit 112 and the grate 104, the step wall 113, the grate 104, the waste on the grate 52 on the grate 104, and the furnace wall 101a within the furnace 101, with the flame transmitted through the images, and outputs the captured images as transmission image data. As shown in FIG. 6, the boundary identification learning model 423 executes a process for generating a boundary line 531 between the waste 50 and other objects for the transmission image data captured by the imaging unit 125. In the example shown in FIG. 6, the boundary line 531 is drawn at the boundary between the waste on the grate 52 and the step wall 113, the furnace wall 101a, and the grate 104. By drawing the boundary line 531, the boundary image data can define the outer edge of the waste on the grate 52 present on the grate 104.

[0046] The data used to generate the boundary identification learning model 423 are the transmission image data captured by the imaging unit 125 and processed image data (hereinafter, boundary image data) in which boundaries are identified in the transmission image data and the above-mentioned boundary line 531 is drawn. The number of transmission image data and boundary image data is preferably, for example, 100 or more. That is, the boundary image data used for generation is image data in which an operator draws boundary lines 531 for each boundary between the waste 50 and the waste supply unit 112, the step wall 113, the furnace wall 101a, and the grate 104 in the transmission image data. As input / output data sets for generating the boundary identification learning model 423, the transmission image data is used as learning input parameters, and the boundary image data is used as learning output parameters. The learning unit 413 of the control unit 41 generates the boundary identification learning model 423 by deep learning using, for example, a hierarchical convolutional neural network (hierarchical CNN) such as U-Net, using the above-mentioned learning input parameters and learning output parameters as training data. The control unit 41 generates boundary image data from the transmission image data based on the content learned by the learning unit 413. The learning unit 413 also appropriately updates the boundary identification learning model 423 using the input transmission image data and boundary image data obtained by the operator correcting or drawing the boundary.

[0047] Furthermore, when the boundary identification learning model 423 includes a combustion state learning model, the input and output data sets used when generating the combustion state learning model are transmission image data or boundary image data as learning input parameters, and extracted image data that extracts a predetermined combustion state as learning output parameters.

[0048] That is, the learning input parameters for the combustion state learning model are at least one of the transmission image data captured by the imaging unit 125 and the boundary image data generated by the boundary generation unit 411 based on the boundary identification learning model 423. The learning output parameters used to generate the combustion state learning model are extracted image data in which an operator has drawn boundaries between the waste on the grate 52 and other areas, and between the waste on the grate 52 whose combustion temperature is above a predetermined temperature and other areas containing waste on the grate 52 whose combustion temperature is below the predetermined temperature, on the transmission image data or the boundary image data. The imaging unit 125, which is equipped with a thermal imaging camera or the like, can output transmission image data based on the temperature distribution of the waste 50. In this case, the output transmission image data can be output as image data in which, for example, the higher the temperature, the higher the brightness, and the lower the temperature, the lower the brightness. This allows the waste on the grate 52 to be extracted from the transmission image data, and high-temperature areas of the extracted waste on the grate 52 that are above a predetermined temperature, as combustion areas, to generate extracted image data. In this way, extracted image data in which the waste 52 on the grate and the combustion area are extracted may be used as boundary image data in comparison with transmission image data in which the temperature distribution can be grasped by brightness.

[0049] The number of transmission image data, boundary image data, and extracted image data used for learning is preferably, for example, 100 or more. The learning unit 413 of the control unit 41 generates a combustion state learning model by machine learning, such as deep learning using a neural network, using the above-mentioned learning input parameters and learning output parameters as training data. The control unit 41 generates extracted image data from the transmission image data or boundary image data based on the content learned by the learning unit 413. The learning unit 413 can also update the combustion state learning model as needed using the input transmission image data or boundary image data and extracted image data obtained by an operator modifying or drawing a boundary.

[0050] (Management method) Next, a management method executed by the waste management apparatus 40 of the waste management system 1 configured as described above will be described. FIG. 7 is a flowchart for explaining the management method according to this embodiment. FIG. 8 is a front view for explaining coordinates (grid lines) on the grate 104 in the furnace 101 according to this embodiment. FIG. 9 is a diagram schematically showing an example of setting a three-vertex closed curve as viewed in the x direction. FIG. 10 is a diagram showing an example of setting a partial volume of waste set for transmission image data captured by the imaging unit 125. Note that the following description will also refer to FIGS. 5 and 6 as appropriate. In this embodiment, step ST1 is a process performed by the imaging unit 125 in the furnace 101, and steps ST2 to ST7 are a process performed by the waste management apparatus 40.

[0051] As shown in FIG. 7, in step ST1, the imaging unit 125 captures an image of the inside of the furnace 101. The imaging unit 125 captures an image of the situation inside the furnace 101 within its field of view as an image through which a flame is transmitted. Specifically, as shown in FIG. 5, the imaging unit 125 captures an image of the pre-supply waste 51, the step wall 113, the waste on the grate 52, the grate 104, and the furnace wall 101a in the waste supply unit 112 as if a luminous flame were transmitted through the image. Note that the pre-supply waste 51 does not need to be captured. The imaging unit 125 transmits the captured transmission image data to the control unit 41 via the input / output unit 44 of the waste management device 40. The control unit 41 stores the received transmission image data in the captured image database 421 of the storage unit 42.

[0052] As shown in FIG. 8 , the imaging unit 125 has a measurement field of view that extends, for example, in the vertical direction (z direction) of the furnace 101, the horizontal direction (furnace width direction: x direction), and the conveying direction (y direction) on the grate 104. In this embodiment, the field of view of the imaging unit 125 includes at least the waste supply unit 112, the step wall 113, the grate 104, and the furnace wall 101a. The furnace wall 101a, which is included in the field of view of the imaging unit 125, restricts the outward movement of the waste 50 in the horizontal direction, i.e., the spread of the waste 50. Note that the field of view of the imaging unit 125 only needs to be large enough to capture the boundary between the waste 52 on the grate present on the grate 104 and the furnace wall 101a, the grate 104, and the step wall 113. Furthermore, it is preferable that the imaging unit 125 can capture the waste 50 conveyed to the waste supply unit 112. This allows the waste 50 falling at the position of the step wall 113 to be captured.

[0053] The volume calculation unit 412 of the waste management apparatus 40 also sets the coordinate of the grate 104 in the transport direction (y direction) relative to the position x in the left-right direction (x direction) of the lower end of the step wall 113, i.e., the intersection of the step wall 113 and the grate 104. That is, for example, a grid-like coordinate (x, y) is set for the upper surface of the grate 104 on the two-dimensional screen of the captured image data. Here, the x direction and the y direction as predetermined axes are usually perpendicular to each other, but are not necessarily orthogonal. Furthermore, the z direction is set as the up-down direction (height direction) of the furnace 101 relative to the plane defined by the x and y directions. Here, the z direction and the y direction are usually perpendicular to each other, but are not necessarily orthogonal. The z direction and the x direction are also usually perpendicular to each other, but are not necessarily orthogonal. By the above settings, three-dimensional coordinates (x, y, z) can be set on the two-dimensional screen of the captured image data. As a result, the volume calculation unit 412 can determine the pile height of the waste 50 near the step wall 113 on the two-dimensional screen of the captured image data using the z-coordinate corresponding to the x-coordinate, and can also determine the downstream end along the conveying direction on the grate 104 using the y-coordinate corresponding to the x-coordinate.

[0054] 7, the process proceeds to step ST2, where the boundary generation unit 411 of the waste management apparatus 40 reads the boundary identification learning model 423 and determines the boundaries between the waste 50 and the waste supply unit 112, the step wall 113, the furnace wall 101a, and the grate 104 based on the transmission image data (see FIG. 5) acquired from the imaging unit 125. The boundary generation unit 411 may also use a rule-based image identification algorithm to mutually identify the waste 50, the waste supply unit 112, the step wall 113, the furnace wall 101a, and the grate 104, and determine the boundaries therebetween.

[0055] Next, the process proceeds to step ST3, where the boundary generation unit 411 draws boundary lines 531 for the boundaries between the area where the waste 50 is present and other objects, i.e., the boundaries between the waste 50 and the waste supply unit 112, the step wall 113, the furnace wall 101a, and the grate 104, in the transmission image data. As a result, as shown in FIG. 6 , the boundary generation unit 411 draws boundary lines 531 for the boundaries between the step wall 113, the grate 104, and the furnace wall 101a and the waste 52 on the grate, for example, in the transmission image data. In other words, the boundary generation unit 411 draws the boundary line 531 so as to surround the outer edge of the waste 52 on the grate. As described above, the boundary generation unit 411 generates boundary image data in which the boundary line 531 is drawn in the transmission image data. The boundary generation unit 411 outputs the generated boundary image data to the volume calculation unit 412.

[0056] Next, the process proceeds to step ST4 shown in FIG. 7, where the volume calculation unit 412 of the control unit 41 calculates the height of the layer of the waste 52 on the grate (hereinafter referred to as the waste layer height z). Specifically, the volume calculation unit 412 of the waste management apparatus 40 calculates the waste layer height z based on the boundary portion between the step wall 113 and the waste 52 on the grate at the boundary line 531. Here, as shown in FIG. 6, the boundary portion between the step wall 113 and the waste 52 on the grate at the boundary line 531 is uneven. The volume calculation unit 412 derives a height coordinate z0 of the boundary line 531 corresponding to an arbitrary position coordinate x0 in the x direction along the intersection portion between the grate 104 and the step wall 113 that is set in advance in the boundary image data.

[0057] Next, proceeding to step ST5 shown in FIG. 7, the volume calculation unit 412 functions as a combustion point position measurement device and measures the position of the waste 52 on the grate 104 in the forward direction of transport, i.e., the combustion point. That is, the boundary line 531a at the forward position of the boundary line 531 between the waste 52 on the grate and the grate 104 is the specific combustion point of the waste 50. Note that the specific combustion point of the waste 50 is typically uneven. The volume calculation unit 412 derives the coordinate y0 of the position in front of the boundary line 531a corresponding to an arbitrary position coordinate x0 in the x direction along the intersection of the grate 104 and the step wall 113, which is preset in the boundary image data. The above steps ST5 and ST6 are not limited to the above-mentioned order, and may be performed in parallel, in reverse order, or in any other order.

[0058] Thereafter, the process proceeds to step ST6, where the volume calculation unit 412 derives three points based on the coordinate z0 of the height of the boundary line 531 corresponding to the position coordinate x0 in the x direction and the coordinate y0 of the position in front of the boundary line 531a, which were derived in steps ST4 and ST5. Here, the three points at the coordinate z0 of the height of the boundary line 531 and the coordinate y0 of the position in front of the boundary line 531a corresponding to the position coordinate x0 in the x direction will be described.

[0059] 9, the volume calculation unit 412 sets a predetermined position x0 in the x direction along the intersection of the step wall 113 of the waste on the grate 52 on the grate 104 and the grate 104 in the boundary image data as point A (x0, 0, 0). The volume calculation unit 412 also sets a position of the waste on the grate 52 near the step wall 113 corresponding to point A in the boundary image data (the upper end of the boundary line 531a) as point B (x0, 0, z0). Furthermore, the volume calculation unit 412 sets a combustion point (a position in front of the boundary line 531a) corresponding to point A in the boundary image data as point C (x0, y0, z0).

[0060] The volume calculation unit 412 sets a three-vertex closed curve consisting of a simple closed curve connecting points A, B, and C in the boundary image data. The three-vertex closed curve ABC corresponds to a vertical cross section of the waste 52 on the grate 104. The vertical cross section, which is the predetermined cross section, is preferably a plane perpendicular to the x-direction, but is not limited thereto. In the example shown in FIG. 9, a triangle with sides AB, AC, and BC formed by straight lines is set as the three-vertex closed curve. The apex angle A is typically 90°, but this is not necessarily limited thereto. Side AC can be set based on the shape of the top surface of the grate 104, and side AB can be set based on the shape of the side surface of the step wall 113. Side BC may be set as a curve that rises upward or a curve that is concave downward, as shown by the dotted line in FIG. 9.

[0061] Furthermore, the volume calculation unit 412 derives the area of ​​a three-vertex closed curve ABC, such as a triangle, with vertices A, B, and C. The area S(x) of the three-vertex closed curve ABC changes along the x direction, and can therefore be expressed by the following equation (1). Area of ​​3-vertex closed curve ABC = S(x) …(1)

[0062] The volume calculation unit 412 derives the above-mentioned points A, B, and C and the area of ​​the three-vertex closed curve ABC at predetermined intervals Δx along the x direction. The predetermined interval Δx can be set to any width in the boundary image data. If the predetermined interval Δx is set to an interval equal to or less than the width of one pixel constituting the boundary image data, an interpolated image using any interpolation method, such as a bicubic filter, can be used. In addition, in the boundary image data, which is two-dimensional data, the unit length in the x direction of the front side of the grate 104 in the conveying direction (y direction) is greater than the unit length in the x direction of the intersection of the step wall 113. That is, in the boundary image data, the x-direction width is displayed so that it increases along the y direction. In this case, the predetermined interval Δx can be set to a minimum of one pixel along the x direction of the intersection of the step wall 113, or it can be set to one pixel along the x direction of the front side of the grate 104 in the conveying direction. The value of one pixel in the captured image data or boundary image data can be determined by the optical system used for capturing the image, and is, for example, approximately 1.1 cm to 10 cm.

[0063] Then, proceeding to step ST7, the volume calculation unit 412 derives a partial volume ΔV of the waste on the grate 52 as shown in FIG. 10 based on the area of ​​the three-vertex closed curve derived at predetermined intervals Δx along the x direction in step ST6. That is, the volume calculation unit 412 first sets a three-vertex closed curve, such as a right triangle, using a height z0 (point B) of the boundary line 531 corresponding to the height of the waste on the grate 52, which corresponds to the horizontal position x0 (point A), and a position y0 (point C) in front of the boundary line 531a. Meanwhile, the volume calculation unit 412 sets a three-vertex closed curve using a height z1 of the boundary line 531 corresponding to the horizontal position x1 in the x direction and a position y1 in front of the boundary line 531a. Here, these three-vertex closed curves may be similar to each other or may have different shapes.

[0064] First, if the three-vertex closed curve ABC is a triangle and the three-vertex closed curve set corresponding to the horizontal position x1 is also a triangle, the partial volume ΔV can be derived by finding the volume of the triangular pyramid truncated by the equation (2), where S(x) is the area of ​​the triangle corresponding to the horizontal position x.

number

[0065] Based on equation (2), the volume V of the waste on the grate 52 piled up on the grate 104 can be derived by summing the partial volumes ΔV along the x direction over the entire width of the step wall 113, as shown in the following equation (3). This makes it possible to approximately estimate the volume V of the waste on the grate 52 using equations (2) and (3). V = Σ (total width of the step wall 113) ΔV ... (3)

[0066] Furthermore, regardless of whether a three-vertex closed curve consisting of horizontal position x0, height z0 corresponding to horizontal position x0, and front position y0 is similar to a three-vertex closed curve consisting of horizontal position x1, height z1 corresponding to horizontal position x1, and front position y1, the partial volume ΔV can generally be derived using the following equation (4). This is true whether three-vertex closed curves set at multiple arbitrary horizontal positions x are similar to each other or not. In equation (4), S(x) is the area of ​​the three-vertex closed curve corresponding to horizontal position x.

number

[0067] Based on equation (4), the volume V of the waste on the grate 52 piled up on the grate 104 can be derived by integrating the partial volume ΔV along the x direction over the entire width of the step wall 113, as shown in the following equation (5). This makes it possible to approximate and estimate the volume V of the waste on the grate 52 using equations (4) and (5). Note that L is the length of the entire width of the step wall 113.

number

[0068] The volume calculation unit 412 stores the derived estimated value of the volume V of the waste 52 on the grate in the volume information database 422.

[0069] Furthermore, by setting a three-vertex closed curve between the height z, which is the upper part of the boundary line 531, and the front position y, which is the lower part of the boundary line, the overall shape of the waste 52 on the grate can be approximated. This makes it possible to accurately estimate the distribution shape of the waste 50 on the grate 104. Data on the distribution shape of the waste 52 on the grate is stored in the volume information database 422. Therefore, the control unit 41 reads out the derived estimated value of the volume V of the waste 52 on the grate and information on the estimated distribution shape of the waste 52 on the grate from the volume information database 422 and transmits them to the monitoring and combustion control device 30. The monitoring and combustion control device 30 can control the waste incinerator 100 with high precision based on the acquired estimated value of the volume of the waste 52 on the grate and information on the estimated distribution shape.

[0070] As a result of the above, the volume calculation unit 412 can estimate an approximate value of the volume V of the waste on the grate 52, and the management process for the waste on the grate 52 according to this embodiment is completed.

[0071] (Variation) Next, modifications of the above-described embodiment will be described. Figures 11A, 11B, 11C, and 11D are schematic diagrams showing waste on a grate as viewed in the x direction according to a first modification, a second modification, a third modification, and a fourth modification, respectively.

[0072] (First Modification) In the above-described embodiment, the three-vertex closed curve ABC of the vertical cross section of the waste on the grate 52 in the boundary image data is a right-angled triangle. In contrast to this, in the first modified example, as shown in Fig. 11A, the three-vertex closed curve ABC is an obtuse triangle in which the apex angle A at the intersection of the step wall 113 and the grate 104 has an angle θ greater than 90°. In this case as well, the estimated value of the volume V of the waste on the grate 52 can be derived as an approximate value from the area S(x) of the vertical cross section of the waste on the grate 52 corresponding to the horizontal position x of the step wall 113 by appropriately using the above-described formulas (1) to (5).

[0073] (Second Modification) 11B, in the second modification, the three-vertex closed curve ABC is a simple closed curve in which the apex angle A at the intersection of the step wall 113 and the grate 104 is 90° and the side BC is a curve that rises upward. Here, the side BC can be a curve that follows various upwardly convex functions, such as a curve that follows an nth-order function (n is an integer greater than or equal to 2) or a part of a trigonometric function. The function that the side BC follows can be selected based on the properties of the waste 50. In this case, too, the estimated volume V of the waste 52 on the grate can be approximated from the area S(x) of the vertical cross section of the waste 52 on the grate corresponding to the horizontal position x of the step wall 113 by appropriately using the above-mentioned formulas (1) to (5).

[0074] (Third Modification) 11C, in the third modified example, the three-vertex closed curve ABC is an acute triangle with an apex angle A of less than 90°, which is the intersection of the step wall 113 and the grate 104. In this case as well, the estimated value of the volume V of the waste on the grate 52 can be derived as an approximate value from the area S(x) of the vertical cross section of the waste on the grate 52 corresponding to the horizontal position x of the step wall 113, by appropriately using the above-mentioned equations (1) to (5).

[0075] (Fourth Modification) 11D, in the fourth modification, the three-vertex closed curve ABC is a three-vertex closed curve consisting of a simple closed curve in which the apex angle A at the intersection of the step wall 113 and the grate 104 is 90° and the side BC is convex downward. Here, the side BC may be a curve along various downwardly convex functions, such as an exponential function, an inverse proportional function, an nth-order function (n is an integer greater than or equal to 2), or a curve along a portion of a trigonometric function. The function along which the side BC is curved may be selected based on the properties of the waste 50. In this case, the estimated volume V of the waste 52 on the grate can be approximated from the area S(x) of the vertical cross section of the waste 52 on the grate corresponding to the horizontal position x of the step wall 113 by appropriately using the above-described formulas (1) to (5).

[0076] The first to fourth modified examples described above can be combined as appropriate. That is, the angle θ between the sides AB and AC can be applied to the second and fourth modified examples, and the curved shape of the side BC can be applied to the first and third modified examples.

[0077] According to the embodiment described above, boundary image data is generated from the image data of the waste 50 (waste 52 on the grate) on the grate 104 inside the waste incinerator 100 captured by the imaging unit 125, and after setting predetermined coordinates for the generated boundary image data, a three-vertex closed curve is set with a height z at the top of the boundary line 531 corresponding to a horizontal position x parallel to the width direction of the step wall 113 and a front position y at the bottom of the boundary line, and the volume is derived from the area S(x) of this three-vertex closed curve, thereby deriving the volume of the waste 52 on the grate. This makes it possible to easily derive the volume of the waste 52 on the grate 104 based on the thermal image data captured inside the waste incinerator 100.

[0078] (Recording medium) In the above-described embodiment, a program capable of executing the management method using the monitoring and combustion control device 30 or the waste management device 40 can be recorded on a computer-readable recording medium in a computer or other machine or device (hereinafter, referred to as a computer, etc.). By loading and executing the program from the recording medium into a computer, etc., the computer functions as the waste management device 40 or the monitoring and combustion control device 30. Here, a computer-readable recording medium refers to a non-transitory recording medium that stores information such as data or programs electrically, magnetically, optically, mechanically, or chemically and can be read by a computer, etc. Examples of such recording media that are removable from a computer, etc. include flexible disks, magneto-optical disks, CD-ROMs, CD-R / Ws, DVDs, Blu-ray Discs, DATs, magnetic tapes, and memory cards such as flash memory. Examples of recording media that are fixed to a computer, etc. include hard disks and ROMs. Furthermore, SSDs can be used as both removable and fixed recording media.

[0079] In addition, the programs executed by the monitoring and combustion control device 30 and waste management device 40 in one embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.

[0080] (Other embodiments) Furthermore, in the monitoring and combustion control device 30 and the waste management device 40 according to one embodiment, the "unit" described above can be read as a "circuit," etc. For example, the communication unit can be read as a communication circuit.

[0081] Further effects and modifications can be easily derived by those skilled in the art. The broader aspects of the present invention are not limited to the specific details and representative embodiments shown and described above. Therefore, various changes are possible without departing from the spirit or scope of the general inventive concept defined by the appended claims and their equivalents. For example, the numerical values ​​and types of information listed in the above embodiment are merely examples, and different numerical values ​​and types of information may be used as necessary. The present invention is not limited by the description and drawings that form part of the disclosure of the above embodiment of the present invention.

[0082] For example, in the above-described embodiment, deep learning using a neural network is employed as an example of machine learning, but machine learning based on other methods may also be performed. For example, other supervised learning methods such as support vector machines, decision trees, naive Bayes, and k-nearest neighbor methods may also be used. Furthermore, semi-supervised learning may also be used instead of supervised learning.

[0083] In addition, in the above-described embodiment, the present invention is applied to a waste treatment facility, but the present invention can be applied to various plants that require processing to estimate the treatment volume, such as biomass treatment facilities. [Explanation of symbols]

[0084] 1. Waste Management System 2 Network 30 Monitoring and combustion control device 31 Calculation control unit 32 Operation volume reference value adjustment section 33 Operational volume reference value correction unit 34,42 Storage part 35 Operation amount adjustment section 36,43 Communications Department 40 Waste Management Equipment 41 Control Unit 44 Input / output section 50 Waste 51 Pre-supply waste 52 Grate waste 100 Waste incinerators 101 Furnace 101a Furnace wall 102 Inlet 103 Feeding device 104 Grate 105 Ash fall hole 106 Combustion air blower 107 Furnace outlet 108 Chimney 109 Boiler 109a heat exchanger 109b Steam drum 110 Cooling air inlet 111 Cooling air blower 112 Waste Supply Department 113 Step wall 114 Combustion air damper 114a, 114b, 114c, 114d Under-grate combustion air damper 115 Cooling air damper 116 Intermediate Ceiling 117 Combustion chamber gas thermometer 118 Main flue gas thermometer 119 Gas thermometer at bottom of furnace outlet 120 Furnace outlet central gas thermometer 121 Furnace outlet gas thermometer 122 Boiler outlet oxygen concentration meter 123 Gas concentration meter 124 Exhaust gas flow meter 125 Imaging unit 126a, 126b Combustion air temperature damper 127 Recirculation Blower 128 Exhaust gas recirculation air damper 341 Setting Value Database 342 Measurement Database 351 Combustion air volume adjustment unit 352 Air volume ratio adjustment unit 353 Cooling air volume adjustment unit 354 Feeder feed speed adjustment unit 355 Grate feed speed adjustment unit 356 Combustion air temperature adjustment unit 357 Exhaust gas recirculation air flow rate adjustment unit 411 Boundary generator 412 Volume calculation unit 413 Learning Department 421 Image Database 422 Volume Information Database 423 Boundary Discrimination Learning Model 531,531a border

Claims

1. A management device including a control unit that acquires image data generated from thermal image information obtained by capturing an image of an area containing waste in a waste incinerator equipped with a fire grate for moving the waste, and performs image processing on the image data, The control unit Acquire the image data and store it in a storage unit; For the image data read from the storage unit, a boundary between an area where the waste is present on the grate and an area other than the waste is identified, a boundary line that defines at least a part of the boundary is generated, and boundary image data including the boundary line is generated; Based on the boundary image data, a predetermined cross section corresponding to a predetermined axis for the waste present on the grate is set; A closed curve is set that connects three vertices, the vertices being the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate, and the area of ​​the closed curve is calculated for a plurality of positions along the specified axis, and the volume of the waste on the grate is calculated based on the area of ​​the closed curve. Management device.

2. The control unit acquiring the image data from the storage unit as an input parameter, inputting the image data into a boundary discrimination learning model, and outputting the boundary image data as an output parameter; The boundary discrimination learning model is a learning model generated by machine learning using the image data as a learning input parameter and processed image data in which the boundary line is drawn on the image data as a learning output parameter. The management device according to claim 1 .

3. The predetermined axis is set parallel to an intersection between the grate and a step wall onto which the waste falls, the predetermined cross section is a plane perpendicular to the predetermined axis, A closed curve connecting the three vertices is set within the plane. The management device according to claim 1 .

4. A management method executed by a management device that acquires image data generated from thermal image information obtained by capturing an image of an area containing waste in a waste incinerator equipped with a fire grate for moving the waste, and performs image processing on the image data, Acquire the image data and store it in a storage unit; For the image data read from the storage unit, a boundary between an area where the waste is present on the grate and an area other than the waste is identified, a boundary line that defines at least a part of the boundary is generated, and boundary image data including the boundary line is generated; Based on the boundary image data, a predetermined cross section corresponding to a predetermined axis for the waste present on the grate is set; A closed curve is set that connects three vertices, the vertices being the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate, and the area of ​​the closed curve is calculated for a plurality of positions along the specified axis, and the volume of the waste on the grate is calculated based on the area of ​​the closed curve. Management method.

5. a control unit of a management device that includes a control unit that acquires image data generated from thermal image information obtained by capturing an image of an area containing waste in a waste incinerator equipped with a fire grate for moving the waste, and performs image processing on the image data; Acquire the image data and store it in a storage unit; For the image data read from the storage unit, a boundary between an area where the waste is present on the grate and an area other than the waste is identified, a boundary line that defines at least a part of the boundary is generated, and boundary image data including the boundary line is generated; Based on the boundary image data, a predetermined cross section corresponding to a predetermined axis for the waste present on the grate is set; A closed curve is set that connects three vertices, the vertices being the upper position of the boundary line in the specified cross section, the lower position of the boundary line, and the position where the waste is supplied to the grate, and the area of ​​the closed curve is calculated for a plurality of positions along the specified axis, and the volume of the waste on the grate is calculated based on the area of ​​the closed curve. A program that makes it happen.

Images