JP7516963B2 - Information processing device and information processing method - Google Patents

Description

The present invention relates to an information processing device and an information processing method.

Conventionally, various demands have been made in the field of waste treatment in order to realize a low-carbon society and a recycling-based society. In response to such demands, various technologies have been proposed as means for grasping the combustion state of waste in a waste incinerator that incinerates waste. Patent Document 1 describes a method for measuring the state of the waste layer through a flame using an infrared camera and controlling various devices, including a dust feeder, in a waste incinerator so that combustion is appropriate. The technology described in Patent Document 1 has the advantage of minimizing fluctuations in the temperature and gas composition of the combustion exhaust gas, suppressing the CO concentration and _NOx concentration in the exhaust gas, and suppressing fluctuations in the amount of steam generated by heat recovery from the exhaust gas.

JP 2017-116252 A

However, the technology disclosed in Patent Document 1 did not consider the details of a method for grasping the combustion state or a specific control method after appropriately grasping the combustion state. In other words, in the above-mentioned conventional technology, there was room for further improvement in the control method for appropriately controlling various devices including the dust feeder. Therefore, there was a demand for technology that can accurately grasp the combustion state of waste supplied to a waste incinerator and more appropriately control various devices in the waste incinerator.

The present invention has been made in consideration of the above, and its object is to provide an information processing device and an information processing method that can grasp the combustion state of waste in a waste incinerator and appropriately control various devices in the waste incinerator based on the grasped combustion state.

In order to solve the above-mentioned problems and achieve the object, an information processing device according to one aspect of the present invention includes a control unit having hardware, and the control unit acquires thermal image information obtained by measuring an area containing waste in a waste incinerator that incinerates the waste, stores the thermal image information in a memory unit, and based on the thermal image information read from the memory unit, distinguishes and extracts burned areas where the combustion temperature of the waste is equal to or higher than a predetermined temperature and unburned areas where the combustion temperature of the waste is lower than a predetermined temperature, derives the amount of burned waste based on the amount of burned waste in the extracted burned areas, and derives the amount of unburned waste based on the amount of unburned waste in the unburned areas.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit identifies boundaries between the burned area, the unburned area, and areas other than the burned area and the unburned area within the waste incinerator for image data generated from the thermal image information read from the memory unit, generates a boundary line that defines at least a portion of the boundary, and generates processed image data including the boundary line.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit acquires the image data from the storage unit as an input parameter, inputs the image data read from the storage unit into a combustion state learning model, and outputs the processed image data in which the boundary line is generated for the image data as an output parameter, and the combustion state learning model is a learning model generated by machine learning with the image data as a learning input parameter and the processed image data in which the boundary line is drawn for the image data as a learning output parameter.

In one aspect of the present invention, the information processing device is the above invention, in which the waste incinerator is equipped with a grate through which the waste is moved, and the boundary line is generated on the outer edge of the waste that is present on the grate in the image data.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit derives the ratio of the amount of the burned waste to the amount of the unburned waste.

In the information processing device according to one aspect of the present invention, in the above invention, the amount of burned waste is a value based on the area of the burned area or the integrated temperature value in the burned area, and the amount of unburned waste is a value based on the area of the unburned area or the integrated temperature value in the unburned area.

In the information processing device according to one aspect of the present invention, in the above invention, the control unit derives the combustion amount and the position of the combustion point based on the extracted combustion region.

A combustion control device according to one aspect of the present invention includes a combustion control unit that acquires the amount of burned waste and the amount of unburned waste obtained by an information processing device according to the above invention, which derives the amount of burned waste and the amount of unburned waste from thermal image information obtained by measuring an area containing waste in a waste incinerator that incinerates the waste, stores the acquired amount of burned waste and the amount of unburned waste in a memory unit, and controls the waste incinerator based on the amount of burned waste and the amount of unburned waste.

In one aspect of the present invention, the combustion control device is the above invention, in which the waste incinerator is provided with a grate for moving the waste and a waste supply means for supplying the waste onto the grate, and the combustion control unit controls at least one of the feed rate at which the waste is supplied by the waste supply means and the grate speed of the grate based on the amount of the burned waste and the amount of the unburned waste.

In one aspect of the present invention, the combustion control device is configured such that, in the above invention, the combustion control unit controls at least one of the air flow rate and the air temperature based on the amount of burned waste and the amount of unburned waste.

In the combustion control device according to one aspect of the present invention, in the above invention, the combustion control unit reads the time-dependent changes in the amount of the unburned waste and the amount of the burned waste from the memory unit, obtains the time-dependent changes in the ratio of the amount of the burned waste to the amount of the unburned waste, and controls the waste incinerator based on the time-dependent changes in the ratio.

An information processing method according to one aspect of the present invention is an information processing method executed by an information processing device having a control unit with hardware, in which the control unit acquires thermal image information obtained by measuring an area containing waste in an incinerator that incinerates the waste, stores the thermal image information in a memory unit, and based on the thermal image information read from the memory unit, distinguishes and extracts burned areas where the combustion temperature of the waste is equal to or higher than a predetermined temperature and unburned areas where the combustion temperature of the waste is lower than a predetermined temperature, derives the amount of burned waste based on the amount of burned waste in the extracted burned areas, and derives the amount of unburned waste based on the amount of burned waste in the extracted unburned areas.

A combustion control method according to one aspect of the present invention is a combustion control method executed by a combustion control device having a combustion control unit that controls a waste incinerator that incinerates waste, in which the combustion control unit acquires the amount of burned waste and the amount of unburned waste derived by the information processing method of the above invention, which derives the amount of burned waste and the amount of unburned waste from thermal image information obtained by measuring an area containing the waste in the waste incinerator that incinerates the waste, stores the acquired amount of burned waste and the amount of unburned waste in a memory unit, and controls the waste incinerator based on the amount of burned waste and the amount of unburned waste.

According to the information processing device and information processing method of the present invention, the combustion state of waste in a waste incinerator can be grasped, and various devices in the waste incinerator can be appropriately controlled based on the grasped combustion state.

FIG. 1 is an overall configuration diagram showing a waste incineration facility to which an information processing device according to an embodiment of the present invention is applied. FIG. 2 is a side view showing waste, a portion of the waste being fed onto a grate, and an imaging section in an incinerator according to an embodiment of the present invention. FIG. 3 is a front view showing the field of view of the imaging unit in the incinerator according to one embodiment of the present invention. FIG. 4 is a block diagram showing the configuration of a combustion control device and a combustion determination device according to an embodiment of the present invention. FIG. 5 is a diagram showing an example of transmission image data of waste being burned, captured by the imaging section according to an embodiment of the present invention. FIG. 6 is a diagram showing an example of boundary image data in which a boundary line is generated for transmission image data captured by the imaging section according to an embodiment of the present invention. FIG. 7 is a diagram showing an example of distinguished image data in which a boundary line is generated by extracting a burned portion from the boundary image data according to an embodiment of the present invention. FIG. 8 is a flowchart for explaining the information processing method and the combustion control method according to one embodiment of the present invention. FIG. 9 is a diagram showing a schematic side view of a fire grate and waste in an incinerator for explaining an information processing method and a combustion control method according to an embodiment of the present invention. FIG. 10 is a diagram showing a modified example of distinguished image data in which a boundary line is generated by extracting a burned portion from the boundary image data according to an embodiment of the present invention.

One embodiment of the present invention will be described below with reference to the drawings. Note that in all the drawings of the embodiment below, the same or corresponding parts are given the same reference numerals. Furthermore, the present invention is not limited to the embodiment described below.

First, according to the knowledge of the present inventor, in order to properly control a waste incinerator, such as a grate (stoker) type waste incinerator (hereinafter, grate incinerator), it is important to grasp the combustion state of the waste. Specifically, it is useful to distinguish between waste in the stage of drying immediately after being fed into the incinerator (hereinafter, unburned waste) and waste in the stage of solid combustion due to a thermal decomposition reaction (hereinafter, burned waste). The present inventor has devised a method for predicting the behavior of waste combustion based on the time change in the amount of unburned waste and the amount of burned waste, preferably based on the time change in the ratio of the amount of unburned waste to the amount of burned waste, by distinguishing between unburned waste and burned waste. If the behavior of waste combustion can be predicted, various devices in the waste incinerator can be properly controlled and combustion fluctuations can be suppressed.

That is, the inventor came up with the idea of extracting relatively high temperature areas as burned waste areas and relatively low temperature areas as unburned waste areas based on image data captured by a thermal imaging camera or the like that transmits specific wavelengths while transmitting the flame (hereinafter, transmitted image data). This makes it possible to distinguish between burned waste and unburned waste, and the inventor came up with a method that contributes to stable combustion by controlling these ratios as indicators. The embodiment described below was devised based on the inventor's diligent investigations.

(Grate incinerator)
Fig. 1 shows a grate incinerator to which an information processing device according to an embodiment of the present invention is applied. As shown in Fig. 1, the grate incinerator as a waste incinerator includes a furnace 1 in which waste is burned, a waste inlet 2 for inputting the waste, and a boiler 9. The boiler 9 as a steam generating section includes a heat exchanger 9a and a steam drum 9b installed downstream of the furnace outlet 7 of the furnace 1.

Waste fed through the waste inlet 2 is transported to the grate 4 by a waste feeder 3, which serves as a waste feed means. The grate 4 moves back and forth to agitate and move the waste. The waste on the grate 4 is burned while being dried by the blowing of combustion air supplied by a combustion air blower 6 into the wind box below the grate 4, producing exhaust gas and ash. The produced ash falls through the ash drop port 5 and is discharged outside the furnace 1.

The total amount of combustion air supplied from under the grate 4 to the inside of the furnace 1 is adjusted by the combustion air damper 14 installed immediately adjacent to the combustion air blower 6 as a forced draft fan. The flow rate of the combustion air supplied to each wind box is adjusted by the under-grate combustion air dampers 14a, 14b, 14c, and 14d installed in the piping that supplies combustion air to each wind box. In other words, the ratio of the flow rate of the combustion air supplied to each wind box is adjusted by the under-grate combustion air dampers 14a to 14d. In FIG. 1, the area under the grate 4 is divided into four wind boxes along the waste transport direction, and combustion air is supplied through each wind box, but the number of under-grate combustion air dampers 14a to 14d and wind boxes is not necessarily limited to four and can be changed as appropriate depending on the size and purpose of the grate incinerator.

Secondary air is blown into the furnace 1 from the secondary air inlet 10 provided in the furnace wall 1a by a secondary air blower 11 acting as a secondary blower. By blowing the secondary air into the furnace 1, unburned components in the combustion gas are further burned and an excessive rise in the temperature of the furnace wall 1a is suppressed. The flow rate of the secondary air supplied into the furnace 1 from the secondary air inlet 10 is adjusted by a secondary air damper 15 provided immediately adjacent to the secondary air blower 11.

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

In the furnace 1, an intermediate ceiling 16 is provided at an upper position along the height direction of the furnace 1. The intermediate ceiling 16 allows the gas flowing in the furnace 1 to be separated and discharged into gas containing a large amount of combustible gas generated in the waste drying process and main combustion process on the upstream side, and combustion exhaust gas generated in the post-combustion process on the downstream side. Specifically, the combustion exhaust gas flows through the flue (main flue) below the intermediate ceiling 16, while the gas containing a large amount of combustible gas flows through the flue (secondary flue) above the intermediate ceiling 16. The combustion exhaust gas and the gas containing a large amount of combustible gas join together in the gas mixing section, which further promotes the stirring and mixing of the gas in the gas mixing section. This makes the combustion in the secondary combustion section more stable, suppresses the generation of dioxins in the combustion process, and suppresses the generation of unburned waste. Note that the intermediate ceiling 16 may not be provided in the furnace 1.

At multiple positions in the furnace 1, thermometers are provided as sensors for measuring the gas temperature in the furnace 1. Specifically, a combustion chamber gas thermometer 17 is provided at the midpoint between the fire grate 4 and the secondary air inlet 10 along the height direction of the furnace 1. A main flue gas thermometer 18 is provided below the furnace outlet 7 along the height direction of the furnace 1. A furnace outlet lower gas thermometer 19 is provided at the lower position of the furnace outlet 7 along the height direction of the furnace 1. A furnace outlet middle gas thermometer 20 is provided at the middle position of the furnace outlet 7 along the height direction of the furnace 1. A furnace outlet gas thermometer 21 for measuring the combustion management temperature is provided downstream of the furnace outlet 7 along the height direction of the furnace 1. The temperature measurement values measured by the combustion chamber gas thermometer 17, the main flue gas thermometer 18, the furnace outlet lower gas thermometer 19, the furnace outlet middle gas thermometer 20, and the furnace outlet gas thermometer 21 are transmitted to the combustion control device 30 as combustion process measurement values and stored in the memory unit 32 (see FIG. 4).

The boiler 9 is provided with a boiler outlet oxygen concentration meter 22 for measuring the concentration of oxygen (O ₂ ) in the exhaust gas on the outlet side. The chimney 8 is provided with a gas concentration meter 23 for measuring the concentration of carbon monoxide (CO) and nitrogen oxides (NO _x ) in the exhaust gas on the inlet side. The pipe connecting the outlet of the boiler 9 to the chimney 8 is provided with an exhaust gas flow meter 24 for measuring the amount of exhaust gas. The gas concentration and flow rate measured by the boiler outlet oxygen concentration meter 22, the gas concentration meter 23, and the exhaust gas flow meter 24 are transmitted to the combustion control device 30 as combustion process measurement values and stored in the memory unit 32. The boiler 9 is also provided with a steam flow meter 25 for measuring the amount of steam generated in the boiler 9. The steam generation amount of the boiler 9 measured by the steam flow meter 25 is transmitted to the combustion control device 30 as combustion process measurement values and stored in the memory unit 32.

An imaging unit 26 is provided downstream in the waste transport direction in the furnace 1. The imaging unit 26 is configured to have a flame-transmitting camera, for example an infrared camera, and an image processing unit that processes the captured image data. FIG. 2 is a side view showing the installation state of the imaging unit 26. The imaging unit 26 may be disposed outside the furnace near a monitoring window provided in the furnace wall 1a, or may have a water-cooled structure and be disposed inside the furnace 1. As shown in FIG. 2, the waste 50 falls from the waste supply unit 12 onto the grate 4 at the step wall 13. The waste 50 that has fallen onto the grate 4 is stirred by the reciprocating motion accompanying the back and forth movement of the grate 4, and is moved forward toward the imaging unit 26.

The imaging unit 26 can obtain thermographic information of the waste 50 on the grate 4 (hereinafter, waste on the grate 52) as thermal image information. Here, the wavelength of the infrared rays emitted from the waste 50 is different from the wavelength of the infrared rays emitted from the high-temperature gas and flame in the space. Therefore, in the imaging unit 26, by appropriately selecting the infrared wavelength to be measured, it is possible to obtain thermal image information corresponding to the temperature distribution of the layer of waste on the grate 52 even if a flame is present within the measurement field of view. In addition, by setting the measurement range in the furnace length direction by the imaging unit 26, it is possible to obtain thermal image information of the layer of waste on the grate 52 at a position upstream of the combustion area (upstream of the flame). The thermal image information can be treated as video data in a state where the flame is transmitted, that is, as multiple image data.

In other words, the imaging unit 26 can capture images of the waste 50 (hereinafter, waste before supply 51) sent out from the waste supply unit 12, the step wall 13 having a step onto which the waste 50 falls, the waste on the grate 52, and the upper surface of the grate 4 in a state where the flame is transmitted through the image. A combustion image capturing unit that captures the combustion state of the waste on the grate 52, i.e., the flame itself, may be further provided. The image data captured by the imaging unit 26 in a state where the flame is transmitted through the image (hereinafter, transmitted image data) is transmitted to the combustion determination device 40 immediately or at a predetermined time interval. The transmitted image data captured by the imaging unit 26 may be stored in the memory unit 32 of the combustion control device 30 and then transmitted from the combustion control device 30 to the combustion determination device 40.

In this embodiment, the imaging unit 26 is installed, for example, in a position that is approximately directly opposite the waste supply unit 12 and the step wall 13. Note that the installation of the imaging unit 26 is not limited to a position that is approximately directly opposite the waste supply unit 12 and the step wall 13. The installation position of the imaging unit 26 can be various positions as long as it is possible to capture an image of at least the boundary portion between the waste on the grate 52 and other objects, in this case the step wall 13 and the grate 4.

Figure 3 is a front view showing an example of the field of view of the imaging unit 26. As shown in Figure 3, the imaging unit 26 has a measurement field of view that extends, for example, in the vertical direction and the furnace width direction (left and right direction) of the furnace 1. In this embodiment, the field of view of the imaging unit 26 is the waste supply unit 12, the step wall 13, the grate 4, and the furnace wall 1a. The furnace wall 1a included in the field of view of the imaging unit 26 restricts the outward movement, i.e., the spread, of the waste 50 in the left and right direction. Note that the field of view of the imaging unit 26 only needs to have a field of view that can capture the boundary portion between the waste 52 on the grate 4 and the grate 4 and the step wall 13. In addition, it is preferable that the imaging unit 26 can capture the waste 50 transported to the waste supply unit 12. This allows the waste 50 falling at the position of the step wall 13 to be captured.

Figure 4 is a block diagram showing the configuration of the combustion control device 30 and the combustion judgment device 40. The combustion control device 30 and the combustion judgment device 40 are connected via a network (not shown) consisting of one or more combinations of a dedicated line, a public communication network such as the Internet, for example, a LAN (Local Area Network), a WAN (Wide Area Network), a telephone communication network such as a mobile phone, a public line, a VPN (Virtual Private Network), etc. Also, the combustion control device 30 and the combustion judgment device 40 may be configured as an integrated unit, and the combustion control device 30 and the combustion judgment device 40 may be installed in the same facility as the grate incinerator or in a different facility. When the grate incinerator, the combustion control device 30, and the combustion judgment device 40 are installed in different facilities, various information and various data are communicated via the above-mentioned network.

As shown in FIG. 4, the combustion control device 30 includes a control unit 31, a memory unit 32, and an operation amount adjustment unit 33. Specifically, the control unit 31 as the combustion control unit and the operation amount adjustment unit 33 include a processor such as a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and an FPGA (Field-Programmable Gate Array) having hardware, and a main memory unit such as a RAM (Random Access Memory) or a ROM (Read Only Memory) (none of which are shown). The memory unit 32 is composed of a storage medium selected from a volatile memory such as a RAM, a non-volatile memory such as a ROM, an EPROM (Erasable Programmable ROM), a hard disk drive (HDD, Hard Disk Drive), and a removable medium. The removable medium is, for example, a USB (Universal Serial Bus) memory, or a disk recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a BD (Blu-ray (registered trademark) Disc). The memory unit 32 may also be configured using a computer-readable recording medium such as an externally attachable memory card.

The memory unit 32 can store an operating system (OS), various programs, various tables, various databases, and the like for executing the operation of the combustion control device 30. Here, the various programs also include information processing programs that realize 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 hard disks, flash memories, CD-ROMs, DVD-ROMs, and flexible disks, and widely distributed.

The combustion control device 30 controls the waste feeder feed rate (also called the dust feed rate) for adjusting the waste feed rate of the waste 50 and the grate feed rate (also called the grate speed) for adjusting the movement rate of the waste 50 as the manipulated variables of each manipulated variable based on a predetermined manipulated variable reference value setting relational expression (hereinafter referred to as the manipulated variable relational expression). The combustion control device 30 also controls the stop and operation of the waste feeder feed rate and the grate feed rate. The combustion control device 30 controls the amount of combustion air and the amount of secondary air as necessary based on the manipulated variable relational expression. The manipulated variable relational expression is, for example, a relational expression between the waste incineration amount set value or the waste material set value and the manipulated variable reference value (target value of the manipulated variable), and includes a control parameter as a correction coefficient. The control parameter is adjusted by the control unit 31 to match the waste incineration amount set value and the waste material set value. When at least one of the waste incineration amount set value and the waste material set value is changed, the adjusted control parameter is changed by the control unit 31 in response to the changed set value. By changing the control parameters, the preset reference values for the manipulated variables are corrected.

The control unit 31 calculates the waste quality (lower heating value of the waste) according to the waste incineration amount set value. The control unit 31 adjusts the operation amount reference value by adjusting the control parameters included in the operation amount relational expression. The control unit 31 corrects the adjusted operation amount reference value based on a predetermined control algorithm such as PID control or fuzzy calculation. The memory unit 32 stores data referenced by the control unit 31. The memory unit 32 stores a predetermined operation amount relational expression, a control algorithm, a predetermined incineration amount set value, and combustion process measurement values acquired as combustion state quantities in the furnace 1.

The operation amount adjustment unit 33 adjusts the operation amount of each operation terminal so that it follows the operation amount reference value. Specifically, the operation amount adjustment unit 33 has a combustion air amount adjustment unit 331, an air amount ratio adjustment unit 332, a secondary air amount adjustment unit 333, a waste supply device feed rate adjustment unit 334, and a grate feed rate adjustment unit 335.

The combustion air amount adjustment unit 331 adjusts the amount of operation so that the amount of combustion air follows the operation amount reference value corrected by the control unit 31 (hereinafter, the corrected operation amount reference value). The air amount ratio adjustment unit 332 controls each of the under-grate combustion air dampers 14a to 14d to adjust the relative ratio of the flow rates in each wind box. The secondary air amount adjustment unit 333 adjusts the amount of operation so that the amount of secondary air follows the corrected operation amount reference value. Here, the combustion air amount and secondary air amount are adjusted by controlling the opening degree of each of the combustion air damper 14, the under-grate combustion air dampers 14a to 14d, and the secondary air damper 15.

The waste feeder feed speed adjustment unit 334 adjusts the operation amount so that the waste feeder feed speed follows the corrected operation amount reference value. The grate feed speed adjustment unit 335 adjusts the operation amount so that the grate feed speed follows the corrected operation amount reference value. When the operation amount reference value is not corrected by the control unit 31, the operation amount adjustment unit 33 adjusts each operation amount based on the uncorrected operation amount reference value.

(Combustion determination device)
The combustion determination device 40 as an information processing device includes a control unit 41, an output unit 42, an input unit 43, and a storage unit 44. The combustion determination device 40 functions as a boundary image data generating device that generates processed image data (hereinafter, boundary image data) by identifying boundaries in the transmission image data and drawing the boundary lines. The combustion determination device 40 also functions as a waste amount measuring device that measures the amount of waste by dividing the waste on the grate 52 into burned waste 52A and unburned waste 52B.

The control unit 41 has the same functional and physical configuration as the control unit 31 described above, and includes a processor such as a CPU, DSP, or FPGA having hardware, and a main memory unit such as a RAM or ROM (none of which are shown). The output unit 42, which serves as an output means, is configured to be able to notify the outside of predetermined information.

The output unit 42, under the control of the control unit 41, displays images of the waste 50 in the furnace 1 on the display monitor, displays characters and figures on the screen of the touch panel display, and outputs sound from the speaker. The input unit 43, which serves as an input means, is configured using a user interface such as a keyboard, input buttons, levers, a touch panel 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 unit 43. The output unit 42 and the input unit 43 may be integrated into an input/output unit, and the input/output unit may be configured from a touch panel display, a speaker microphone, or the like.

The memory unit 44 has the same functional and physical configuration as the memory unit 32 described above, and is composed of a storage medium selected from a volatile memory such as a RAM, a non-volatile memory such as a ROM, an EPROM, a HDD, and a removable medium. Note that the removable medium is, for example, a USB memory or a disk recording medium such as a CD, DVD, or BD. The memory unit 44 may also be composed of a computer-readable recording medium such as an externally attachable memory card.

The memory unit 44 can store an OS, various programs, various tables, various databases, and the like for executing the operation of the combustion determination device 40. Here, the various programs include an information processing program that realizes control using the learning model or the learned model according to this embodiment. The memory unit 44 may be provided in another server that can communicate via various networks, or may be provided in the combustion control device 30. Specifically, the memory unit 44 stores a boundary discrimination learning model 44a, a combustion state learning model 44b, and a waste amount information database 44c.

The boundary discrimination learning model 44a and the combustion state learning model 44b are each an updatable model including at least one learning model. If the learning model is not updated, it is stored in the storage unit 44 as a learned model. The boundary discrimination learning model 44a and the combustion state learning model 44b may be constructed as one learning model, for example, a combustion boundary discrimination learning model. In addition, instead of the boundary discrimination learning model 44a or the combustion state learning model 44b, a rule-based information processing program that performs a predetermined information processing on input data and is created without learning or the like may be used. Furthermore, an automatic judgment processing program that realizes judgment processing using a combustion image learning model that can perform a predetermined judgment from the data of the combustion image of the flame itself captured by the combustion image capturing unit may be included. These various programs can also be recorded on computer-readable recording media such as hard disks, flash memories, CD-ROMs, DVD-ROMs, and flexible disks and widely distributed.

The waste amount information database 44c stores the change over time of the amount of burned waste 52A present in the burned area A31 (described later), the change over time of the amount of unburned waste 52B present in the unburned area A32, and the change over time of the waste amount ratio α, which is the ratio of the amount of burned waste 52A to the amount of unburned waste 52B, in association with time. The waste amount information database 44c also stores at least one of area information and temperature integrated value information for each of the burned area A31 and unburned area A32 (described later) as waste amount information.

The control unit 41 can realize a function that meets a predetermined purpose by loading a program stored in the memory unit 44 into the working area of the main memory unit and executing the program, and controlling each component through the execution of the program. In this embodiment, the control unit 41 executes the functions of the boundary generation unit 411, the combustion judgment unit 412, and the learning unit 413 by executing the program stored in the memory unit 44. Specifically, for example, the control unit 41 executes the function of the boundary generation unit 411 by reading the boundary discrimination learning model 44a, which is a program, from the memory unit 44. In addition, the control unit 41 executes the function of the combustion judgment unit 412 by reading the combustion state learning model 44b, which is a program, from the memory unit 44. Details of the functions of the boundary generation unit 411, the combustion judgment unit 412, and the learning unit 413 will be described later.

(Boundary discrimination learning model)
Here, the boundary discrimination learning model 44a stored in the storage unit 44 and a method for generating the same will be described. Fig. 5 is a diagram showing an example of transmission image data of waste being burned, captured by the imaging unit 26 of this embodiment. Fig. 6 is a diagram showing an example of boundary image data in which a boundary line is generated for the transmission image data captured by the imaging unit 26 of this embodiment.

As shown in FIG. 5, the imaging unit 26 images the waste supply unit 12, the waste before being supplied onto the grate 4, the step wall 13, the grate 4, the waste on the grate 4, and the furnace wall 1a in the furnace 1 while transmitting the flame (also called luminous flame), and outputs the image data as transmission image data. As shown in FIG. 6, the boundary discrimination learning model 44a executes a process for generating a boundary line 53 between the waste 50 and other objects for the transmission image data captured by the imaging unit 26. In the example shown in FIG. 6, a boundary line 531 is drawn on the boundary between the waste 50 and the waste supply unit 12, the step wall 13, and the furnace wall 1a, and a boundary line 532 is drawn on the boundary between the waste 50 and the step wall 13, the furnace wall 1a, and the grate 4. By drawing the boundary line 53, the boundary image data can be divided into, for example, four regions A1, A2, A3, and A4.

The data used to generate the boundary discrimination learning model 44a are the transmission image data and the boundary image data captured by the imaging unit 26. The number of the transmission image data and the boundary image data is preferably, for example, 100 or more. That is, the boundary image data used for generation is image data in which the worker draws a boundary line 53 for each boundary between the waste 50 and the waste supply unit 12, the step wall 13, the furnace wall 1a, and the grate 4 on the transmission image data. As input/output data sets when generating the boundary discrimination learning model 44a, the transmission image data is used as a learning input parameter, and the boundary image data is used as a learning output parameter. The learning unit 413 of the control unit 41 generates the boundary discrimination learning model 44a by machine learning such as deep learning using a neural network, using the above-mentioned learning input parameters and learning output parameters as teacher data. The control unit 41 generates the boundary discrimination learning model 44a from the transmission image data based on the contents learned by the learning unit 413. In addition, the learning unit 413 appropriately updates the boundary identification learning model 44a using the inputted transparent image data and boundary image data obtained by the worker correcting or drawing the boundary.

(Combustion state learning model)
Next, the combustion state learning model 44b stored in the storage unit 44 and a method for generating the same will be described. FIG. 7 is a diagram showing an example of processed image data (hereinafter, distinguished image data) in which the area of the burned waste 52A (burned area A31) and the area of the unburned waste 52B (unburned area A32) of the waste on the grate 52 are distinguished from the boundary image data created by the boundary generation unit 411 according to this embodiment. The imaging unit 26 transmits the transmission image data shown in FIG. 5 to the control unit 41. The boundary generation unit 411 of the control unit 41 generates the boundary image data shown in FIG. 6 from the input transmission image data based on the boundary discrimination learning model 44a. The combustion state learning model 44b is a learning model capable of executing a process of extracting the burned area A31 as the burned waste area and the unburned area A32 as the unburned waste area from the boundary image data based on the image data of the inside of the furnace 1, such as the transmission image data and the boundary image data, as shown in FIG. 7.

The learning input parameters used to generate the combustion state learning model 44b are at least one of the transmission image data captured by the imaging unit 26 and the boundary image data generated by the boundary generation unit 411 based on the boundary discrimination learning model 44a. The learning output parameters used to generate the combustion state learning model 44b are discrimination image data in which the boundary between the waste on the grate 52 and other areas, and the boundary between the burned area A31, which is the area of the waste on the grate 52 whose combustion temperature is equal to or higher than a predetermined temperature, and the unburned area A32, which is the area of the waste on the grate 52 whose combustion temperature is lower than the predetermined temperature, are drawn on the transmission image data or the boundary image data by an operator.

In the example shown in FIG. 7, the burned area A31 of the waste on the grate 52 where the combustion temperature is equal to or higher than a predetermined temperature, for example, 1000K or higher, is drawn in white, and the unburned area A32 where the temperature is lower than the predetermined temperature, for example, lower than 1000K, is drawn in dots. In the waste on the grate 52 shown in FIG. 7, a boundary line 532a is drawn on the boundary between the burned area A31 where the combustion temperature is equal to or higher than a predetermined temperature and other areas, i.e., on the outer edge of the burned area A31. In addition, in the waste on the grate 52, a boundary line 532b is drawn on the boundary between the unburned area A32 where the combustion temperature is lower than a predetermined temperature and other areas, i.e., on the outer edge of the unburned area A32. The imaging unit 26 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 the brightness is increased as the temperature increases and the brightness is decreased as the temperature decreases, for example. This allows the waste on the grate 52 to be extracted from the transmission image data, and in the extracted waste on the grate 52, high temperature areas that are equal to or higher than a predetermined temperature can be extracted as the burnt area A31, and areas that are lower than the predetermined temperature can be extracted as the unburnt area A32. In this way, image data that extracts the burnt area A31 and the unburnt area A32 of the waste on the grate 52 from the transmission image data in which the temperature distribution can be grasped by brightness can be used as distinguished image data.

The number of the transparent image data, the boundary image data, and the distinction image data used for learning is preferably, for example, 100 or more. As the input/output data set when generating the combustion state learning model 44b, the transparent image data or the boundary image data is used as the learning input parameter, and the distinction image data is used as the learning output parameter. The learning unit 413 of the control unit 41 generates the combustion state learning model 44b by machine learning such as deep learning using a neural network, using the above-mentioned learning input parameters and learning output parameters as teacher data. The control unit 41 generates the distinction image data from the transparent image data or the boundary image data based on the contents learned by the learning unit 413. In addition, the learning unit 413 appropriately updates the combustion state learning model 44b using the input transparent image data or the boundary image data, and the distinction image data obtained by the operator correcting or drawing the boundary.

The image data includes transmission image data captured by the imaging unit 26, boundary image data in which a boundary line 53 is drawn on the transmission image data, and distinction image data in which waste on the grate 52 and burned area A31 are extracted from the transmission image data or the boundary image data. When using transmission image data as the image data, the transmission image data captured by the imaging unit 26 is used. When using boundary image data as the image data, it is possible to use boundary image data generated by the boundary discrimination learning model 44a, boundary image data generated or modified by an operator, etc. Similarly, when using distinction image data as the image data, it is possible to use distinction image data generated by the combustion state learning model 44b, distinction image data generated or modified by an operator, etc.

At least the following information can be obtained from the differentiated image data:
The area of the waste 52 on the grate (in FIG. 7, the area S of the waste 50 in the areas A31 and A32)
Area of the burnt area A31 (area S ₁ of the burnt area A31 in FIG. 7 )
Maximum temperature, average temperature, and integrated temperature value of the burnt area A31 Area of the unburnt area A32 (area _S2 of the unburnt area A32 in FIG. 7)
Minimum temperature, average temperature, and accumulated temperature value of unburned region A32 The accumulated temperature value is a value obtained by accumulating the temperatures of each predetermined region, such as a pixel, in the burned region A31 and the unburned region A32 of the image data.

The following information can be further obtained from the classification image data:
Height of the waste on the grate 52 (local height of the layer of waste on the grate 52 in Figs. 6 and 7, average height of the layer of waste on the grate)
Position of the combustion point of the waste 52 on the grate (end of the burned area A31 on the side of the imaging unit 26) (line F in Figures 6 and 7)

The above-mentioned combustion state learning model 44b may further include a learning model capable of executing processes such as deriving the height of the layer (waste layer) of the waste 52 on the grate, measuring the position of the combustion point, and deriving the amount of waste. In this case, as input/output data sets for generating the combustion state learning model 44b, transmission image data or boundary image data is used as the learning input parameters, and as learning output parameters, distinction image data, data on the waste layer height, data on the position of the combustion point, and data on the amount of combustion (e.g., temperature accumulation value, area, average temperature, etc.) of the burned area A31 and the unburned area A32 are used. The number of input/output data sets is preferably, for example, 100 or more. The learning unit 413 of the control unit 41 generates the combustion state learning model 44b by machine learning such as deep learning using a neural network, using the above-mentioned learning input parameters and learning output parameters as teacher data. The control unit 41 can generate distinction image data from the transmission image data and boundary image data based on the contents learned by the learning unit 413, and derive the waste layer height, the position F of the combustion point, the combustion amount, and the waste amount. A learning model that derives the waste layer height, the position F of the combustion point, the combustion amount, and the waste amount from the distinction image data may be generated separately. The learning unit 413 may appropriately update the combustion state learning model 44b using distinction image data corrected by the operator or derived values of the waste layer height, the position F of the combustion point, the combustion amount, and the waste amount measured from the image data by a rule-based combustion state derivation program.

(Information processing method and combustion control method)
Next, an information processing method and a combustion control method according to an embodiment of the present invention will be described. Fig. 8 is a flow chart for explaining the information processing method and the combustion control method according to this embodiment. In this embodiment, step ST1 is a process performed by the imaging unit 26 in the furnace 1, steps ST2, ST3, and ST6 to ST9 are a process performed by the combustion determination device 40, steps ST4 and ST5 are a process performed by an operator, and step ST10 is a process performed by the combustion control device 30.

As shown in FIG. 8, in step ST1, the imaging unit 26 images the inside of the furnace 1. The imaging unit 26 images the situation inside the furnace 1 within the field of view as an image through the flame. Specifically, as shown in FIG. 5, the imaging unit 26 images the pre-supply waste 51, the step wall 13, the waste on the grate 52, the grate 4, and the furnace wall 1a in the waste supply unit 12 as a state in which the flame is transmitted. Note that it is not necessary to image the pre-supply waste 51 and the furnace wall 1a. The imaging unit 26 transmits the captured transmission image data to the control unit 41 through the input unit 43 of the combustion determination device 40. The control unit 41 stores the received transmission image data in the memory unit 44.

Next, proceeding to step ST2 shown in FIG. 8, the boundary generation unit 411 of the combustion determination device 40 reads the boundary discrimination learning model 44a, reads out the transmission image data (see FIG. 5) acquired from the imaging unit 26 from the memory unit 44, and discriminates the boundaries between the waste 50 and the waste supply unit 12, the step wall 13, the furnace wall 1a, and the grate 4 from the read transmission image data. Note that the boundary generation unit 411 may use a rule-based image discrimination algorithm to discriminate between the waste 50, the waste supply unit 12, the step wall 13, the furnace wall 1a, and the grate 4, and discriminate the boundaries between them.

The combustion determination unit 412 of the control unit 41 reads the combustion state learning model 44b, identifies the waste on the grate 52 from other areas, identifies the burned area A31 with a temperature above a predetermined temperature and the unburned area A32 below the predetermined temperature in the identified waste on the grate 52, and determines the boundary between them. The combustion determination unit 412 may also use a rule-based image recognition algorithm to identify the waste on the grate 52 from other areas, identifies the burned area A31 with a temperature above a predetermined temperature and the unburned area A32 below the predetermined temperature in the identified waste on the grate 52, and determines the boundary between them.

Next, proceeding to step ST3, the boundary generation unit 411 draws boundary lines 53 for the boundaries between the waste 50 and other objects, i.e., the boundaries between the waste 50 and the waste supply unit 12, the step wall 13, the furnace wall 1a, and the grate 4, on the transparent image data. As shown in FIG. 6, the boundary generation unit 411 draws boundary lines 531 and 532 for the boundaries between the waste before supply 51 and the waste supply unit 12, the furnace wall 1a, and the step wall 13, and the boundaries between the waste on the grate 52 and the step wall 13, the grate 4, and the furnace wall 1a, on the transparent image data, respectively. In other words, the boundary generation unit 411 draws the boundary line 531 so as to surround the outer edge of the waste before supply 51. The boundary generation unit 411 also draws the boundary line 532 so as to surround the outer edge of the waste on the grate 52. As a result, the boundary generation unit 411 generates boundary image data in which the boundary line 53 is drawn on the transparent image data. The boundary generation unit 411 outputs the generated boundary image data to the combustion determination unit 412.

In step ST3, the combustion judgment unit 412 distinguishes between the burnt area A31 having a temperature equal to or higher than a predetermined temperature and the unburnt area A32 having a temperature lower than a predetermined temperature in the identified waste on the grate 52, and draws the boundaries 532a and 532b on the boundary image data input from the boundary generation unit 411. In other words, the combustion judgment unit 412 draws the boundary line 532a on the boundary image data so as to surround the outer edge of the burnt area A31, and draws the boundary line 532b on the boundary image data so as to surround the outer edge of the unburnt area A32 in the waste on the grate 52. As a result, the combustion judgment unit 412 generates distinguished image data in which the boundaries 532a and 532b are drawn on the boundary image data. The combustion judgment unit 412 may generate distinguished image data in which the boundaries 532a and 532b are drawn on the transparent image data for which the boundary generation process by the boundary generation unit 411 has not been performed. In this case, the boundary image data generation process by the boundary generation unit 411 may not be performed. In addition, the boundary image data may be generated by generating a boundary line 532 (532a, 532b) that divides the burned area A31 and the unburned area A32 of the waste on the grate 52 in the area A3 where the waste on the grate 52 exists. In other words, the distinguishing image data may be image data that can extract the area where the waste on the grate 52 exists and can distinguish the burned area A31 of the waste on the grate 52 that is at a temperature above a predetermined temperature from the burned area A31 of the waste on the grate 52 that is below the predetermined temperature. In addition, the combustion determination unit 412 may output the result of identifying the area of the waste on the grate 52 that is at a temperature above a predetermined temperature as the burned area A31 and the area below the predetermined temperature as the unburned area A32 in the boundary image data to the boundary generation unit 411, and the boundary generation unit 411 may draw the boundary lines 532a, 532b.

Next, the process proceeds to step ST4 shown in FIG. 8, where the operator of the combustion determination device 40 checks the distinction image data output to the output unit 42. The operator determines whether or not the boundary lines 532a, 532b drawn on the checked distinction image data are accurate. If the operator determines that the boundary lines 532a, 532b are not accurate (step ST4: No), the learning unit 413 sets a flag indicating that learning is required and proceeds to step ST5. On the other hand, if the operator determines in step ST4 that the boundary line 53 is accurate (step ST4: Yes), the process proceeds to step ST7. The processing of step ST7 will be described later.

In step ST5, the worker uses the input unit 43 to correct the boundary lines 532a and 532b drawn on the distinction image data generated by the combustion judgment unit 412. This creates the corrected distinction image data. Note that the method of correcting the corrected distinction image data is not limited to the worker using the input unit 43, and the worker may correct the boundary lines 532a and 532b on a printed matter on which the distinction image data is printed, and then use a scanner or the like as the input unit 43 to read and input the corrected printout into the combustion judgment device 40.

Then, the process proceeds to step ST6, where the learning unit 413 of the combustion determination device 40 learns to identify the boundary and updates the combustion state learning model 44b. That is, the learning unit 413 updates the combustion state learning model 44b using an input/output data set in which the transmission image data acquired in step ST1 or the boundary image data acquired in step ST3 is used as a learning input parameter and the corrected distinguished image data input from the input unit 43 is used as a learning output parameter, as teacher data. The learning unit 413 may update the combustion state learning model 44b by correcting the coefficients of each parameter of the combustion state learning model 44b using the corrected distinguished image data by a back error propagation method or the like. After the update of the combustion state learning model 44b is completed, the learning unit 413 turns off the flag indicating that learning is required.

In addition, the boundary discrimination learning model 44a may be further updated using an input/output data set in which the transmission image data acquired in step ST1 is used as a learning input parameter and the corrected boundary image data input by the operator from the input unit 43 in step ST5 is used as a learning output parameter, as teacher data, in a similar manner to the above-described method for updating the combustion state learning model 44b. The processing of steps ST4 to ST6 is repeatedly executed until the operator determines in step ST4 that the boundary line 53 is accurate (step ST4: Yes). Note that, when a rule-based image recognition algorithm is employed or when the boundary discrimination learning model 44a and the combustion state learning model 44b are not updated, the processing of steps ST4 to ST6 may be omitted.

When proceeding to step ST7, the combustion judgment unit 412 functions as a waste amount measuring device and calculates the waste amount of the burned area A31 and the unburned area A32 in the waste on the grate 52. That is, as shown in FIG. 7, in the distinguished image data, the area where the combustion temperature of the waste on the grate 52 is equal to or higher than a predetermined temperature is surrounded by a boundary line 532a and extracted as the burned area A31 (white area in FIG. 7). Similarly, the area where the combustion temperature of the waste on the grate 52 is lower than a predetermined temperature is surrounded by a boundary line 532b and extracted as the unburned area A32 (dotted area in FIG. 7). Here, in the distinguished image data, for example, a luminance corresponding to the combustion temperature is set for each pixel of the image. Note that instead of pixels, the burned area 53A may be divided into a plurality of predetermined meshes, and a luminance corresponding to the combustion temperature may be set for each mesh (calculation grid). Also, instead of luminance, information on the measured temperature may be embedded in the distinguished image data as meta information associated with pixels or meshes.

9 is a schematic diagram of the combustion part of an incinerator for explaining an information processing method according to an embodiment of the present invention. As shown in FIG. 9, in the furnace 1, pre-supply waste 51 falls onto the grate 4 in response to the movement of the waste supply device 3. In the grate 4, along the upstream to downstream side of the movement direction of the waste 50, mainly, a drying stage for drying the waste 50, a combustion stage for burning the waste 50, and a post-combustion stage for transporting the combustion ash of the waste 50 after combustion are provided. Usually, the combustion temperature of the waste 52 on the grate becomes the highest in the combustion stage, and the part shown by the diagonal lines in FIG. 9 becomes the burned area A31. In this case, the area of the burned area A31 shown in FIG. 7 is approximately proportional to the amount of burned waste 52A. It is also possible to assume that the temperature integrated value of the burned area A31 corresponds to the amount of burned waste 52A. That is, the combustion judgment unit 412 performs image processing on the transmission image data and boundary image data to generate distinguishing image data, and calculates the area or temperature integrated value in the burned area A31, thereby deriving the amount of burned waste 52A in the burned area A31. Similarly, the combustion judgment unit 412 generates distinguishing image data and calculates the area or temperature integrated value in the unburned area A32, thereby deriving the amount of unburned waste 52B in the waste on the grate 52. The combustion judgment unit 412 derives the amount of burned waste 52A and the amount of unburned waste 52B at a predetermined interval, for example, about 10 seconds to 1 minute, or at any time. The combustion judgment unit 412 stores at least one of the derived information on the area and the integrated temperature value in each of the burned area A31 and the unburned area A32 in the waste amount information database 44c of the memory unit 44.

Next, the process proceeds to step ST8 shown in Fig. 8, where the combustion determination unit 412 derives a waste amount ratio α, which is the ratio of the amount of combusted waste 52A to the amount of uncombusted waste 52B, for example, according to the following formula (1). The combustion determination unit 412 derives the waste amount ratio α at a predetermined time interval, for example, at intervals of about 10 seconds to 1 minute. The combustion determination unit 412 stores the derived waste amount ratio α in the waste amount information database 44c of the storage unit 44.
Waste amount ratio α=(amount of burned waste 52A)/(amount of unburned waste 52B) (1)

Next, the process proceeds to step ST9, where the combustion determination unit 412 derives the time change in the waste amount ratio α. The combustion determination unit 412 associates the derived information on the time change in the amount of burned waste 52A and the amount of unburned waste 52B with the information on the time change in the derived value of the waste amount ratio α, and transmits them to the combustion control device 30.

Next, the process proceeds to step ST10 shown in FIG. 8, where the control unit 31 executes combustion control so that the combustion state of the waste 52 on the grate is appropriate based on the information on the time change in the value of the waste amount ratio α transmitted from the combustion determination device 40 and the information on the time change in the amount of the associated burned waste 52A and the amount of unburned waste 52B. That is, the control unit 31 corrects the control parameters in the above-mentioned combustion control device 30 based on the acquired information, and controls the furnace 1 by adjusting the grate feed speed (hereinafter, grate speed), the waste supply device feed speed (hereinafter, dust feed speed), the combustion air volume (hereinafter, primary blower volume), and the combustion air temperature. Specifically, an example of control based on the change in the waste amount ratio α and the change in the amount of burned waste 52A and unburned waste 52B is shown in Table 1.

As shown in Table 1, when the ratio of the amount of burned waste 52A to the amount of unburned waste 52B increases, i.e., when the waste amount ratio α increases, one of the following two types of control is performed depending on the change in the amount of burned waste 52A and the change in the amount of unburned waste 52B.

First, when the amount of unburned waste 52B decreases, the supply of waste 50 decreases and the proportion of unburned waste 52B decreases. As a result, the control unit 31 predicts that a so-called "garbage shortage" will occur on the grate 4, where the waste 52 on the grate is insufficient, suppressing combustion and reducing the amount of steam generated. In this situation, the control unit 31 controls various devices in the furnace 1 to adjust them in a direction that promotes combustion. Specifically, the grate speed is controlled to slow down, including stopping, the dust supply speed is increased, the flow rate of the primary air (primary air) is increased to promote combustion, and the combustion air temperature is increased to promote combustion.

Secondly, when the amount of burned waste 52A increases, the amount of burned waste 52A increases due to the unburned waste 52B, which is dried among the waste on the grate 52, being ignited. As a result, the control unit 31 predicts that the ratio of burned waste 52A on the grate 4 will increase, combustion on the grate 4 will become more active, and the amount of steam generated will increase. In this situation, the control unit 31 controls various devices in the furnace 1 to adjust in a direction to suppress combustion. Specifically, the grate speed is controlled to slow down, including stopping, the dust supply speed is maintained to maintain the supply of a constant amount of waste 50, the primary air flow rate is reduced overall to suppress the drying of the waste on the grate 52, and the combustion air temperature is lowered to suppress the drying of the waste in the drying stage. The reason for maintaining the dust supply speed is that if the dust supply speed is controlled to be slowed down or stopped in order to suppress combustion, the amount of unburned waste 52B will decrease and the waste on the grate 52 will be insufficient, which may lead to a so-called garbage starvation situation.

Also, as shown in Table 1, when the ratio of the amount of burned waste 52A to the amount of unburned waste 52B becomes smaller, i.e., when the waste amount ratio α decreases, one of the following two types of control is performed depending on the change in the amount of burned waste 52A and the change in the amount of unburned waste 52B.

First, when the amount of unburned waste 52B increases, the supply of waste 50 increases and the proportion of unburned waste 52B increases. In this case, the control unit 31 predicts that the total amount of waste 52 on the grate 4 will increase and the supplied unburned waste 52B will cover the burned area A31 of the burned waste 52A. In this situation, the control unit 31 controls the various devices in the furnace 1 to adjust them in a direction that promotes combustion overall. Specifically, the grate speed is controlled to increase, the dust supply speed is controlled to decrease or stop, the flow rate of the primary air (primary air) is reduced to suppress excessive combustion, and the combustion air temperature is lowered to suppress excessive combustion.

Secondly, when the amount of burned waste 52A decreases, the combustion of the burned waste 52A is promoted and the proportion of the amount of unburned waste 52B increases. In this case, the control unit 31 predicts that the amount of burned waste will gradually decrease as a result of the supply of waste 50 with a low combustion calorie, which will take time to dry. In this situation, the control unit 31 performs control to promote the drying of the waste 52 on the grate in the drying stage and adjust in a direction to promote combustion. Specifically, the grate speed is controlled to increase, the dust supply speed is maintained to maintain the supply of a constant amount of waste 50, the primary air flow rate is increased overall to promote the drying and combustion of the waste 52 on the grate, and the combustion air temperature is increased to promote the drying of the waste 52 on the grate. The reason for maintaining the dust supply speed is that if the supply of waste 50 is increased even when the amount of unburned waste 52B is sufficient, the waste layer will become thicker and excessive combustion may occur. With the above, the control process of the furnace 1 according to this embodiment is completed.

(Modification)
Next, a modified example of the embodiment described above will be described. FIG. 10 is a diagram showing a modified example of the distinguished image data. In the modified example, in step ST3 shown in FIG. 8, the combustion determination unit 412 draws a boundary line 54 on the transmission image data for the boundaries between the waste 50 and other objects, that is, the boundaries between the waste 50 and the waste supply unit 12, the step wall 13, and the grate 4. As shown in FIG. 10, the boundary generation unit 411 draws a boundary line 541 on the transmission image data for the boundaries between the waste 51 before supply and the step wall 13. The boundary generation unit 411 draws boundary lines 542 and 544 on the boundaries between the waste 52 on the grate and the step wall 13 and the grate 4, respectively. As described above, the boundary generation unit 411 generates boundary image data in which the boundary line 53 is drawn on the transmission image data. The boundary generation unit 411 outputs the generated boundary image data to the combustion determination unit 412.

Next, the combustion judgment unit 412 distinguishes between the burned area A31 having a temperature equal to or higher than a predetermined temperature in the waste on the grate 52 and the unburned area A32 having a temperature lower than the predetermined temperature in the boundary image data input from the boundary generation unit 411, and draws the boundary line 543. As a result, the combustion judgment unit 412 generates distinguished image data in which the boundary line 543 is drawn on the boundary image data. The combustion judgment unit 412 may also draw the boundary line 544 based on the identified burned area A31. The combustion judgment unit 412 may also generate distinguished image data in which the boundary line 542 and the boundary lines 543 and 544 are drawn on the transmission image data input from the imaging unit 26. In this case, the boundary image data generation process by the boundary generation unit 411 may not be executed. In other words, the distinguished image data may be image data that can extract the area in which the waste on the grate 52 exists and can distinguish the burned area A31 and the unburned area A32 in the waste on the grate 52. The combustion determination unit 412 may also output the results of identifying the burnt area A31 having a temperature equal to or higher than a predetermined temperature and the unburnt area A32 having a temperature lower than the predetermined temperature in the boundary image data to the boundary generation unit 411, and the boundary generation unit 411 may draw the boundary lines 542, 543, and 544. The other configurations are the same as those of the above-described embodiment.

According to the embodiment described above, the waste 52 on the grate 4 in the incinerator furnace 1 is imaged, and boundary lines 53, 54 are generated and superimposed on the boundary between the waste 52 on the grate 4 and the area where other objects exist, and the area on the grate 52 where the combustion temperature is equal to or higher than a predetermined temperature is identified as the burned area A31, and the area below the predetermined temperature is identified as the unburned area A32. This allows the combustion state of the waste 50 supplied onto the grate 4 in the grate incinerator to be grasped. Furthermore, the combustion state of the waste 50 obtained, i.e., the time change in the amount of each of the burned waste 52A and the unburned waste 52B in the waste 52 on the grate, and the time change in the waste amount ratio α, are controlled based on the various devices in the furnace 1, so that the combustion of the waste 50 can be appropriately controlled and the combustion can be stabilized.

Although one embodiment of the present invention has been specifically described above, the present invention is not limited to the above-described embodiment, and various modifications based on the technical concept of the present invention are possible. For example, the numerical values given in the above-described embodiment are merely examples, and numerical values different from these may be used as necessary, and the present invention is not limited by the description and drawings that form part of the disclosure of the present invention according to this embodiment.

For example, in the embodiment described above, the boundary discrimination learning model 44a, the combustion state learning model 44b, and the waste amount information database 44c are stored in the storage unit 44, but they can also be stored in the storage unit of another server that can communicate through a network. That is, the boundary discrimination learning model 44a can also be stored in the storage unit of an image server that can communicate with the combustion judgment device 40 through a network such as a public circuit network. In this case, the transmission image data captured by the imaging unit 26 is transmitted to the image server through the network and stored in the storage unit. Thereafter, in response to a request from the combustion judgment device 40, the control unit of the image server draws boundary lines 53 and 54 on the transmission image data to generate boundary image data and transmits it to the combustion judgment device 40. Similarly, the combustion state learning model 44b can also be stored in the storage unit of a judgment server that can communicate through a network. In this case, the judgment server receives and acquires image data such as the transmission image data and boundary image data from the storage unit of the image server. The control unit of the determination server distinguishes between the burned area A31 and the unburned area A32 based on the acquired transmission image data and boundary image data, derives the time change in the amount of burned waste 52A and unburned waste 52B, derives the waste amount ratio α, and transmits it to the combustion control device 30. In other words, the image learning unit having the functions of the boundary generation unit 411 and the learning unit 413, and the combustion learning unit having the functions of the learning unit 413 and the combustion judgment unit 412 may be provided in different devices that can communicate with each other via a network. Furthermore, the boundary generation unit 411, the combustion judgment unit 412, and the learning unit 413 may each be provided in a different device that can communicate with each other via a network.

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

In addition, for example, based on the amounts of burned waste 52A and unburned waste 52B derived from the distinguished image data generated by the combustion determination device 40 and the time change in the waste amount ratio α derived from these, the results of the power generation amount and steam generation amount when the combustion control device 30 controls the furnace 1 may be used as rewards, and machine learning such as reinforcement learning and deep reinforcement learning may be performed to generate or update the boundary discrimination learning model 44a and the combustion state learning model 44b.

In addition, for example, in the above-mentioned embodiment, an example was described in which a grate incinerator having a step wall 13 was used as the incinerator, but the incinerator is not necessarily limited to a grate incinerator. In the case of an incinerator other than a grate incinerator having a step wall 13, the boundary image data and the distinction image data may be used in which, in addition to the boundary between the waste 50 and other areas, an isotherm based on the combustion temperature of the waste 50 is generated as a boundary line and superimposed on the transparent image data. In this case, for example, an isotherm for every 100°C may be generated for the combustion temperature of the waste 50 and used as the boundary image data. In addition, in addition to the boundary between the waste 50 and other areas, image data in which a boundary line is generated by geometrically distinguishing the waste in the incinerator and superimposed on the transparent image data may be used as the boundary image data. Even in this case, it is possible to generate distinction image data in which a boundary line is drawn to distinguish between an area where the combustion temperature is equal to or higher than a predetermined temperature and an area where the combustion temperature is lower than a predetermined temperature. In other words, it is possible to use, as the boundary image data, image data in which various boundaries according to the structure of the incinerator are set and a boundary line is generated and superimposed on the transparent image data. Furthermore, as the distinction image data, image data may be used that is generated as a boundary line, such as an isotherm based on the combustion temperature of the waste 50, and superimposed on the image data.

For example, the combustion judgment unit 412 of the control unit 41 may calculate the height of the layer of waste 52 on the grate (hereinafter, waste layer height). In this case, specifically, the combustion judgment unit 412 calculates the height of the waste 52 on the grate (hereinafter, waste layer height) based on the boundary portion between the step wall 13 and the waste 52 on the grate at the boundary line 532. Here, the boundary portion between the step wall 13 and the waste 52 on the grate at the boundary line 532 is uneven (see Figures 6 and 7). The combustion judgment unit 412 as a calculation unit calculates the waste layer height by averaging the height from the intersection of the grate 4 and the step wall 13 determined in the boundary image data to the top of the waste 52 on the grate obtained by the boundary line 532 in the width direction.

The combustion judgment unit 412 may also calculate the waste layer height by deriving the area of the waste 52 on the grate between the boundary line 532 and the intersection of the grate 4 and the step wall 13 in the boundary image data or the distinction image data, and dividing the derived area by the width of the furnace 1 (the width from left to right in FIG. 7), which is a constant, and averaging the area. The calculated waste layer height is a physical quantity corresponding to the amount of waste 52 on the grate. The control unit 41 transmits information on the calculated waste layer height of the waste 52 on the grate to the combustion control device 30. The control unit 31 of the combustion control device 30 stores the received waste layer height information in the memory unit 32.

(recoding media)
In the above-described embodiment, a program for executing the processing method executed by the combustion control device 30 or the combustion determination device 40 can be recorded on a recording medium readable by a computer or other machine or device such as a wearable device (hereinafter referred to as a computer, etc.). By having a computer, etc. read and execute the program from the recording medium, the computer, etc. functions as a mobile object control device. Here, a recording medium readable by a computer, etc. refers to a non-transient recording medium that accumulates information such as data and programs by electrical, magnetic, optical, mechanical, or chemical action and can be read from a computer, etc. Among such recording media, those that can be removed from a computer, etc. include, for example, a flexible disk, a magneto-optical disk, a CD-ROM, a CD-R/W, a DVD, a BD, a DAT, a magnetic tape, and a memory card such as a flash memory. In addition, a hard disk, a ROM, etc. are examples of recording media fixed to a computer, etc. Furthermore, an SSD can be used as a recording medium that can be removed from a computer, etc., or as a recording medium fixed to a computer, etc.

In addition, the programs executed by the combustion control device 30 and the combustion determination device 40 in one embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading via the network.

Other Embodiments
In one embodiment, the above-mentioned "unit" can be read as a "circuit" etc. For example, the control unit can be read as a control circuit.

Note that in the explanation of the flowcharts in this specification, the order of processing between steps is clearly indicated using expressions such as "first," "next," "then," and "continue." However, the order of processing required to implement this embodiment is not uniquely determined by these expressions. In other words, the order of processing in the flowcharts described in this specification can be changed as long as there are no contradictions.

Further advantages and modifications may be readily derived by those skilled in the art. The broader aspects of the present disclosure are not limited to the specific details and representative embodiments shown and described above. Thus, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and equivalents thereof.

1 Furnace 1a Furnace wall 2 Waste inlet 3 Waste supply device 4 Grate 5 Ash drop port 6 Combustion air blower 7 Furnace outlet 8 Chimney 9 Boiler 9a Heat exchanger 9b Steam drum 10 Secondary air blowing port 11 Secondary air blower 12 Waste supply section 13 Step wall 14 Combustion air damper 14a, 14b, 14c, 14d Under-grate combustion air damper 15 Secondary air damper 16 Intermediate ceiling 17 Combustion chamber gas thermometer 18 Main flue gas thermometer 19 Furnace outlet lower gas thermometer 20 Furnace outlet middle gas thermometer 21 Furnace outlet gas thermometer 22 Boiler outlet oxygen concentration meter 23 Gas concentration meter 24 Exhaust gas flow meter 25 Steam flow meter 26 Imaging section 30 Combustion control device 31, 41 Control section 32, 44 Memory section 33 Operation amount adjustment section 40 Combustion determination device 42 Output section 43 Input section 44a Boundary discrimination learning model 44b Combustion state learning model 44c Waste amount information database 50 Waste 51 Waste before supply 52 Waste on grate 52A Burned waste 52B Unburned waste 53, 531, 532, 532a, 532b, 54, 541, 542, 543, 544 Boundary line 331 Combustion air amount adjustment section 332 Air amount ratio adjustment section 333 Secondary air amount adjustment section 334 Waste supply device feed speed adjustment section 335 Grate feed speed adjustment section 411 Boundary generation section 412 Combustion judgment section 413 Learning section A31 Burned area A32 Unburned area

Claims (6)

A control unit having hardware,
The control unit is
In a waste incinerator equipped with a fire grate that moves the waste while incinerating it, an imaging unit capable of imaging pre-supply waste sent out from a waste supply unit, a step wall onto which the pre-supply waste falls, the waste moving on the fire grate, and the upper surface of the fire grate in a state where a flame is transmitted therethrough is used to capture an image of an area including the waste, and the image data is acquired and stored in a memory unit;
The transmission image data read from the storage unit is input as an input parameter to a boundary discrimination learning model, a boundary line is generated for a boundary between the waste and an object other than the waste in the waste incinerator, and the boundary image data obtained by drawing the boundary line on the transmission image data is output as an output parameter;
inputting the boundary image data as an input parameter into a combustion state learning model, distinguishing between a burned region where the combustion temperature of the waste is equal to or higher than a predetermined temperature and an unburned region where the combustion temperature of the waste is lower than the predetermined temperature, and outputting distinguished image data in which a boundary line between the burned region and the unburned region is drawn as an output parameter;
From the distinguished image data,
The amount of burned waste in the burned area is derived based on the amount of burned waste obtained from an area of the burned area or a temperature integrated value obtained by integrating the temperature of each predetermined area in the burned area;
An information processing device that derives the amount of unburned waste in the unburned region based on an area of the unburned region or a combustion amount of the unburned waste obtained from an integrated temperature value obtained by integrating temperatures for each predetermined region in the unburned region. 2. The information processing device according to claim 1, wherein the combustion state learning model is a learning model generated by machine learning using at least one of the transmission image data and the boundary image data generated by a boundary discrimination learning model as learning input parameters, and using distinction image data in which the boundary line between the burnt area and the unburnt area is drawn on the boundary image data as a learning output parameter. The information processing apparatus according to claim 1 or 2, wherein a boundary line in the boundary image data is generated on an outer edge of the waste present on the grate with respect to the transmission image data. The control unit is
The information processing apparatus according to claim 3 , further comprising: a position of a combustion point, which is a downstream end of the burnt region of the waste present on the fire grate in the transmission image data, based on the burnt region. The control unit is
The information processing apparatus according to any one of claims 1 to 4, further comprising: a calculation unit for calculating a ratio of the amount of the burned waste to the amount of the unburned waste. An information processing method executed by an information processing device having a control unit having hardware,
The control unit is
In a waste incinerator equipped with a fire grate that moves waste while incinerating it, an imaging unit capable of imaging pre-supply waste sent out from a waste supply unit, a step wall onto which the pre-supply waste falls, the waste moving on the fire grate, and the upper surface of the fire grate in a state where a flame is transmitted therethrough is used to obtain transmission image data of an area including the waste, and the transmission image data is stored in a memory unit;
The transmission image data read from the storage unit is input as an input parameter to a boundary discrimination learning model, a boundary line is generated for a boundary between the waste and an object other than the waste in the waste incinerator, and the boundary image data obtained by drawing the boundary line on the transmission image data is output as an output parameter;
inputting the boundary image data as an input parameter into a combustion state learning model, distinguishing between a burned region where the combustion temperature of the waste is equal to or higher than a predetermined temperature and an unburned region where the combustion temperature of the waste is lower than the predetermined temperature, and outputting distinguished image data in which a boundary line between the burned region and the unburned region is drawn as an output parameter;
From the distinguished image data,
The amount of burned waste in the burned area is derived based on the amount of burned waste obtained from an area of the burned area or a temperature integrated value obtained by integrating the temperature of each predetermined area in the burned area;
An information processing method comprising: deriving an amount of unburned waste in the unburned region based on an amount of unburned waste burned, the amount being obtained from an area of the unburned region or an integrated temperature value obtained by integrating temperatures for each predetermined region in the unburned region.

Images