Information processing apparatus, information processing method, and information processing program

Abstract

To provide a technique for classifying, predicting, and estimating a combustion state in an incinerator with higher accuracy.SOLUTION: An information processing apparatus includes: a first image analyzing unit which uses a first learned model having machine-learned first teacher data generated by assigning a classification label in at least one first evaluation axis, which becomes an element for determining a combustion state to evaluate the data in the first evaluation axis using new infrared image data in an incinerator as input, for infrared image data in the incinerator captured by an infrared imaging apparatus; and a combustion state determining unit for determining the current combustion state based on results of the evaluation in the first evaluation axis.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program for determining a combustion state in an incinerator. [Background technology]

[0002] In waste incineration facilities, automatic combustion control (ACC) is introduced to stabilize waste combustion in order not only to efficiently recover heat from combustion exhaust gas but also to curb the emission of harmful substances (CO, dioxins, NOx, etc.).

[0003] However, when the ACC is unable to maintain the combustion state inside the incinerator due to a significant change in waste quality, an experienced operator may need to intervene manually. At this time, the experienced operator makes the decision to intervene manually based on process values ​​obtained from various sensors and footage of the combustion state.

[0004] The information from the combustion images is a very important indicator, and various companies have filed patent applications for technology to classify combustion states and predict process values ​​from combustion images, mainly using image recognition technology that employs deep learning. For example, Patent Document 1 proposes using a classification model that uses combustion images as input to classify combustion states into, for example, eight types. Patent Document 2 also proposes creating an estimation model that uses combustion images as input to predict estimated values ​​(CO concentration, NOx concentration, unburned content in ash, etc.) according to the combustion state. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-8991 [Patent Document 2] Patent No. 6824859 Summary of the Invention [Problem to be solved by the invention]

[0006] The combustion footage mainly captures the flames in the main combustion area inside the incinerator (flames that arise from the combustion of combustible gases produced by the thermal decomposition and partial oxidation of waste), and the combustion footage provides information such as the strength of the flames.

[0007] However, the combustion state is affected not only by the state of the flame but also by information about the combusted material (for example, the amount, quality, and type of combusted material). For example, even if the flame is burning with the same intensity, if the amount of combusted material burning at that time is different, the actual values ​​of the exhaust gas concentration (CO concentration, etc.) are likely to be different. In addition, with regard to technology that classifies the combustion state and predicts process values ​​from combustion images, if only the combustion image, which can grasp only the flame state, is used, it is highly likely that the combustion state will be classified as the same even if the actual combustion state is different due to, for example, differences in the amount of combusted material, so it may not be possible to predict or estimate process values ​​or classify, predict, or estimate the combustion state well.

[0008] The present invention has been made in consideration of the above points, and an object of the present invention is to provide a technology for more accurately classifying, predicting, and estimating the combustion state in an incinerator. [Means for solving the problem]

[0009] An information processing device according to a first aspect of the present invention includes: The combustion state is judged based on infrared image data from inside the incinerator captured by an infrared imaging device. A first image analysis unit that uses a first trained model obtained by machine learning first teacher data generated by assigning a classification label in at least one first evaluation axis as an element to input new infrared imaging data of the inside of the incinerator and performs evaluation along the first evaluation axis; The combustion state determination unit determines a current combustion state based on a result of the evaluation on the first evaluation axis.

[0010] According to this aspect, by appropriately selecting the imaging wavelength, the infrared imaging device can obtain infrared imaging data of the inside of the incinerator including images from the upstream side of the incinerator with the influence of the flame removed to images of the actual burning material. Therefore, by using the infrared imaging data of the inside of the incinerator to perform an evaluation on at least one first evaluation axis which is an element for determining the combustion state, and determining the combustion state based on the evaluation results, it is possible to classify, predict, and estimate the combustion state inside the incinerator more accurately than when the combustion state or process value is predicted and estimated only from the combustion image, which can only grasp the flame condition.

[0011] An information processing device according to a second aspect of the present invention is the information processing device according to the first aspect, The first evaluation axis includes at least one of the amount of the combusted material, the quality of the combusted material, the type of the combusted material, the temperature of the combusted material, the amount of combustion gas generated (CO, etc.), and the temperature of the wall of the incinerator.

[0012] An information processing device according to a third aspect of the present invention is the information processing device according to the first or second aspect, The infrared imaging data is video data of 60 seconds or less.

[0013] According to the knowledge of the present inventors, the combustion state inside an incinerator changes in 5 to 10 seconds. Therefore, according to this embodiment, by using video data of up to 60 seconds as one section as infrared imaging data inside the incinerator, the combustion state inside the incinerator can be classified, predicted, and estimated with higher accuracy.

[0014] An information processing device according to a fourth aspect of the present invention is an information processing device according to any one of the first to third aspects, The infrared imaging data is moving image data of 5 seconds or more.

[0015] According to this embodiment, while the combustion conditions inside an incinerator change every 5 to 10 seconds, by using video data of 5 seconds or more as one segment of infrared imaging data inside the incinerator, the combustion conditions inside the incinerator can be more accurately classified, predicted, and estimated.

[0016] An information processing device according to a fifth aspect of the present invention is an information processing device according to any one of the first to fourth aspects, The classification label is at least one of a label indicating which of predetermined classification items the data falls into and a relative order among the plurality of infrared imaging data.

[0017] The inventors of the present invention have actually verified that the combustion state in the incinerator can be classified, predicted, and estimated with higher accuracy by evaluating the infrared imaging data of the incinerator captured by the infrared imaging device on the first evaluation axis using a first trained model that is machine-learned (ranking-learned) with first teacher data that is generated by assigning a relative order on the first evaluation axis among multiple infrared imaging data, and judging the combustion state based on the evaluation result. Therefore, according to this embodiment, the combustion state in the incinerator can be classified, predicted, and estimated with higher accuracy.

[0018] An information processing device according to a sixth aspect of the present invention is an information processing device according to any one of the first to fifth aspects, The first image analysis unit uses a first trained model obtained by machine learning first teacher data generated by assigning classification labels on the first evaluation axis to a combination of infrared imaging data inside the incinerator and process data obtained from sensors installed in the facility and / or a calculation amount obtained by calculation from the process data, and performs an evaluation on the first evaluation axis using as input a combination of new infrared imaging data inside the incinerator and new process data and / or a calculation amount obtained by calculation from the process data.

[0019] An information processing device according to a seventh aspect of the present invention is the information processing device according to the sixth aspect, The process data is data that takes into consideration a time lag between the imaging time of the infrared imaging data and the response time of the sensor, and the time lag may be appropriately determined based on the response speed of the sensor, the installation position of the sensor in the facility, an experiment, a simulation, or an operator's experience.

[0020] An information processing device according to an eighth aspect of the present invention is an information processing device according to any one of the first to seventh aspects, The first image analysis unit uses a first trained model obtained by machine learning first teacher data generated by assigning classification labels in each of the two or more first evaluation axes, which are elements for determining the combustion state, to the infrared imaging data inside the incinerator, and performs an evaluation on each of the two or more first evaluation axes using new infrared imaging data inside the incinerator as an input, The combustion state determination unit determines the current combustion state by mapping the evaluation results for each of the two or more first evaluation axes onto a predetermined combustion state determination map having the two or more first evaluation axes as coordinate axes.

[0021] According to this embodiment, the combustion state is evaluated in two or more first evaluation axes, which are elements for judging the combustion state, using infrared imaging data inside the incinerator, and the combustion state is judged based on the evaluation results in each of the two or more first evaluation axes, so that the combustion state can be classified, predicted, and estimated with higher accuracy than when the combustion state is judged based on the evaluation result in one evaluation axis. In addition, the combustion state is judged by mapping the evaluation results in each of the two or more first evaluation axes on a combustion state judgment map, so that it is possible to intuitively grasp the relationship between the evaluation results in each of the two or more first evaluation axes and the combustion state, which is the judgment result, and it is also possible to quickly judge the combustion state.

[0022] An information processing device according to a ninth aspect of the present invention is an information processing device according to any one of the first to seventh aspects, A second image analysis unit is further provided that uses a second trained model that is machine-learned with second teacher data generated by adding a classification label in at least one second evaluation axis that is an element for determining the combustion state to the visible light imaging data of the inside of the incinerator captured by the visible light imaging device, and performs an evaluation on the second evaluation axis using new visible light imaging data of the inside of the incinerator as an input, The combustion state determination unit determines the current combustion state by mapping the evaluation results for each of the first evaluation axis and the second evaluation axis onto a predetermined combustion state determination map having the first evaluation axis and the second evaluation axis as coordinate axes.

[0023] According to this embodiment, in addition to using infrared imaging data from inside the incinerator to perform an evaluation along the first evaluation axis, which is a factor in determining the combustion state, visible light imaging data from inside the incinerator is used to perform an evaluation along the second evaluation axis, which is a factor in determining the combustion state, and the combustion state is determined based on the evaluation results along each of the first and second evaluation axes, so that the combustion state can be classified, predicted, and estimated with higher accuracy than when the combustion state is determined based on the evaluation result along one evaluation axis. Also, the evaluation results along each of the first and second evaluation axes are mapped onto a combustion state determination map. Since the combustion state is judged by this, it is possible to intuitively grasp the relationship between the evaluation results on the first evaluation axis and the second evaluation axis and the judged combustion state, and it is also possible to quickly judge the combustion state.

[0024] An information processing device according to a tenth aspect of the present invention is the information processing device according to the ninth aspect, The second evaluation axis includes at least one of the flame state, the position of the combustion completion point, the shape of the combustion completion point, the amount of the combusted material, the quality of the combusted material, the type of the combusted material, the amount of unburned material, and the amount of incineration ash.

[0025] An information processing device according to an eleventh aspect of the present invention is the information processing device according to any one of the first to tenth aspects, The combustion state determination unit corrects the determination result of the combustion state in accordance with process data obtained from a sensor installed in the facility and / or a calculation amount obtained by calculation from the process data.

[0026] An information processing device according to a twelfth aspect of the present invention is an information processing device according to any one of the first to eleventh aspects, The combustion state determination unit displays or issues an alert depending on a result of the combustion state determination.

[0027] An information processing device according to a thirteenth aspect of the present invention is an information processing device according to any one of the first to twelfth aspects, The combustion control device further includes an instruction unit that transmits an operation instruction to a crane control device and / or a combustion control device based on a determination result of the combustion state determination unit.

[0028] An information processing device according to a 14th aspect of the present invention is the information processing device according to any one of the first to 13th aspects, The algorithm used for the machine learning includes at least one of maximum likelihood classification, Boltzmann machine, neural network (NN), support vector machine (SVM), Bayesian network, sparse regression, decision tree, statistical inference using random forest, boosting, reinforcement learning, and deep learning.

[0029] An information processing device according to a fifteenth aspect of the present invention is the information processing device according to any one of the first to fourteenth aspects, The incinerator further includes a model construction unit that generates the first trained model by machine learning first training data generated by assigning classification labels in a first evaluation axis, which is an element for determining the combustion state, to infrared imaging data of the inside of the incinerator captured by an infrared imaging device.

[0030] A system according to a sixteenth aspect of the present invention comprises: An information processing device according to a thirteenth aspect, The crane control device controls a crane that mixes or transports waste based on an operation instruction transmitted from the information processing device, and / or the combustion control device controls the combustion of waste in an incinerator; Equipped with.

[0031] An information processing method according to a seventeenth aspect of the present invention is an information processing method executed by a computer, comprising: The combustion state is judged based on infrared image data from inside the incinerator captured by an infrared imaging device. A step of using a first trained model obtained by machine learning first teacher data generated by assigning a classification label in at least one first evaluation axis as an element, and performing an evaluation on the first evaluation axis using new infrared imaging data of the inside of the incinerator as an input; determining a current combustion state based on an evaluation result on the first evaluation axis; Includes.

[0032] A program according to an eighteenth aspect of the present invention is a program for executing a program on a computer, comprising: A step of using a first trained model obtained by machine learning first teacher data generated by assigning a classification label in at least one first evaluation axis, which is an element for determining the combustion state, to infrared imaging data of the inside of the incinerator captured by an infrared imaging device, and performing an evaluation on the first evaluation axis using new infrared imaging data of the inside of the incinerator as an input; determining a current combustion state based on an evaluation result on the first evaluation axis; Execute the command. Effect of the Invention

[0033] According to the present invention, the combustion state inside an incinerator can be classified, predicted, and estimated with greater accuracy. [Brief description of the drawings]

[0034] [Figure 1] FIG. 1 is a schematic diagram showing the configuration of an incineration facility according to a first embodiment. [Diagram 2]FIG. 2 is a block diagram showing the configuration of the information processing apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of an information processing method by the information processing device according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the combustion state determination map. [Diagram 5] FIG. 5 is a schematic diagram showing the configuration of an incineration facility according to the second embodiment. [Figure 6] FIG. 6 is a block diagram showing the configuration of an information processing apparatus according to the second embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of an information processing method by the information processing device according to the second embodiment. [Figure 8] FIG. 8 is a schematic diagram showing the configuration of an incineration facility according to the third embodiment. [Figure 9] FIG. 9 is a block diagram showing the configuration of an information processing device according to the third embodiment. [Figure 10] FIG. 10 is a flowchart showing an example of an information processing method by the information processing device according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0035] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the drawings used in the following description, the same reference numerals are used for parts that can be configured identically, and duplicated descriptions will be omitted.

[0036] In this specification, "A and / or B" means one or both of A and B. In addition, in this specification, "visible light" refers to electromagnetic waves with a wavelength of 360 nm to 830 nm, and "infrared light" refers to electromagnetic waves with a wavelength of 830 nm to 14,000 nm.

[0037] (First embodiment) FIG. 1 is a schematic diagram showing the configuration of an incineration facility 1 according to a first embodiment.

[0038] As shown in FIG. 1, the incineration facility 1 includes a platform 21 on which a transport vehicle (garbage truck) 22 carrying waste is parked, a garbage pit 3 in which the waste input from the platform 21 is stored, and a crane 5 for mixing and transporting the waste stored in the garbage pit 3. The incineration facility 1 is provided with a hopper 4 into which waste transported by a crane 5 is fed, an incinerator 6 for incinerating the waste fed from the hopper 4, and a waste heat boiler 2 for recovering waste heat from exhaust gas generated in the incinerator 6. The type of incinerator 6 is not limited to a stoker furnace as shown in FIG. 1, but also includes a fluidized furnace (also called a fluidized bed furnace). The structure of the waste pit 3 is not limited to a one-tier pit as shown in FIG. 1, but also includes a two-tier pit. The incineration facility 1 is also provided with a crane control device 50 for controlling the operation of the crane 5, and a combustion control device 20 for controlling the combustion of the waste (material to be combusted) in the incinerator 6.

[0039] Waste carried in on a transport vehicle 22 is dumped from a platform 21 into a garbage pit 3, where it is stored. The waste stored in the garbage pit 3 is stirred by a crane 5, and is transported by the crane 5 to a hopper 4, through which it is dumped into an incinerator 6, where it is incinerated and disposed of.

[0040] As shown in FIG. 1, the incineration facility 1 of this embodiment is provided with an infrared imaging device 71 and a visible light imaging device 72 for imaging the inside of the incinerator 6, and an information processing device 10 for determining the combustion state inside the incinerator 6.

[0041] In the illustrated example, the infrared imaging device 71 is installed above the downstream side of the incinerator 6. A plurality of infrared imaging devices 71 may be installed above the downstream side of the incinerator 6. The installation position of the infrared imaging device 71 is not limited to above the downstream side of the incinerator 6, and the infrared imaging device 71 may be installed horizontally above or horizontally on the downstream side or upstream side of the incinerator 6. The infrared imaging device 71 has an imaging wavelength (e.g., 3.7 μm to 4.0 μm) appropriately selected in advance so as to cut the wavelength of the flame (e.g., 4.1 μm to 4.5 μm), and is capable of acquiring an image including an image of the incinerator 6 from the upstream side to the actual burning material, with the influence of the flame removed, as infrared imaging data (video image data). The infrared imaging device 71 captures the wavelengths of CO2 and water vapor in addition to the wavelength of the flame. The imaging wavelength (e.g., 3.7 μm to 4.0 μm) is appropriately selected in advance to further cut off the infrared rays (e.g., 4.0 μm to 4.2 μm). The infrared imaging data (video image data) is obtained by removing the effects of the flame, CO2, and water vapor from the upstream side of the incinerator 6. It may be possible to obtain an image including an image of an object to be burned that is actually burning. The frame rate of the infrared imaging device 71 does not need to be a particularly high frame rate, and may be a general frame rate (about 30 fps) or a low frame rate (about 5 to 10 fps).

[0042] In the illustrated example, the visible light imaging device 72 is installed above the downstream side of the incinerator 6, and is capable of acquiring visible light imaging data (moving image data) of the flame state (combustion state) of the material to be burned on the grate. A plurality of visible light imaging devices 72 may be installed above the downstream side of the incinerator 6. The installation position of the visible light imaging device 72 is not limited to above the downstream side of the incinerator 6, and the visible light imaging device 72 may be installed horizontally on the downstream side of the incinerator 6 or above or horizontally on the upstream side. The visible light imaging device 72 may be any of an RGB camera, a 3D camera, and an RGB-D camera, or may be a combination of two or more of these. The frame rate of the visible light imaging device 72 does not need to be a particularly high frame rate, and may be a general frame rate (about 30 fps) or a low frame rate (about 5 to 10 fps).

[0043] Next, a description will be given of the configuration of the information processing device 10 according to the present embodiment. Fig. 2 is a block diagram showing the configuration of the information processing device 10. The information processing device 10 is made up of one or more computers.

[0044] 2, the information processing device 10 includes a communication unit 11, a control unit 12, and a storage unit 13. Each unit is connected to each other via a bus or a network so as to be able to communicate with each other.

[0045] Of these, the communication unit 11 is a communication interface between each of the devices, the infrared imaging device 71, the visible light imaging device 72, the crane control device 50, and the combustion control device 20, and the information processing device 10. The communication unit 11 transmits and receives information between each of the devices, the infrared imaging device 71, the visible light imaging device 72, the crane control device 50, and the combustion control device 20, and the information processing device 10.

[0046] The storage unit 13 is a non-volatile data storage such as a hard disk or a flash memory. The storage unit 13 stores various data handled by the control unit 12. The storage unit 12 also stores a first algorithm 13a1 used for machine learning by a first model construction unit 12c1 described later, a second algorithm 13a2 used for machine learning by the first model construction unit 12c1, first imaging data 13b1 acquired by the first imaging data acquisition unit 12a1, second imaging data 13b2 acquired by the second imaging data acquisition unit 12a2, first teacher data 13c1 generated by the first teacher data generation unit 12b, second teacher data 13c2 generated by the second teacher data generation unit 12b, and a combustion state determination map 13d used by the combustion state determination unit 12e. Details of each piece of information 13a1 to 13d will be described later.

[0047] The control unit 12 is a control means for performing various processes of the information processing device 10. As shown in Fig. 2, the control unit 11 has a first imaging data acquisition unit 12a1, a second imaging data acquisition unit 12b1, a first teacher data generation unit 12b1, a second teacher data generation unit 12b2, a first model construction unit 12c1, a second model construction unit 12c2, a first image analysis unit 12d1, a second image analysis unit 12d2, a combustion state determination unit 12e, an instruction unit 12f, and a process data acquisition unit 12g. Each of these units may be realized by a processor in the information processing device 10 executing a predetermined program, or may be implemented by hardware.

[0048] The first imaging data acquisition unit 12a1 acquires, as the first imaging data 13b1, infrared imaging data of the inside of the incinerator 6 captured by the infrared imaging device 71. The first imaging data 13b1 is stored in the storage unit 13.

[0049] The second imaging data acquisition unit 12a2 acquires, as second imaging data 13b2, visible light imaging data of the inside of the incinerator 6 captured by the visible light imaging device 72. The second imaging data 13b2 is stored in the storage unit 13.

[0050] The process data acquisition unit 12g acquires process data (for example, furnace outlet temperature and evaporation rate) measured by various sensors (not shown) installed in the incineration facility 1, and / or calculation data obtained by calculation from the process data. The process data and / or calculation data may be stored in the storage unit 13. The calculation data may be a difference value (or an absolute value of the difference value) between the actual measurement value PV and the set value SV, or a value over a predetermined period (for example, 1 minute, 10 minutes, 20 minutes, etc.) Moving average, maximum, minimum, median, integral, differential, and standard deviation for the period (1 hour, 1 hour) , or a difference value between the value a predetermined time ago (or an absolute value of the difference value).

[0051] The first teacher data generating unit 12b1 generates first teacher data 13c1 by linking a classification label in at least one first evaluation axis, which is an element for determining the combustion state and which is artificially assigned by the operator based on experience, to the first imaging data 13b1. The first teacher data generating unit 12b1 divides the first imaging data 13b1 into a plurality of blocks (e.g., a drying region, a gasification combustion region, and an o-combustion region in the combustion process) and links a classification label in at least one first evaluation axis, which is an element for determining the combustion state and which is artificially assigned by the operator based on experience, to the data in block units. , the first teacher data 13c1 may be generated. The first teacher data 13c1 is stored in the storage unit 13. Here, the classification label may be absolute classification information on the first evaluation axis (classification determined in relation to a predetermined absolute standard (threshold)) or a relative order on the first evaluation axis among a plurality of infrared imaging data (relative order relationship within a group consisting of a plurality of infrared imaging data). The first evaluation axis may include at least one of the amount of the combusted material, the quality of the combusted material, the type of the combusted material, the temperature of the combusted material, the amount of combustion gas generated (CO, etc.), and the temperature of the wall of the incinerator. The amount of the combusted material is, for example, a value corresponding to the volume, weight, density, cross-sectional area, etc. of the combusted material. The quality of the combusted material is, for example, a value corresponding to the flammability, heat generation, moisture, density, etc. of the combusted material. The types of combustible materials are, for example, unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, burlap bags, paper bags, bottom garbage (garbage that exists near the bottom of the garbage pit 3 and is compressed into information waste and has a high moisture content), wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, plants, soil, medical waste, incineration ash, bicycles, chests of drawers, beds, shelves, desks, chairs, agricultural vinyl products, PET bottles, polystyrene foam, meat and bone meal, agricultural crops, ceramics, glass waste, metal waste, rubble, concrete waste, tatami mats, bamboo, straw, and activated carbon. The temperature of the combustible materials is, for example, a value corresponding to the temperature of the combustible materials. The amount of combustion gas generated is, for example, a value corresponding to the amount of gas generated during the combustion process, such as CO, hydrogen, hydrocarbons, NOx, SOx, HCl, and dioxins. The temperature of the incinerator wall is, for example, a value corresponding to the temperature of the walls and ceiling of the incinerator.

[0052] As an example, when the amount of combustible materials is the first evaluation axis, the classification label may be large, normal, or small (absolute information) (the number of types of labels may be increased), or may be an order of the amount of combustible materials for a plurality of first image data (relative information). As another example, when the quality of combustible materials is the evaluation axis, the classification label may be normal garbage, high-quality garbage (i.e., high-calorie garbage), or low-quality garbage (i.e., low-calorie garbage) (absolute information) (the number of types of labels may be increased), or may be an order of the quality of combustible materials for a plurality of first image data (relative information). As another example, when the type of combustible materials is the first evaluation axis, the classification label may be garbage bags, unbroken garbage bags, pruning branches, or futons (absolute information) (the number of types of labels may be increased). As another example, when the amount of combustion gas generated (CO, etc.) is used as the evaluation axis, the classification label may be high, normal, low (absolute information) (the number of types of labels may be increased), or the amount of combustion gas generated (CO, etc.) may be ranked in order for a plurality of first imaging data (relative information). As another example, when the temperature of the incinerator wall is used as the first evaluation axis, the classification label may be high, normal, low (the number of types of labels may be increased), or the amount of combustion gas generated (CO, etc.) may be ranked in order for a plurality of first imaging data (relative information).

[0053] The first teacher data generating unit 12b1 may generate the first teacher data 13c1 by linking a classification label in the first evaluation axis artificially assigned by the operator based on empirical rules to a combination of the first imaging data 13b1 and process data obtained from various sensors (not shown) installed in the incineration facility 1 and / or a calculation amount obtained by calculation from the process data. Here, the process data is data that takes into account the time lag between the imaging time of the first imaging data and the response time of the sensor. The time lag may be appropriately determined based on the response speed of the sensor, the installation position of the sensor in the facility, an experiment, a simulation, and the operator's empirical rules.

[0054] The second teacher data generating unit 12b2 generates second teacher data 13c2 by linking a classification label in at least one second evaluation axis, which is an element for judging the combustion state and is artificially assigned by an operator based on empirical rules, to the second imaging data 13b1. The second teacher data generating unit 12b2 divides the second imaging data 13b1 into a plurality of blocks (for example, a drying region, a gasification combustion region, and an oak combustion region in the combustion process) and The second teacher data 13c2 may be generated by linking at least one classification label in the first evaluation axis, which is an element for judging the combustion state and is artificially assigned by an operator based on empirical rules, to the unit data. The second teacher data 13c2 is stored in the storage unit 13. Here, the classification label may be absolute classification information in the second evaluation axis (classification determined by a relationship with a predetermined absolute standard (threshold)) or a relative order in the second evaluation axis among a plurality of visible light imaging data (relative order relationship within a group consisting of a plurality of visible light imaging data). The second evaluation axis may include at least one of the flame state, the position of the combustion completion point (burnout point), the shape of the combustion completion point, the amount of the combusted material, the quality of the combusted material, the type of the combusted material, the amount of unburned material, and the amount of incineration ash. The flame state is, for example, a value corresponding to the strength or weakness of the flame, the brightness of the flame, etc. The position of the combustion completion point is, for example, a value corresponding to a position on a grate constituting an incinerator. The shape of the combustion end point is, for example, a value corresponding to the curvature or radius of curvature of the combustion end point. The amount of the combusted material is, for example, a value corresponding to the volume, weight, density, cross-sectional area, etc. of the combusted material. The quality of the combusted material is, for example, a value corresponding to the flammability, heat generation, moisture, density, etc. of the combusted material. The types of combusted material are, for example, unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, burlap bags, paper bags, bottom garbage (garbage that exists near the bottom of the garbage pit 3 and is compressed into information waste and has a high moisture content), wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, vegetation, soil, medical waste, incineration ash, bicycles, chests of drawers, beds, shelves, desks, chairs, agricultural vinyl products, PET bottles, polystyrene foam, meat and bone meal, agricultural crops, ceramics, glass waste, metal waste, rubble, concrete waste, tatami mats, bamboo, straw, and activated carbon. The amount of unburned material is a value corresponding to, for example, the volume, weight, density, cross-sectional area, amount, etc. of the unburned material. The amount of incineration ash is a value corresponding to, for example, the volume, weight, density, cross-sectional area, etc. of the incineration ash.

[0055] As an example, when the flame state is the second evaluation axis, the classification label may be good, normal, or bad (absolute information) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the flame state for a plurality of (for example, two) second imaging data (relative information). As another example, when the position of the combustion completion point (burnout point) is the evaluation axis, the classification label may be near, slightly near, normal, slightly far, or far (the number of types of labels may be increased), or may be an order of the distance of the position of the combustion completion point for a plurality of second imaging data. As another example, when the shape of the combustion completion point is the evaluation axis, the classification label may be good, normal, or bad (the number of types of labels may be increased), or may be an order of superiority or inferiority of the shape of the combustion completion point for a plurality of second imaging data. As another example, when the amount of combustible material is the second evaluation axis, the classification label may be many, normal, or few (the number of types of labels may be increased), or may be an order of the amount of combustible material for a plurality of second imaging data. As another example, when the quality of the combusted material is the second evaluation axis, the classification label may be normal garbage, high-quality garbage (i.e., high-calorie garbage), or low-quality garbage (i.e., low-calorie garbage) (the number of types of labels may be increased), or the quality of the combusted material may be ranked for a plurality of second imaging data. As another example, when the type of combusted material is the second evaluation axis, the classification label may be garbage bags, unbroken garbage, pruning branches, or futons (the number of types of labels may be increased). As another example, when the amount of unburned material is the second evaluation axis, the classification label may be large, normal, or small (the number of types of labels may be increased), or the amount of unburned material may be ranked for a plurality of second imaging data. As another example, when the amount of incineration ash is the second evaluation axis, the classification label may be large, normal, or small (the number of types of labels may be increased), or the amount of incineration ash may be ranked for a plurality of second imaging data.

[0056] The second teacher data generating unit 12b2 generates teacher data based on the operator's experience for a combination of the second imaging data 13b2 and process data obtained from various sensors (not shown) installed in the incineration facility 1 and / or a calculation amount obtained by calculation from the process data. The second teacher data 13c2 may be generated by linking the classification labels in the second evaluation axis that are artificially assigned. Here, the process data is data that takes into account the time lag between the imaging time of the second imaging data and the response time of the sensor. The time lag may be appropriately determined based on the response speed of the sensor, the installation position of the sensor in the facility, experiments, simulations, and the operator's empirical rules.

[0057] The first imaging data 13b1 and / or the second imaging data 13b2 may be video data of 60 seconds or less, or video data of 30 seconds or less. According to the knowledge of the present inventors, the combustion state inside the incinerator 6 changes every 5 to 10 seconds. Therefore, by using video data of, for example, 60 seconds or less (or 30 seconds or less) as the first imaging data 13b1 and / or the second imaging data 13b2 as one section, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0058] Furthermore, the first imaging data 13b1 and / or the second imaging data 13b2 may be moving image data of 5 seconds or more, or 7 seconds or more. The combustion state inside the incinerator 6 changes every 5 to 10 seconds, so by using moving image data of, for example, 5 seconds or more (or 7 seconds or more) as the first imaging data 13b1 and / or the second imaging data 13b2 as one segment, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0059] The first model construction unit 13c1 generates a first trained model by performing machine learning on the first teacher data 13b1 generated by the first teacher data generation unit 12b1 using a first algorithm 13a1. The first algorithm 13a1 used for the machine learning may include at least one of a maximum likelihood classification method, a Boltzmann machine, a neural network (NN), a support vector machine (SVM), a Bayesian network, a sparse regression, a decision tree, a statistical estimation using a random forest, boosting, reinforcement learning, and deep learning.

[0060] Similarly, the second model construction unit 13c2 generates a second trained model by performing machine learning on the second teacher data 13b2 generated by the second teacher data generation unit 12b2 using the second algorithm 13a2. The second algorithm 13a2 used for the machine learning may include at least one of a maximum likelihood classification method, a Boltzmann machine, a neural network (NN), a support vector machine (SVM), a Bayesian network, a sparse regression, a decision tree, a statistical estimation using a random forest, boosting, reinforcement learning, and deep learning.

[0061] The first image analysis unit 13d1 receives new first imaging data (infrared imaging data) of the inside of the incinerator 6 acquired by the first imaging data acquisition unit 13a1 as input, and acquires an evaluation result on a first evaluation axis (e.g., the amount of material to be burned) as output data using the first trained model generated by the first model construction unit 13c1. The first image analysis unit 13d1 may normalize (score) the evaluation result on the first evaluation axis to a numerical range of, for example, 0 to 100, and acquire a numerical value (score) within the range as output data.

[0062] The second image analysis unit 13d2 receives as input the new second imaging data (visible light imaging data) of the inside of the incinerator 6 acquired by the second imaging data acquisition unit 13a2, and acquires the evaluation result on the second evaluation axis (for example, flame state) as output data using the second trained model generated by the second model construction unit 13c2. The second image analysis unit 13d2 may normalize (score) the evaluation result on the second evaluation axis to a numerical range of, for example, 0 to 100, and acquire the numerical value (score) within the range as output data.

[0063] The combustion state determination unit 12e determines the current combustion state in the incinerator 6 based on the evaluation result (score) in the first evaluation axis by the first image analysis unit 13d1 and the evaluation result (score) in the second evaluation axis by the second image analysis unit 13d2. The combustion state determination result may be a label indicating the characteristics of the combustion state (excessive combustion, thick garbage layer combustion, thin garbage layer combustion, exhausted garbage, low-quality garbage combustion, etc.), or may be a numerically modified version of the label. Excessive combustion is, for example, a combustion state in which there is a large amount of high-quality (easily combustible) garbage in the combusted material, and the combustion temperature is very high, resulting in active combustion. Thick garbage layer combustion is, for example, a combustion state in which the amount of combusted material is greater than normal. Thin garbage layer combustion is, for example, a combustion state in which the amount of combusted material is less than normal. Exhausted garbage is, for example, a combustion state in which the amount of combusted material is extremely less than normal, resulting in a low combustion temperature. Low-quality waste combustion refers to a combustion state in which the combustion temperature is low or the combustion is weak, for example, when there is a large amount of low-quality waste (such as low-calorie waste) among the materials being combusted.

[0064] The combustion state determination unit 12e may determine the current combustion state in the incinerator 6 by mapping a set (X, Y) consisting of the evaluation result (X) on the first evaluation axis and the evaluation result (Y) on the second evaluation axis on a predetermined combustion state determination map 13d in which the first evaluation axis is the X-coordinate axis and the second evaluation axis is the Y-coordinate axis. The combustion state determination unit 12e may determine the current combustion state in the incinerator 6 by mapping a set (X, Y, Z, . . .) consisting of one or more evaluation results on the first evaluation axis and one or more evaluation results on the second evaluation axis on a predetermined N-dimensional space (N is an integer of 3 or more) in which, for example, one of the first evaluation axes is the X-coordinate axis, another one of the first evaluation axes is the Y-coordinate axis, and one of the second evaluation axes is the Z-coordinate axis.

[0065] FIG. 4 is a diagram showing an example of the combustion state determination map 13d. In the combustion state determination map 13d shown in FIG. 4, an XY coordinate plane with the amount of material to be burned as the X coordinate axis and the flame state as the Y coordinate axis is divided into a plurality of regions (six regions in the illustrated example: a garbage dead zone, an overburned zone, a thin garbage layer burning zone, a good combustion (normal) zone, a thick garbage layer burning zone, and a low-quality garbage burning zone). The combustion state determination unit 12e maps a set (X, Y) consisting of an evaluation result (X) on the first evaluation axis and an evaluation result (Y) on the second evaluation axis when the amount of material to be burned is the first evaluation axis and the flame state is the second evaluation axis, on this combustion state determination map 13d. For example, as shown in FIG. 4, when a point P showing a set (X, Y) consisting of an evaluation result (X) on the first evaluation axis and an evaluation result (Y) on the second evaluation axis is mapped within the good combustion (normal) zone, the combustion state determination unit 12e determines that the current combustion state is "good combustion (normal)". The range of the above-mentioned area (threshold (position, length and shape of the boundary line)) may be determined based on the operator's experience, or may be determined by machine learning the correspondence between the evaluation result (X) on the first evaluation axis and the evaluation result (Y) on the second evaluation axis and the process data using an algorithm including at least one of maximum likelihood classification, a Boltzmann machine, a neural network (NN), a support vector machine (SVM), a Bayesian network, sparse regression, a decision tree, a statistical estimation using random forest, a Kalman filter, an autoregression, boosting, reinforcement learning and deep learning.

[0066] The combustion state determination unit 12e may correct the combustion state determination result according to process data obtained from various sensors (not shown) installed in the facility and / or the amount of calculation obtained by calculation from the process data. For example, if the combustion state determination result is "low-quality waste combustion" and the furnace outlet temperature or evaporation amount difference value PV-SV at that time satisfies a predetermined condition, the combustion state determination result may be corrected to "good combustion (normal)."

[0067] The combustion state determination unit 12e may display an alert on a display (not shown) or issue an audible alert in response to the determination result of the combustion state, such as a warning that it is difficult to keep the performance management index value within a predetermined range. The alarm may be issued by means of a vibration, light, etc.

[0068] The instruction unit 12f transmits an operation instruction to the crane control device 50 and / or the combustion control device 20 based on the judgment result of the combustion state judgment unit 12e. For example, the instruction unit 12f transmits an operation instruction defined in advance for each zone on the combustion state judgment map to the crane control device 50 and / or the combustion control device 20 based on the judgment result of the combustion state judgment unit 12e. Specifically, for example, the instruction unit 12f transmits an operation instruction suitable for the current combustion state (increasing or decreasing the combustion temperature, increasing or decreasing the combustion time, increasing or decreasing the air amount, and increasing or decreasing the amount of garbage sent) to the combustion control device 20. As an example, when the current combustion state is "over-combustion", the instruction unit 12f may transmit an operation instruction such as decreasing the air amount or decreasing the amount of garbage sent to the combustion control device 20. As another example, when the current combustion state is "thick garbage layer combustion", the instruction unit 12f may transmit an operation instruction such as decreasing the amount of garbage sent to the combustion control device 20 in order to thin the garbage layer. As another example, when the current combustion state is "thin waste layer combustion", the instruction unit 12f may transmit to the combustion control device 20 operation instructions such as decreasing the amount of air or decreasing the amount of waste fed in order to thicken the waste layer. As another example, when the current combustion state is "out of waste", the instruction unit 12f may transmit to the combustion control device 20 operation instructions such as decreasing the amount of air or increasing the amount of waste fed in order to increase the amount of waste fed into the incinerator. As another example, when the current combustion state is "low-quality waste combustion", the instruction unit 12f may transmit to the combustion control device 20 operation instructions such as increasing the amount of air or decreasing the amount of waste fed in order to thoroughly burn the existing waste.

[0069] Next, an example of an information processing method by the information processing device 10 having such a configuration will be described. Fig. 3 is a flowchart showing an example of the information processing method.

[0070] As shown in Fig. 3, first, before the incineration facility 1 is operated, the first teacher data generating unit 12b1 generates first teacher data 13c1 by linking at least one classification label in a first evaluation axis that is an element for determining the combustion state, which is artificially assigned by the operator based on experience, to past infrared imaging data (first imaging data 13b1) of the incinerator 6 captured by the infrared imaging device 71. The second teacher data generating unit 12b2 generates second teacher data 13c2 by linking at least one classification label in a second evaluation axis that is an element for determining the combustion state, which is artificially assigned by the operator based on experience, to past visible light imaging data (second imaging data 13b2) of the incinerator 6 captured by the visible light imaging device 72 (step S11).

[0071] Next, the first model construction unit 13c1 generates a first trained model by performing machine learning on the first teacher data 13b1 generated by the first teacher data generation unit 12b1 using the first algorithm 13a1. Also, the second model construction unit 13c2 generates a second trained model by performing machine learning on the second teacher data 13b2 generated by the second teacher data generation unit 12b2 using the second algorithm 13a2 (step S12).

[0072] Next, during operation of the incineration facility 1, the first imaging data acquisition unit 12a1 acquires new infrared imaging data of the inside of the incinerator 6 captured by the infrared imaging device 71 as first imaging data 13b1, and the second imaging data acquisition unit 12a2 acquires visible light imaging data of the inside of the incinerator 6 captured by the visible light imaging device 72 as second imaging data 13b2 (step S13).

[0073] Next, the first image analysis unit 13d1 receives new first imaging data (infrared imaging data) of the inside of the incinerator 6 acquired by the first imaging data acquisition unit 13a1 as input, and acquires an evaluation result on the first evaluation axis (for example, the amount of material to be burned) as output data using the first trained model generated by the first model construction unit 13c1. Also, the second image analysis unit 13d2 receives new second imaging data (possibly The second model construction unit 13c2 uses the second trained model generated by the second model construction unit 13c2 with the visual light imaging data as input, and obtains an evaluation result on a second evaluation axis (e.g., a flame state) as output data (step S14).

[0074] Then, the combustion state determination unit 12e determines the current combustion state within the incinerator 6 based on the evaluation result in the first evaluation axis by the first image analysis unit 13d1 and the evaluation result in the second evaluation axis by the second image analysis unit 13d2 (step 15).

[0075] In step S15, the combustion state determination unit 12e may determine the current combustion state in the incinerator 6 by mapping a pair (X, Y) consisting of the evaluation result (X) on the first evaluation axis and the evaluation result (Y) on the second evaluation axis onto a predetermined combustion state determination map 13d in which the first evaluation axis is the X coordinate axis and the second evaluation axis is the Y coordinate axis (see FIG. 4).

[0076] Thereafter, the instruction unit 12f transmits an operation instruction to the crane control device 50 and / or the combustion control device 20 based on the determination result of the combustion state determination unit 12e (step S16).

[0077] According to the present embodiment as described above, by appropriately selecting the imaging wavelength, the infrared imaging device 71 can obtain, as infrared imaging data (first imaging data) of the inside of the incinerator 6, an image that includes an image from the upstream side of the incinerator 6 to the actual burning material, with the influence of the flame removed. Therefore, by using the infrared imaging data of the inside of the incinerator 6 to perform an evaluation in at least one first evaluation axis that is an element for determining the combustion state, and by determining the combustion state based on the evaluation result, it is possible to classify, predict, and estimate the combustion state inside the incinerator 6 more accurately than when the combustion state is classified, predicted, and estimated or the process value is predicted and estimated only from the combustion image, which can grasp only the flame condition.

[0078] Moreover, according to this embodiment, by judging the combustion state based on the evaluation results on each of the first evaluation axis X and the second evaluation axis Y, the combustion state in the incinerator 6 can be classified, predicted, and estimated with higher accuracy than when the combustion state is judged based on the evaluation result on one evaluation axis. Moreover, by judging the combustion state by mapping the evaluation results on each of the first evaluation axis X and the second evaluation axis Y on the combustion state judgment map 13d, it is possible to intuitively grasp the relationship between the evaluation results on each of the first evaluation axis X and the second evaluation axis Y and the combustion state, which is the judgment result, and it is also possible to quickly judge the combustion state.

[0079] Second embodiment Next, a second embodiment will be described with reference to Figures 5 to 7. Figure 5 is a schematic diagram showing the configuration of an incineration facility 1 according to the second embodiment.

[0080] As shown in FIG. 5, the incineration facility 1 according to the second embodiment differs from the first embodiment only in that the visible light imaging device 72 for imaging the inside of the incinerator 6 is omitted, and the other configurations are the same as those of the first embodiment.

[0081] 6 is a block diagram showing the configuration of an information processing device 10 according to the second embodiment. The information processing device 10 is made up of one or more computers.

[0082] 6, the information processing device 10 includes a communication unit 11, a control unit 12, and a storage unit 13. Each unit is connected to each other via a bus or a network so as to be able to communicate with each other.

[0083] The communication unit 11 is a communication interface between the infrared imaging device 71, the crane control device 50, the combustion control device 20, and the information processing device 10. It transmits and receives information to and from the processing device 10 .

[0084] The storage unit 13 is a non-volatile data storage such as a hard disk or a flash memory. The storage unit 13 stores various data handled by the control unit 12. The storage unit 12 also stores a first algorithm 13a1 used for machine learning by a first model construction unit 12c1 described later, first imaging data 13b1 acquired by a first imaging data acquisition unit 12a1, first teacher data 13c1 generated by a first teacher data generation unit 12b1, and a combustion state determination map 13d used by a combustion state determination unit 12e. Details of each piece of information 13a1 to 13d will be described later.

[0085] The control unit 12 is a control means for performing various processes of the information processing device 10. As shown in Fig. 6, the control unit 11 has a first imaging data acquisition unit 12a1, a first teacher data generation unit 12b1, a first model construction unit 12c1, a first image analysis unit 12d1, a combustion state determination unit 12e, an instruction unit 12f, and a process data acquisition unit 12g. Each of these units may be realized by a processor in the information processing device 10 executing a predetermined program, or may be implemented by hardware.

[0086] Among these, the first imaging data acquisition unit 12a1, the process data acquisition unit 12g, and the instruction unit 12f are configured similarly to those in the first embodiment, and therefore description thereof will be omitted.

[0087] The first teacher data generating unit 12b1 generates the first teacher data 13c1 by linking classification labels in each of two or more first evaluation axes, which are factors for judging the combustion state and which are artificially assigned by the operator based on empirical rules, to the first imaging data 13b1. The first teacher data 13c1 is stored in the storage unit 13. Here, the classification label may be absolute classification information in the first evaluation axis (classification determined in relation to a predetermined absolute standard (threshold)) or a relative order in the first evaluation axis among a plurality of infrared imaging data (relative order relationship within a group consisting of a plurality of infrared imaging data). The first evaluation axis may include two or more of the flame state, the amount of combusted material, the quality of the combusted material, the type of the combusted material, the temperature of the combusted material, the amount of combustion gas generated (CO, etc.), and the temperature of the wall of the incinerator. The flame state can be judged from the amount of gaseous fluctuations reflected in the first imaging data 13b1 (infrared imaging data).

[0088] As an example, when the flame state is one of the first evaluation axes, the classification label may be good, normal, or bad (absolute information) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the flame state for a plurality of first imaging data (relative information). As another example, when the amount of combustible material is one of the first evaluation axes, the classification label may be large, normal, or small (absolute information) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the amount of combustible material for a plurality of first imaging data (relative information). As another example, when the quality of combustible material is one of the first evaluation axes, the classification label may be normal garbage, high-quality garbage (i.e., high-calorie garbage), or low-quality garbage (i.e., low-calorie garbage) (absolute information) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the quality of combustible material for a plurality of first imaging data (relative information). As another example, if the type of combusted material is used as a first evaluation axis, the classification label may be garbage bags, unbroken garbage bags, pruning branches, or futons (absolute information) (the number of label types may be increased). As another example, if the amount of combustion gas generated (CO, etc.) is used as a first evaluation axis, the classification label may be high, normal, or low (absolute information) (the number of label types may be increased), or the amount of combustion gas generated (CO, etc.) may be ranked according to magnitude for a plurality of first imaging data (relative information). As another example, if the temperature of the incinerator wall is used as a first evaluation axis, the classification label may be high, normal, or low (the number of label types may be increased), or the amount of combustion gas generated (CO, etc.) may be ranked according to magnitude for a plurality of first imaging data (relative information). (relative information) may also be used.

[0089] The first teacher data generating unit 12b1 may generate the first teacher data 13c1 by linking classification labels in each of two or more first evaluation axes artificially assigned by the operator based on empirical rules to a combination of the first imaging data 13b1 and process data obtained from various sensors (not shown) installed in the incineration facility 1 and / or a calculation amount obtained by calculation from the process data. Here, the process data is data that takes into account the time lag between the imaging time of the first imaging data and the response time of the sensor. The time lag may be appropriately determined based on the response speed of the sensor, the installation position of the sensor in the facility, an experiment, a simulation, and the operator's empirical rules.

[0090] The first imaging data 13b1 may be video data within 60 seconds or video data within 30 seconds. According to the knowledge of the present inventors, the combustion state inside the incinerator 6 changes every 5 to 10 seconds. Therefore, by using video data within 60 seconds (or within 30 seconds) as one segment as the first imaging data 13b1, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0091] The first imaging data 13b1 may be video data of 5 seconds or more, or may be video data of 7 seconds or more. The combustion state inside the incinerator 6 changes every 5 to 10 seconds, so by using video data of, for example, 5 seconds or more (or 7 seconds or more) as the first imaging data 13b1 as one segment, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0092] The first model construction unit 13c1 generates a first trained model by performing machine learning on the first teacher data 13b1 generated by the first teacher data generation unit 12b1 using a first algorithm 13a1. The first algorithm 13a1 used for the machine learning may include at least one of a maximum likelihood classification method, a Boltzmann machine, a neural network (NN), a support vector machine (SVM), a Bayesian network, a sparse regression, a decision tree, a statistical estimation using a random forest, boosting, reinforcement learning, and deep learning.

[0093] The first image analysis unit 13d1 receives new first imaging data (infrared imaging data) of the inside of the incinerator 6 acquired by the first imaging data acquisition unit 13a1 as input, and acquires evaluation results on two or more first evaluation axes (for example, flame state and amount of material to be burned) as output data using the first trained model generated by the first model construction unit 13c1. The first image analysis unit 13d1 may normalize (score) the evaluation results on two or more first evaluation axes to a numerical range of, for example, 0 to 100, and acquire a numerical value (score) within the range as output data.

[0094] The combustion state determination unit 12e determines the current combustion state in the incinerator 6 based on the evaluation results (scores) in each of the two or more first evaluation axes by the first image analysis unit 13d1. The determination result of the combustion state may be a label indicating the characteristics of the combustion state (excessive combustion, thick garbage layer combustion, thin garbage layer combustion, dead garbage, low-quality garbage combustion, etc.), or may be a numerically modified version of the label.

[0095] The combustion state determination unit 12e may determine the current combustion state within the incinerator 6 by mapping a set of evaluation results for each of two or more first evaluation axes onto a predetermined combustion state determination map 13d having the two or more first evaluation axes as coordinate axes.

[0096] FIG. 4 is a diagram showing an example of the combustion state determination map 13d. In the map 13d, an XY coordinate plane with the amount of material to be burned as the X-coordinate axis and the flame state as the Y-coordinate axis is divided into a plurality of regions (six regions in the illustrated example: a garbage dead zone, an over-burned zone, a thin garbage layer burning zone, a good combustion (normal) zone, a thick garbage layer burning zone, and a low-quality garbage burning zone). The combustion state determination unit 12e maps a set (X, Y) of evaluation results on each first evaluation axis when the amount of material to be burned and the flame state are set as two different first evaluation axes on this combustion state determination map 13d. For example, as shown in FIG. 4, when a point P indicating a set (X, Y) of an evaluation result (X) when the amount of material to be burned is set as the first evaluation axis and an evaluation result (Y) when the flame state is set as the first evaluation axis is mapped within the good combustion (normal) zone, the combustion state determination unit 12e determines that the current combustion state is "good combustion (normal)".

[0097] The combustion state determination unit 12e may correct the combustion state determination result according to process data obtained from various sensors (not shown) installed in the facility and / or the amount of calculation obtained by calculation from the process data. For example, if the combustion state determination result is "low-quality waste combustion" and the furnace outlet temperature or evaporation amount difference value PV-SV at that time satisfies a predetermined condition, the combustion state determination result may be corrected to "good combustion (normal)."

[0098] Depending on the combustion state judgment result, the combustion state judgment unit 12e may display an alert on a display (not shown) indicating that it is difficult to maintain the performance management index value within a specified range, or may issue an alert by sound, vibration, light, etc.

[0099] Next, an example of an information processing method by the information processing device 10 configured as above will be described below. Fig. 7 is a flowchart showing an example of the information processing method.

[0100] As shown in FIG. 7, first, before the incineration facility 1 is operated, the first teacher data generation unit 12b1 generates first teacher data 13c1 by linking classification labels in two or more first evaluation axes, which are factors for determining the combustion state and which have been artificially assigned by the operator based on empirical rules, to past infrared imaging data (first imaging data 13b1) of the inside of the incinerator 6 captured by the infrared imaging device 71 (step S21).

[0101] Next, the first model construction unit 13c1 generates a first trained model by machine learning the first teacher data 13b1 generated by the first teacher data generation unit 12b1 using the first algorithm 13a1 (step S22).

[0102] Next, while the incineration facility 1 is in operation, the first imaging data acquisition unit 12a1 acquires new infrared imaging data of the inside of the incinerator 6 captured by the infrared imaging device 71 as first imaging data 13b1 (Step S23).

[0103] Next, the first image analysis unit 13d1 uses as input new first imaging data (infrared imaging data) of inside the incinerator 6 acquired by the first imaging data acquisition unit 13a1, and acquires evaluation results for each of two or more first evaluation axes (e.g., the amount of material to be burned and the flame state) as output data using the first trained model generated by the first model construction unit 13c1 (step S24).

[0104] Then, the combustion state determination unit 12e determines the current combustion state inside the incinerator 6 based on the evaluation result in the first evaluation axis by the first image analysis unit 13d1 (step 25).

[0105] In step S25, the combustion state determination unit 12e converts a set of evaluation results for each of the two or more first evaluation axes into a predetermined combustion state determination method using the two or more first evaluation axes as coordinate axes. The current combustion conditions within the incinerator 6 may be determined by mapping the combustion conditions onto a constant map 13d (see FIG. 4).

[0106] Thereafter, the instruction unit 12f transmits an operation instruction to the crane control device 50 and / or the combustion control device 20 based on the determination result of the combustion state determination unit 12e (step S16).

[0107] According to the present embodiment as described above, by appropriately selecting the imaging wavelength, the infrared imaging device 71 can obtain, as infrared imaging data (first imaging data) of the inside of the incinerator 6, images that include images of the actual burning material from the upstream side of the incinerator 6 with the influence of the flame removed. Therefore, by using the infrared imaging data of the inside of the incinerator 6 to perform evaluation on two or more first evaluation axes that are elements for determining the combustion state, and by determining the combustion state based on the evaluation results, it is possible to classify, predict, and estimate the combustion state inside the incinerator 6 more accurately than when the combustion state is classified, predicted, and estimated or the process value is predicted and estimated only from the combustion image, which can grasp only the flame state.

[0108] Moreover, according to this embodiment, by judging the combustion state based on the evaluation results in each of two or more first evaluation axes, the combustion state in the incinerator 6 can be classified, predicted, and estimated with higher accuracy than when the combustion state is judged based on the evaluation result in one evaluation axis. Moreover, by judging the combustion state by mapping the evaluation results in each of two or more first evaluation axes on the combustion state judgment map 13d, it is possible to intuitively grasp the relationship between the evaluation results in each of two or more first evaluation axes and the combustion state, which is the judgment result, and it is also possible to quickly judge the combustion state.

[0109] (Third embodiment) Next, a third embodiment will be described with reference to Figures 8 to 10. Figure 8 is a schematic diagram showing the configuration of an incineration facility 1 according to the third embodiment.

[0110] As shown in FIG. 8, the incineration facility 1 of the third embodiment differs from the first embodiment only in that the infrared imaging device 71 that captures images inside the incinerator 6 is omitted, and the other configurations are the same as those of the first embodiment.

[0111] 9 is a block diagram showing the configuration of an information processing device 10 according to the third embodiment. The information processing device 10 is made up of one or more computers.

[0112] 9, the information processing device 10 includes a communication unit 11, a control unit 12, and a storage unit 13. Each unit is connected to each other via a bus or a network so as to be able to communicate with each other.

[0113] Of these, the communication unit 11 is a communication interface between each of the devices, the visible light imaging device 72, the crane control device 50, and the combustion control device 20, and the information processing device 10. The communication unit 11 transmits and receives information between each of the devices, the visible light imaging device 72, the crane control device 50, and the combustion control device 20, and the information processing device 10.

[0114] The storage unit 13 is a non-volatile data storage such as a hard disk or a flash memory. The storage unit 13 stores various data handled by the control unit 12. The storage unit 12 also stores a second algorithm 13a2 used for machine learning by a second model construction unit 12c2 described later, second imaging data 13b2 acquired by the second imaging data acquisition unit 12a2, second teacher data 13c2 generated by the second teacher data generation unit 12b2, and a combustion state determination map 13d used by the combustion state determination unit 12e. Details of each piece of information 13a2 to 13d will be described later.

[0115] The control unit 12 is a control means for performing various processes of the information processing device 10. As shown in Fig. 9, the control unit 11 has a second imaging data acquisition unit 12a2, a second teacher data generation unit 12b2, a second model construction unit 12c2, a second image analysis unit 12d2, a combustion state determination unit 12e, an instruction unit 12f, and a process data acquisition unit 12g. Each of these units may be realized by a processor in the information processing device 10 executing a predetermined program, or may be implemented by hardware.

[0116] Among these, the second imaging data acquisition unit 12a2, the process data acquisition unit 12g, and the instruction unit 12f are configured similarly to those in the first embodiment, and therefore description thereof will be omitted.

[0117] The second teacher data generating unit 12b2 generates the second teacher data 13c2 by linking the classification labels in each of two or more second evaluation axes, which are factors for judging the combustion state and are artificially assigned by the operator based on empirical rules, to the second imaging data 13b2. The second teacher data 13c2 is stored in the storage unit 13. Here, the classification labels may be absolute classification information in the second evaluation axis (classification determined in relation to a predetermined absolute standard (threshold)) or a relative order in the second evaluation axis among a plurality of visible light imaging data (relative order relationship within a group consisting of a plurality of visible light imaging data). The second evaluation axis may include two or more of the flame state, the position of the combustion completion point, the shape of the combustion completion point, the amount of the combusted material, the quality of the combusted material, the type of the combusted material, the amount of unburned material, and the amount of incineration ash.

[0118] As an example, when the flame state is one of the second evaluation axes, the classification label may be good, normal, or bad (absolute information) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the flame state for a plurality of second imaging data (relative information). As another example, when the position of the combustion completion point (burnout point) is one of the second evaluation axes, the classification label may be near, slightly near, normal, slightly far, or far (the number of types of labels may be increased), or may be an order of the distance of the position of the combustion completion point for a plurality of second imaging data. As another example, when the shape of the combustion completion point is one of the second evaluation axes, the classification label may be good, normal, or bad (the number of types of labels may be increased), or may be an order of superiority or inferiority of the shape of the combustion completion point for a plurality of second imaging data. As another example, when the amount of combustible materials is set as one second evaluation axis, the classification label may be large, normal, or small (absolute information) (the number of types of labels may be increased), or may be an order of the amount of combustible materials for multiple second imaging data (relative information). As another example, when the quality of combustible materials is set as one second evaluation axis, the classification label may be normal garbage, high-quality garbage (i.e., high-calorie garbage), or low-quality garbage (i.e., low-calorie garbage) (the number of types of labels may be increased), or may be an order of superiority or inferiority of the quality of combustible materials for multiple second imaging data. As another example, when the type of combustible materials is set as one second evaluation axis, the classification label may be garbage bag, unbroken garbage, pruning branch, or futon (the number of types of labels may be increased). As another example, when the amount of unburnt materials is set as the second evaluation axis, the classification label may be large, normal, or small (the number of types of labels may be increased), or may be an order of superiority or inferiority of the amount of unburnt materials for multiple second imaging data. As another example, if the amount of incineration ash is used as one second evaluation axis, the classification label may be large, normal, or small (the number of label types may be increased), or the amount of incineration ash may be ranked for multiple second imaging data.

[0119] The second teacher data generating unit 12b2 may generate the second teacher data 13c2 by linking classification labels in each of two or more second evaluation axes artificially assigned by the operator based on empirical rules to a combination of the second imaging data 13b2 and process data obtained from various sensors (not shown) installed in the incineration facility 1 and / or a calculation amount obtained by calculation from the process data. Here, the process data is generated by the first imaging data. The time lag may be determined appropriately based on the response speed of the sensor, the installation position of the sensor in the facility, experiments, simulations, and the operator's experience.

[0120] The second imaging data 13b2 may be video data within 60 seconds or video data within 30 seconds. According to the knowledge of the present inventors, the combustion state inside the incinerator 6 changes every 5 to 10 seconds. Therefore, by using video data within 60 seconds (or within 30 seconds) as one segment as the second imaging data 13b1, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0121] The second imaging data 13b2 may be video data of 5 seconds or more, or may be video data of 7 seconds or more. The combustion state inside the incinerator 6 changes every 5 to 10 seconds, so by using video data of, for example, 5 seconds or more (or 7 seconds or more) as the second imaging data 13b2 as one segment, it becomes possible to classify, predict, and estimate the combustion state inside the incinerator 6 with higher accuracy.

[0122] The second model construction unit 13c2 generates a second trained model by performing machine learning on the second teacher data 13b2 generated by the second teacher data generation unit 12b2 using the second algorithm 13a2. The second algorithm 13a2 used for the machine learning may include at least one of a maximum likelihood classification method, a Boltzmann machine, a neural network (NN), a support vector machine (SVM), a Bayesian network, a sparse regression, a decision tree, a statistical estimation using a random forest, boosting, reinforcement learning, and deep learning.

[0123] The second image analysis unit 13d2 receives new second imaging data (visible light imaging data) of the inside of the incinerator 6 acquired by the second imaging data acquisition unit 13a2 as input, and acquires evaluation results on two or more second evaluation axes (for example, flame state and amount of material to be burned) as output data using the second trained model generated by the second model construction unit 13c2. The second image analysis unit 13d2 may normalize (score) the evaluation results on two or more second evaluation axes to a numerical range of, for example, 0 to 100, and acquire a numerical value (score) within the range as output data.

[0124] The combustion state determination unit 12e determines the current combustion state in the incinerator 6 based on the evaluation results (scores) in each of the two or more second evaluation axes by the second image analysis unit 13d2. The combustion state determination result may be a label indicating the characteristics of the combustion state (excessive combustion, thick garbage layer combustion, thin garbage layer combustion, dead garbage, low-quality garbage combustion, etc.), or may be a numerically modified version of the label.

[0125] The combustion state determination unit 12e may determine the current combustion state within the incinerator 6 by mapping a set of evaluation results for each of two or more second evaluation axes onto a predetermined combustion state determination map 13d having the two or more second evaluation axes as coordinate axes.

[0126] FIG. 4 is a diagram showing an example of the combustion state determination map 13d. In the combustion state determination map 13d shown in FIG. 4, an XY coordinate plane with the amount of material to be burned as the X coordinate axis and the flame state as the Y coordinate axis is divided into a plurality of regions (in the illustrated example, six regions are the dead garbage zone, the over-burned zone, the thin garbage layer burning zone, the good combustion (normal) zone, the thick garbage layer burning zone, and the low-quality garbage burning zone). The combustion state determination unit 12e maps a set (X, Y) of evaluation results on each second evaluation axis when the amount of material to be burned and the flame state are set as two different second evaluation axes on this combustion state determination map 13d. For example, as shown in FIG. 4, the evaluation result (X) when the amount of material to be burned is set as the second evaluation axis and the evaluation result (Y) when the flame state is set as the second evaluation axis are set as the Y coordinate axis. If a point P indicating a pair (X, Y) consisting of the above is mapped within the good combustion (normal) zone, the combustion state determination unit 12e determines that the current combustion state is “good combustion (normal)”.

[0127] The combustion state determination unit 12e may correct the combustion state determination result according to process data obtained from various sensors (not shown) installed in the facility and / or the amount of calculation obtained by calculation from the process data. For example, if the combustion state determination result is "low-quality waste combustion" and the furnace outlet temperature or evaporation amount difference value PV-SV at that time satisfies a predetermined condition, the combustion state determination result may be corrected to "good combustion (normal)."

[0128] Depending on the combustion state judgment result, the combustion state judgment unit 12e may display an alert on a display (not shown) indicating that it is difficult to maintain the performance management index value within a specified range, or may issue an alert by sound, vibration, light, etc.

[0129] Next, an example of an information processing method by the information processing device 10 having such a configuration will be described. Fig. 10 is a flowchart showing an example of the information processing method.

[0130] As shown in FIG. 10, first, before the incineration facility 1 is operated, the second teacher data generation unit 12b2 generates second teacher data 13c2 by linking classification labels in two or more second evaluation axes, which are factors for determining the combustion state and which have been artificially assigned by the operator based on empirical rules, to past visible light imaging data (second imaging data 13b2) of the inside of the incinerator 6 captured by the visible light imaging device 72 (step S31).

[0131] Next, the second model construction unit 13c2 generates a second trained model by machine learning the second teacher data 13b2 generated by the second teacher data generation unit 12b2 using the second algorithm 13a2 (step S32).

[0132] Next, while the incineration facility 1 is in operation, the second imaging data acquisition unit 12a2 acquires new visible light imaging data of the inside of the incinerator 6 captured by the visible light imaging device 72 as second imaging data 13b2 (Step S33).

[0133] Next, the second image analysis unit 13d2 uses the new second imaging data (visible light imaging data) of the incinerator 6 acquired by the second imaging data acquisition unit 13a2 as input, and acquires evaluation results for each of two or more second evaluation axes (e.g., the amount of material to be burned and the flame state) as output data using the second trained model generated by the second model construction unit 13c2 (step S34).

[0134] Then, the combustion state determination unit 12e determines the current combustion state inside the incinerator 6 based on the evaluation result in the second evaluation axis by the second image analysis unit 13d2 (step 35).

[0135] In step S35, the combustion state determination unit 12e may determine the current combustion state within the incinerator 6 by mapping a set of evaluation results for each of the two or more second evaluation axes onto a predetermined combustion state determination map 13d having the two or more second evaluation axes as coordinate axes (see Figure 4).

[0136] Thereafter, the instruction unit 12f transmits an operation instruction to the crane control device 50 and / or the combustion control device 20 based on the determination result of the combustion state determination unit 12e (step S16).

[0137] According to the present embodiment as described above, the evaluation result is evaluated based on each of two or more second evaluation axes. By judging the combustion state based on the evaluation results in one evaluation axis, the combustion state in the incinerator 6 can be classified, predicted, and estimated with higher accuracy than when the combustion state is judged based on the evaluation results in one evaluation axis. In addition, by judging the combustion state by mapping the evaluation results in each of two or more second evaluation axes onto the combustion state judgment map 13d, it is possible to intuitively grasp the relationship between the evaluation results in each of two or more second evaluation axes and the combustion state, which is the judgment result, and it is also possible to quickly judge the combustion state.

[0138] In the above-described embodiment, a part of the processing of the control unit 12 may be performed on a cloud server other than the information processing device 10, instead of the information processing device 10. A part of the storage unit 13 may be located on a cloud server other than the information processing device 10, instead of the information processing device 10.

[0139] For example, the processing of the first teacher data generating unit 12d1 and / or the second teacher data generating unit 12d2 may be executed on a cloud server to generate the first teacher data 13c1 and / or the second teacher data 13c2, or the processing of the first model constructing unit 12c1 and / or the second model constructing unit 12c2 may be executed on a cloud server to construct a trained model. In addition, the processing of the first image analysis unit 12d1 and / or the second image analysis unit 12d2 may be executed on the cloud server using the trained model constructed on the cloud server, or the information processing device 10 may download the trained model (trained parameters) from the cloud server and use it in the information processing device 10 to execute the processing of the first image analysis unit 12d1 and / or the second image analysis unit 12d2.

[0140] Although the embodiment and modified examples of the present invention have been described above by way of example, the scope of the present invention is not limited to these, and can be modified or changed according to the purpose within the scope of the claims. Furthermore, each embodiment and modified example can be appropriately combined within a range that does not cause contradiction in the processing content.

[0141] In addition, the information processing device 10 according to the embodiment of the present invention may be configured by one or more computers, and a program for realizing the information processing device 10 in one or more computers and a computer-readable recording medium on which the program is non-temporarily recorded are also covered by the present case. [Explanation of symbols]

[0142] 1. Incineration facilities 2. Boiler 3. Garbage Pit 4 Hopper 5. Crane 6. Incinerator 71 Infrared imaging device 72 Visible light imaging device 10. Information processing device 11 Communications Department 12 Control section 12a1 First imaging data acquisition unit 12a2 Second imaging data acquisition unit 12b1 First teacher data generation unit 12b2 Second teacher data generation unit 12c1 First Model Construction Section 12c2 Second Model Construction Section 12d1 1st image analysis section 12d2 2nd image analysis section 12e Combustion state determination unit 12f Instruction section 12g Process data acquisition section 13 Storage section 13a1 First algorithm 13a2 Second Algorithm 13b1 First Imaging Data 13b2 Second Imaging Data 13c1 First teacher data 13c2 Second teacher data 13d Combustion state judgment map 20 Combustion control device 21 Platform 22 Transport vehicle 50 Crane control device

Claims

1. A first image analysis unit that uses a first trained model obtained by machine learning first teacher data generated by assigning a classification label in at least one first evaluation axis, which is an element for determining the combustion state, to image data of the inside of the incinerator and performs an evaluation along the first evaluation axis using new image data of the inside of the incinerator as an input; a combustion state determination unit that determines a current combustion state based on an evaluation result on the first evaluation axis; Equipped with 2. An information processing apparatus, comprising: an information processing device, wherein the imaging data is video data of 60 seconds or less.

2. The imaging data is infrared imaging data of the inside of an incinerator captured by an infrared imaging device.

2. The information processing apparatus according to claim 1,

3. The first evaluation axis includes at least one of the amount of combusted material, the quality of the combusted material, the type of the combusted material, the temperature of the combusted material, the amount of combustion gas generated, and the temperature of the wall of the incinerator; 3. The information processing apparatus according to claim 2.

4. The imaging data is visible light imaging data of the inside of an incinerator captured by a visible light imaging device.

2. The information processing apparatus according to claim 1,

5. The first evaluation axis includes at least one of a flame state, a position of a combustion completion point, a shape of a combustion completion point, an amount of a combusted material, a quality of a combusted material, a type of a combusted material, an amount of unburned material, and an amount of incineration ash; 5. The information processing apparatus according to claim 4.

6. The imaging data is video data of 5 seconds or more.

6. The information processing device according to claim 1,

7. The classification label is at least one of a label indicating which of a plurality of predetermined classification items the image data corresponds to and a relative order among a plurality of image data.

7. The information processing apparatus according to claim 1,

8. The first image analysis unit performs an evaluation on the first evaluation axis by inputting a combination of new image data in the incinerator and new process data and / or a calculation amount obtained by calculation from the process data, using a first trained model obtained by machine learning first teacher data generated by assigning a classification label on the first evaluation axis to a combination of image data in the incinerator and process data obtained from a sensor installed in the facility and / or a calculation amount obtained by calculation from the process data, 8. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

9. the process data is data taking into consideration a time lag between an imaging time of the imaging data and a response time of the sensor, The time lag is determined based on at least one of a response speed of the sensor, an installation position of the sensor in a facility, an experiment, a simulation, and an operator's empirical rule.

9. The information processing apparatus according to claim 8,

10. The first image analysis unit uses a first trained model obtained by machine learning first teacher data generated by assigning classification labels in each of the two or more first evaluation axes that are elements for determining the combustion state to the image data inside the incinerator, and performs evaluation on each of the two or more first evaluation axes using new image data inside the incinerator as input, the combustion state determination unit determines a current combustion state by mapping the evaluation results in each of the two or more first evaluation axes onto a predetermined combustion state determination map having the two or more first evaluation axes as coordinate axes.

10. The information processing device according to claim 1,

11. A second image analysis unit is further provided that uses a second trained model obtained by machine learning second teacher data generated by adding a classification label in at least one second evaluation axis, which is an element for determining the combustion state, to visible light imaging data of the inside of the incinerator captured by a visible light imaging device, and performs an evaluation on the second evaluation axis using new visible light imaging data of the inside of the incinerator as an input, the combustion state determination unit determines a current combustion state by mapping the evaluation results on each of the first evaluation axis and the second evaluation axis onto a predetermined combustion state determination map having the first evaluation axis and the second evaluation axis as coordinate axes. The information processing apparatus according to any one of claims 2, 3 and 6 to 10 which cites claim 2.

12. The second evaluation axis includes at least one of the following: a flame state, a position of a combustion completion point, a shape of a combustion completion point, an amount of combusted material, a quality of combusted material, a type of combusted material, an amount of unburned material, and an amount of incineration ash; 12. The information processing apparatus according to claim 11 .

13. The combustion state determination unit corrects the determination result of the combustion state in accordance with process data obtained from a sensor installed in the facility and / or a calculation amount obtained by calculation from the process data.

13. The information processing device according to claim 1,

14. The combustion state determination unit displays or issues an alert depending on the combustion state determination result.

14. The information processing device according to claim 1,

15. The combustion control device further includes an instruction unit that transmits an operation instruction to a crane control device and / or a combustion control device based on a judgment result of the combustion state judgment unit.

15. The information processing device according to claim 1,

16. The algorithm used for the machine learning includes at least one of maximum likelihood classification, Boltzmann machine, neural network (NN), support vector machine (SVM), Bayesian network, sparse regression, decision tree, statistical inference using random forest, boosting, reinforcement learning, and deep learning; 16. The information processing device according to claim 1,

17. The apparatus further includes a model construction unit that generates the first trained model by machine learning first teacher data generated by assigning a classification label in at least one first evaluation axis that is an element for determining the combustion state to image data inside the incinerator.

17. The information processing apparatus according to claim 1,

18. An information processing device according to claim 15; the crane control device that controls a crane that mixes or transports waste based on an operation instruction transmitted from the information processing device, and / or the combustion control device that controls the combustion of waste in an incinerator; A system comprising:

19. 1. A computer-implemented information processing method, comprising: A step of evaluating new image data of the incinerator along the first evaluation axis by using a first trained model obtained by machine learning first teacher data generated by assigning a classification label along at least one first evaluation axis that is an element for determining the combustion state to the image data of the incinerator; and determining a current combustion state based on an evaluation result on the first evaluation axis; The imaging data is video data of 60 seconds or less.

23. An information processing method comprising:

20. On the computer, A step of evaluating new image data of the incinerator along the first evaluation axis by using a first trained model obtained by machine learning first teacher data generated by assigning a classification label along at least one first evaluation axis that is an element for determining the combustion state to the image data of the incinerator; and determining a current combustion state based on an evaluation result on the first evaluation axis; Run the command, The imaging data is video data of 60 seconds or less; An information processing program characterized by:

Images