CN118159776A

CN118159776A - Control device

Info

Publication number: CN118159776A
Application number: CN202280068548.2A
Authority: CN
Inventors: 岩下信治; 高木博幸; 濑户口稔彦; 今田润司; 滑泽幸司; 林庆一; 江草知通
Original assignee: Mitsubishi Heavy Industries Environmental and Chemical Engineering Co Ltd
Current assignee: Mitsubishi Heavy Industries Environmental and Chemical Engineering Co Ltd
Priority date: 2021-10-15
Filing date: 2022-09-30
Publication date: 2024-06-07
Also published as: KR20240073073A; JP2023059470A; JP7296436B2; TW202323728A; WO2023063107A1

Abstract

The control device of the present disclosure includes an information acquisition unit, a vapor flow rate prediction unit, and a control unit. The information acquisition unit acquires information on an object to be incinerated before being supplied to a processing space in the incineration equipment. The steam flow rate prediction unit predicts a main steam flow rate generated in the boiler of the incineration facility based on the prediction information including the information acquired by the information acquisition unit. The control unit performs combustion control based on the main steam flow rate predicted by the steam flow rate prediction unit.

Description

Control device

Technical Field

The present disclosure relates to a control device.

The present application claims priority from japanese patent application No. 2021-169507 filed 10/15 in 2021, the contents of which are incorporated herein by reference.

Background

Patent document 1 discloses a combustion control method that obtains information indicating the current combustion state in real time, estimates the amount of combustion heat and the amount of boiler evaporation based on the information, and thereby enables combustion control of waste without time delay. The combustion control method obtains carbon, hydrogen and moisture in the waste directly related to the heat generation amount of the waste to be the fuel from the composition of the exhaust gas immediately after combustion obtained in real time, and calculates the oxygen consumption, the combustion heat, the latent heat and the waste amount (treatment amount) based on the obtained results.

Patent document 2 discloses an evaporation amount control method including: a plurality of imaging devices having different viewpoints are used to acquire images of flames reaching the secondary combustion region from the primary combustion region, and an image synthesis process is performed on the acquired plurality of images from different viewpoints, thereby producing a three-dimensional image including flames in the secondary combustion region. In this evaporation amount control method, the three-dimensional image is analyzed, and a temporal change in flame moving speed along the direction of the flow path of the combustion gas generated in the primary combustion or the secondary combustion is calculated, thereby obtaining an index of the heat currently generated in the combustion chamber.

Patent document 3 discloses a combustion control method including: a plurality of infrared cameras are used to observe at least waste deposited in a drying section and a combustion section through a filter that selectively transmits light of a wavelength that does not radiate flame, a plurality of thermal images having different viewpoints are obtained, and a three-dimensional thermal image is created based on the plurality of thermal images. The combustion control method calculates thickness passing information indicating how the thickness of the waste varies in time series based on the three-dimensional thermal image, determines a combustion correction coefficient based on the variation of the volume flow rate of the waste from the past to the current time point, and calculates an index of heat generated from the waste.

Prior art literature

Patent literature

Patent document 1: japanese patent laid-open No. 2017-096517

Patent document 2: japanese patent application laid-open No. 2019-219108

Patent document 3: japanese patent laid-open No. 2021-067381

Disclosure of Invention

Problems to be solved by the invention

However, the main vapor flow rate may vary greatly depending on the state of the object to be incinerated. Therefore, in the techniques described in patent documents 1 to 3, it may be difficult to perform combustion control based on a highly accurate predicted value of the main vapor flow rate.

The present disclosure has been made to solve the above-described problems, and an object thereof is to provide a control device capable of performing combustion control based on a highly accurate predicted value of a main vapor flow rate.

Means for solving the problems

In order to solve the above problems, the control device of the present disclosure includes an information acquisition unit, a vapor flow rate prediction unit, and a control unit. The information acquisition unit acquires information on an object to be incinerated before being supplied to a processing space in the incineration equipment. The steam flow rate prediction unit predicts a main steam flow rate generated in the boiler of the incineration facility based on the prediction information including the information acquired by the information acquisition unit. The control unit performs combustion control based on the main steam flow rate predicted by the steam flow rate prediction unit.

Effects of the invention

According to the control device of the present disclosure, combustion control can be performed based on a highly accurate predicted value of the main vapor flow rate.

Drawings

Fig. 1 is a schematic configuration diagram showing the whole of the incineration facility according to the embodiment of the present disclosure.

Fig. 2 is a block diagram showing a functional structure of a combustion apparatus according to an embodiment of the present disclosure.

Fig. 3 is a block diagram showing a functional configuration of a data conversion unit according to an embodiment of the present disclosure.

Fig. 4 is a graph showing a correlation between an estimated value of the amount of generated dust based on the detection result of the moisture meter according to the embodiment of the present disclosure and the amount of generated dust confirmed in the actual machine.

Fig. 5 is a diagram showing an example of processing performed by the first feature amount extraction unit according to the embodiment of the present disclosure.

Fig. 6 is a diagram showing an example of processing performed by the image conversion unit according to the embodiment of the present disclosure.

Fig. 7 is a diagram showing an example of processing performed by the garbage layer height detecting unit according to the embodiment of the present disclosure.

Fig. 8 is a diagram showing an example of a correlation between each input information and the main vapor flow rate according to the embodiment of the present disclosure.

Fig. 9 is a diagram showing an example of time delay setting values for each input information according to the embodiment of the present disclosure.

Fig. 10 is a diagram showing an example of the evaluation process performed by the prediction model determination unit according to the embodiment of the present disclosure.

Fig. 11 is a diagram showing an example of control contents by the control unit according to the embodiment of the present disclosure.

Fig. 12 is a flowchart showing a flow of a prediction model creation process according to an embodiment of the present disclosure.

Fig. 13 is a flowchart showing a flow of processing at an operation stage of the combustion apparatus according to the embodiment of the present disclosure.

Fig. 14 is a diagram showing an example of a comparison result between a predicted value and an actual measured value of the main vapor flow rate according to the embodiment of the present disclosure.

Fig. 15 is a hardware configuration diagram showing a configuration of a computer according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, a control device according to an embodiment of the present disclosure will be described with reference to the drawings. In the following description, the same reference numerals are given to structures having the same or similar functions. In addition, a repetitive description of these structures may be omitted. In this disclosure, "based on XX" means "based at least on XX" and may include cases based on other elements in addition to XX. The term "based on XX" is not limited to the case where XX is directly used, and may include the case where XX is calculated and processed. In the present disclosure, "XX or YY" is not limited to any one of XX and YY, and may include both XX and YY. The same applies to the case where three or more elements are selected. "XX" and "YY" are arbitrary elements (e.g., arbitrary beliefs).

(Embodiment)

<1. Integral Structure of incineration plant >

Fig. 1 is a schematic configuration diagram showing the overall configuration of the incineration facility SF according to the embodiment. The incineration facility SF is, for example, a grate furnace that uses municipal waste, industrial waste, biomass, or the like as the incineration target G. Hereinafter, for convenience of explanation, the "burned object G" will be referred to as "refuse G". The incineration device SF is not limited to the grate furnace, and may be another type of incineration device. In the present embodiment, the incineration facility SF includes, for example, a crane 1, an incinerator 2, a waste heat recovery boiler 3, a cooling tower 4, a dust collection device 5, a flue 6, a chimney 7, and a control device 100.

The crane 1 conveys the garbage G stored in the garbage pit to a hopper 11 of the incinerator 2 described later, and inputs the garbage G into the hopper 11. The crane 1 includes a grip portion 1a for gripping the refuse G and a weight sensor 1b provided to the grip portion 1 a. The weight sensor 1b is, for example, a load cell. The weight sensor 1b detects the weight of the garbage G gripped by the grip portion 1a in a state where the garbage G is gripped and lifted by the grip portion 1 a. The detection result of the weight sensor 1b is transmitted to the control device 100. The detection result of the weight sensor 1b is an example of "information related to the garbage G before being supplied to the processing space V", and is an example of "information related to the property of the garbage G".

In the present disclosure, "information related to the property of garbage G" refers to information related to the property or state of garbage G. In the present disclosure, the "information related to the property of the garbage G" is not limited to the information directly indicating the property of the garbage G, and may be information for specifying the property of the garbage G (for example, information capable of specifying the property of the garbage G by combining other information) or the like. For example, the weight of the refuse G is information that can determine the density of the refuse G by combining the volume of the refuse G described later. The density of the garbage G is an example of the property of the garbage G.

The incinerator 2 burns refuse G charged into a hopper 11 described later while conveying the refuse. With the combustion of the waste G in the incinerator 2, exhaust gas is generated in the incinerator 2. The generated exhaust gas is sent to the exhaust heat recovery boiler 3 provided at the upper portion of the incinerator 2. The exhaust heat recovery boiler 3 heats water by heat exchange between the exhaust gas generated in the incinerator 2 and the water to generate steam.

The exhaust gas having passed through the exhaust heat recovery boiler 3 is cooled in the cooling tower 4 and then sent to the dust collecting device 5. The exhaust gas is discharged to the atmosphere through the flue 6 and the chimney 7 after the soot and dust are removed by the dust collecting device 5. The flue 6 is provided with a gas concentration sensor 6a. The gas concentration sensor 6a detects the concentration (e.g., oxygen concentration) of various gases contained in the exhaust gas flowing through the flue 6. The detection result of the gas concentration sensor 6a may include one or more of a CO concentration, a NOx concentration, and a SOx concentration instead of or in addition to the oxygen concentration. The detection result of the gas concentration sensor 6a is sent to the control device 100.

<2 > Incinerator >

Next, the incinerator 2 will be described in detail. The incinerator 2 includes, for example, a supply mechanism 10, a furnace main body 20, a grate 30, a bellows 41, a discharge chute 42, a furnace 43, and an air blowing mechanism 50.

<2.1 Supply mechanism >

The supply mechanism 10 temporarily stores the refuse G carried by the crane 1 and sequentially supplies the refuse G to a processing space V of the furnace main body 20 described later. The supply mechanism 10 includes, for example, a hopper 11, a feeder 12, a pushing device 13 (see fig. 2), an object detector 14, and a moisture detector 15.

The hopper 11 is a storage unit provided for supplying the refuse G into the furnace main body 20. The garbage G carried by the crane 1 is thrown into the hopper 11. The hopper 11 has an inlet portion 11a and an outlet portion 11b. The inlet 11a is an inlet for inputting the garbage G from the outside. The inlet 11a extends in the vertical direction, for example. The garbage G introduced into the inlet 11a moves downward by gravity. The outlet portion 11b is provided below the inlet portion 11 a. The outlet portion 11b is an outlet portion that guides the refuse G supplied from the inlet portion 11a toward a processing space V in the furnace main body 20 described later. The outlet portion 11b extends in the horizontal direction, for example.

The feeder 12 is provided at the outlet portion 11b of the hopper 11. The feeder 12 is plate-shaped along the bottom of the outlet portion 11b of the hopper 11, and is disposed along the bottom of the outlet portion 11b of the hopper 11. The feeder 12 is reciprocatingly movable in a direction from the outlet portion 11b of the hopper 11 toward the processing space V of the furnace main body 20. The feeder 12 is driven by the pushing device 13, and pushes out the garbage G deposited inside the hopper 11 (for example, the outlet portion 11b of the hopper 11) toward the processing space V of the furnace main body 20.

The object detector 14 detects the height of the refuse G charged into the hopper 11 by the crane 1. The object detector 14 is, for example, a Light Detection AND RANGING. The object detector 14 is provided at the inlet 11a of the hopper 11, for example, and detects the height of the garbage GM passing through the inlet 11a of the hopper 11. Instead of the height of the refuse G, the object detector 14 may directly detect the volume of the refuse G by three-dimensional measurement. The detection result of the object detector 14 is transmitted to the control device 100. The detection result of the object detector 14 is an example of "information related to the garbage G before being supplied to the processing space V", and an example of "information related to the property of the garbage G".

The moisture meter 15 is a meter that detects a value (for example, a moisture rate or a moisture amount) related to moisture contained in the garbage G charged into the hopper 11. In the present embodiment, the moisture meter 15 includes an irradiation unit and a detection unit provided in the hopper 11, and an analysis unit. The irradiation unit irradiates electromagnetic waves of a predetermined frequency band to the garbage G deposited in the hopper 11. The detection unit receives electromagnetic waves that are irradiated from the irradiation unit and that pass through the garbage G or are reflected by the garbage G. The analysis unit stores, for example, correlation information indicating a relationship between a characteristic change (for example, a change in amplitude or a change in phase) of the electromagnetic wave and a moisture content in advance. The analysis unit detects the moisture content of the garbage G based on the characteristic change of the electromagnetic wave between the irradiation unit and the detection unit and the correlation information.

In the present embodiment, the irradiation unit and the detection unit of the moisture meter 15 are provided slightly above the feeder 12, and detect the moisture content of the garbage G deposited on the upper surface of the feeder 12. The detection result of the moisture meter 15 is transmitted to the control device 100. The detection result of the moisture meter 15 is an example of "information related to the garbage G before being supplied to the processing space V", an example of "information related to the property of the garbage G", and an example of "moisture measurement result in the hopper 11".

<2.2 Furnace body >

The furnace main body 20 is provided adjacent to the hopper 11 and burns the refuse G while conveying the refuse. Hereinafter, the conveying direction of the refuse G in the combustion apparatus F is referred to as "conveying direction D". The furnace main body 20 includes a drying section 20a, a combustion section 20b, and a burnout section 20c in this order from the upstream side toward the downstream side in the conveying direction D. The drying section 20a is located upstream of the combustion section 20b and the ember section 20c, and is a region where the refuse G supplied from the hopper 11 is dried before combustion on the grate 30. The combustion section 20b and the ember section 20c are regions in which the garbage G dried by the drying section 20a is burned on the grate 30. In the combustion section 20b, diffusion combustion is caused by the pyrolysis gas generated from the garbage G, generating the optical flame F. In the burnout section 20c, the fixed carbon combustion after the diffusion combustion of the refuse G is caused, and thus the optical flame F is not generated. The combustion section 20b and the ember section 20c are examples of the processing space V for burning the refuse G. The drying section 20a is an example of a region upstream of the processing space V in the conveying direction D.

In the present embodiment, the furnace main body 20 has a visible light camera 21 and an infrared camera 22. The visible light camera 21 and the infrared camera 22 are disposed downstream of the processing space V in the conveyance direction D, and capture images of the upstream side of the conveyance direction D from the downstream side. In the present embodiment, the visible light camera 21 and the infrared camera 22 are provided at the end portion (hereinafter referred to as "tail portion") of the furnace main body 20 on the downstream side in the conveying direction D. For example, the visible light camera 21 and the infrared camera 22 capture images of the upstream side in the conveying direction D from the downstream side through a window portion provided at the furnace tail of the furnace main body 20. For example, the visible light camera 21 and the infrared camera 22 are disposed at positions adjacent to each other in the vertical direction or in the horizontal direction.

The visible light camera 21 photographs the light flame F from the furnace tail of the furnace main body 20. The photographing result of the visible light camera 21 is transmitted to the control apparatus 100.

The infrared camera 22 photographs the garbage G deposited on the drying section 20a of the furnace main body 20 (i.e., on the upstream side of the processing space V) from the furnace tail of the furnace main body 20 through the optical flame F. In the present embodiment, the infrared camera 22 photographs the outlet portion 11b of the hopper 11 from the furnace tail of the furnace main body 20 through the light flame F. For example, the infrared camera 22 captures an image including the garbage G deposited on the feeder 12 (an image indicating a deposition state of the garbage G) at the outlet portion 11b of the hopper 11. The result of the photographing by the infrared camera 22 is transmitted to the control device 100. The imaging result by the infrared camera 22 is an example of "information related to the garbage G before being supplied to the processing space V", and is an example of "accumulation state information indicating the accumulation state of the garbage G in the hopper 11".

In the present embodiment, images of both the drying section 20a including the furnace main body 20 and the outlet portion 11b of the hopper 11 (for example, the garbage G deposited on the feeder 12) are captured by one infrared camera 22. Instead of this, the furnace main body 20 may be provided with a first infrared camera that photographs the drying section 20a of the furnace main body 20 and a second infrared camera that photographs the outlet portion 11b of the hopper 11 (for example, the garbage G deposited on the feeder 12), respectively. The infrared camera 22 may be provided at another position instead of the furnace tail of the furnace main body 20.

<2.3 Grate >

The fire grate 30 includes a plurality of fire grate segments 31 and a fire grate segment driving means 32 (refer to fig. 2). The plurality of grate segments 31 form a grate surface 30a of the furnace body 20 that is a bottom surface (e.g., a bottom surface of the processing space V). The refuse G is supplied in layers to the grate surface 30a by the supply mechanism 10. The grate surface 30a is disposed throughout the drying section 20a, the combustion section 20b, and the ember section 20 c. The plurality of grate segments 31 includes fixed grate segments and movable grate segments. The fixed grate segments are fixed to the upper surface of a bellows 41, which will be described later. The movable grate segments reciprocate in the conveying direction D at a constant speed, so that the garbage G on the movable grate segments and the fixed grate segments (on the grate surface 30 a) is conveyed downstream while being stirred and mixed.

<2.4 Bellows, discharge chute, stove >

The bellows 41 is provided below the fire grate 30, and supplies combustion air to the inside of the furnace body 20 through the fire grate 30. The windbox 41 is arranged in plurality in the conveying direction D. The bellows 41 has a bellows pressure sensor 41a. The bellows pressure sensor 41a detects the pressure inside the bellows 41. The pressure inside the bellows 41 corresponds to the pressure of combustion air supplied to the inside of the furnace main body 20 through a primary air line 52 described later. The detection result of the bellows pressure sensor 41a is sent to the control device 100.

The discharge chute 42 is a device for causing the refuse G, which has been burned to become ash, to fall down to an ash pushing device located below the furnace main body 20. The discharge chute 42 is provided at the furnace tail of the furnace main body 20.

The burner 43 extends upward from the upper portion of the burner body 20. The exhaust gas generated by burning the waste G in the processing space V is sent to the waste heat recovery boiler 3 through the burner 43.

<2.5 Air supply mechanism >

The blower mechanism 50 supplies air (for example, combustion air) into the furnace main body 20. The blower mechanism 50 includes, for example, a blower 51, a primary air line 52, an air preheater 53, a secondary air line 54, a damper 55, and an air flow sensor 56.

The blower 51 is a press-in blower that presses air (for example, combustion air) into the furnace main body 20. The blower 51 includes, for example, a first blower 51A and a second blower 51B. The first blower 51A presses combustion air into the furnace main body 20 (e.g., the processing space V) through the primary air line 52 and the bellows 41. The second blower 51B presses combustion air toward the inside of the furnace 43 through the secondary air line 54.

The primary air line 52 connects the first blower 51A and the air box 41. One or more (for example, a plurality of) primary air dampers 55A are provided in the middle of the primary air line 52. The primary air damper 55A changes the flow rate of the combustion air flowing through the primary air line 52 according to the opening degree of the primary air damper 55A.

The air preheater 53 is a heat exchanger that preheats air blown from the first blower 51A. For example, the air preheater 53 is provided midway in the primary air line 52.

A secondary air line 54 connects the second blower 51B with the burner 43. The secondary air supplied into the furnace 43 is directed toward the waste G from above the grate 30. One or more (e.g., a plurality of) secondary air dampers 55B are provided midway in the secondary air line 54. The secondary air damper 55B changes the flow rate of the combustion air flowing in the secondary air line 54 by the opening degree of the secondary air damper 55B. Hereinafter, for convenience of explanation, the primary air damper 55A and the secondary air damper 55B are collectively referred to as "dampers 55".

The air flow sensor 56 detects the flow rate of air (for example, combustion air) supplied into the furnace main body 20. The air flow sensor 56 includes, for example, a first air flow sensor 56A and a second air flow sensor 56B. The first air flow sensor 56A is provided midway in the primary air line 52, and detects the flow rate of air supplied through the primary air line 52. The second air flow sensor 56B is provided midway in the secondary air line 54, and detects the flow rate of air supplied through the secondary air line 54. In the following description, the "detection result of the air flow sensor 56" includes, for example, the detection result of the first air flow sensor 56A and the detection result of the second air flow sensor 56B.

< 3> Waste heat recovery boiler

Next, the exhaust heat recovery boiler 3 will be described. The exhaust heat recovery boiler 3 includes, for example, a boiler body 61, a pipe 62, a radiation temperature sensor (infrared temperature sensor) 63, an in-furnace pressure sensor 64, a water supply flow rate sensor 65, and a superheater cooler flow rate sensor (steam flow rate sensor) 66.

The boiler body 61 is connected to the furnace 43 of the incinerator 2. The exhaust gas generated in the incinerator 2 flows into the boiler body 61. The radiation temperature sensor 63 and the intra-furnace pressure sensor 64 are provided in the boiler body 61. The radiation temperature sensor 63 detects the temperature of the inside of the boiler body 61. The in-furnace pressure sensor 64 detects the pressure inside the boiler body 61. The detection results of the radiation temperature sensor 63 and the intra-furnace pressure sensor 64 are transmitted to the control device 100.

The piping 62 extends inside the boiler body 61. A plurality of superheaters and a plurality of desuperheaters are provided in the pipe 62. Water is supplied from the water supply portion to the inlet portion of the pipe 62. At least a part of the water flowing through the pipe 62 is heated by heat exchange in the boiler body 61, and the main steam flows toward an external device (for example, a turbine). The "main vapor flow rate" described below refers to the flow rate of vapor flowing from the pipe 62 toward an external device (for example, a turbine).

The water supply flow rate sensor 65 is provided at the inlet of the pipe 62, and detects the flow rate of water supplied to the pipe 62. A desuperheater flow sensor 66 is provided midway in the line 62 to detect the flow rate of the fluid (e.g., vapor) flowing through the line 62. For example, the desuperheater flow sensor 66 includes a first desuperheater flow sensor 66A that detects the flow of fluid through the primary desuperheater (primary desuperheater flow) and a second desuperheater flow sensor 66B that detects the flow of fluid through the secondary desuperheater (secondary desuperheater flow). In the following description, the "detection result of the superheater cooler flow sensor 66" includes, for example, the detection result of the first superheater cooler flow sensor 66A and the detection result of the second superheater cooler flow sensor 66B. The detection result of the water supply flow rate sensor 65 and the superheater cooler flow rate sensor 66 is transmitted to the control device 100.

<4 > Control device >

Next, the control device 100 will be described.

Fig. 2 is a block diagram showing a functional configuration of the incineration facility SF according to the embodiment. The control device 100 controls the incineration equipment SF uniformly. For example, the control device 100 performs combustion control of the waste G in the processing space V of the furnace main body 20. In the present embodiment, the control device 100 includes, for example, an information acquisition unit 110, a data conversion unit 120, a prediction model generation unit 130, a prediction model determination unit 140, a vapor flow rate prediction unit 150, and a control unit 160. The control target device (hereinafter referred to as "control target device S") of the control device 100 includes the push-out device 13, the blower 51, the damper 55, the fire grate segment driving device 32, and the like.

<4.1 Information acquisition section >

The information acquisition unit 110 acquires detection results and the like detected by the various sensors included in the incineration facility SF. For example, the information acquisition unit 110 acquires a detection result (garbage weight) of the weight sensor 1b, a detection result (garbage height) of the object sensor 14, a detection result (garbage moisture detection result) of the moisture sensor 15, a photographing result (combustion flame image) of the visible light camera 21, a photographing result (garbage layer image) of the infrared camera 22, a detection result (bellows pressure) of the bellows pressure sensor 41a, a detection result (press-in air flow) of the air flow sensor 56, a detection result (in-furnace temperature) of the radiation temperature sensor 63, a detection result (in-furnace pressure) of the in-furnace pressure sensor 64, a detection result (water supply flow) of the water supply flow sensor 65, a detection result (superheater cooler flow) of the superheater cooler flow sensor 66, a detection result (oxygen concentration) of the gas concentration sensor 6a, and the like.

Here, one or more of the above-described detection result of the bellows pressure sensor 41a, the detection result of the air flow sensor 56, the detection result of the radiation temperature sensor 63, the detection result of the in-furnace pressure sensor 64, the detection result of the feed water flow sensor 65, the detection result of the superheater cooler flow sensor 66, and the detection result of the gas concentration sensor 6a are included in process data (process data) described later. These detection results are examples of "information for prediction" together with the detection results of the weight sensor 1b, the detection results of the object detector 14, the detection results of the moisture detector 15, the imaging results of the visible light camera 21, and the imaging results of the infrared camera 22, respectively. In the present disclosure, "acquisition" is not limited to the case of actively acquiring by outputting a transmission request, but includes the case of passively receiving information transmitted from various devices. This definition is also the same as in the following description.

The information acquisition unit 110 acquires, as part of process data to be described later, a process value indicating the state of each device included in the control target device S. For example, the control target device S acquires, as part of the process data, a process value indicating the state of the ejector 13 (for example, the stroke length of the feeder 12 and/or the moving speed of the feeder 12), a process value indicating the state of the blower 51 (for example, the rotational speed of the blower 51), a process value indicating the state of the damper 55 (for example, the opening degree of the damper 55), and a process value indicating the state of the grate segment driving device 32 (for example, the moving speed of the grate segment 31). These process data (process values) are examples of "prediction information". The process value (for example, the stroke length of the feeder 12 and/or the moving speed of the feeder 12) indicating the state of the ejector 13 is an example of "information indicating the operation of the feeder 12", and is an example of "supply state information indicating the supply state of the garbage G from the hopper 11 to the processing space V". The information acquisition unit 110 outputs the acquired various information and process data to the data conversion unit 120.

<4.2 Data conversion section >

The data conversion unit 120 performs predetermined data conversion on the information received from the information acquisition unit 110. For example, the data conversion unit 120 performs extraction of feature amounts, adjustment of time delay, and averaging processing as predetermined data conversion.

Fig. 3 is a block diagram showing a functional configuration of the data conversion unit 120 according to the embodiment. The data conversion unit 120 includes, for example, a first heat generation amount estimation unit 121, a second heat generation amount estimation unit 122, a first feature amount extraction unit 123, an oxygen concentration estimation unit 124, a flame retardant coefficient calculation unit 125, an image conversion unit (image processing unit) 126, a garbage level detection unit 127, a second feature amount extraction unit 128, a feeder supply amount estimation unit 129, and an adjustment processing unit PU.

(First heat generation amount estimation unit)

The detection result (garbage weight) of the weight sensor 1b and the detection result (garbage height) of the object detector 14 are input to the first heat generation amount estimating unit 121. The first heat generation amount estimating unit 121 calculates the volume of the refuse G based on the height of the refuse G (for example, based on the height of the refuse G and the size of the grip portion 1a of the crane 1). The first heat generation amount estimating unit 121 divides the weight of the garbage G by the volume of the garbage G to calculate the density of the garbage G. The first heat generation amount estimating unit 121 has correlation information indicating a correlation between the density of the garbage G and the heat generation amount of the garbage G (for example, low-order heat generation amount LHV: lower Heating Value) (hereinafter referred to as "garbage heat generation amount"). The correlation information is, for example, a calorific value estimation formula for calculating an estimated value of the calorific value of the garbage from the density of the garbage G. The first heat generation amount estimating unit 121 calculates an estimated value of the amount of heat generated by the garbage G based on the calculated density of the garbage G and the correlation information. The first heat generation amount estimation unit 121 outputs the calculated estimated value of the amount of heat generation of the garbage to the adjustment processing unit PU.

Here, the density in the present embodiment refers to, for example, bulk density. The bulk density is not an inherent density (true density) of the object, but a density calculated from "weight per unit volume including voids". However, the first heat generation amount estimating unit 121 may estimate and use the true density instead of the bulk density. The density of the garbage G calculated by the first heat generation amount estimating unit 121 is based on the weight or the like measured outside the hopper 11, but corresponds to the density of the garbage G in the hopper 11. Therefore, the density of the garbage G calculated by the first heat generation amount estimating unit 121 is an example of "the density of the garbage G in the hopper 11".

(Second heating value estimating section)

The detection result (garbage moisture detection result) of the moisture meter 15 is input to the second heat generation amount estimation unit 122. The volume of the garbage G calculated by the first heat generation amount estimating unit 121 may be further input to the second heat generation amount estimating unit 122. When the volume of the garbage G is input, the second heat generation amount estimation unit 122 calculates the moisture content of the garbage G by multiplying the moisture content of the garbage G by the volume of the garbage G. The second heat generation amount estimation unit 122 has correlation information indicating a correlation between a value (moisture percentage or moisture amount) related to moisture of the garbage G and a garbage heat generation amount (for example, low-order heat generation amount). The correlation information is, for example, a calorific value estimation formula for calculating an estimated value of the calorific value of the garbage from a value related to the moisture of the garbage G. The second heat generation amount estimation unit 122 calculates an estimated value of the heat generation amount of the garbage on the basis of the value related to the moisture of the garbage G and the related information. The second heat generation amount estimation unit 122 outputs the estimated value of the calculated garbage heat generation amount to the adjustment processing unit PU.

Here, fig. 4 is a diagram showing a correlation between the estimated value of the waste heat value based on the detection result of the moisture detector 15 and the waste heat value checked in the actual machine. As shown in fig. 4, it is confirmed by the present inventors that: there is a sufficiently high correlation between the estimated value of the amount of generated dust based on the detection result of the moisture meter 15 and the amount of generated dust confirmed in the actual machine. Further, since the estimated value of the amount of heat generated by the garbage based on the detection result of the moisture meter 15 is information advanced with respect to the amount of heat generated by the garbage G confirmed in the actual machine, the present inventors confirmed that: by taking the time delay into consideration, it is possible to improve the correlation between the estimated value of the waste heat value based on the detection result of the moisture meter 15 and the waste heat value confirmed in the actual machine.

(First feature quantity extraction section)

The imaging result (combustion flame image) of the visible light camera 21 is input to the first feature amount extraction unit 123. The first feature amount extraction unit 123 performs clustering processing on the input combustion flame image, thereby converting the combustion flame image into color image data IM (see fig. 5) divided into a plurality of color areas according to color information. The first feature amount extraction unit 123 extracts a feature amount related to the flame state based on the color image data IM.

An example of "dividing an image into a plurality of color areas according to color information by clustering" will be described. The color information is each color component of RGB, and the plurality of color areas are set by the clustering process so that each color component of RGB does not overlap with each other. The first feature amount extraction unit 123 decomposes the combustion flame image into RGB color components for each pixel, and determines a color region including each pixel. The color information is not limited to each color component of RGB, and may be luminance or chromaticity.

The clustering algorithm is not particularly limited, and various known clustering algorithms can be used. For example, the clustering may be performed by using an algorithm capable of specifying the number of clusters, such as k-means, or by using an algorithm capable of determining the number of automatic determinants, such as flowsom.

Fig. 5 is a diagram showing an example of the color image data IM. In the color image data IM illustrated in fig. 5, the color image data IM is divided into seven color areas a by the clustering process, and includes a first color area A1, a second color area A2, a third color area A3, a fourth color area A4, a fifth color area A5, a sixth color area A6, and a seventh color area A7 in order of the brightness. The first to seventh color areas A1 to A7 are converted into a gradation value of white-black (gray scale), respectively, and become thicker as the first color area A1 enters the seventh color area A7.

Next, an example of "extracting a feature amount from color image data IM" will be described. The first feature amount extraction unit 123 calculates the total (i.e., the area) of the number of pixels divided into the first color region A1, and extracts the total number of pixels as the feature amount. For example, the first feature amount extraction unit 123 extracts the total number of pixels of the first color region A1 for each predetermined time (for example, every second). The first feature amount extraction unit 123 also calculates the total number of pixels per predetermined time for each of the second to seventh color areas A2 to A7, and extracts the total number of pixels as the feature amount. In the present embodiment, the feature quantity includes the total number of pixels of all the color areas (the first color area A1 to the seventh color area A7) among the plurality of color areas, but the present disclosure is not limited to this embodiment. The feature quantity may include the total number of pixels in at least one of the plurality of color areas.

The first feature amount extraction unit 123 outputs the extracted feature amount related to the flame state to the oxygen concentration estimation unit 124 and to the adjustment processing unit PU. The method of extracting the feature amount by the first feature amount extraction unit 123 is not limited to clustering, and may be another method.

(Oxygen concentration estimation unit)

The feature extracted by the first feature extraction unit 123 and part or all of the process data acquired by the information acquisition unit 110 are input to the oxygen concentration estimation unit 124. The process data input to the oxygen concentration estimating unit 124 is, for example, one or more of the detection result of the bellows pressure sensor 41a, the detection result of the air flow sensor 56, the detection result of the radiation temperature sensor 63, the detection result of the in-furnace pressure sensor 64, the detection result of the water supply flow sensor 65, the detection result of the superheater cooler flow sensor 66, the detection result of the gas concentration sensor 6a, and the like. The oxygen concentration estimating unit 124 performs regression analysis by machine learning based on the input feature amount and the process data, and thereby derives an estimation formula for estimating the oxygen concentration in the processing space V. The oxygen concentration estimating unit 124 calculates an estimated value of the oxygen concentration in the processing space V in real time based on the input feature amount and the process data and the estimated expression. The oxygen concentration estimating unit 124 outputs the estimated value of the calculated oxygen concentration to the flame retardant coefficient calculating unit 125. The method of deriving the above-described estimation expression by the oxygen concentration estimation unit 124 is not limited to regression analysis, and may be another method. The algorithm of the machine learning is not particularly limited, and various known algorithms can be used.

(Flame retardant coefficient calculating section)

The estimated value of the oxygen concentration calculated by the oxygen concentration estimating unit 124 and part or all of the process data acquired by the information acquiring unit 110 are input to the flame retardant coefficient calculating unit 125. The process data input to the oxygen concentration estimating unit 124 is, for example, one or more of the detection result of the radiation temperature sensor 63, the moving speed of the feeder 12, and the like. In the present embodiment, the flame retardant coefficient calculating unit 125 calculates the flame retardant coefficient for digitizing the combustion state of the processing space V based on the estimated value of the oxygen concentration, the detection result of the radiation temperature sensor 63, the amount of change in the movement speed of the feeder 12, and the like. The flame retardant coefficient calculating unit 125 outputs the calculated flame retardant coefficient to the adjustment processing unit PU. In the present disclosure, "flame retardant" refers to "combustion conditions".

(Image converting section)

The image conversion unit 126 receives the imaging result (garbage layer image) of the infrared camera 22. The image conversion unit 126 performs predetermined image processing on the input garbage layer image, and simplifies the garbage layer image. For example, the image conversion unit 126 binarizes the input garbage layer image. The binarization method is, for example, the Ojin method, but is not limited thereto.

Fig. 6 is a diagram showing an example of the processing performed by the image conversion unit 126. As shown in fig. 6, a garbage layer image, which is a color image (or a monochrome image) captured by the infrared camera 22, is converted into a white-black image by the image conversion section 126. The image (for example, white-black image) obtained by the image conversion unit 126 is output to the garbage layer height detection unit 127.

(Refuse layer height detecting section)

The image obtained by the image conversion unit 126 is input to the garbage layer height detection unit 127. The trash level detecting unit 127 detects the height of the trash G (trash level) in the drying section 20a of the oven main body 20 based on the inputted image.

Fig. 7 is a diagram showing an example of the processing performed by the garbage layer height detecting unit 127. The trash level detecting unit 127 sets one or more (two in the example shown in fig. 6) of the image obtained by the image converting unit 126 as a predetermined region of interest R (see fig. 6) that is a part of the image. The garbage layer height detection unit 127 sets a plurality of divided regions Ra (for example, a divided region Ra in which the region of interest R is divided by 20 in the up-down direction and is divided by 5 in the left-right direction) for the image of the set region of interest R (see (a) of fig. 7). In fig. 7, data of two regions of interest R are illustrated in a lateral arrangement.

The garbage layer height detection unit 127 assigns "1" to each of the divided areas Ra when the black color is greater than 50%, and assigns "0" to the divided area Ra when the black color is 50% or less (see (b) of fig. 7). The garbage layer height detection unit 127 calculates the position of the division area Ra of the uppermost "1" as the garbage layer height. For example, in the example shown in fig. 7, the height position of the outgoing line H is calculated as the trash level. The garbage layer height detection unit 127 outputs the calculated garbage layer height to the feeder supply amount estimation unit 129.

(Second feature quantity extraction section)

The imaging result (garbage layer image) of the infrared camera 22 is input to the second feature amount extraction unit 128. The second feature amount extraction unit 128 performs clustering processing on the input garbage layer image, thereby converting the garbage layer image into color image data divided into a plurality of color areas according to color information. The second feature amount extraction unit 128 extracts feature amounts related to the supply state of the trash based on the color image data. The processing method and the clustering algorithm for "dividing the image into a plurality of color areas based on the color information by the clustering process" are the same as those of the first feature amount extraction unit 123, for example, but may be different.

In the present embodiment, the second feature amount extraction unit 128 divides the input garbage layer image into a plurality of color areas by the clustering process. Then, the second feature amount extraction unit 128 calculates the total number of pixels (i.e., the area) of the divided color regions, and extracts the total number of pixels as the feature amount related to the supply state of the trash G. The second feature amount extraction unit 128 extracts the total number of pixels of each color region for each predetermined time (for example, every second). In the present embodiment, the feature amount includes the total number of pixels of all the color areas among the plurality of color areas, but the present disclosure is not limited to this embodiment. The feature quantity may include the total number of pixels of at least one of the plurality of color areas. The second feature amount extraction unit 128 outputs the feature amount extracted in relation to the supply state of the refuse G to the feeder supply amount estimation unit 129. The method of extracting the feature amount by the second feature amount extraction unit 128 is not limited to clustering, and may be another method.

(Feeder supply amount estimation section)

The feeder supply amount estimating unit 129 receives information indicating the height of the garbage layer calculated by the garbage layer height detecting unit 127 and information indicating the feature amount of the supply state of the garbage G extracted by the second feature amount extracting unit 128. The feeder supply amount estimating unit 129 has correlation information indicating a correlation between the characteristic amount of the height of the garbage layer and the supply state of the garbage G and the supply amount of the garbage G supplied from the feeder 12. The correlation information is, for example, a supply amount estimation formula for calculating the supply amount of the garbage G from the feeder 12 based on the feature amount of the garbage layer height and the supply state of the garbage G. The feeder supply amount estimating unit 129 calculates an estimated value of the supply amount of the refuse G supplied from the feeder 12 based on the information indicating the inputted height of the refuse layer, the characteristic amount of the supply state of the refuse G, and the correlation information. The feeder supply amount estimating unit 129 outputs the estimated value of the calculated supply amount of the garbage G to the adjustment processing unit PU. The estimated value of the supply amount of the garbage G is another example of "supply state information indicating a supply state of the garbage G from the hopper 11 to the processing space V".

(Adjustment processing section)

The information calculated by the first heat generation amount estimating unit 121, the second heat generation amount estimating unit 122, the first feature amount extracting unit 123, the flame retardant coefficient calculating unit 125, and the feeder supply amount estimating unit 129, and the process data acquired by the information acquiring unit 110 are input to the adjustment processing unit PU. Hereinafter, these will be collectively referred to as "input information". In the present embodiment, the process data input to the adjustment processing unit PU includes, for example, a process value of the feeder 12 (for example, a stroke length of the feeder 12 and/or a moving speed of the feeder 12), a detection result of the blower pressure sensor 41a, a detection result of the air flow sensor 56, a detection result of the in-furnace pressure sensor 64, a detection result of the radiation temperature sensor 63, a detection result of the water supply flow sensor 65, a detection result of the superheater cooler flow sensor 66, and a detection result of the gas concentration sensor 6a (for example, oxygen concentration). It should be noted that some or all of the above-described process data (e.g., the process values of the feeder 12) may be omitted.

The adjustment processing unit PU performs predetermined processing on the input information to convert the input information into data to be input to a main vapor flow rate prediction model M described later. The adjustment processing unit PU includes, for example, a preprocessing unit Pua and a time delay adjustment unit PUb.

The preprocessing unit PUa performs preprocessing such as averaging processing on one or more pieces of input information. For example, the preprocessing unit PUa averages values obtained at a plurality of detection time points for one or more pieces of input information. The preprocessing by the preprocessing unit PUa may be performed instead of the averaging processing or may be performed by differential processing or the like. The preprocessing unit PUa outputs the preprocessed input information to the time delay adjustment unit PUb.

The time delay adjustment unit Pub performs association on the time axis of the input information simultaneously inputted as one data set (set of input information) to the main vapor flow rate prediction model M based on each input information and the time delay set value set individually for each input information. That is, there is a time delay between the change in each input information and the change in the main vapor flow rate. In other words, each piece of input information becomes a preceding signal that advances with respect to the change in the main vapor flow rate. For example, the input information related to the hopper 11 or the position near the hopper 11 becomes a preceding signal that is much advanced compared to the input information related to the position near the processing space V.

Fig. 8 is a diagram showing an example of a correlation between each piece of input information and the main vapor flow rate. In this embodiment, the length of the time delay setting value is changed for each piece of input information a plurality of times, and the time delay setting value having the highest correlation between the input information and the main vapor flow rate is selected.

For example, the correlation between the input information indicating the supply amount from the feeder 12 and the main vapor flow rate (see fig. 8 (a)) is highest when T2 minutes is set as the time delay set value. In other words, the input information indicating the supply amount from the feeder 12 becomes a preceding signal advanced by T2 minutes with respect to the main vapor flow rate. Similarly, the correlation between the input information indicating the flame retardant coefficient and the main vapor flow rate (see (b) of fig. 8) is highest when T3 min is set as the time delay set value. In other words, the input information indicating the flame retardant coefficient is a preceding signal advanced by T3 minutes with respect to the main vapor flow rate. For example, T3 minutes is a shorter time than T2 minutes.

Fig. 9 is a diagram showing an example of the time delay setting value for each input information. In FIG. 9, T1[ min ] > T2[ min ] > T3[ min ]. However, these relationships are not limiting. The time delay setting value for each input information can be set appropriately.

The time delay adjustment unit Pub correlates the input information simultaneously input to the main vapor flow rate prediction model M based on the time delay setting value for each input information, and generates a data set (i.e., an aggregate of input information subjected to time adjustment) for predicting the main vapor flow rate at a certain point in the future. The adjustment processing unit PU outputs the data set generated by the time delay adjustment unit PUb.

<4.3 Prediction model creation part >

In the prediction model creation process (learning process), a combination of the data set generated by the adjustment processing unit PU and the positive solution data of the predicted value of the main vapor flow rate corresponding to the data set is input as learning data to the prediction model creation unit 130. The prediction model creation unit 130 performs machine learning based on the input learning data, thereby creating a main vapor flow rate prediction model M for predicting a main vapor flow rate at a future point in time. The main vapor flow rate prediction model M is a learning completion model that outputs a predicted value of the main vapor flow rate at a future point in time when the data set generated by the adjustment processing unit PU is input. The main vapor flow rate prediction model M is, for example, LSTM (Long Short Term Memory) or XGBoost (eXtreme Gradient Boosting), but is not limited to these. The algorithm of the machine learning is not particularly limited, and various known algorithms of the machine learning can be used.

In the present embodiment, the prediction model creation unit 130 creates a plurality of main vapor flow rate prediction models M for predicting main vapor flow rates at a plurality of future time points different from each other. For example, the prediction model creation unit 130 creates a plurality of main vapor flow rate prediction models M that output predicted values of the main vapor flow rates for the first 60 seconds, the first 120 seconds, and the first 180 seconds, respectively. Instead of generating the plurality of main vapor flow rate prediction models M, the prediction model generation unit 130 may generate one main vapor flow rate prediction model M that outputs a plurality of prediction values corresponding to a plurality of future time points.

The prediction model creation unit 130 changes the learning period (the accumulation period of learning data) to generate a plurality of main vapor flow rate prediction models M based on the learning data of a plurality of learning periods having different lengths. For example, the prediction model creation unit 130 creates the main vapor flow rate prediction model M corresponding to the learning data corresponding to 1 day, the learning data corresponding to 2 days, …, and the learning data corresponding to 7 days, respectively.

<4.4 Prediction model determination part >

The prediction model determination unit 140 evaluates a plurality of main vapor flow rate prediction models M corresponding to the plurality of learning periods generated by the prediction model generation unit 130, and selects the main vapor flow rate prediction model M used in the vapor flow rate prediction unit 150.

Fig. 10 is a diagram showing an example of the evaluation process performed by the prediction model determination unit 140. In the present embodiment, the prediction model determination unit 140 evaluates a plurality of main vapor flow rate prediction models M corresponding to a plurality of learning periods based on an accuracy index such as a root mean square error (RMSE: root Mean Square Error) and an average absolute scale error (MASE: mean Absolute scale Error). In the present embodiment, as the main vapor flow rate prediction model M corresponding to each learning period, a set of a plurality of main vapor flow rate prediction models M that predict the main vapor flow rates of the first 60 seconds, the first 120 seconds, and the first 180 seconds, respectively, is evaluated. Then, among the plurality of main vapor flow rate prediction models M corresponding to the plurality of learning periods, a set of main vapor flow rate prediction models M corresponding to a learning period in which prediction accuracy at a plurality of future time points (the first 60 seconds, the first 120 seconds, and the first 180 seconds) is most integrated is selected. In the example shown in fig. 10, a group corresponding to the main vapor flow rate prediction model M for the learning period corresponding to 5 days is selected. The main vapor flow rate prediction model M selected by the prediction model determination unit 140 is output to the vapor flow rate prediction unit 150. The values of S1 to S7 in fig. 10 are specifically calculated based on the calculation formula of RMSE or MASE, and represent examples of S1< S2< S3< S4< S5< S6< S7.

<4.5 Main vapor flow prediction portion >

The vapor flow rate prediction unit 150 derives a predicted value of the main vapor flow rate at a future point in time, using the data set generated by the adjustment processing unit PU and the main vapor flow rate prediction model M selected by the prediction model determination unit 140, in the operating stage of the incineration facility SF. In the present embodiment, the prediction values of the main vapor flow rates of the first 60 seconds, the first 120 seconds, and the first 180 seconds are derived using a plurality of main vapor flow rate prediction models M that predict the main vapor flow rates of the first 60 seconds, the first 120 seconds, and the first 180 seconds, respectively. The vapor flow rate predicting unit 150 derives a predicted value of the main vapor flow rate at a predetermined cycle (for example, every second or every 10 seconds). The vapor flow rate prediction unit 150 outputs the derived prediction value of the main vapor flow rate to the control unit 160.

<4.6 Control part >

The control unit 160 performs combustion control of the processing space V based on the predicted values (for example, predicted values of the first 60 seconds, the first 120 seconds, and the first 180 seconds) of the main vapor flow rate derived by the vapor flow rate predicting unit 150. Specifically, the control unit 160 controls the control target device S so that the amount of change in the combustion state of the processing space V becomes small.

Fig. 11 is a diagram showing an example of the control content by the control unit 160. When a predicted value (for example, any one of the predicted values of the first 60 seconds, the first 120 seconds, and the first 180 seconds) of the main vapor flow rate in the future is lower than a preset lower threshold THl, the control unit 160 determines that a combustion shortage is generated in the future and controls the combustion to be promoted. When a future predicted value (for example, any one of the predicted values of the first 60 seconds, the first 120 seconds, and the first 180 seconds) of the main vapor flow rate exceeds a preset upper threshold TH2, the control unit 160 determines that excessive combustion is likely to occur, and controls the suppression of combustion.

In the present embodiment, since the control instruction is output based on the deviation of the predicted value from the set value (reference value), the variation in the main vapor flow rate can be suppressed. That is, in the present embodiment, the control instruction to change the combustion control is output not at the time point (point a in fig. 11) when the actual measurement value of the main vapor flow rate reaches the lower limit threshold TH1 or the upper limit threshold TH2, but at the time point (point B in fig. 11) when the predicted value of the main vapor flow rate at the future time point reaches the lower limit threshold TH1 or the upper limit threshold TH 2. The variation of the main vapor flow rate when the control is performed based on the predicted value (see the two-dot chain line in fig. 11) is smaller than the variation of the main vapor flow rate when the control is performed based on the actual measured value (see the solid line in fig. 11).

Specifically, the control unit 160 includes a feeder control unit 161, an air supply control unit 162, and a grate segment control unit 163. Each control unit performs PI control (proportional integral control), for example. However, the control algorithm is not limited to PI control, and various known control algorithms may be used.

The feeder control unit 161 obtains a process value indicating movement of the feeder 12 from the ejector 13, and generates a control instruction value related to the feeder 12 based on PI control, for example. The feeder control unit 161 outputs the generated control instruction value to the pushing device 13, thereby controlling the movement of the feeder 12 and controlling the amount of the garbage G supplied to the processing space V. For example, the feeder control unit 161 increases the amount of the supplied refuse G when combustion is promoted. On the other hand, the feeder control unit 161 reduces the amount of the supplied refuse G while suppressing the combustion.

The air supply control unit 162 obtains a process value related to the rotational speed of the blower 51 and/or the opening degree of the damper 55 from the blower 51 or the damper 55, and generates a control instruction value related to the blower 51 and/or the damper 55 based on PI control, for example. The air supply control unit 162 outputs the generated control instruction value to the blower 51 and/or the damper 55, thereby controlling the blower 51 and/or the damper 55 and controlling the supply amount of air (for example, combustion air) to the processing space V. For example, the air supply control unit 162 increases the supply amount of air when combustion is promoted. On the other hand, the air supply control unit 162 reduces the supply amount of air while suppressing combustion.

The grate segment control unit 163 acquires process data related to the movement speed of the grate segment 31 from the grate segment driving device 32, and generates a control instruction value related to the grate segment 31 based on PI control, for example. The grate segment control unit 163 outputs the generated control instruction value to the grate segment driving device 32, thereby controlling the grate segment 31 and controlling the stirring state of the garbage G. For example, the grate segment control unit 163 increases the movement speed of the grate segment 31 when combustion is promoted. On the other hand, the grate segment control unit 163 reduces the moving speed of the grate segment 31 while suppressing combustion.

< Flow of 5 treatment >

Next, an example of the flow of the processing in the control device 100 will be described. However, the order of the processing described below is not limited to the following example, and may be appropriately switched.

<5.1 Preparation of predictive model >

First, a process of creating the main vapor flow rate prediction model M (learning process) will be described. The process of creating the main vapor flow rate prediction model M described below is also performed in parallel in the operation stage of the incineration facility SF described below.

Fig. 12 is a flowchart showing a flow of the prediction model creation process. First, the information acquisition unit 110 acquires the detection results and process data of various sensors (S101). Next, the data conversion unit 120 generates a data set to be input to the main vapor flow rate prediction model M based on the detection results of the various sensors and the process data acquired by the information acquisition unit 110 (S102). That is, the data conversion unit 120 performs computation and clustering using various estimated expressions, and performs adjustment processing or the like on the input information obtained by these, which is related to time delay, to generate a data set.

Next, the prediction model creation unit 130 accumulates the data set generated by the data conversion unit 120 over a plurality of days (S103). The prediction model creation unit 130 then makes the learning period (the accumulation period of learning data) variable, and generates a plurality of main vapor flow rate prediction models M based on learning data of a plurality of learning periods having different lengths (S104).

Next, the prediction model determination unit 140 evaluates a plurality of main vapor flow rate prediction models M having different learning periods generated by the prediction model generation unit 130, and selects the main vapor flow rate prediction model M to be used in the vapor flow rate prediction unit 150 (S105). In the present embodiment, the prediction model determination unit 140 determines whether or not a main vapor flow rate prediction model M having higher prediction accuracy than the main vapor flow rate prediction model M currently in use in the vapor flow rate prediction unit 150 exists among the plurality of main vapor flow rate prediction models M newly generated by the prediction model generation unit 130.

If there is no main vapor flow rate prediction model M having higher prediction accuracy than the main vapor flow rate prediction model M currently in use among the plurality of new main vapor flow rate prediction models M (S105: NO), the processing of S103 and S104 is performed again before returning to the processing of S103. On the other hand, when there is a main vapor flow rate prediction model M having higher prediction accuracy than the main vapor flow rate prediction model M currently in use among the plurality of newly generated main vapor flow rate prediction models M (yes in S106), the prediction model determination unit 140 outputs the main vapor flow rate prediction model M having higher prediction accuracy to the vapor flow rate prediction unit 150, and updates the main vapor flow rate prediction model M in use (S107). The processes of S101 to S107 described above are repeatedly performed in the operation stage of the incineration apparatus SF.

<5.2 Treatment of the operational phase of Combustion apparatus >

Next, a process in the operation stage of the incineration facility SF will be described.

Fig. 13 is a flowchart showing a flow of processing in the operation phase of the combustion apparatus. First, the information acquisition unit 110 acquires detection results and process data of various sensors (S201). Next, the data conversion unit 120 generates a data set to be input to the main vapor flow rate prediction model M based on the detection results of the various sensors and the process data acquired by the information acquisition unit 110 (S202). The data conversion unit 120 outputs the generated data set to the vapor flow rate prediction unit 150.

Next, the vapor flow rate predicting unit 150 derives a predicted value of the main vapor flow rate at a future point in time based on the data set received from the data converting unit 120 and the main vapor flow rate prediction model M (S203). The vapor flow rate prediction unit 150 outputs the predicted value of the main vapor flow rate at the future time point thus derived to the control unit 160. Next, the control unit 160 derives the control amount of the control target device S based on the predicted value of the main vapor flow rate (S204). Then, the control unit 160 outputs a control instruction value based on the derived control amount to the control target device S (S205). The processes of S201 to S205 described above are repeatedly performed in the operation stage of the incineration apparatus SF.

<6. Effect >

The main steam flow rate may vary greatly depending on the supply state of the refuse G and the property of the refuse G. Therefore, in the case of performing prediction based on information after the combustion process, it may be difficult to improve the accuracy of prediction of the main vapor flow rate.

On the other hand, in the present embodiment, the control device 100 includes: an information acquisition unit 110 that acquires information on the garbage G before being supplied to the processing space V in the incineration facility SF; a steam flow rate prediction unit 150 that predicts a main steam flow rate generated by the waste heat recovery boiler 3 of the incineration facility SF based on the prediction information including the information acquired by the information acquisition unit 110; and a control unit 160 that performs combustion control based on the main steam flow rate predicted by the steam flow rate prediction unit 150.

According to this configuration, the main vapor flow rate is predicted based on the information on the garbage G before being supplied to the processing space V, and therefore the main vapor flow rate can be predicted with high accuracy. Thus, the control device 100 can perform combustion control based on the highly accurate predicted value of the main vapor flow rate. As a result, the fluctuation range of the main vapor flow rate can be suppressed.

Fig. 14 is a diagram showing an example of a comparison result between the predicted value and the measured value in the present embodiment. As shown in fig. 14, it can be confirmed that the predicted value of the main vapor flow rate based on the control device 100 follows the actual measured value of the main vapor flow rate with high accuracy. In addition, it was confirmed by the present inventors: according to the predicted value of the main vapor flow rate based on the control device 100 of the present embodiment, the prediction accuracy is improved compared to the case where prediction is performed based on only the information after the combustion process.

<7 > Modification example

In the above-described embodiment, the time delay set value set for each input information is set independently, and after the time delay set value having the highest correlation between each input information and the main vapor flow rate is selected and set, the set time delay set value is used as the fixed value. However, the time delay adjustment unit Pub may recalculate the correlation between each piece of input information and the main vapor flow rate at a predetermined cycle, and change the time delay setting value so that the correlation between each piece of input information and the main vapor flow rate becomes higher. According to such a configuration, even when the characteristics of the refuse G change according to seasons and other factors, the accuracy of predicting the main vapor flow rate may be further improved.

(Other embodiments)

The embodiments of the present disclosure have been described in detail above with reference to the drawings, and the specific configuration is not limited to the embodiments, and includes design changes and the like without departing from the scope of the gist of the present disclosure.

Fig. 14 is a hardware configuration diagram showing a configuration of a computer 1100 according to the present embodiment. The computer 1100 includes, for example, a processor 1110, a main memory 1120, a storage 1130, and an interface 1140.

The functional units of the control device 100 described above are mounted on the computer 1100. The operations of the respective functional units described above are stored in the memory 1130 in the form of programs. The processor 1110 reads a program from the storage 1130 and expands in the main memory 1120, and executes the above-described process according to the program. The processor 1110 also secures a storage area for each of the above-described functional units in the main memory 1120 according to a program.

The program may also be used to realize a part of functions that enable the computer 1100 to function. For example, the program may function by being combined with another program stored in the memory 1130 or by being combined with another program installed in another device. The computer 1100 may include a custom LSI (LARGE SCALE INTEGRATED Circuit) such as PLD (Programmable Logic Device) in addition to or instead of the above configuration. As an example of PLD, PAL(Programmable Array Logic)、GAL(Generic Array Logic)、CPLD(Complex Programmable Logic Device)、FPGA(Field Programmable Gate Array). in this case, part or all of the functions realized by processor 1110 may be realized by the integrated circuit.

Examples of the storage 1130 include a magnetic disk, a magneto-optical disk, and a semiconductor memory. The storage 1130 may be an internal medium directly connected to the bus of the computer 1100, or an external medium connected to the computer 1100 via the interface 1140 or a communication line. When the program is distributed to the computer 1100 via a communication line, the computer 1100 that received the distribution may expand the program in the main memory 1120 and execute the above-described processing. In addition, the program may be used to realize a part of the functions described above. The program may be a program that realizes the above-described functions by combining with another program stored in the storage 11130, or a so-called differential file (differential program).

< Additional notes >

The control device 100 according to each embodiment is grasped as follows, for example.

(1) The control device 100 according to the first aspect includes: an information acquisition unit 110 that acquires information on an object G to be incinerated before being supplied to the treatment space V in the incineration facility SF; a steam flow rate prediction unit 150 that predicts a main steam flow rate generated by the waste heat recovery boiler 3 of the incineration facility SF based on prediction information including the information acquired by the information acquisition unit 110; and a control unit 160 that performs combustion control based on the main steam flow rate predicted by the steam flow rate prediction unit 150. The term "prediction information" is used in a broad sense, not meaning information dedicated to prediction, but meaning information usable for prediction. That is, the prediction information may be information collected or stored for a purpose different from the prediction of the main vapor flow rate as a main purpose.

According to this configuration, the main vapor flow rate is predicted based on the information on the object G before being supplied to the processing space V, and therefore the main vapor flow rate can be predicted with high accuracy. Thus, the control device 100 can perform combustion control based on the highly accurate predicted value of the main vapor flow rate.

(2) The control device 100 according to the second aspect includes information related to the behavior of the incineration object G in addition to the control device 100 according to the first aspect. The "information related to the property of the object to be incinerated G" is, for example, one or more of a value related to moisture of the object to be incinerated G (moisture content, moisture amount, etc.), a weight of the object to be incinerated G, a height of the object to be incinerated G, a volume of the object to be incinerated G, a density (bulk density or true density) of the object to be incinerated G, and a heat generation amount of the object to be incinerated G.

According to such a configuration, the main vapor flow rate can be predicted by reflecting the behavior of the object G to be incinerated that affects the main vapor flow rate. This enables the main vapor flow rate to be predicted with high accuracy.

(3) The control device 100 according to the third aspect is the control device 100 according to the first or second aspect, wherein the information includes accumulation state information indicating the accumulation state of the objects G to be incinerated in the hopper 11 of the incineration equipment SF.

According to this configuration, the main vapor flow rate can be predicted by reflecting the accumulation state of the objects G to be incinerated in the hopper 11, which affects the main vapor flow rate. This enables the main vapor flow rate to be predicted with high accuracy.

(4) The control device 100 according to the fourth aspect is the control device 100 according to the third aspect, wherein the deposition state information includes an infrared image obtained by capturing an image of the outlet 11b of the hopper 11 through the flame in the processing space V from the downstream side in the conveyance direction D of the objects G to be incinerated in the incineration facility SF.

According to this configuration, the accumulation state of the objects G to be burned in the hopper 11 can be reflected with higher accuracy based on the infrared image. Thus, the main vapor flow rate is further predicted with high accuracy.

(5) The control device 100 according to the fifth aspect is the control device 100 according to any one of the first to fourth aspects, wherein the information includes supply state information of the supply state of the objects G to be incinerated from the hopper 11 of the incineration facility SF to the treatment space V.

According to this configuration, the main vapor flow rate can be predicted by reflecting the supply state of the objects G to be incinerated from the hopper 11 to the treatment space V, which affects the main vapor flow rate. This enables the main vapor flow rate to be predicted with high accuracy.

(6) The control device 100 according to the sixth aspect further includes a heat generation amount estimating unit (the first heat generation amount estimating unit 121 or the second heat generation amount estimating unit 122) that estimates a lower heat generation amount of the incineration object G based on a density of the incineration object G in the hopper 11 of the incineration facility SF or a result of measuring a moisture of the incineration object G in the hopper 11, which is included in the above information or obtained based on the above information, in addition to any one of the control device 100 according to the first to fifth aspects, and the steam flow rate estimating unit 150 estimates a main steam flow rate based on the lower heat generation amount estimated by the above heat generation amount estimating unit.

According to this configuration, the main vapor flow rate can be predicted by reflecting the low-level heat generation amount of the incineration subject G estimated from the density of the incineration subject G in the hopper 11 or the moisture measurement result. This enables the main vapor flow rate to be predicted with high accuracy.

(7) The control method of the seventh aspect includes: acquiring information related to the garbage G before being supplied to the treatment space V in the incineration facility SF; based on the prediction information including the acquired information, the main steam flow rate generated by the waste heat recovery boiler 3 of the incineration facility SF is predicted; and performing combustion control based on the predicted main vapor flow. With this configuration, as in the case of the control device 100 according to the first aspect, combustion control can be performed based on the highly accurate predicted value of the main vapor flow rate.

(8) The program of the eighth aspect causes a computer to execute: acquiring information related to the garbage G before being supplied to the treatment space V in the incineration facility SF; based on the prediction information including the acquired information, the main steam flow rate generated by the waste heat recovery boiler 3 of the incineration facility SF is predicted; and performing combustion control based on the predicted main vapor flow. With this configuration, as in the case of the control device 100 according to the first aspect, combustion control can be performed based on the highly accurate predicted value of the main vapor flow rate.

Industrial applicability

The present disclosure relates to a control device for controlling incineration equipment of municipal waste, industrial waste, biomass, or the like, for example. According to the control device of the present disclosure, combustion control can be performed based on a highly accurate predicted value of the main vapor flow rate.

Reference numerals illustrate:

SF … incineration equipment, G … incinerated substances (refuse), 1 … crane, 2 … incinerator, 3 … waste heat recovery boiler, 4 … cooling tower, 5 … dust collecting device, 6 … flue, 7 … chimney, 10 … supply mechanism, 11 … hopper, 11a … inlet part, 11b … outlet part, 12 … feeder, 13 … push-out device, 14 … object meter, 15 … moisture meter, 20 … furnace body, 20a … drying section, 20b … combustion section, 20c … combustion section, V … treatment space, 21 … visible light camera, 22 … infrared camera, 30 … fire grate, 31 … fire grate segment, 32 … fire grate segment driving device, 41 air box, 41a … windbox pressure sensor, 50 … blower mechanism, 51 … blower, 52 … primary air line, 53 … air preheater, 54 … secondary air line, 55 … damper, 56 … air flow sensor, 61 … boiler body, 62 … line, 63 … radiant temperature sensor, 64 … intra-furnace pressure sensor, 65 … water supply flow sensor, 66 … superheater desuperheater flow sensor, 100 … control device, 110 … information acquisition unit, 120 … data conversion unit, 130 … predictive model creation unit, 140 … predictive model determination unit, 150 … vapor flow prediction unit, 160 … control unit.

Claims

1. A control device, wherein,

The control device is provided with:

an information acquisition unit that acquires information on an object to be incinerated before being supplied to a processing space in an incineration facility;

A steam flow rate prediction unit that predicts a main steam flow rate generated in a boiler of the incineration facility, based on prediction information including the information acquired by the information acquisition unit; and

And a control unit that performs combustion control based on the main steam flow rate predicted by the steam flow rate prediction unit.

2. The control device according to claim 1, wherein,

The information includes information related to the behavior of the object to be incinerated.

3. The control device according to claim 1 or claim 2, wherein,

The information includes accumulation state information indicating an accumulation state of the objects to be incinerated in the hopper of the incineration facility.

4. The control device according to claim 3, wherein,

The accumulation state information includes an infrared image obtained by capturing an infrared image of the outlet portion of the hopper from a downstream side in the conveying direction of the objects to be incinerated in the incineration facility through a flame in the treatment space.

5. The control device according to any one of claim 1 to claim 4, wherein,

The information includes supply state information indicating a supply state of the objects to be incinerated from a hopper of the incineration equipment to the treatment space.

6. The control device according to any one of claim 1 to claim 5, wherein,

The control device further includes a heat generation amount estimation unit that estimates a lower heat generation amount of the incineration object based on a density of the incineration object in a hopper of the incineration device or a result of measuring moisture of the incineration object in the hopper, the result being included in the information or obtained from the information,

The vapor flow rate predicting unit predicts the main vapor flow rate based on the low-order heat generation amount estimated by the heat generation amount estimating unit.