Heat transfer surface monitoring device and heat transfer surface monitoring method

Abstract

To provide a heat transfer surface monitoring device and a heat transfer surface monitoring method capable of quantitatively estimating thickness distribution of a deposit adhering to a heat transfer surface.SOLUTION: A heat transfer surface monitoring device comprises: an infrared camera that measures a surface temperature of a heat transfer surface by photographing the heat transfer surface exposed inside a boiler; a thermometer that measures a gas temperature in an internal space of the boiler; and a calculator that estimates a thickness of a deposit adhering to the heat transfer surface. The calculator estimates the thickness of the deposit adhering to the heat transfer surface using the measured surface temperature of the heat transfer surface and the measured gas temperature.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a heat transfer surface monitoring device and a heat transfer surface monitoring method for monitoring the adhesion state of deposits on the heat transfer surface of a heat transfer tube installed in a boiler.

Background Art

[0002] In a waste heat boiler or a coal-fired boiler that uses high-temperature exhaust gas such as a garbage incinerator, the exhaust gas in the furnace contains a high concentration of dust. The furnace wall of such a boiler has a structure in which heat transfer tubes through which cooling water circulates inside are connected. When such exhaust gas containing a large amount of dust is introduced into the boiler, the dust gradually adheres to the heat transfer surface of the heat transfer tube.

[0003] When the thickness of the deposits adhering to the heat transfer surface increases, the amount of heat exchange between the inside of the furnace, the heat transfer tube, and the cooling water decreases. In addition, there is a risk that the heat transfer surface will be corroded by the deposits. For this reason, regular inspections and cleaning operations have been conventionally performed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] A configuration in which water is sprayed or the like onto the heat transfer surface inside the boiler for cleaning is also known. However, the amount of deposits adhering to the heat transfer surface inside the boiler is not uniform over the entire heat transfer surface. When the entire heat transfer surface is cleaned based on the adhesion state of the deposits on a part of the heat transfer surface inside the boiler, the cleaning pressure may become excessive at locations where the amount of deposits is small, and there is a risk of shaving the heat transfer surface. On the other hand, there is a risk that the heat transfer surface cannot be sufficiently cleaned at locations where the amount of deposits is large.

[0006] Regarding this, Patent Document 1 discloses an apparatus for measuring the adhesion state of dust adhering to heat transfer tubes at various locations inside a boiler. However, the configuration of Patent Document 1 requires providing probe insertion holes for inserting probes at multiple locations on the furnace wall. Further, the configuration of Patent Document 1 estimates the thickness of the dust adhering to the heat transfer surface by photographing the dust deposited on the probe inserted into the boiler through the probe insertion hole. Therefore, the adhesion state of the dust to the probe may differ from the actual adhesion state of the dust on the heat transfer surface around the probe.

[0007] Also, Patent Document 2 discloses a configuration for calculating the thickness of dust by photographing the heat transfer surface with a television camera and comparing it with a photographed image before dust adhesion. However, it is difficult to quantitatively calculate the thickness of dust by comparing the images photographed with a television camera.

[0008] The present disclosure has been made to solve the above-described problems, and an object thereof is to provide a heat transfer surface monitoring apparatus and a heat transfer surface monitoring method capable of quantitatively estimating the thickness distribution of deposits adhering to a heat transfer surface.

Means for Solving the Problems

[0009] A heat transfer surface monitoring apparatus according to an aspect of the present disclosure includes an infrared camera that measures the surface temperature of the heat transfer surface by photographing the heat transfer surface exposed inside the boiler, a thermometer that measures the gas temperature in the internal space of the boiler, and an arithmetic unit that estimates the thickness of deposits adhering to the heat transfer surface. The arithmetic unit estimates the thickness of deposits adhering to the heat transfer surface using the measured surface temperature of the heat transfer surface and the measured gas temperature.

[0010] The heat transfer surface monitoring method according to another aspect of the present disclosure measures the surface temperature of the heat transfer surface by photographing the heat transfer surface exposed inside the boiler with an infrared camera, measures the gas temperature in the internal space of the boiler, and uses the measured surface temperature of the heat transfer surface and the measured gas temperature to estimate the thickness of the deposit adhering to the heat transfer surface.

Advantages of the Invention

[0011] According to the present disclosure, the thickness distribution of the deposit adhering to the heat transfer surface can be quantitatively estimated.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0013] Hereinafter, a heat transfer surface monitoring device and a heat transfer surface cleaning system using the same according to an embodiment of the present disclosure will be described with reference to the drawings. In the present embodiment, a case where the heat transfer surface monitoring device and the heat transfer surface cleaning system are applied to an incineration plant having a waste heat boiler will be exemplified.

[0014] [Heat Transfer Surface Monitoring Device] First, the heat transfer surface monitoring device in the present embodiment will be described. FIG. 1 is a schematic cross-sectional view showing the internal structure of an incineration plant to which the heat transfer surface monitoring device and the heat transfer surface cleaning system in the present embodiment are applied. The incineration plant 100 shown in FIG. 1 includes an incinerator 102 having a furnace chamber 103 for incinerating waste using an oxygen-containing gas, and a boiler 104 which is a steam recovery device for recovering exhaust heat from the combustion exhaust gas discharged from the incinerator 102 as steam. On the side opposite to the boiler 104 of the incinerator 102, that is, on the upstream side, a hopper 105 and a chute 106 are arranged, and on the downstream side from the boiler 104, an exhaust path 107 for the combustion exhaust gas extends to a chimney 108. For example, an economizer, a desuperheater, a dust collector, and a blower may be provided in the exhaust path 107 in order from the upstream side.

[0015] The incinerator 102 has a stoker provided below the furnace chamber 103. The stoker functions as a waste conveying means. The stoker has a drying stoker 111, a combustion stoker 112, and a post-combustion stoker 113 in order from the side close to the chute 106. That is, these stokers 111, 112, 113 are arranged in the moving direction of the waste. Below the drying, combustion, and post-combustion stokers 111, 112, 113, wind boxes 114, 115, 116 are provided respectively.

[0016] Furthermore, the incinerator 102 has a reburning chamber 117 continuous with the furnace chamber 103 between the furnace chamber 103 and the boiler 104. Note that the combustion stoker 112 is one stage in the illustrated example, but two or more stages may be provided. Each of the stokers 111, 112, 113 operates intermittently at different intervals, for example.

[0017] In the furnace chamber 103, combustion gas is generated by the thermal decomposition and partial oxidation reaction of the waste, and this combustion gas is burned together with the waste. The reburning chamber 117 is for completely burning the combustion gas flowing out from the furnace chamber 103. The dust after the combustion of the waste is discharged from an outlet 118 provided adjacent to the post-combustion stoker 113.

[0018] In the boiler 104, steam is generated by the waste heat of the combustion exhaust gas discharged from the incinerator 102. More specifically, as shown in FIG. 1, the boiler 104 includes an exhaust gas passage 109 through which the combustion exhaust gas passes. The exhaust gas passage 109 includes a radiation chamber 119 disposed above the reburning chamber 117, a first flue 120 in communication with the upper part of the radiation chamber 119, and a second flue 121 in communication with the lower part of the first flue 120. In other words, the boiler 104 has, as an internal space, the radiation chamber 119, the first flue 120, and the second flue 121.

[0019] A plurality of heat transfer tubes 123 are provided on each of the walls defining the radiation chamber 119, the first flue 120, and the second flue 121. The material of the plurality of heat transfer tubes 123 is carbon steel such as STB340, for example. The boiler 104 includes a boiler drum 124 connected to the plurality of heat transfer tubes 123. Water sent from the boiler drum 124 flows through the plurality of heat transfer tubes 123. The water in the plurality of heat transfer tubes 123 recovers the waste heat of the radiation chamber 119 and the first flue 120, and a part of the water evaporates to become steam-water mixture and is returned to the boiler drum 124. A part of the steam-water mixture returned to the boiler drum 124 has vaporized into steam.

[0020] A superheater 125 is provided in the second flue 121. The superheater 125 includes superheater tubes 126 for superheating the steam in the boiler drum 124 with the heat of combustion or the heat of the combustion exhaust gas. The superheated steam superheated by the superheater 125 to become high temperature and high pressure is sent to a turbine 128 connected to a generator 127 and used for power generation. Most of the combustion exhaust gas that has passed through the boiler 104 is discharged into the atmosphere from the chimney 108 after flowing through the exhaust path 107.

[0021] Figure 2 is a sectional view taken along line II-II of the radiation chamber shown in Figure 1. As shown in Figure 2, the radiation chamber 119 has a rectangular cross-section partitioned by four heat transfer surfaces F1, F2, F3, and F4. Each of the four heat transfer surfaces F1, F2, F3, and F4 has a membrane wall to which a plurality of heat transfer tubes 123 are connected. Hereinafter, the four heat transfer surfaces will be referred to as the first heat transfer surface F1, the second heat transfer surface F2, the third heat transfer surface F3, and the fourth heat transfer surface F4. The second heat transfer surface F2 faces the first heat transfer surface F1, and the fourth heat transfer surface F4 faces the third heat transfer surface F3.

[0022] The first heat transfer surface F1 and the second heat transfer surface F2 are planes parallel to a first virtual plane including the arrangement directions of the radiation chamber 119, the first flue 120, and the second flue 121, that is, planes parallel to the plane of the paper in Figure 1. The third heat transfer surface F3 and the fourth heat transfer surface F4 are planes intersecting the first heat transfer surface F1 and the second heat transfer surface F2. The third heat transfer surface F3 is also a heat transfer surface partitioning the first flue 120.

[0023] The first heat transfer surface F1 has a first window W1 through which infrared rays can pass. The heat transfer surface monitoring device 1 includes a first infrared camera 11 provided outside the first heat transfer surface F1 so as to photograph the second heat transfer surface F2 through the first window W1. Further, the heat transfer surface monitoring device 1 includes a second infrared camera 12 provided outside the second heat transfer surface F2 so as to photograph the first heat transfer surface F1 through the second window W2. The position P1 in Figure 1 indicates the positions of the first window W1 and the second window W2. The position P1 is located, for example, at the center in the waste gas flow direction in the radiation chamber 119.

[0024] The first infrared camera 11 measures the surface temperature of the second heat transfer surface by photographing the second heat transfer surface F2. Similarly, the second infrared camera 12 measures the surface temperature of the first heat transfer surface F1 by photographing the first heat transfer surface F1. The measurement results by the infrared cameras 11 and 12 are obtained as the surface temperature distribution in the photographing ranges of the infrared cameras 11 and 12. The surface temperature distribution is, for example, image data in which the photographing range is color-coded into a plurality of colors different according to a predetermined temperature range.

[0025] Furthermore, the heat transfer surface monitoring device 1 includes a thermometer 13 that measures the gas temperature in the radiation chamber 119. The thermometer 13 includes, for example, a temperature sensor having a thermocouple or the like. The thermometer 13 is disposed in the radiation chamber 119. The disposition position of the thermometer 13 is not particularly limited, but for example, it is disposed within the imaging angle of view of the first infrared camera 11 or the second infrared camera 12.

[0026] The first infrared camera 11 is rotatable around a predetermined rotation axis R1 along the vertical direction. Similarly, the second infrared camera 12 is also rotatable around a predetermined rotation axis R2 along the vertical direction. Both the rotation axis R1 and the rotation axis R2 are parallel to the first heat transfer surface F1 or the second heat transfer surface F2 and parallel to the third heat transfer surface F3 or the fourth heat transfer surface F4.

[0027] FIG. 3 is a diagram showing a state where the infrared cameras shown in FIG. 2 are rotated. In the example of FIG. 3, a state is shown in which both the first infrared camera 11 and the second infrared camera 12 are rotated so as to face the third heat transfer surface F3. Thus, by rotating the first infrared camera 11 or the second infrared camera 12, the third heat transfer surface F3 can be photographed and the surface temperature of the third heat transfer surface F3 can be measured. Similarly, by rotating the first infrared camera 11 or the second infrared camera 12, the fourth heat transfer surface F4 can be photographed and the surface temperature of the fourth heat transfer surface F4 can be measured.

[0028] Note that the imaging angle of view of the first infrared camera 11 can be set to an angle of view that includes both horizontal ends of the second heat transfer surface F2 in a state where the first infrared camera 11 is positioned at the facing position of the second heat transfer surface F2, for example. However, it may be a narrower angle of view. In this case, by rotating the first infrared camera 11 by a predetermined angle around the rotation axis F1 and taking a plurality of images as described above, the surface temperature distribution over the entire horizontal region of the second heat transfer surface F2 may be obtained. The same applies to the second infrared camera 12.

[0029] FIG. 4 is a block diagram showing a schematic configuration of the heat transfer surface monitoring device according to the present embodiment. The heat transfer surface monitoring device 1 includes the above-described first infrared camera 11, second infrared camera 12, thermometer 13, and calculator 14. The calculator 14 is constituted by a computer having a storage for storing various data. For example, the calculator 14 includes a CPU, main memory (RAM), storage, communication interface, and the like.

[0030] Note that the functions of the elements disclosed in this specification can be executed using a general-purpose processor, a dedicated processor, an integrated circuit, an ASIC (Application Specific Integrated Circuits), a conventional circuit, or a circuit or processing circuit including a combination thereof that is configured or programmed to execute the disclosed functions. Since a processor includes transistors and other circuits, it is regarded as a processing circuit or a circuit. In this specification, a circuit, a unit, or a means (… unit) is hardware that executes the listed functions, or hardware that is programmed to execute the listed functions. The hardware may be the hardware disclosed in this specification, or other known hardware that is programmed or configured to execute the listed functions. When the hardware is a processor considered to be a type of circuit, the circuit, unit, or means is a combination of hardware and software, and the software is used for the configuration of the hardware and / or the processor.

[0031] The calculator 4 acquires the surface temperature distributions of the heat transfer surfaces F1, F2, F3, F4 to be monitored from the corresponding infrared cameras 11, 12. Further, the calculator 14 acquires the gas temperature in the internal space of the boiler 104 partitioned by the heat transfer surfaces F1, F2, F3, F4 to be monitored from the thermometer 13. The calculator 4 performs an estimation calculation for estimating the thickness of the deposit attached to the corresponding heat transfer surface using the surface temperature of the heat transfer surface and the gas temperature.

[0032] Here, the surface temperature Td of the dust as the deposit is expressed by the following equation using the gas temperature Tg and the thickness td of the dust.

[0033] [Equation] Here, K is the heat transfer rate of the heat transfer tube 123, Kd is the heat transfer rate at the surface of the dust, Tw is the temperature of the water flowing inside the heat transfer tube 123. αc is the convective heat transfer rate, αr is the radiative heat transfer rate, and αw is the internal heat transfer rate of the heat transfer tube 123. λ is the thermal conductivity of the heat transfer tube 123, t is the wall thickness of the heat transfer tube 123. λd is the thermal conductivity of the dust.

[0034] Values other than the surface temperature Td of the dust, the gas temperature Tg, and the thickness td of the dust used in the above equations (1) to (4) are all given in advance from heat calculations at the time of design or average measured values, etc. Therefore, the above equations (1) to (4) can be rewritten as equations for obtaining the thickness td of the dust from the surface temperature Td of the dust and the gas temperature Tg as follows.

[0035] [Equation]

[0036] The surface temperature Td of the dust corresponds to the surface temperature of the heat transfer surface acquired by the infrared cameras 11, 12. The gas temperature Tg is the temperature acquired by the thermometer 13. When the arithmetic unit 14 acquires the gas temperature Tg measured by the thermometer 13 and acquires the temperature at a certain position coordinate from the surface temperature distribution of the heat transfer surface, and uses the acquired temperature as the surface temperature Td of the dust, it calculates the thickness td of the dust from the above equation (5). That is, the above equation (5) includes the variables Tg and Td in the first term, and the second term is a constant.

[0037] In the above formula (5), when the gas temperature Tg increases, the numerator of the first term becomes larger than the denominator, so the dust thickness td increases. This means that when the dust thickness td increases, the heat exchange between the exhaust gas in the boiler 104 and the heat transfer tube 123 decreases, and as a result, the decrease in the gas temperature Tg is suppressed. Also, in the above formula (5), when the surface temperature Td of the dust increases, the denominator of the first term becomes smaller, so the dust thickness td increases. This means that when the dust thickness td increases, the heat exchange between the exhaust gas in the boiler 104 and the heat transfer tube 123 decreases, and as a result, the surface temperature Td of the dust increases. Therefore, the higher the gas temperature Tg, the larger the dust thickness td, and the higher the surface temperature Td of the dust, the larger the dust thickness td.

[0038] The calculator 14 calculates the dust thickness td for a plurality of position coordinates in the surface temperature distribution of the heat transfer surface, that is, in the captured images of the infrared cameras 11 and 12. For example, the calculator 14 acquires the temperature at each predetermined coordinate position interval from the surface temperature distribution, and calculates the dust thickness td for each of the acquired temperatures. Thereby, the dust thickness distribution on the heat transfer surface within the imaging range of the infrared cameras 11 and 12 can be obtained.

[0039] As described above, according to the heat transfer surface monitoring device 1 in the present embodiment, from the surface temperatures of the heat transfer surfaces F1, F2, F3, F4 obtained from the captured images taken by the infrared cameras 11 and 12 and the gas temperature in the boiler 104, the dust thickness td, which is an attachment, can be obtained as three-dimensional information with thickness information added to the planar image that is the imaging range of the infrared cameras 11 and 12. Therefore, the thickness distribution of the dust adhering to the heat transfer surfaces F1, F2, F3, F4 can be estimated quantitatively and in real time. Also, by performing repeated imaging according to the passage of time, the temporal change in the thickness distribution of the dust adhering to the heat transfer surfaces F1, F2, F3, F4 can also be obtained.

[0040] In addition, since the infrared cameras 11 and 12 are arranged to face each other, it is possible to estimate the thickness distribution of dust on both of the opposing heat transfer surfaces F1 and F2. Further, since the infrared cameras 11 and 12 rotate around the rotation axes R1 and R2, it is also possible to estimate the thickness distribution of dust on the heat transfer surfaces F3 and F4 that are orthogonal to the first heat transfer surface F1 and the second heat transfer surface F2 where the first window W1 and the second window W2 for the infrared cameras 11 and 12 are installed. Therefore, it is possible to monitor the conditions of a wide range of heat transfer surfaces while suppressing the number of components required for the heat transfer surface monitoring device 1.

[0041] The positions of the infrared cameras 11 and 12 can be appropriately set according to the position of the heat transfer surface to be measured. For example, in order to obtain the thickness distribution of dust on the heat transfer surface in the first flue 120, the infrared cameras 11 and 12 are installed at the position P2, the position P3, or both positions in the first flue 120. Also, for example, in order to obtain the thickness distribution of dust on the heat transfer surface in the second flue 121, the infrared cameras 11 and 12 are installed at the positions P4, P5, or both positions in the second flue 121.

[0042] In this way, the infrared cameras 11 and 12 can be installed at one or more locations in each exhaust gas path partitioned by the heat transfer pipes 123. When installing the infrared cameras 11 and 12 at multiple locations, they may be installed in the flow direction of the exhaust gas path, for example, vertically, or in a direction intersecting the flow direction of the exhaust gas path, for example, horizontally. Also, in this embodiment, an example is shown where the infrared cameras 11 and 12 can rotate in the left-right direction, but in addition to this, or instead of this, they may be able to rotate in the up-down direction. For example, the infrared cameras 11 and 12 may be able to rotate around a rotation axis parallel to the horizontal plane.

[0043] By installing the infrared cameras 11 and 12 at multiple locations, rotating the infrared cameras 11 and 12, or a combination thereof, it is possible to photograph the entire desired heat transfer surface. That is, the surface temperature distribution of the entire heat transfer surface can be obtained. Therefore, the arithmetic unit 14 can estimate the thickness distribution of dust adhering to the entire heat transfer surface from the surface temperature distribution of the entire heat transfer surface.

[0044] The thermometer 13 for measuring the gas temperature in the boiler 104 can also be installed at a plurality of locations in the boiler 104. For example, when monitoring the heat transfer surface in the first flue 120, the thermometer 13 may be installed in the first flue 120. Also, for example, when monitoring the heat transfer surface in the second flue 121, the thermometer 13 may be installed in the second flue 121. Further, the thermometer 13 may be installed in each of the radiation chamber 119, the first flue 120, and the second flue 121. In this case, for the estimation calculation of the dust thickness distribution on the heat transfer surface of the radiation chamber 119, the gas temperature measured by the thermometer 13 in the radiation chamber 119 is used, and for the estimation calculation of the dust thickness distribution in the first flue 120, the gas temperature measured by the thermometer 13 in the first flue 120 is used, and for the estimation calculation of the dust thickness distribution in the second flue 121, the gas temperature measured by the thermometer 13 in the second flue 121 may be used.

[0045] As described above, by obtaining the dust thickness distribution on the heat transfer surfaces F1, F2, F3, F4, it is possible to efficiently set the maintenance timing for performing cleaning or the like inside the boiler 104 to an appropriate timing. For example, the calculator 14 may display, on a predetermined monitor, the dust thickness distribution as image data color-coded into a plurality of different colors according to a predetermined thickness range. Further, the location where cleaning is to be performed inside the boiler 104 can be determined precisely.

[0046] For example, when the area where the dust thickness td exceeds a predetermined threshold value on the entire heat transfer surface becomes equal to or greater than a predetermined reference area, maintenance may be performed. For example, the calculator 14 may display an image of the thickness distribution on a monitor and highlight the locations where the dust thickness exceeds the threshold value on the image. The highlighting may include, for example, causing the locations to blink. Also, the cleaning location when performing maintenance may be within a predetermined range centered on the locations where the threshold value is exceeded. The maintenance or cleaning work may be performed manually by an operator entering the boiler 104, or may be performed by the cleaning device 21 described later.

[0047] [Heat Transfer Surface Cleaning System] Furthermore, in the present embodiment, the incineration plant 100 includes a heat transfer surface cleaning system 2 for cleaning inside the boiler 104. FIG. 5 is a block diagram showing a schematic configuration of the heat transfer surface cleaning system in the present embodiment. As shown in FIG. 5, the heat transfer surface cleaning system 2 also includes infrared cameras 11, 12 and a thermometer 13, similar to the heat transfer surface monitoring device 1. The infrared cameras 11, 12 and the thermometer 13 may be shared by the heat transfer surface monitoring device 1 and the heat transfer surface cleaning system 2, or the infrared cameras 11, 12 and the thermometer 13 for the heat transfer surface monitoring device 1 and the infrared cameras 11, 12 and the thermometer 13 for the heat transfer surface cleaning system 2 may be installed inside the boiler 104.

[0048] Furthermore, the heat transfer surface cleaning system 2 includes a cleaning device 21 and a controller 22. The cleaning device 21 is not particularly limited, but for example, it is a water injection cleaning device having a water injection nozzle 21a for injecting water as a cleaning fluid. The cleaning device 21 has a main body portion 21b installed outside the boiler 104 and a water supply pipe 21c extending into the boiler 104 and connecting between the main body portion 21b and the water injection nozzle 21a. The water supply pipe 21c is inserted into the boiler 104 through an insertion hole located in the ceiling portion of the boiler 104. The main body portion 21b includes a pump for pumping water. Water flows through the water supply pipe 21c from the main body portion 21b, and water is injected into the boiler 104 from the water injection nozzle 21a. The main body portion 21b includes a drive unit for changing the water injection direction or injection range at the water injection nozzle 21a and changing the vertical position of the water injection nozzle 21a.

[0049] The controller 22 is constituted by a computer having a storage for storing various data. For example, the controller 22 includes a CPU, a main memory (RAM), a storage, a communication interface, etc.

[0050] The controller 22 controls the operation of the cleaning device 21. For example, the controller 22 controls the vertical position of the water injection nozzle 21a. Further, the controller 22 controls the direction or injection range of the water injection at the water injection nozzle 21a. Thereby, the position where water is injected from the water injection nozzle 21a onto the heat transfer surface is controlled. In addition, the controller 22 controls the injection amount of the water injected from the water injection nozzle 21a.

[0051] The controller 22 controls the position of the water injection nozzle 21a and the injection amount of water based on the dust thickness distribution estimated by the arithmetic unit 14 of the heat transfer surface monitoring device 1. For example, the controller 22 sets, as a target position, a position where the dust thickness is equal to or greater than a predetermined threshold from the dust thickness distribution, and controls the position of the water injection nozzle 21a so that water injection is performed toward the target position. Further, the controller 22 controls the injection amount of water according to the dust thickness at the target position. The injection amount of water is adjusted, for example, by changing the injection time, changing the injection amount per unit time, or changing the number of injections when a predetermined injection amount is injected each time.

[0052] Regarding the control of the water injection amount, the controller 22 may determine the injection amount using a learned model based on machine learning. In the following example, an aspect in which the controller 22 generates a learned model by reinforcement learning is illustrated. In reinforcement learning, the learning of the agent progresses through the interaction between the agent that is the subject of learning and the environment that is the control target. In the present embodiment, the agent is the controller 22, and the environment that is the control target is the boiler 104 and the cleaning device 21. More specifically, the following (A) to (D) are repeated when the agent learns. (A) The agent observes the state S of the environment at time T t of the environment. (B) Based on the observation result and past learning, the agent selects an action A t that it can take and executes the action A t of the environment. (C) By executing the action A t the state S t of the environment changes to the next state S t+1changes to, and based on this change in state, the agent receives reward R t+1 to receive. (D) The agent advances learning based on state S t , action A t , reward R t+1 and the results of past learning.

[0053] In the learning in (D) above, the agent uses state S t , action A t , reward R t+1 as information serving as a criterion for judging the amount of reward R that can be obtained in the future, and obtains the mapping of. For example, if the number of possible states at each time is m and the number of possible actions is n, by repeating the action, state S t and action A t for the pair of, a two-dimensional m×n array storing reward R t+1 is obtained. Then, using a value function or evaluation function, which is a function indicating how good the current state and action are based on the obtained mapping, the value function is updated while repeating the action to learn the optimal action for the state.

[0054] The state-action value function Q(S t ,A t ), known as one of the value functions, indicates how good action A t is in a certain state S t . The state-action value function Q(S t ,A t ) is expressed as a function taking the state and action as arguments. The state-action value function Q(S t ,A t ) is updated based on the reward obtained for the action in a certain state and the value of the action in the future state transitioned to by the action during learning while repeating the action. The update formula of the state-action value function Q(S t ,A t ) is defined according to the reinforcement learning algorithm. For example, in Q-learning, which is one of the typical reinforcement learning algorithms, the state-action value function Q(S t ,At ) The update formula is defined by the following formula (6).

[0055] [Number] However, Q: State-action value function S t : State at time t A t : Action for the state at time t R t+1 : Reward obtained from the state at time t+1 η: Learning coefficient (0 < η ≤ 1) γ: Discount rate (0 < γ ≤ 1)

[0056] And, in the selection of action A in the above (B) t , the value function created by past learning is used to calculate the future reward (R t +R t+1 +…) that is optimal for the current state S t+2 , that is, the action A t that maximizes the future reward, i.e., the action A t with the highest value in state S t is selected. In Q-learning, the action A t+1 for which the reward (R t+2 +R t +…) is optimal t+1 corresponds to the action A t+2 for which the reward (R t +R

[0057] As reinforcement learning algorithms, various methods such as Q-learning, SARSA method, TD learning, and AC method are well-known. However, any reinforcement learning algorithm may be adopted as the method applied to the present invention. Since these reinforcement learning algorithms are well-known, further detailed descriptions of each algorithm in this specification are omitted.

[0058] Also, as a method for updating the value function, by applying a certain action A t to the current state S t , the state S ttransitions to a new state S t+1 Each time it transitions, it is not necessary to adopt a learning method of updating the value function, so-called online learning. For example, for the current state S t when a certain action A t is applied, the state S t transitions to a new state S t+1 This process is repeated, and these states and actions are accumulated as learning data, and so-called batch learning or mini-batch learning that updates the value function using the accumulated learning data may be adopted.

[0059] For this purpose, the controller 22 includes an injection amount output unit 221, a state value acquisition unit 222, a reward calculation unit 223, and a learning unit 224.

[0060] The injection amount output unit 221 outputs an injection amount as a command value for the cleaning device 21. The injection amount becomes an operation value described later. The state value acquisition unit 222 acquires the surface temperature of the heat transfer surface obtained from the captured images taken by the infrared cameras 11 and 12 and the gas temperature Tg measured by the thermometer 13 as state values. The acquired state values are stored in the storage of the controller 22. In the storage, the state values at predetermined time intervals are stored as a history. Further, the state value acquisition unit 222 also acquires the injection amount command value and stores it in the storage. In the storage, the position of the heat transfer surface where the cleaning device 21 has performed cleaning, the time when the cleaning was performed, and the water injection amount are stored as a history. As a result, the reward calculation unit 223 regards the surface temperature Td of the heat transfer surface and the gas temperature Tg at the position of the heat transfer surface included in the period up to a predetermined time before the time when cleaning was performed at a predetermined heat transfer surface position as the pre-cleaning surface temperature and the pre-cleaning gas temperature, and regards the surface temperature Td of the heat transfer surface and the gas temperature Tg at the position of the heat transfer surface included in the period from the time when cleaning was performed to a predetermined time later as the post-cleaning surface temperature and the post-cleaning gas temperature, and performs the following calculations.

[0061] The reward calculation unit 223 analyzes the state values acquired by the state value acquisition unit 222 based on preset reward conditions to calculate the reward. The reward calculation unit 223 outputs the calculated reward to the learning unit 224.

[0062] The reward condition is a condition for giving rewards in reinforcement learning. The reward condition is stored in advance in storage memory. For example, when it is determined that the post-washing gas temperature is low, the reward condition includes giving a larger reward than when it is determined that the post-washing gas temperature is high. Also, for example, when it is determined that the post-washing surface temperature is high, the reward condition includes giving a larger reward than when it is determined that the post-washing surface temperature is low. Rewards include, for example, positive rewards, negative rewards, or no reward, i.e., zero reward.

[0063] The reward calculation unit 223 calculates a positive reward when the post-washing gas temperature is lower than a predetermined first reference value, and calculates a negative or zero reward when it is higher than the first reference value. Also, the reward calculation unit 223 calculates a positive reward when the post-washing surface temperature is lower than a predetermined second reference value, and calculates a negative or zero reward when it is higher than the second reference value. The first reference value and the second reference value are determined based on simulations, past operation results, etc., and are stored in advance in the storage of the controller 22.

[0064] Instead of comparing the post-washing gas temperature itself, the reward calculation unit 223 may compare the value obtained by subtracting the post-washing gas temperature from the pre-washing gas temperature with a predetermined third reference value, and calculate a positive reward when the value is larger than the third reference value, and calculate a negative or zero reward when the value is smaller than the third reference value. Similarly, instead of comparing the post-washing surface temperature itself, the reward calculation unit 223 may compare the value obtained by subtracting the post-washing surface temperature from the pre-washing surface temperature with a predetermined fourth reference value, and calculate a positive reward when the value is larger than the fourth reference value, and calculate a negative or zero reward when the value is smaller than the fourth reference value.

[0065] Here, for the calculation of the reward, it is not necessary to perform cleaning at all heat transfer surface positions. For example, when the thickness of the dust estimated by the arithmetic unit 14 at a heat transfer surface position predetermined as a calculation target becomes equal to or greater than a predetermined threshold value, and the cleaning device 21 cleans the heat transfer surface position, the reward calculation unit 223 may calculate the reward from the injection amount of water, the surface temperature after cleaning, and the gas temperature after cleaning related to the cleaning.

[0066] The learning unit 224 performs machine learning to determine the operation value, that is, the injection amount output by the injection amount output unit 221, from the current state value based on the injection amount command value to the cleaning device 21, the state value acquired from the state value acquisition unit 222, and the reward calculated by the reward calculation unit 223. More specifically, the learning unit 224 is a state S defined by a combination of state values t and the determination of the operation value in the state are expressed as arguments, for example, the value function, such as the state-action value function Q(S t , A t ), and updates the value function so that the obtained reward is maximized.

[0067] The result of learning by the learning unit 224 is stored in the storage as a learned model. As a method of storing the value function as the learning result, a method using an approximation function or a method using an array is generally used. However, in addition to these methods, for example, when the state takes many states, the state S t , action A t A method using a supervised learning device such as a multi-value output SVM or neural network that outputs a value with S and A as inputs may also be used.

[0068] The injection amount output unit 221 outputs the injection amount, which is the operation value, based on the learned model and the current state value.

[0069] Note that the learned model may be a common learned model regardless of the position of the heat transfer surface, or may include a plurality of different learned models according to the position or region of the heat transfer surface. For example, in the radiation chamber 119, the first flue 120, and the second flue 121, the learned models used to determine the injection amount may be different from each other. In this case, the learning unit 224 performs machine learning based on the state value in the radiation chamber 119 and the injection amount in the radiation chamber 119. The same applies to the first flue 120 and the second flue 121. Further, for example, in the first heat transfer surface F1, the second heat transfer surface F2, the third heat transfer surface F3, and the fourth heat transfer surface F4, the learned models used to determine the injection amount may be different from each other.

[0070] Next, the flow of machine learning in the present embodiment will be described. FIG. 6 is a flowchart showing the flow of machine learning performed by the controller shown in FIG. 5.

[0071] When machine learning is started, the state value acquisition unit 222 acquires, in step S1, the state value at time t as data for specifying the state S t . The state value acquisition unit 222 stores the acquired state value in the storage. The learning unit 224 specifies, in step S2, the current state S t based on the state value acquired by the state value acquisition unit 222. The learning unit 224 selects, in step S3, the action A t based on the past learning result and the specified state S t . The action A t is the determination of the operation value corresponding to the defined state S t . Here, for example, a plurality of operation values may be prepared as selectable actions, and the action A that maximizes the reward R that can be obtained in the future based on the past learning result may be selected. The injection amount output unit 221 determines the operation value to be output based on the selected action A t , and outputs the determined operation value to the cleaning device 21. In step S4, the action A t is executed by the cleaning device 21, and the cleaning in the boiler 104 is performed.

[0072] Action A t After Action A is executed and the state transitions, the state value acquisition unit 222 acquires, in step S5, data for specifying state S t+1 as the state value. At this stage, the state of the boiler 104 changes with the time progression from time t to time t + 1 due to the executed Action A t . The reward calculation unit 223 obtains, in step S6, reward R t+1 from the state value at time t + 1 based on the set reward conditions. The learning unit 224 proceeds with machine learning in step S7 based on t state S t , Action A t+1 , and reward R

[0073] . The value function used for learning is determined according to the learning algorithm to be applied. The learning unit 224 stores the learning result in the storage in step S8. The learning at time t + 1 can be executed in the same manner as above by reading time t in the flowchart shown in FIG. 6 as time t + 1

[0074] In this way, the learning unit 224 repeats the machine learning. The learning by the learning unit 224 may be completed at the stage where it is confirmed that an optimal system for injection amount control has been realized. For example, the learning by the learning unit 224 may be completed at the stage where the reward calculated by the reward calculation unit 223 becomes positive at a predetermined rate or more. After the learning is completed, learning using the newly obtained state value and operation value is not performed, and the learned model is not updated

[0075] As described above, according to the heat transfer surface cleaning system 2 in the present embodiment, the surface temperatures of the heat transfer surfaces F1, F2, F3, and F4 obtained from the captured images taken by the infrared cameras 11 and 12 and the gas temperature Tg in the boiler 104 are used as state values, and the reward is calculated based on the gas temperature Tg after cleaning by the cleaning device 21, whereby the optimal injection amount of water injected from the cleaning device 21, which is an operation value, is learned. Thereby, the thickness td of the dust estimated from the surface temperature Td of the heat transfer surface and the gas temperature Tg and the injection amount of water for cleaning the dust can be correlated pinpoint by position of the heat transfer surface according to the surface temperature distribution of the heat transfer surface. Therefore, an appropriate cleaning ability can be applied to the thickness of the dust adhering to the heat transfer surface.

[0076] Further, in the present embodiment, as described above, when the post-cleaning gas temperature is lower than a predetermined first reference value, the reward calculation unit 223 calculates a positive reward, and when it is higher than the first reference value, it calculates a negative or zero reward. Alternatively, when the value obtained by subtracting the pre-cleaning gas temperature from the post-cleaning gas temperature is lower than a predetermined third reference value, the reward calculation unit 223 calculates a positive reward, and when it is higher than the third reference value, it calculates a negative or zero reward. Thereby, it is possible to evaluate that the decrease in the gas temperature Tg due to cleaning is regarded as a reduction in the dust thickness td and an increase in the thermal efficiency between the exhaust gas in the boiler 104 and the heat transfer pipe 123.

[0077] Furthermore, in the present embodiment, in addition to the temperature of the gas after cleaning, the reward is calculated based on the surface temperature after cleaning. As a result, more appropriate learning using a plurality of evaluation criteria can be performed. At this time, when the surface temperature after cleaning is greater than a predetermined second reference value, the reward calculation unit 223 calculates a positive reward, and when it is less than the second reference value, the reward calculation unit 223 calculates a negative or zero reward. Alternatively, when the value obtained by subtracting the surface temperature before cleaning from the surface temperature after cleaning is greater than a predetermined fourth reference value, the reward calculation unit 223 calculates a positive reward, and when it is less than the fourth reference value, the reward calculation unit 223 calculates a negative or zero reward. Thereby, it can be evaluated that the surface temperature of the heat transfer surface has increased due to cleaning, assuming that the thickness td of the dust has decreased and the thermal efficiency between the exhaust gas in the boiler 104 and the heat transfer tube 123 has increased.

[0078] Furthermore, in the present embodiment, a water injection cleaning device that injects water is used as the cleaning device 21. As a result, cleaning in a narrow area unit becomes possible, and more pinpoint cleaning can be performed.

[0079] [Modification Example] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above embodiments, and various improvements, changes, and modifications are possible without departing from the spirit thereof.

[0080] For example, in the above embodiment, an example applied to a waste heat boiler that uses the exhaust gas of the incineration plant 100 has been shown, but the configuration of the present disclosure can be widely applied to a solid fuel-fired boiler that generates dust.

[0081] Also, in the above embodiment, an aspect in which the infrared cameras 11 and 12 are installed on the first heat transfer surface F1 and the second heat transfer surface F2 has been illustrated. In addition to or instead of this, an infrared camera may be installed on the third heat transfer surface F3 or the fourth heat transfer surface F4. Also, at least one infrared camera may be installed to obtain the surface temperature distribution on at least one heat transfer surface.

[0082] Also, in the above-described embodiment, an example was shown in which the arithmetic unit 14 of the heat transfer surface monitoring device 1 and the controller 22 of the heat transfer surface cleaning system 2 are configured by different computers, but the present invention is not limited to this. For example, the controller 22 of the heat transfer surface cleaning system 2 may have the arithmetic unit 14 of the heat transfer surface monitoring device 1. Further, for example, the control device of the incinerator 100 may have the arithmetic unit 14 and the controller 22.

[0083] Also, in the above-described embodiment, an aspect was exemplified in which the controller 22 has the functional blocks or circuits 222, 223, 224 for performing machine learning. However, the heat transfer surface cleaning system 2 may separately include a learning device for performing machine learning.

[0084] Also, in the above-described embodiment, an aspect was exemplified in which the reward calculation unit 223 calculates the reward based on the surface temperature after cleaning in addition to the gas temperature after cleaning. However, the reward calculation unit 223 may calculate the reward based only on the gas temperature after cleaning.

[0085] Also, in the above-described embodiment, an example was shown in which the cleaning device 21 is a water injection cleaning device including a water injection nozzle 21a that injects water as a cleaning fluid, but the present invention is not limited to this. For example, the cleaning device 21 may be a steam cleaning device including a steam injection nozzle that injects steam as a cleaning fluid. Further, for example, the cleaning device 21 may be a pressure wave cleaning device including a discharge duct that ejects a pressure wave as a cleaning fluid. A plurality of types of cleaning devices may be combined. For example, the cleaning device 21 for cleaning the radiation chamber 119 and the first flue 120 may be a water injection cleaning device, and the cleaning device 21 for cleaning the second flue 121 in which the superheater protrudes inside may be a pressure wave cleaning device or a steam cleaning device.

[0086] In addition, in the above-described embodiment, an example configuration is shown in which the cleaning device 21 supplies the cleaning fluid into the boiler 104 via the ceiling portion of the boiler 104. However, the present invention is not limited to this. For example, the cleaning device 21 may supply the cleaning fluid into the boiler 104 via the side wall portion of the boiler 104. For example, at least any one of the heat transfer surfaces F1, F2, F3, and F4 may have an insertion hole through which the water supply pipe 21c is inserted. In this case, in order to enable cleaning of a plurality of heat transfer surface regions, the heat transfer surface may have a plurality of insertion holes.

[0087] In addition, in the above-described embodiment, an example configuration is shown in which the incineration plant 100 includes both the heat transfer surface monitoring device 1 and the heat transfer surface cleaning system 2. However, the heat transfer surface monitoring device 1 is also applicable to boilers such as incineration plants that do not have the heat transfer surface cleaning system 2. That is, the heat transfer surface monitoring device 1 is also applicable to the boiler 104 in which control of the injection amount for cleaning using the learned model is not performed.

[0088] [Summary of the Present Disclosure] A heat transfer surface monitoring device (1) according to an aspect of the present disclosure includes an infrared camera (11, 12) that measures the surface temperature of the heat transfer surfaces (F1, F2, F3, F4) by photographing the heat transfer surfaces (F1, F2, F3, F4) exposed inside the boiler (104), a thermometer (13) that measures the gas temperature in the internal space of the boiler (104), and an arithmetic unit (14) that estimates the thickness of deposits adhering to the heat transfer surfaces (F1, F2, F3, F4). The arithmetic unit (14) estimates the thickness of deposits adhering to the heat transfer surfaces (F1, F2, F3, F4) using the measured surface temperature of the heat transfer surfaces (F1, F2, F3, F4) and the measured gas temperature.

[0089] According to the above configuration, from the surface temperatures of the heat transfer surfaces F1, F2, F3, and F4 obtained from the captured images taken by the infrared cameras 11 and 12, and the gas temperature inside the boiler 104, the thickness td of the dust, which is the deposit, can be obtained as three-dimensional information with thickness information added to the planar image within the imaging ranges of the infrared cameras 11 and 12. Therefore, the thickness distribution of the dust adhering to the heat transfer surfaces F1, F2, F3, and F4 can be quantitatively estimated.

[0090] The heat transfer surface includes a first heat transfer surface (F1) that defines the internal space of the boiler (104), and a second heat transfer surface (F2) that faces the first heat transfer surface (F1). The first heat transfer surface (F1) has a first window (W1) through which infrared rays can pass, and the second heat transfer surface (F2) has a second window (W2) through which infrared rays can pass. The infrared camera may include a first infrared camera (11) provided outside the first heat transfer surface (F1) so as to capture the second heat transfer surface (F2) through the first window (W1), and a second infrared camera (12) provided outside the second heat transfer surface (F2) so as to capture the first heat transfer surface (F1) through the second window (W2).

[0091] According to this aspect, since the infrared cameras 11 and 12 are arranged to face each other, the thickness distribution of the dust on both of the opposing heat transfer surfaces F1 and F2 can be estimated.

[0092] The heat transfer surface includes a third heat transfer surface (F3) provided in a direction intersecting the second heat transfer surface (F2). The first infrared camera (11) may rotate around a rotation axis (R1) parallel to the second heat transfer surface (F2) and the third heat transfer surface (F3) in order to capture the second heat transfer surface (F2) and the third heat transfer surface (F3).

[0093] According to this aspect, since the first infrared camera 11 rotates around the rotation axis R1, it is also possible to estimate the thickness distribution of dust on the second heat transfer surface F2 facing the first heat transfer surface F1 where the first window W1 for the first infrared camera 11 is installed and on the third heat transfer surface F3 orthogonal to the second heat transfer surface F2. Therefore, it is possible to monitor the conditions of a wide range of heat transfer surfaces while suppressing the number of components required for the heat transfer surface monitoring device 1.

[0094] The heat transfer surface monitoring method according to another aspect of the present disclosure photographs the heat transfer surfaces (F1, F2, F3, F4) exposed inside the boiler (104) with infrared cameras (11, 12) to measure the surface temperature of the heat transfer surfaces (F1, F2, F3, F4), measures the gas temperature in the internal space of the boiler (104), and estimates the thickness of the deposits adhering to the heat transfer surfaces (F1, F2, F3, F4) using the measured surface temperature of the heat transfer surfaces (F1, F2, F3, F4) and the measured gas temperature.

Explanation of Reference Numerals

[0095] 1 Heat transfer surface monitoring device 11 First infrared camera 12 Second infrared camera 13 Thermometer 14 Arithmetic unit 104 Boiler F1, F2, F3, F4 Heat transfer surfaces W1 First window W2 Second window

Claims

1. An infrared camera that measures the surface temperature of the heat transfer surface by photographing the heat transfer surface exposed inside the boiler, a thermometer that measures the gas temperature in the internal space of the boiler, and a calculator that estimates the thickness of the deposit adhering to the heat transfer surface, wherein the calculator estimates the thickness of the deposit adhering to the heat transfer surface using the measured surface temperature of the heat transfer surface and the measured gas temperature. A heat transfer surface monitoring device.

2. The heat transfer surface includes a first heat transfer surface that defines the internal space of the boiler and a second heat transfer surface that faces the first heat transfer surface, the first heat transfer surface has a first window through which infrared rays can pass, the second heat transfer surface has a second window through which infrared rays can pass, the infrared camera includes a first infrared camera provided outside the first heat transfer surface so as to photograph the second heat transfer surface through the first window, and a second infrared camera provided outside the second heat transfer surface so as to photograph the first heat transfer surface through the second window. The heat transfer surface monitoring device according to Claim 1.

3. The heat transfer surface includes a third heat transfer surface provided in a direction intersecting the second heat transfer surface, wherein the first infrared camera rotates around a rotation axis parallel to the second heat transfer surface and the third heat transfer surface in order to photograph the second heat transfer surface and the third heat transfer surface. The heat transfer surface monitoring device according to Claim 2.

4. The surface temperature of the heat transfer surface is measured by photographing the heat transfer surface exposed inside the boiler with an infrared camera, the gas temperature in the internal space of the boiler is measured, and the thickness of the deposit adhering to the heat transfer surface is estimated using the measured surface temperature of the heat transfer surface and the measured gas temperature. A heat transfer surface monitoring method.

Images