WO2022210827A1 - Control method for wet flue gas desulfurisation device, control device for wet flue gas desulfurisation device, remote monitoring system comprising said control device for wet flue gas desulfurisation device, information processing device, and information processing system - Google Patents

Abstract

A wet flue gas desulfurisation device comprises an absorption column, a circulating pump and an absorbing agent slurry supply unit. In this control method for said device, a learning model is constructed, by machine learning, for the relationship between: explanatory variables which include the absorbing agent concentration in an absorption liquid, the circulation flow rate of the absorption liquid and at least one parameter that correlates with the output of a generator; and a target variable which is a future concentration of sulfur dioxide at the outlet of the absorption column. For each generator output, a predicted value of the concentration of sulfur dioxide from the learning model is calculated, and a table indicating an introduced amount of the absorbing agent and a circulation flow rate of the absorption liquid that would be required for the predicted value to be less than or equal to a reference value is created. On the basis of said table, control target values are determined for the introduced amount of the absorbing agent and the circulation flow rate of the absorption liquid, which correspond to the state of the generator.

Description

Control method for wet flue gas desulfurization equipment, control device for wet flue gas desulfurization equipment, remote monitoring system provided with this control device for wet flue gas desulfurization equipment, information processing device, and information processing system

The present disclosure relates to a control method for a wet flue gas desulfurization apparatus, a control apparatus for a wet flue gas desulfurization apparatus, a remote monitoring system provided with the control apparatus for the wet flue gas desulfurization apparatus, an information processing device, and an information processing system.
This application claims priority based on Japanese Patent Application No. 2021-061440 filed with the Japan Patent Office on March 31, 2021, the content of which is incorporated herein.

In a wet flue gas desulfurization system, exhaust gas generated by a combustion device such as a boiler is introduced into an absorption tower of the desulfurization system, and brought into gas-liquid contact with an absorption liquid circulating in the absorption tower. During the gas-liquid contact process, the absorbent (e.g., calcium carbonate) in the absorbent reacts with the sulfur dioxide (SO ₂ ) in the flue gas, so that the SO ₂ in the flue gas is absorbed by the absorbent and removed from the flue gas. SO2 is removed ₍ exhaust gas is desulfurized). On the other hand, the absorbent that has absorbed SO ₂ drops and is stored in the storage tank below the absorption tower. An absorbent is supplied to the storage tank, and the absorbent whose absorption performance has been restored by the supplied absorbent is supplied to the upper part of the absorption tower by a circulating pump, and is subjected to gas-liquid contact with exhaust gas ₍ SO2 absorption). be done. Since the circulation pump that circulates the absorbent consumes a large amount of power, conventionally, in order to suppress power consumption, the amount of absorbent required based _on the flow rate of the flue gas flowing into the absorber and the SO2 concentration in the flue gas is used. The circulation flow rate is calculated and the number of operating circulation pumps is controlled.

Patent Literature 1 discloses a technique for appropriately adjusting operating conditions of a circulation pump for circulating an absorbent in an absorption tower of such a wet flue gas desulfurization apparatus. In this document, using operating data obtained from a combustion apparatus such as a boiler and a wet flue gas desulfurization apparatus, the correlation between the operating data and the SO ₂ concentration at the absorption tower outlet, and the operating data and the absorption liquid The correlation with the absorbent concentration is modeled by machine learning, and based on the table obtained by these two learning models, the circulating flow rate of the absorbent and the absorbent concentration are controlled to be optimized.

JP 2020-11163 A

However, Patent Document 1 does not specify parameters that are highly correlated with the SO ₂ concentration and the absorbent concentration at the outlet of the absorption tower when constructing the learning model. Therefore, there is a risk that prediction disturbance will occur, and the widening of the learning range of the operating data may increase the computational load. In addition, it is necessary to construct two learning models by machine learning the correlation between the operating data and the SO ₂ concentration at the absorption tower outlet, and the correlation between the operating data and the concentration of the absorbent contained in the absorbent. The calculation tends to be complicated because of the presence of

At least one embodiment of the present disclosure has been made in view of the above circumstances, and control of a wet flue gas desulfurization apparatus that can easily perform control for circulating an absorbent in an absorption tower of a wet flue gas desulfurization apparatus An object is to provide a method, a control device, a remote monitoring system, an information processing device, and an information processing system.

In order to solve the above problems, a method for controlling a wet flue gas desulfurization apparatus according to at least one embodiment of the present disclosure includes:
A control method for a wet flue gas desulfurization apparatus for performing desulfurization by bringing exhaust gas generated in a combustion apparatus and an absorbing liquid into gas-liquid contact in an absorption tower, comprising:
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A step of building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A step of creating a table showing the input amount of and the circulation flow rate of the absorbent;
and determining control target values for the amount of the absorbent to be supplied and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

In order to solve the above problems, a control device for a wet flue gas desulfurization apparatus according to at least one embodiment of the present disclosure includes:
A control device for a wet flue gas desulfurization device that performs gas-liquid contact between an exhaust gas generated in a combustion device and an absorbing liquid in an absorption tower to perform desulfurization,
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model building unit for building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
A control target value determination unit for determining control target values of the amount of the absorbent charged and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

In order to solve the above problems, the remote monitoring system according to at least one embodiment of the present disclosure,
a control device for a wet flue gas desulfurization system according to at least one embodiment of the present disclosure;
and a remote monitoring device electrically connected to the control device of the wet flue gas desulfurization system.

An information processing device according to at least one embodiment of the present disclosure, in order to solve the above problems,
An information processing device that executes processing related to control of a wet flue gas desulfurization device that performs desulfurization by bringing exhaust gas generated in a combustion device and an absorbent into gas-liquid contact in an absorption tower,
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model building unit for building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
A control target value determination unit for determining control target values of the amount of the absorbent charged and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

An information processing system according to at least one embodiment of the present disclosure, in order to solve the above problems,
Information processing consisting of an information processing device that executes processing related to the control of a wet flue gas desulfurization device that performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact with the absorption liquid in the absorption tower, and a terminal capable of communication. a system,
The information processing device is
At least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower and the output of a generator driven by the gas generated in the combustion device, according to the request from the terminal and a learning model building unit for building a learning model by machine learning about the relationship between the explanatory variable including the future absorption tower outlet and the objective variable, which is the sulfur dioxide concentration;
calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
A control target value determination unit for determining control target values of the amount of the absorbent charged and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

According to at least one embodiment of the present disclosure, a control method, a control device, and a remote monitoring system for a wet flue gas desulfurization apparatus capable of easily performing control for circulating an absorbent in an absorption tower of a wet flue gas desulfurization apparatus , an information processing device, and an information processing system.

1 is a configuration diagram of a wet flue gas desulfurization apparatus according to one embodiment; FIG. 1 is a configuration diagram of a remote monitoring system according to one embodiment; FIG. 4 is a flow chart showing a control method for a wet flue gas desulfurization system according to one embodiment. FIG. 4 is a flowchart showing a correction calculation for the objective variable of the learning model in step S3 of FIG. 3; FIG. 4 is a flowchart showing a correction calculation for explanatory variables of a learning model in step S3 of FIG. 3; FIG. 6 is a flowchart showing correction calculation of explanatory variables of a learning model using correction values calculated in FIG. 5 ; FIG. 7 is a diagram showing a determination flow of optimization conditions for performing a correction operation in FIG. 6; FIG. 10 is a calculation example showing predicted values of SO ₂ concentration calculated by a learning model when CaCO ₃ concentration and the number of operating fixed displacement circulating pumps are changed for each generator output; FIG. 9 is an example of a table created based on the calculation result of FIG. 8. FIG. It is an example of computation showing predicted values of SO ₂ concentration calculated by a learning model when the CaCO ₃ concentration and the displacement of a variable displacement circulating pump are changed for each generator output. 11 is an example of a table created based on the calculation result of FIG. 10; 1 is a configuration diagram of an information processing system according to an embodiment; FIG. 13 is a diagram showing an internal configuration of the information processing apparatus of FIG. 12 together with a control device; FIG.

Several embodiments of the present invention will be described below with reference to the drawings. However, the scope of the present invention is not limited to the following embodiments. The dimensions, materials, shapes, relative positions, and the like of components described in the following embodiments are not intended to limit the scope of the present invention, but merely illustrative examples.

FIG. 1 is a configuration diagram of a wet flue gas desulfurization apparatus 10 according to one embodiment.
The wet flue gas desulfurization device 10 is a device for desulfurizing the exhaust gas generated in the combustion device 1 . The combustion device 1 is, for example, a boiler for generating steam, and is configured as part of a power plant capable of generating power by supplying the steam generated by the combustion device 1 to a power generator 5 . The wet flue gas desulfurization apparatus 10 includes an absorption tower 11 communicating with a combustion apparatus 1 via a pipe 2, and a plurality of circulation pumps 12a, 12b provided in a circulation pipe 3 for absorbing liquid circulating in the absorption tower 11. 12c, . An absorbent slurry supply unit 13 for supplying slurry (absorbent slurry) of calcium carbonate (CaCO ₃ ), which is an absorbent contained in the liquid, into the absorption tower 11, and gypsum for recovering gypsum in the absorbent. and a recovery unit 14 . The absorber 11 is provided with an outflow pipe 16 through which the exhaust gas desulfurized by the operation described later flows out from the absorber ₁₁ as an outflow gas. gas analyzer 17 is provided.

The absorbent slurry supply unit 13 includes an absorbent slurry production facility 21 for producing absorbent slurry, an absorbent slurry supply pipe 22 communicating between the absorbent slurry production facility 21 and the absorption tower 11, and an absorbent slurry. An absorbent slurry supply amount control valve 23 for controlling the flow rate of the absorbent slurry flowing through the supply pipe 22 is provided. The gypsum recovery unit 14 includes a gypsum separator 25, a gypsum slurry withdrawal pipe 26 communicating between the gypsum separator 25 and the absorption tower 11, and a gypsum slurry withdrawal pump 27 provided in the gypsum slurry withdrawal pipe 26. I have it.

The wet type flue gas desulfurization device 10 is provided with a control device 15 for the wet type flue gas desulfurization device 10 . The control device 15 acquires operation data including various detectors for acquiring various operation data (e.g., temperature and pressure at various parts, flow rates of various fluids, etc.) of the combustion device 1 and the wet flue gas desulfurization device 10. A driving data receiving unit 30 electrically connected to the unit 20 is provided. The operating data acquisition unit 20 includes a gas analyzer 17 .

The control device 15 includes a learning model construction unit 38 electrically connected to the operation data reception unit 30, a table generation unit 31 electrically connected to the learning model construction unit 38, and a table generation unit 31 electrically connected to the learning model construction unit 38. The connected control target value determination unit 32, the circulation pump adjustment unit 33 electrically connected to the control target value determination unit 32, and the absorbent slurry supply control unit electrically connected to the control target value determination unit 32. 34 and a learning model correction unit 35 electrically connected to the learning model construction unit 38 . The circulation pump adjustment unit 33 is electrically connected to each circulation pump 12 . The absorbent slurry supply controller 34 is electrically connected to the absorbent slurry supply amount control valve 23 .

FIG. 2 shows the configuration of a remote monitoring system 40 for remotely monitoring the control state of the wet flue gas desulfurization equipment 10 (see FIG. 1). The remote monitoring system 40 is electrically connected to a distributed control system (DCS) 41 of each device constituting the combustion device 1 (see FIG. 1) and the wet flue gas desulfurization device 10 (see FIG. 1), and to the DCS 41. An edge server 42 equipped with a control device 15, and a remote monitoring device such as a desktop personal computer or tablet computer electrically communicatively connected to the edge server 42 via a cloud or a virtual private network (VPN). 43. A control state of the wet flue gas desulfurization apparatus 10 can be remotely monitored by a remote monitoring device 43 which is normally located away from the edge server 42 .

Next, the operation of desulfurizing the exhaust gas generated in the combustion device 1 by the wet flue gas desulfurization device 10 will be described.
As shown in FIG. 1, the exhaust gas generated in the combustion device 1 flows through the pipe 2, flows into the absorption tower 11, and rises in the absorption tower 11. As shown in FIG. By operating at least one of the circulation pumps 12 , the absorbent flows through the circulation pipe 3 and into the absorption tower 11 , where the absorption liquid flows down. The absorbent flowing down in the absorption tower 11 accumulates in the absorption tower 11 , flows out from the absorption tower 11 by the circulation pump 12 , and flows through the circulation pipe 3 . Thus, the absorbent circulates within the absorption tower 11 .

In the absorption tower 11, the rising exhaust gas and the flowing absorbing liquid come into gas-liquid contact. SO ₂ contained in the exhaust gas is expressed by the following reaction formula: SO ₂ +CaCO ₃ +2H ₂ O+1/2O ₂ →CaSO _{4.2H 2} O+CO ₂
, reacts with CaCO ₃ in the absorbent to precipitate gypsum (CaSO ₄ .2H ₂ O) in the absorbent.

In this way, since part of the SO ₂ in the flue gas is removed as gypsum in the absorbent, that is, the flue gas is desulfurized, SO ₂ concentration is lower than the SO ₂ concentration in the flue gas flowing into the absorption tower 11 via the pipe 2 . _The effluent gas that has flowed out of the absorption tower 11 flows through the outflow pipe 16 and is released into the atmosphere. It is transmitted to the receiver 30 .

The SO ₂ concentration in the effluent gas tends to decrease as the circulation flow rate of the absorbent circulating in the absorption tower 11 increases, unless the CaCO ₃ concentration in the absorbent fluctuates greatly. The control device 15 controls the number of operating circulation pumps 12 by a control method described later to control the circulation flow rate, thereby controlling the concentration of SO ₂ in the outflow gas, for example, below a preset value. _So the SO2 concentration in the effluent gas can be controlled.

The gypsum precipitated in the absorbing liquid in the absorption tower 11 is extracted as gypsum slurry from the absorption tower 11 by the gypsum slurry extraction pump 27 , and the gypsum slurry flows through the gypsum slurry extraction pipe 26 to the gypsum separator 25 . flow into Gypsum and water are separated in the gypsum separator 25, the gypsum is recovered, and the water is sent to a drainage facility (not shown).

Since CaCO ₃ in the absorbing liquid reacts with SO ₂ to form gypsum, the concentration of CaCO ₃ in the absorbing liquid decreases as the exhaust gas is desulfurized. The control device 15 controls the opening degree of the absorbent slurry supply amount control valve 23 by a control method to be described later, and absorbs the absorbent slurry produced in the absorbent slurry production facility 21 through the absorbent slurry supply pipe 22. Feed into column 11 . As a result, the CaCO ₃ concentration in the absorbent falls within a preset range, and large fluctuations in the CaCO ₃ concentration during desulfurization of the flue gas are suppressed.

Next, a method of controlling the wet flue gas desulfurization apparatus 10 by the control device 15 will be described. FIG. 3 is a flow chart showing a control method for the wet flue gas desulfurization system 10 according to one embodiment.

First, after collecting various operation data of the combustion device 1 and the wet-type flue gas desulfurization device 10 in step S1, in step S2, various operation data and the future SO2 concentration in the outflow gas flowing out from the absorber ₁₁ Build a learning model for relationships using machine learning. Next, in step S3, the learning model constructed in step S2 is corrected. Then, in step S4, a table is created using the corrected learning model obtained in step S3. In the following step S5, based on the table created in step S4, the circulation flow rate of the absorbing liquid and the supply amount of the CaCO ₃ absorbent slurry are controlled so that the SO ₂ concentration in the outflow gas is equal to or lower than a preset value. A target value is determined, in step S6, the operating conditions of the circulation pump 12 are adjusted based on the control target value of the circulation flow rate determined in step S5, and in step S7, the CaCO ₃ absorbent determined in step S5 The absorbent slurry supply amount control valve 23 is controlled based on the control target value of the slurry supply amount. Thereby, the SO ₂ concentration in the outflow gas is controlled so as to be equal to or lower than the preset value.

Note that the correction of the learning model in step S3 may be omitted if the accuracy of the learning model before correction is sufficient. Further, FIG. 3 illustrates the case where step S7 is performed after step S6, but step S7 may be performed before step S6, or steps S6 and S7 may be performed simultaneously.

Next, each step of the method of controlling the wet flue gas desulfurization apparatus 10 by the control device 15 will be described in detail.
In step S1, as shown in FIG. 1, after the operation data acquisition unit 20 acquires various operation data of the combustion device 1 and the wet-type flue gas desulfurization device 10, the acquired various operation data are transmitted to the control device 15. The control device 15 collects various types of operation data as the operation data receiving unit 30 receives the operation data. As described above, since the operating data acquisition section ₂₀ includes the gas analyzer 17, various operating data include the SO2 concentration in the outflow gas.

In step S2, the learning model building unit 38 builds a learning model by machine learning regarding the relationship between the various operating data collected by the operating data acquisition unit 20 and the future SO ₂ concentration in the outflow gas. The learning model is constructed as a regression model using a regression technique such as multiple regression, ridge regression, Lasso regression, or Elastic Net, for example. In this embodiment, as an example of a learning model, a regression model represented by a linear polynomial as shown in the following equation is constructed.
SO ₂ concentration at the outlet of the absorption tower=k1×explanatory variable 1+k2×explanatory variable 2+ . . . +kn×explanatory variable n+b (1)
By using a linear polynomial as a learning model in this way, the explainability (interpretability) is higher than that of a complicated simulation model, and the computational load can be effectively reduced. Note that n is an arbitrary natural number, k1 to kn are coefficients, and b is an arbitrary intercept.

The learning model obtained by machine learning uses an explanatory variable consisting of a plurality of parameters included in the operating data acquired by the operating data acquisition unit 20 and the future SO ₂ concentration in the outflow gas as objective variables, and calculates the correlation between the two. It is built as a model to show. The combination of parameters included in the explanatory variables of the learning model can be arbitrarily selected from the following candidates.
i) generator output command value (output command value from the outside for the generator 5)
ii) generator output (output of generator 5)
iii) Boiler air flow rate or boiler exhaust gas flow rate (supply air flow rate to combustion device 1 or exhaust gas flow rate from combustion device 1)
iv) desulfurization inlet SO2 concentration or boiler outlet SO2 concentration ₍ SO2 concentration at the absorption tower ₁₁ inlet or _SO2 concentration at the combustion device ₁ outlet)
v) desulfurization outlet SO2 concentration or flue inlet SO2 concentration _{( SO2} concentration at the outlet of the absorber tower ₁₁ )
vi) _CaCO3 concentration or pH of the absorption liquid
vii) Absorbent circulation flow rate (control value for the number of operating circulation pumps 12 or discharge flow rate)
These candidates are typically parameters conventionally measurable in many wet flue gas desulfurization systems 10 .

In this embodiment, the explanatory variables of the learning model are, among the above candidates, i) generator output command value (output command value from the outside for the generator 5), iii) boiler air flow rate or boiler exhaust gas flow rate (for the combustion device 1 supply air flow rate or flue gas flow rate from the combustion device ₁ ), or iv) desulfurization inlet SO2 concentration or boiler outlet SO2 concentration ₍ SO2 concentration at the inlet of the absorption tower ₁₁ or SO2 concentration at the combustion device ₁ outlet). One is selected to be included. More preferably, the explanatory variables of the learning model are, among the above candidates, iii) boiler air flow rate or boiler exhaust gas flow rate (supply air flow rate to combustion device 1 or exhaust gas flow rate from combustion device 1), and iv) desulfurization inlet SO ₂ concentration or boiler exit SO2 concentration ₍ SO2 concentration at absorber ₁₁ inlet or SO2 concentration at combustor ₁ exit). As a result, it is possible to build a learning model capable of predicting the future SO ₂ concentration in the outflow gas, which is the objective function, with good accuracy. By selecting some parameters as explanatory variables from the operating data acquired by the operating data acquisition unit 20, it is possible to efficiently narrow down the data to be learned and reduce the computational load of machine learning. .

In step S3, the learning model correction unit 35 corrects the learning model constructed in step S2. The correction of the learning model is performed based on the error between the SO ₂ concentration predicted value calculated by the learning model and the measured value, and is performed for the explanatory variable and the objective function of the learning model.

　Here, FIG. 4 is a flowchart showing the correction calculation for the objective variable of the learning model in step S3 of FIG.

In the correction calculation for the objective variable, first, the correction time ΔVp corresponding to the measurement delay is output after the predicted value Vp calculated using the learning model to be corrected. The predicted value Vp calculated using the learning model does not include the time required for the gas analyzer 17 to measure the measured value Vm. The correction time ΔVp corresponds to the time required for the gas analyzer 17 to measure the actual measurement value Vm. It can be made comparable to the value Vm. By outputting the correction time ΔVp with a delay from the predicted value Vp, the corrected predicted value Vp′ is obtained. Then, the ratio (Vm/Vp') between the predicted value Vp' after correction and the measured value Vm of the gas analyzer 17 is calculated, and the moving average thereof is calculated to obtain the correction value A related to the objective function.

The correction value A calculated in this manner is applied to the learning model. For example, in the case of the learning model represented by the above formula (1), the learning model after correction is expressed by the following formula.
SO ₂ concentration at the outlet of the absorption tower = (k1 x explanatory variable 1 + k2 x explanatory variable 2 + ... + kn x explanatory variable n + b) x A (2)

Next, FIG. 5 is a flowchart showing the correction calculation for the explanatory variables of the learning model in step S3 of FIG. Here, as an example of the correction calculation, a case of correcting the explanatory variable SG, which is a parameter having a correlation with the output of the generator 5 (the generator output Y), will be described.

A reference table Tr that defines the correlation between the generator output Y and the values X1 to X4 of the explanatory variable SG is prepared in advance. The reference table Tr prescribes values X1 to X4 of the explanatory variable SG for each value of the generator output Y, as shown in FIG. In this embodiment, the values X1 to A reference table Tr is shown containing characteristic functions defining X4.

The learning model correction unit 35 outputs the corresponding explanatory variable SG by inputting the generator output Y obtained from the outside to such a reference table Tr. On the other hand, the learning model correction unit 35 obtains the actual measurement value SGm of the explanatory variable based on the result obtained by the operation data receiving unit 30, and the ratio (SGm/SG) to the value SG of the explanatory variable output from the reference table Tr. Ask for Then, by calculating the moving average of the ratio, the correction value B for the explanatory function is obtained.

The correction value B for the explanatory variable SG calculated in this way is applied to the learning model. FIG. 6 is a flowchart showing correction calculation of the explanatory variable SG of the learning model using the correction value B calculated in FIG.

As shown in FIG. 6, when the optimization condition C is satisfied, the characteristic function defined in the reference table Tr is corrected by the correction value B. The optimization condition C includes at least one (for example, all) conditions for determining whether or not the environment for correcting the reference table Tr with the correction value B is in place. It can be determined from various points of view that the operation state is stable in the control device 15 and that no abnormality has occurred.

FIG. 7 is a diagram showing a determination flow of the optimization condition C for performing correction calculation in FIG. In FIG. 7, as an example of the optimization condition C, determination is made based on the following five conditions.
(Condition 1) Abnormalities are not monitored in explanatory variables.
(Condition 2) The instrument for acquiring the actual measurement value SGm of the explanatory variable is not being adjusted.
(Condition 3) The generator output (or boiler load) is above a predetermined value (for example, 0% to 50%).
(Condition 4) The plant must be in a smoking state.
(Condition 5) Initialization of the computing software must be completed.

When such an optimization condition C is satisfied, the learning model correction unit 35 multiplies the correction value B by the explanatory variable SG value corresponding to the generator output for the characteristic function defined in the reference table Tr. By doing so, the explanatory variables are corrected. As a result of such correction, the characteristic functions defined in the reference table Tr are updated as shown in FIG. ing).

At step S4, a table T is created based on the learning model corrected at step S3. Table T is created by the amount of absorbent added so that the predicted value of SO ₂ concentration calculated by the learning model satisfies a preset reference value (for example, becomes equal to or lower than the reference value) for each generator output. and by calculating the circulation flow rate of the absorbent.

Here, the method of creating the table T in step S4 of FIG. 3 will be specifically described. First, a case where the circulation pumps 12 are of a fixed capacity type and the circulation flow rate of the absorbent is controlled by controlling the number of circulation pumps 12 will be described with reference to FIGS. 8 and 9. FIG. FIG. 8 is a calculation example showing predicted values of SO ₂ concentration calculated by the learning model when changing the CaCO ₃ concentration and the number of fixed capacity circulation pumps 12 in operation for each generator output. 9 is an example of a table T created based on the calculation result of FIG.

Incidentally, the CaCO ₃ concentration is a parameter corresponding to the amount of absorbent charged, and can take a value of "2 to 5" as an allowable range. The number of circulating pumps 12 in operation is a parameter corresponding to the circulating amount of the absorbent, and can take a value of "8 to 10" as an allowable range. These tolerances may be preset from plant design values, for example.

In FIG. 8, focusing on the case where the generator output is "50%", when the _CaCO3 concentration is "3" and the number of operating circulation pumps is " ₈ ", the predicted value of the SO2 concentration by the learning model is It is 105 ppm, exceeding the standard value (100 ppm). In this case, the table creating unit 31 changes the CaCO 3 concentration to "4" by increasing by one step the CaCO ₃ concentration, which has less impact on the operation cost than the number of operating circulation pumps. Then, the predicted value of the SO ₂ concentration by the learning model is 100 ppm, which is below the reference value (100 ppm). Therefore, the table creating unit 31 specifies that the optimum CaCO ₃ concentration at the generator output of "50%" is "4" and the number of operating circulation pumps is "8".

Next, focusing on the case where the generator output is "60%", the _CaCO3 concentration is "4", and the number of operating circulation pumps is " ₈ ", the SO2 concentration predicted by the learning model is 120 ppm. , exceeds the reference value (100 ppm). In this case, the table creation unit 31 changes the CaCO 3 concentration to “5” by increasing by one step the CaCO ₃ concentration, which has less influence on the operation cost than the number of operating circulation pumps. However, the SO ₂ concentration predicted by the learning model is 110 ppm, still exceeding the reference value (100 ppm). In this case, even if the CaCO ₃ concentration reaches the upper limit of the allowable range “5”, the standard value cannot be satisfied, so the number of operating circulation pumps is increased to “9” and the CaCO ₃ concentration is set to “3”. Decrease. As a result, the predicted value of SO ₂ concentration by the learning model is 100 ppm, which is below the reference value (100 ppm). Therefore, the table creation unit 31 specifies that the optimum CaCO ₃ concentration is "3" and the number of operating pumps is "9" when the generator output is "60%".

The table creation unit 31 creates the table T shown in FIG. 9 by specifying the optimum CaCO ₃ concentration and the number of operating circulation pumps for each generator output in this way. In FIG. 9, the table T is created so that the CaCO ₃ concentration decreases and increases at the timing when the number of operating circulation pumps 12 increases stepwise as the generator output increases.

Next, a case where the circulating pump 12 is of a variable capacity type so that the circulating flow rate of the absorbent is controlled by controlling the capacity of the circulating pump 12 will be described with reference to FIGS. 10 and 11. FIG. FIG. 10 is a calculation example showing predicted values of the SO ₂ concentration calculated by the learning model when the CaCO ₃ concentration and the capacity of the variable displacement circulation pump 12 are changed for each generator output, and FIG. is an example of a table T created based on the calculation result of FIG.

Incidentally, the CaCO ₃ concentration is a parameter corresponding to the amount of absorbent charged, and can take a value of "2 to 5" as an allowable range. Also, the circulating pump capacity is a parameter corresponding to the circulating amount of the absorbent, and can take a value of "10 to 100" as an allowable range. These tolerances may be preset from plant design values, for example.

In FIG. 10, when the generator output is "50%", when the _CaCO3 concentration is "3" and the circulating pump capacity is " ₁₀ ", the SO2 concentration predicted by the learning model is 105 ppm. and exceeds the standard value (100 ppm). In this case, the table creating unit 31 changes the CaCO 3 concentration to "4" by increasing by one step the CaCO ₃ concentration, which has less influence on the operation cost than the capacity of the circulating pump. Then, the predicted value of the SO ₂ concentration by the learning model is 100 ppm, which is below the reference value (100 ppm). Therefore, the table creating unit 31 specifies that the optimum CaCO ₃ concentration at the generator output of "50%" is "4" and the circulation pump capacity is "10".

Next, focusing on the case where the generator output is "60%", when the _CaCO3 concentration is "5" and the circulation pump capacity is " ₁₀ ", the predicted value of the SO2 concentration by the learning model is 120 ppm, It exceeds the standard value (100 ppm). In this case, since the CaCO ₃ concentration has reached the upper limit of the allowable range of "5", the table creating unit 31 changes the pump displacement to "15". However, the SO ₂ concentration predicted by the learning model is 110 ppm, still exceeding the reference value (100 ppm). In this case, the table generator 31 changes the circulating pump capacity to "18". As a result, the predicted value of SO ₂ concentration by the learning model is 100 ppm, which is below the reference value (100 ppm). Therefore, the table creation unit 31 specifies that the optimum CaCO ₃ concentration at the generator output of "60%" is "5" and the circulation pump capacity is "18".

The table creating unit 31 creates the table shown in FIG. 11 by specifying the optimum CaCO ₃ concentration and circulation pump capacity for each generator output in this way. In FIG. 11, the table T is created so that the pump displacement increases at the timing when the increase in the CaCO ₃ concentration becomes insufficient as the generator output increases.

8 to 11, the search for the optimum CaCO ₃ concentration and the number of operating circulation pumps (or circulation pump capacity) for creating the tables is performed to minimize the operation cost. Although the case is shown in which the predicted value of the SO ₂ concentration that satisfies the reference value is obtained while keeping the pump capacity as small as possible, the search may be performed from other viewpoints.

Also, in this embodiment, the graph-format table T as shown in FIGS. 9 and 11 is illustrated, but the table T does not necessarily have to be in such a form, and may be in the form of a matrix, formula, or the like.

In step S5, the control target value determination unit 32 acquires the command value of the generator output, and based on the table T created in step S4, the control target value (absorbent input amount and Each control target value) of the circulation flow rate of the absorbing liquid is determined. In steps S6 and S7, the circulation pump adjustment unit 33 controls the circulation pumps 12a to 12c based on the control target value determined in step S5, and the absorbent slurry supply control unit 34 adjusts the supply amount of the absorbent. Control.

In step S5, the circulation flow rate is adjusted by controlling the number of circulation pumps based on the table shown in FIG. , the pump capacity is controlled based on the table T shown in FIG.

As described above, according to the above embodiment, the amount of absorbent introduced into the absorption tower 11 and the inside of the absorption tower 11 are controlled within a range in which the SO ₂ concentration in the future outflow gas is equal to or lower than the preset reference value. The circulation flow rate of the circulating absorbent can be adjusted appropriately. Such a control calculation can obtain control target values for the amount of absorbent introduced into the absorber 11 and the circulation flow rate of the absorbent circulating in the absorber 11 based on a single learning model. Therefore, the computational burden is small.

Each processing executed by the control device 15 in the above embodiment is executed by the information processing device 44 (see FIG. 12) electrically communicably connected to the edge server 42 in the cloud environment or via VPN. Configurations are possible. In this case, the information processing device 44 includes an operation data reception unit 30, a learning model construction unit 38, a learning model correction unit 35, a table creation unit 31, and a control target value determination unit 32. The control target value determination unit 32 By communicating the determined control target value to the circulation pump adjustment section 33 and the absorbent slurry supply control section 34 in the control device 15, the circulation pump and the absorbent supply amount may be controlled.

Further, the operation data receiving unit 30 may receive various kinds of operation data via the operation data relay unit 39 (FIG. 13) of the control device 15, or may receive various kinds of operation data from the operation data acquisition unit 20 as described above. may be received. In particular, when calculating in a cloud environment, from the viewpoint of security, there are cases where the control target values of the circulating pump and absorbent are not directly controlled, but only displayed. For example, there are cases where a driving index map generated in a cloud environment is sent to a customer-owned device (terminal 45) and illustrated through a dedicated application, and the local driving index map is updated by the customer. On the other hand, the information processing device 44 may also include a circulation pump control section 33 and an absorbent slurry supply control section 34 to remotely control the circulation pump and the supply amount of absorbent. Furthermore, the information processing device 44 may be configured to execute each process in response to a request from the terminal 45 .

In addition, it is possible to appropriately replace the components in the above-described embodiments with well-known components within the scope of the present disclosure, and the above-described embodiments may be combined as appropriate.

The contents described in each of the above embodiments can be understood, for example, as follows.

(1) A method for controlling a wet flue gas desulfurization apparatus according to one embodiment includes:
In the absorption tower (for example, the absorption tower 11 of the above-described embodiment), the wet-type flue gas desulfurization device (for example, the wet-type flue gas desulfurization device of the above-described embodiment) performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact. 10) The control method,
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A step of building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
A predicted value of the sulfur dioxide concentration by the learning model is calculated for each output based on a reference table that defines the relationship between the parameter and the output (for example, the reference table Tr of the above embodiment), and the predicted value A step of creating a table (for example, table T in the above embodiment) showing the amount of the absorbent charged and the circulation flow rate of the absorbent for satisfying the reference value;
and determining control target values for the amount of the absorbent to be supplied and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

According to the above aspect (1), the amount of absorbent introduced into the absorption tower and the amount of absorbent circulated in the absorption tower are within the range where the SO ₂ concentration in the future outflow gas is equal to or lower than the preset reference value. It is possible to appropriately adjust the circulation flow rate of the absorbent. Since such a control calculation can obtain control target values for the amount of absorbent introduced into the absorption tower and the circulation flow rate of the absorbent circulating in the absorption tower based on a single learning model, Low computational load.

(2) In another aspect, in the aspect of (1) above,
In the step of creating the table, at least one circulation pump (e.g., In order to reduce the operation cost of the circulation pump 12) of the above-described embodiment, a search is made for the amount of the absorbent to be supplied and the circulation flow rate of the absorbent so that the predicted value satisfies the reference value.

According to the aspect (2) above, in the range where the predicted value of the concentration of sulfur dioxide discharged from the absorption tower is equal to or lower than the reference value, the amount of absorbent input and the circulation flow rate of the absorbent are adjusted so as to reduce the operating cost. is searched for. By performing control based on the control target value searched for in this way, the operating cost of the plant can be effectively reduced while suppressing the sulfur dioxide discharged from the absorption tower within a necessary range.

(3) In another aspect, in the aspect of (1) above,
A step of correcting the learning model based on an error between the predicted value of the concentration of sulfur dioxide in the exhaust gas at the outlet of the absorber by the learning model and the measured value is further provided.

According to the aspect (3) above, the control accuracy can be improved by correcting the learning model based on the error between the predicted value obtained by the learning model and the actual measurement value.

(4) In another aspect, in any one aspect of (1) to (3) above,
The at least one parameter includes at least one of an external command value of the output, the output, the air flow rate of the combustion device, and the sulfur dioxide concentration at the absorption tower inlet.

According to the above aspect (4), by including any one of these parameters in the explanatory variables of the learning model, the data to be learned is efficiently narrowed down, thereby reducing the computational burden of machine learning and improving the performance. It is possible to build a learning model that can predict with high accuracy.

(5) In another aspect, in the aspect of (4) above,
The at least one parameter includes the combustor air flow rate and the absorber inlet sulfur dioxide concentration.

According to the above aspect (5), by including these parameters in the explanatory variables of the learning model, the learning target data can be efficiently narrowed down to further reduce the computational burden of machine learning, while achieving better accuracy. Build predictable learning models.

(6) In another aspect, in any one aspect of (1) to (5) above,
The learning model is represented by a linear polynomial.

According to the aspect (6) above, by using a linear polynomial as a learning model, the explainability (interpretability) is high compared to a complicated simulation model, and the computational load can be effectively reduced.

(7) In another aspect, in any one aspect of (1) to (6) above,
The reference table is defined as a function indicating the relationship between the previously specified parameters and the output.

According to the aspect (7) above, the parameters having a correlation with the generator output are defined as a reference table indicating the correlation.

(8) In another aspect, in the aspect of (2) above,
The at least one circulation pump is of fixed displacement type.

According to the above aspect (8), in a plant having a fixed displacement circulating pump, the amount of absorbent to the absorption tower is within the range where the concentration of sulfur dioxide in the future effluent gas is equal to or lower than a preset reference value. The amount of input and the circulation flow rate of the absorbent circulating in the absorption tower can be adjusted appropriately.

(9) In another aspect, in the aspect of (2) above,
The at least one circulation pump is of variable displacement type.

According to the above aspect (9), in a plant having a variable displacement circulating pump, the amount of absorbent to the absorption tower is within the range where the concentration of sulfur dioxide in the future effluent gas is equal to or lower than a preset reference value. The amount of input and the circulation flow rate of the absorbent circulating in the absorption tower can be adjusted appropriately.

(10) A control device for a wet flue gas desulfurization system according to one aspect,
In the absorption tower (for example, the absorption tower 11 of the above-described embodiment), the wet-type flue gas desulfurization device (for example, the wet-type flue gas desulfurization device of the above-described embodiment) performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact. 10) of the control device (for example, the control device 15 of the above embodiment),
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model construction unit (for example, the learning model construction unit 38 of the above embodiment) for constructing a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
A predicted value of the sulfur dioxide concentration by the learning model is calculated for each output based on a reference table that defines the relationship between the parameter and the output (for example, the reference table Tr of the above embodiment), and the predicted value A table creating unit (for example, the table creating unit 31 )When,
Based on the table, a control target value determination unit (for example, the control target value decision unit 32).

According to the above aspect (10), the amount of absorbent introduced into the absorption tower and the amount of absorbent circulated in the absorption tower are within the range where the SO ₂ concentration in the future outflow gas is equal to or lower than the preset reference value. It is possible to appropriately adjust the circulation flow rate of the absorbent. Such a control calculation can obtain control target values for the amount of absorbent introduced into the absorber 11 and the circulation flow rate of the absorbent circulating in the absorber based on a single learning model. , the computational burden is small.

(11) A remote monitoring system according to one aspect includes:
a control device for a wet flue gas desulfurization system according to the above aspect (10);
and a remote monitoring device electrically connected to the control device of the wet flue gas desulfurization system.

According to the aspect (11) above, the control state of the wet flue gas desulfurization system can be remotely monitored.

(12) An information processing device according to one aspect,
In the absorption tower (for example, the absorption tower 11 of the above-described embodiment), the wet-type flue gas desulfurization device (for example, the wet-type flue gas desulfurization device of the above-described embodiment) performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact. 10) an information processing device (for example, the information processing device 44 of the above embodiment) that executes the process related to the control,
Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model construction unit (for example, the learning model construction unit 38 of the above embodiment) for constructing a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
A predicted value of the sulfur dioxide concentration by the learning model is calculated for each output based on a reference table that defines the relationship between the parameter and the output (for example, the reference table Tr of the above embodiment), and the predicted value A table creating unit (for example, the table creating unit 31 )When,
Based on the table, a control target value determination unit (for example, the control target value decision unit 32).

According to the above aspect (12), the amount of absorbent introduced into the absorption tower and the amount of absorbent circulated in the absorption tower are within the range where the SO ₂ concentration in the future outflow gas is equal to or lower than the preset reference value. It is possible to appropriately adjust the circulation flow rate of the absorbent. Since such a control calculation can obtain control target values for the amount of absorbent introduced into the absorption tower and the circulation flow rate of the absorbent circulating in the absorption tower based on a single learning model, Low computational load.

(13) An information processing system according to one aspect,
In the absorption tower (for example, the absorption tower 11 of the above-described embodiment), the wet-type flue gas desulfurization device (for example, the wet-type flue gas desulfurization device of the above-described embodiment) performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact. 10) An information processing system (for example, the an information processing system 46),
The information processing device is
At least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower and the output of a generator driven by the gas generated in the combustion device, according to the request from the terminal and a learning model construction unit (for example, the learning model construction unit 38 of the above embodiment) for constructing a learning model by machine learning about the relationship between the explanatory variable including the future absorption tower outlet and the objective variable, which is the sulfur dioxide concentration ,
A predicted value of the sulfur dioxide concentration by the learning model is calculated for each output based on a reference table that defines the relationship between the parameter and the output (for example, the reference table Tr of the above embodiment), and the predicted value A table creating unit (for example, the table creating unit 31 )When,
Based on the table, a control target value determination unit (for example, the control target value decision unit 32).

According to the above aspect (13), the amount of absorbent introduced into the absorption tower and the amount of absorbent circulated in the absorption tower are within the range where the SO ₂ concentration in the future outflow gas is equal to or lower than the preset reference value. It is possible to appropriately adjust the circulation flow rate of the absorbent. Since such a control calculation can obtain control target values for the amount of absorbent introduced into the absorption tower and the circulation flow rate of the absorbent circulating in the absorption tower based on a single learning model, Low computational load.

1 Combustion device 2 Pipe 3 Circulation pipe 5 Generator 10 Wet flue gas desulfurization device 11 Absorption tower 12 Circulation pump 13 Absorbent slurry supply unit 14 Gypsum recovery unit 15 Control device 16 Outflow pipe 17 Gas analyzer 20 Operation data acquisition unit 21 Absorbent slurry production equipment 22 Absorbent slurry supply pipe 23 Absorbent slurry supply amount control valve 25 Gypsum separator 26 Gypsum slurry extraction pipe 27 Gypsum slurry extraction pump 30 Operation data receiving unit 31 Table creation unit 32 Control target value determination Unit 33 Circulation pump adjustment unit 34 Absorbent slurry supply control unit 35 Learning model correction unit 38 Learning model construction unit 39 Operation data relay unit 40 Remote monitoring system 42 Edge server 43 Remote monitoring device 44 Information processing device 45 Terminal 46 Information processing system

Claims (13)

1. A control method for a wet flue gas desulfurization apparatus for performing desulfurization by bringing exhaust gas generated in a combustion apparatus and an absorbing liquid into gas-liquid contact in an absorption tower, comprising:
   Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A step of building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
   calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A step of creating a table showing the input amount of and the circulation flow rate of the absorbent;
   A control method for a wet flue gas desulfurization system, comprising the step of determining control target values for the amount of absorbent to be supplied and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.
2. In the step of creating the table, operation of at least one circulation pump for circulating the absorbent in the absorption tower within a preset permissible range for the input amount of the absorbent and the circulation flow rate of the absorbent. 2. The method of controlling a wet flue gas desulfurization apparatus according to claim 1, wherein the amount of absorbent to be supplied and the circulation flow rate of the absorbent for satisfying the reference value for the predicted value are searched so as to reduce the cost.
3. 3. The wet exhaust system according to claim 1 or 2, further comprising a step of correcting the learning model based on an error between the predicted value of the sulfur dioxide concentration of the exhaust gas at the absorber outlet by the learning model and the measured value. Control method for flue desulfurization equipment.
4. 4. The at least one parameter includes at least one of an external command value of the output, the output, the air flow rate of the combustion device, and the sulfur dioxide concentration at the inlet of the absorption tower. A control method for the described wet flue gas desulfurization system.
5. The method for controlling a wet flue gas desulfurization system according to claim 4, wherein said at least one parameter includes the air flow rate of said combustion device and the concentration of sulfur dioxide at said absorption tower inlet.
6. The method for controlling a wet flue gas desulfurization apparatus according to any one of claims 1 to 5, wherein the learning model is represented by a linear polynomial.
7. The control method for a wet flue gas desulfurization apparatus according to any one of claims 1 to 6, wherein said reference table is defined as a function indicating a relationship between said previously specified parameter and said output.
8. The method for controlling a wet flue gas desulfurization apparatus according to any one of claims 2 to 7, wherein said at least one circulation pump is of a fixed displacement type.
9. The method for controlling a wet flue gas desulfurization apparatus according to any one of claims 2 to 7, wherein said at least one circulation pump is of a variable displacement type.
10. A control device for a wet flue gas desulfurization device that performs gas-liquid contact between an exhaust gas generated in a combustion device and an absorbing liquid in an absorption tower to perform desulfurization,
    Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model building unit for building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
    calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
    A wet flue gas desulfurization system, comprising: a control target value determination unit for determining control target values of the absorbent input amount and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table. controller.
11. a control device for a wet flue gas desulfurization system according to claim 10;
    and a remote monitoring device electrically connected to the controller of the wet flue gas desulfurization system.
12. An information processing device that executes processing related to control of a wet flue gas desulfurization device that performs desulfurization by bringing exhaust gas generated in a combustion device and an absorbent into gas-liquid contact in an absorption tower,
    Explanatory variables including at least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower, and the output of a generator driven by the gas produced in the combustion device; A learning model building unit for building a learning model by machine learning about the relationship with the objective variable, which is the concentration of sulfur dioxide at the outlet of the absorption tower;
    calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
    an information processing apparatus comprising: a control target value determining unit for determining control target values of the absorbent injection amount and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.
13. Information processing consisting of an information processing device that executes processing related to the control of a wet flue gas desulfurization device that performs desulfurization by bringing the exhaust gas generated in the combustion device and the absorbing liquid into gas-liquid contact with the absorption liquid in the absorption tower, and a terminal capable of communication. a system,
    The information processing device is
    At least one parameter correlated with the absorbent concentration and circulation flow rate of the absorbent in the absorption tower and the output of a generator driven by the gas generated in the combustion device, according to the request from the terminal and a learning model building unit for building a learning model by machine learning about the relationship between the explanatory variable including the future absorption tower outlet and the objective variable, which is the sulfur dioxide concentration;
    calculating the predicted value of the sulfur dioxide concentration by the learning model for each output based on a reference table that defines the relationship between the parameter and the output, and the absorbent for the predicted value to satisfy the reference value; A table creation unit for creating a table showing the input amount of and the circulation flow rate of the absorbent;
    an information processing system, comprising: a control target value determining unit for determining control target values of the absorbent input amount and the circulation flow rate of the absorbent corresponding to the state of the generator based on the table.

Images