WO2025225383A1 - Plant control assistance device, plant control assistance method, and plant control assistance program - Google Patents

Abstract

The present application relates to a plant control assistance device for assisting with plant control in which a plurality of process values of the plant are used, said process values having been respectively predicted using a plurality of prediction models. This device has a first prediction model training unit for training a plurality of first prediction models as a plurality of prediction models, using training data that is operation data of the plant. For a first prediction model which is among the plurality of first prediction models and in which the prediction accuracy is less than a reference value, a second prediction model is retrained using, as training data, the operation data to which additional data has been added. For a second prediction model in which the prediction accuracy is less than the reference value, a third prediction model is retrained using, as training data, similar operation data which is among the operation data and is similar to an operation point of the plant. The prediction model with the best prediction accuracy among the first prediction model, the second prediction model, and the third prediction model is selected as a prediction model.

Description

Plant control support device, plant control support method, and plant control support program

The present disclosure relates to a plant control support device, a plant control support method, and a plant control support program.
This application claims priority based on Japanese Patent Application No. 2024-070327, filed with the Japan Patent Office on April 24, 2024, the contents of which are incorporated herein by reference.

Controllers are known for controlling plants that are made up of various devices. In these types of controllers, control is carried out based on process values related to the plant's characteristics. However, if the process value is a parameter that is difficult to measure, or if it is a parameter that can be measured but it is preferable to avoid measuring it for reasons such as cost reduction, the process value may be obtained as a calculated predicted value using a predictive model that simulates the plant's behavior. Such predictive models can be constructed, for example, by machine learning, using the plant's past operating data as learning data. For example, Patent Document 1 describes how by training a predictive model for each operating condition of the plant, it is possible to appropriately predict process values even when operating conditions are switched.

Patent No. 7222943

In the above-mentioned Patent Document 1, a prediction model is constructed by performing learning for each driving condition, but the number of data points that can be used as learning data may differ depending on the driving conditions. In this case, it may not be possible to prepare sufficient learning data depending on the driving conditions, which could result in a decrease in the prediction accuracy of the prediction model constructed through learning.

At least one embodiment of the present disclosure has been made in consideration of the above circumstances, and aims to provide a plant control support device, a plant control support method, and a plant control support program that can achieve good prediction accuracy of process values using a prediction model regardless of the operating conditions of the plant.

In order to solve the above problems, a plant control assistance device according to at least one embodiment of the present disclosure includes:
1. A plant control support device for supporting plant control using a plurality of process values of a plant that are predicted using a plurality of prediction models, the device comprising:
a first prediction model learning unit configured to learn a plurality of first prediction models as the plurality of prediction models by using learning data that is operation data of the plant;
a second prediction model learning unit configured to re-learn a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
a third prediction model learning unit configured to re-learn a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data for the second prediction model whose prediction accuracy is less than the reference value;
a prediction model selection unit that selects, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the highest prediction accuracy;
Equipped with.

In order to solve the above problem, a plant control support method according to at least one embodiment of the present disclosure includes:
1. A plant control support method for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the method comprising:
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
Equipped with.

In order to solve the above problem, a plant control assistance program according to at least one embodiment of the present disclosure includes:
1. A plant control support program for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the program comprising:
To the computer device,
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
is possible.

At least one embodiment of the present disclosure provides a plant control support device, a plant control support method, and a plant control support program that can achieve good prediction accuracy of process values using a prediction model regardless of the operating conditions of the plant.

1 is an overall configuration diagram of a plant control system according to an embodiment; FIG. 2 is a schematic diagram showing a virtual space that defines an operating point of a plant. FIG. 2 is an explanatory diagram showing a calculation flow of a predicted value using a prediction model stored in a prediction model storage unit in FIG. 1 . 1. FIG. 4 is an explanatory diagram showing a calculation flow of an index used in searching for an operation condition in the operation condition searching unit of FIG. 1 is a flowchart illustrating a plant control support method according to an embodiment.

Several embodiments of the present disclosure will be described below with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative arrangements, etc. of the components described as embodiments or shown in the drawings are not intended to limit the scope of the present disclosure and are merely illustrative examples.

First, we will explain the overall configuration of a plant control system 1 that includes a plant control assistance device 100 according to at least one embodiment of the present disclosure. Figure 1 is a diagram showing the overall configuration of a plant control system 1 according to one embodiment.

The plant control assistance device 100 is a device for assisting the control performed by the control device 200, which is a control unit for controlling the plant 10. The plant 10 is, for example, a boiler device for generating steam supplied to a steam turbine (not shown) connected to a generator in a thermal power plant, but this is merely an example and is not limiting.

The control device 200 controls the operating state of the plant 10 by transmitting and receiving various signals to and from the plant 10. The control by the control device 200 is performed in accordance with preset operating conditions, and the control device 200 acquires operating parameters from the plant 10 and outputs control signals corresponding to the operating parameters to the plant 10. In the plant 10, each component device is controlled based on the control signal input from the control device 200.
The detailed configuration of the control device 200 will be similar to that of a known example, and will not be described here.

The plant control assistance device 100 includes an external input interface 102, a preprocessing unit 104, an operating data accumulation unit 106, a prediction model learning unit 108, a prediction model storage unit 110, a prediction accuracy determination unit 112, an operating condition search unit 114, a search range setting unit 116, and an external output interface 118.

The external input interface 102 is an interface configuration for inputting data from the control device 200, which is an external device to the plant control assistance device 100. Various data handled by the control device 200 is input to the external input interface 102. This data includes data that becomes operating data that is processed by the pre-processing unit 104 and treated as learning data in the machine learning of the prediction model M in the prediction model learning unit 108. Data input from the control device 200 is also carried out repeatedly at predetermined time intervals.

The preprocessing unit 104 is configured to perform preprocessing on data input from the external input interface 102. The preprocessing includes at least a process of extracting driving data from the data input to the external input interface 102, which is used as learning data in the machine learning of the prediction model M in the prediction model learning unit 108, but the detailed processing content is not particularly limited.

The operating data storage unit 106 is a component (e.g., a database) for storing operating data created by the preprocessing unit 104. In the plant control assistance device 100, each time data is input from the control device 200 to the external input interface 102, preprocessing is performed in the preprocessing unit 104 to process the operating data, which is then sequentially stored in the operating data storage unit 106.

The prediction model learning unit 108 is configured to construct a prediction model M by performing machine learning using the driving data stored in the driving data storage unit 106 as learning data. This machine learning constructs the prediction model M by specifying explanatory variables and an objective function from each parameter included in the driving data and learning the correlation between the explanatory variables and the objective variable according to a machine learning algorithm. Examples of machine learning algorithms that can be used include, but are not limited to, linear regression, neural networks, and random forests.

The prediction model training unit 108 includes a first prediction model training unit 120, a second prediction model training unit 122, and a third prediction model training unit 124.

The first prediction model learning unit 120 is configured to construct a prediction model (hereinafter referred to as the "first prediction model M1" as appropriate) through machine learning using the driving data accumulated in the driving data accumulation unit 106 as learning data. The machine learning by this first prediction model learning unit 120 is performed prior to the machine learning by the second prediction model learning unit 122 and the third prediction model learning unit 124, and is machine learning for constructing a so-called original prediction model M.

The second prediction model learning unit 122 is configured to construct a prediction model (hereinafter referred to as the "second prediction model M2" as appropriate) by additional driving data relearning. In additional driving data relearning, the second prediction model M2 can be constructed by relearning using driving data that was used as learning data when the first prediction model M1 was constructed, with additional data added as learning data. As described above, driving data is sequentially accumulated in the driving data accumulation unit 106, and the additional data is driving data that has been accumulated in the driving data accumulation unit 106 after the first prediction model M1 was learned. In additional driving data relearning, by relearning using driving data with a larger amount of data due to the addition of additional data, it is possible to construct a second prediction model M2 with improved prediction accuracy compared to the first prediction model M1.

The third prediction model learning unit 124 is configured to construct a prediction model (hereinafter referred to as the "third prediction model M3" as appropriate) by similar operating data relearning. In similar operating data relearning, the third prediction model M3 can be constructed by performing similar operating data relearning, using as learning data similar operating data that belongs to a predetermined operating region including the operating point of the plant 10 from the operating data stored in the operating data accumulation unit 106.

Now, referring to Figure 2, we will explain in detail the similar operating data that is treated as learning data by the third prediction model learning unit 124. Figure 2 is a schematic diagram showing a virtual space V that defines the operating point of the plant 10. In Figure 2, the current operating point of the plant is shown in virtual space V, which is a multidimensional space defined with multiple parameters representing the operating point as spatial axes (for ease of illustration, Figure 2 illustrates an example where the number of dimensions of virtual space V is "3").

In FIG. 2, when coordinate A corresponding to the current operating point of the plant in a virtual space V defined by three spatial axes x, y, and z is (x1, y1, z1), and coordinates of an arbitrary point B in the virtual space are (x2, y2, z2), the degree of deviation L between the two is expressed by the following equation:
L={(x1-x2) ² + (y1-y2) ² + (z1-z2) ² } ^0.5
The similar driving data is defined as, for example, data included in a similar driving range in which the deviation L expressed in this way is within a predetermined value L0 (in FIG. 2 , the similar driving range is schematically shown as being within a sphere indicated by a dashed line). Thus, in the similar driving data relearning, driving data at operating points with similar driving conditions is used as learning data for relearning, thereby suitably improving the prediction accuracy of the prediction model M.

Note that while the example here illustrates a case in which deviation L is defined using Euclidean distance, deviation L may also be defined using Mahalanobis distance. Furthermore, similar driving data may be defined as data extracted from driving data in ascending order of deviation L until a predetermined percentage or a predetermined number is reached. As mentioned above, if similar driving data is defined as data whose deviation L is within a predetermined value L0, if there is not enough data within that range, sufficient learning data cannot be extracted, and learning of the predictive model M itself may become impossible. In contrast, in this aspect, by defining similar driving data as data extracted until a predetermined percentage or a predetermined number is reached, it is possible to prevent a shortage of data necessary for learning even when there is little driving data with a small deviation L, and to perform similar driving data relearning. (This is equivalent to setting the predetermined value L0 to a variable value and determining that a predetermined number or a predetermined percentage of driving data with a small deviation L is extracted from the driving data.)

Returning to Figure 1, the prediction model storage unit 110 is configured to store the prediction model M constructed by the prediction model learning unit 108. The prediction model learning unit 108 constructs at least one of the first prediction model M1, second prediction model M2, and third prediction model M3 as the prediction model M, and these prediction models M are stored in the prediction model storage unit 110 so that they can be used as needed.

The prediction accuracy determination unit 112 is configured to determine the prediction accuracy of each prediction model M (first prediction model M1, second prediction model M2, or third prediction model M3) stored in the prediction model storage unit 110. The prediction accuracy of the prediction model M is calculated, for example, by aggregating the mean absolute error of predicted values for verification data such as actual measured values, but any known method can be used and is not limited to this method. The prediction accuracy determination unit 112 is able to determine whether the prediction accuracy of the prediction model M is below the reference value by comparing the calculated prediction accuracy with a reference value stored in advance in the acceptable accuracy database 126.

The operating condition search unit 114 is configured to search for operating conditions for the control device 200 using the prediction model M stored in the prediction model storage unit 110. The search for operating conditions is performed within the search range set by the search range setting unit 116, by calculating an index corresponding to the performance of the plant 10 based on the predicted value calculated using the prediction model M, and optimizing the index.

Here, Figure 3 is an explanatory diagram showing the calculation flow of a predicted value P using a prediction model M stored in the prediction model storage unit 110 of Figure 1, and Figure 4 is an explanatory diagram showing the calculation flow of an index used to search for operation conditions in the operation condition search unit 114 of Figure 1.

As shown in FIG. 3, prediction model M receives parameters corresponding to explanatory variables and outputs a predicted value P corresponding to the objective variable. For example, if plant 10 is a boiler system, predicted value P is a process value related to the operating state of the boiler system, and more specifically, the steam temperature and pressure in each part of the boiler system, metal temperature, or NOx concentration emitted from the boiler system. Explanatory variables are various operating parameters of the boiler system, and more specifically, the angle of the burner that injects fuel, the opening degrees of various dampers that adjust the air volume, etc. Prediction models M are constructed in prediction model learning unit 108 according to the type of objective variable, and multiple prediction models M according to the type of objective variable are stored in prediction model storage unit 110.

Furthermore, if a second prediction model M2 or a third prediction model M3 is stored in addition to a first prediction model M1 for a prediction model M corresponding to a certain objective variable, the predicted value P is calculated using the prediction model with the best prediction accuracy among these prediction models. In other words, the predicted values P for multiple objective variables are calculated using multiple corresponding prediction models M, and each prediction model M is the one with the best prediction accuracy among the prediction models for the corresponding objective variable (at least one of the first prediction model M1, second prediction model M2, or third prediction model M3).

The operation condition search unit 114 inputs input parameters (initial values) corresponding to preset operation conditions into multiple prediction models M stored in the prediction model storage unit 110, and finds each predicted value P (hereinafter, when distinguishing between them, they will be referred to as "predicted values P1, P2, ..." as appropriate). These predicted values P are converted into an index IN for evaluating the predicted values P using a predetermined conversion formula. Specifically, as shown in FIG. 4, the operation condition search unit 114 converts each predicted value P1, P2, ... into a corresponding score SC1, SC2, ... and calculates the index IN (= SC1 + SC2 + ...) as the sum of these scores. The operation condition search unit 114 then searches for operation conditions that will optimize the index IN (e.g., minimum or maximum) (i.e., by repeatedly changing the operation conditions and calculating the index IN, the operation conditions that optimize the index IN are identified).

The search for operation conditions in the operation condition search unit 114 is performed within a search range set by the search range setting unit 116. This search range is set to a first search range by default, but when the search range restriction process is executed as described below, it is restricted to a second search range that is specified to be narrower than the first search range. By restricting the search range for operation conditions to a range where the prediction model M has good prediction accuracy or a range that does not significantly impair the driving state, it is possible to substantially improve prediction accuracy and improve driving reliability.

The operating conditions searched for by the operating condition search unit 114 are output to the control device 200 via the external output interface 118. The control device 200 controls the plant 10 in accordance with the operating conditions output in this manner, thereby ensuring optimal control of the plant 10.

Next, we will explain the plant control support method implemented using the plant control support device 100 having the above configuration. Figure 5 is a flowchart showing the plant control support method according to one embodiment.

First, operating data is collected in the operating data storage unit 106 (step S100). In step S100, operating data is input from the control device 200 that controls the operating plant 10 to the plant control assistance device 100 via the external input interface 102, and the data is processed into operating data by preprocessing performed by the preprocessing unit 104. The processed operating data is collected by being sequentially stored in the operating data storage unit 106. Such storage of operating data is performed sequentially as described above, and in the following explanation, it is assumed that sufficient operating data has been stored in the operating data storage unit 106 to train the prediction model M (first prediction model M1).

Next, the prediction model learning unit 108 constructs a first prediction model M1 through machine learning using the driving data accumulated in the driving data accumulation unit 106 as learning data (step S101). In step S101, the first prediction model learning unit 120 of the prediction model learning unit 108 constructs a first prediction model M1 as a prediction model M. The first prediction model learning unit 120 constructs the first prediction model M1 based on at least one type of machine learning algorithm prepared in advance. In this embodiment in particular, the first prediction model learning unit 120 has multiple types of machine learning algorithms prepared in advance, and generates multiple prediction model candidates corresponding to the first prediction model M1 using the multiple machine learning algorithms for each dependent variable. The first prediction model learning unit 120 then calculates the prediction accuracy of the multiple prediction model candidates corresponding to these first prediction models M1, and adopts the one with the best prediction accuracy as the first prediction model M1 for that dependent variable. The first prediction model M1 adopted in this way is stored in the prediction model storage unit 110. The first prediction model M1 stored in the prediction model storage unit 110 can be accessed as needed by the operation condition search unit 114.

Note that the learning of the first prediction model M1 in step S101 may be performed every predetermined period T1. In other words, machine learning may be performed every predetermined period T1 using the driving data accumulated in the driving data accumulation unit 106 as learning data, thereby updating the first prediction model M1 based on the latest driving data.

Next, the prediction accuracy determination unit 112 determines whether the prediction accuracy of the first prediction model M1 constructed in step S101 is less than a preset reference value (step S102). In step S102, the first prediction model M1 stored in the prediction model storage unit 110 is accessed every predetermined period T2 to calculate the prediction accuracy of the first prediction model M1 and compare this prediction accuracy with the reference value. This predetermined period T2 may be different from the aforementioned predetermined period T1, and in particular may be shorter than the predetermined period T1.

Next, if the prediction accuracy is less than the reference value (step S102: YES), the prediction model learning unit 108 performs additional driving data relearning using the second prediction model learning unit 122 to learn the second prediction model M2 (step S103). In the additional driving data relearning, the second prediction model M2 is constructed by relearning using the driving data used as learning data when constructing the first prediction model M1 in step S101, with additional data added as learning data. Therefore, if the prediction accuracy of the first prediction model M1 is less than the reference value, the additional driving data relearning can be performed using driving data with a larger amount of data due to the addition of the additional data, thereby constructing a second prediction model M2 with improved prediction accuracy compared to the first prediction model M1.

Note that the construction of the second prediction model M2 in the second prediction model training unit 122 may be performed using at least one type of machine learning algorithm, as in the above-described first prediction model training unit 120. In this embodiment, in particular, the second prediction model training unit 122 is provided with multiple types of machine learning algorithms, and multiple prediction model candidates corresponding to the second prediction model M2 are generated for each dependent variable using the multiple machine learning algorithms. The second prediction model training unit 122 then calculates the prediction accuracy of the multiple prediction model candidates corresponding to the second prediction model M2, and adopts the one with the best prediction accuracy as the second prediction model M2 for that dependent variable. The constructed second prediction model M2 is stored in the prediction model storage unit 110 instead of or in addition to the above-described first prediction model M1. The second prediction model M2 stored in the prediction model storage unit 110 can be accessed as needed by the operation condition search unit 114.

The prediction accuracy determination unit 112 then determines whether the prediction accuracy of the second prediction model M2 constructed in step S103 is less than a preset reference value (step S104). In step S104, following the procedure in step S102 described above, the prediction accuracy of the second prediction model M2 is calculated and compared with the reference value.

Note that the reference value used as the judgment criterion in step S104 may be the same as the reference value used as the judgment criterion in step S102, or may be different.

Next, if the prediction accuracy is less than the reference value (step S104: YES), the prediction model learning unit 108 performs similar operating data relearning using the third prediction model learning unit 124 (step S105), or performs search range restriction processing using the search range setting unit 116 (step S106). As shown in FIG. 1, the plant control assistance device 100 according to one embodiment includes a display unit 130 and a selection unit 132, allowing the operator to selectively perform either step S105 or S106.

The display unit 130 is a display device such as a display that displays various information necessary for the operator. The information displayed on the display unit 130 can broadly include information used when the operator selects either step S105 or S106, and may include, for example, the prediction accuracy calculated in the process of making the judgment in the prediction accuracy judgment unit 112.

The selection unit 132 is configured to allow the operator, referring to the information displayed on the display unit 130, to select step S105 or S106, and may be an input device such as a keyboard, mouse, or touch panel. The operator can refer to the information displayed on the display unit 130 and operate the selection unit 132 based on their own judgment, thereby selecting whether to perform step S105 or S106 when the prediction accuracy of the second prediction model M2 is below the reference value.

In general, the search range limiting process tends to require shorter calculation times than similar driving data relearning. Therefore, the selection criteria used by the selector 132 can be, for example, to select step S105 when a high-quality prediction model M with good prediction accuracy is required, or to select step S106 when shorter calculation times are a priority.

If similar driving data relearning is performed in step S105, the third prediction model learning unit 124 constructs a third prediction model M3 using the similar driving data as learning data. In similar driving data relearning, driving data at driving points with similar driving conditions is used as learning data to perform relearning, thereby obtaining a third prediction model M3 with improved prediction accuracy.

Note that the construction of the third prediction model M3 in the third prediction model training unit 124 may be performed using at least one type of machine learning algorithm, similar to the construction of the first prediction model M1 in the first prediction model training unit 120 and the construction of the second prediction model M2 in the second prediction model training unit 122 described above. In this embodiment, particularly, the third prediction model training unit 124 is provided with multiple types of machine learning algorithms in advance, and multiple prediction model candidates corresponding to the third prediction model M3 are generated using the multiple machine learning algorithms for each dependent variable. The third prediction model training unit 124 then calculates the prediction accuracy of the multiple prediction model candidates corresponding to these multiple third prediction models M3, and adopts the one with the best prediction accuracy as the third prediction model M3 for that dependent variable. The constructed third prediction model M3 is stored in the prediction model storage unit 110 instead of or in addition to the second prediction model M2 described above. The third prediction model M3 stored in the prediction model storage unit 110 can be accessed as needed by the operation condition search unit 114.

On the other hand, when the search range restriction process is performed in step S106, the search range when searching for operating conditions in step S110, described below, is restricted to a specified range, thereby improving the feasibility of optimizing driving using a predictive model. For example, if the search range is restricted to a range in which the prediction accuracy of prediction model M is equal to or greater than a threshold, prediction accuracy can be substantially improved. Furthermore, if the search range is restricted to a range that does not significantly impair the driving state, driving can be optimized using prediction model M while maintaining safe driving.

Next, for each of the multiple prediction models M, the prediction model with the best prediction accuracy is selected from the first prediction model M1, the second prediction model M2, or the third prediction model M3 (step S107). As mentioned above, multiple prediction models are prepared depending on the type of dependent variable, and for each of these, at least one of the first prediction model M1, the second prediction model M2, or the third prediction model M3 is constructed in the above-mentioned step. In step S107, the prediction model with the best prediction accuracy is adopted from the first prediction model M1, the second prediction model M2, or the third prediction model M3.

Next, operating conditions are searched for using each prediction model M selected in step S107 (step S108), and the searched operating conditions are output to the control device 200 via the external output interface 118 (step S109). In step S108, as described above with reference to FIG. 4, an index IN is calculated based on each predicted value P using each prediction model M selected in step S107, and operating conditions are searched for to optimize the index IN.

Note that if search range restriction processing was performed in step S106, the search range for operation conditions in step S108 will be limited to the specified range.

Furthermore, within the scope of the spirit of this disclosure, the components in the above-described embodiments may be replaced with well-known components, 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 plant control assistance device according to one aspect includes:
1. A plant control support device for supporting plant control using a plurality of process values of a plant that are predicted using a plurality of prediction models, the device comprising:
a first prediction model learning unit configured to learn a plurality of first prediction models as the plurality of prediction models by using learning data that is operation data of the plant;
a second prediction model learning unit configured to re-learn a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
a third prediction model learning unit configured to re-learn a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data for the second prediction model whose prediction accuracy is less than the reference value;
a prediction model selection unit that selects, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the highest prediction accuracy;
Equipped with.

According to aspect (1) above, multiple first prediction models are constructed using operating data as learning data, each corresponding to a plurality of process values to be predicted. For those first prediction models whose prediction accuracy is below a reference value, additional operating data relearning is performed using the operating data to which additional data has been added as learning data, thereby constructing a second prediction model with improved prediction accuracy. If the prediction accuracy of the second prediction model is still below the reference value, similar operating data relearning is performed using similar operating data similar to the operating point of the plant from the operating data, thereby improving the prediction accuracy of a third prediction model with improved prediction accuracy. The plant control device selects the first, second, or third prediction model with the best prediction accuracy as the prediction model for predicting each of the plurality of process values. This enables accurate prediction of each process value, thereby suitably improving the controllability of the plant control device.

(2) In another aspect, in the above aspect (1),
At least one of the first prediction model learning unit, the second prediction model learning unit, or the third prediction model learning unit generates multiple prediction model candidates for each of the multiple prediction models using multiple types of machine learning algorithms, and selects the one with the best prediction accuracy from the multiple prediction model candidates as the first prediction model, the second prediction model, or the third prediction model.

According to aspect (2) above, at least one of the first prediction model learning unit, the second prediction model learning unit, and the third prediction model learning unit generates multiple prediction model candidates using multiple types of machine learning algorithms. Then, by selecting the prediction model with the best prediction accuracy from among these multiple prediction model candidates, it becomes possible to build a prediction model with excellent prediction accuracy.

(3) In another aspect, in the above aspect (1) or (2),
The similar driving data is constructed by extracting a predetermined ratio or number of data that have a small deviation from the driving point from the driving data and the additional data.

According to aspect (3) above, the similar driving data used as learning data in similar driving data relearning is constructed by extracting a predetermined percentage or number of data that have a small deviation from the driving point from the driving data and additional data. As a result, in similar driving data relearning, by performing relearning using such similar driving data, the prediction accuracy of the prediction model can be suitably improved.

(4) In another aspect, in any one of the above (1) to (3),
The additional data is data collected from the plant since the first prediction model was last trained.

According to aspect (4) above, the learning data used in the additional operating data relearning includes additional data collected from the plant between the previous learning and the relearning, in addition to the operating data used during the previous learning of the prediction model. This makes it possible to suitably improve the prediction accuracy of the prediction model by relearning using learning data that contains a larger amount of data than during the previous learning.

(5) In another aspect, in any one of the above (1) to (4),
an index calculation unit for calculating an index related to performance of the plant based on the plurality of process values predicted using the plurality of prediction models;
an operating condition search unit for searching for operating conditions of the plant based on the index;
a control unit for controlling the plant based on the operating conditions;
Further provided with:

According to aspect (5) above, by using the predicted values of the process values obtained using the prediction model with improved prediction accuracy as described above, it is possible to optimally search for plant operating conditions and control the plant.

(6) In another aspect, in any one of the above (1) to (5),
The plant is a boiler unit.

According to the above aspect (6), process values related to the characteristics of the boiler equipment can be suitably predicted using a prediction model with good prediction accuracy.

(7) A plant control support method according to one aspect includes:
1. A plant control support method for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the method comprising:
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
Equipped with.

According to aspect (7) above, multiple first prediction models are constructed using operating data as learning data, each corresponding to a plurality of process values to be predicted. For those first prediction models whose prediction accuracy is below a reference value, additional operating data relearning is performed using the operating data to which additional data has been added as learning data, thereby constructing a second prediction model with improved prediction accuracy. If the prediction accuracy of the second prediction model is still below the reference value, similar operating data relearning is performed using similar operating data from the operating data that is similar to the operating point of the plant as learning data, thereby improving the prediction accuracy of a third prediction model with improved prediction accuracy. The plant control device selects the first, second, or third prediction model with the best prediction accuracy as the prediction model for predicting each of the plurality of process values. This enables each process value to be predicted with high accuracy, thereby suitably improving the controllability of the plant control device.

(8) A plant control assistance program according to one aspect includes:
1. A plant control support program for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the program comprising:
To the computer device,
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
is possible.

According to aspect (8) above, multiple first prediction models are constructed using operating data as learning data, each corresponding to a plurality of process values to be predicted. For those first prediction models whose prediction accuracy is below a reference value, additional operating data relearning is performed using the operating data to which additional data has been added as learning data, thereby constructing a second prediction model with improved prediction accuracy. If the prediction accuracy of the second prediction model is still below the reference value, similar operating data relearning is performed using similar operating data similar to the operating point of the plant from the operating data, thereby improving the prediction accuracy of a third prediction model with improved prediction accuracy. The plant control device selects the first, second, or third prediction model with the best prediction accuracy as the prediction model for predicting each of the plurality of process values. This enables each process value to be predicted with high accuracy, thereby suitably improving the controllability of the plant control device.

REFERENCE SIGNS LIST 1 Plant control system 10 Plant 100 Plant control support device 102 External input interface 104 Preprocessing unit 106 Operation data accumulation unit 108 Prediction model learning unit 110 Prediction model storage unit 112 Prediction accuracy determination unit 114 Operation condition search unit 116 Search range setting unit 118 External output interface 120 First prediction model learning unit 122 Second prediction model learning unit 124 Third prediction model learning unit 130 Display unit 132 Selection unit 200 Control device M Prediction model M1 First prediction model M2 Second prediction model M3 Third prediction model V Virtual space

Claims (8)

1. A plant control support device for supporting plant control using a plurality of process values of a plant that are predicted using a plurality of prediction models, the device comprising:
a first prediction model learning unit configured to learn a plurality of first prediction models as the plurality of prediction models by using learning data that is operation data of the plant;
a second prediction model learning unit configured to re-learn a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
a third prediction model learning unit configured to re-learn a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data for the second prediction model whose prediction accuracy is less than the reference value;
a prediction model selection unit that selects, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the highest prediction accuracy;
A plant control support device comprising: The plant control assistance device of claim 1, wherein at least one of the first prediction model learning unit, the second prediction model learning unit, and the third prediction model learning unit generates multiple prediction model candidates for each of the multiple prediction models using multiple types of machine learning algorithms, and selects the prediction model with the best prediction accuracy from the multiple prediction model candidates as the first prediction model, the second prediction model, or the third prediction model. The plant control assistance device according to claim 1 or 2, wherein the similar operating data is constructed by extracting a predetermined percentage or number of data from the operating data and the additional data that have a small deviation from the operating point. The plant control assistance device according to claim 1 or 2, wherein the additional data is data collected from the plant since the previous learning of the first prediction model. an index calculation unit for calculating an index related to performance of the plant based on the plurality of process values predicted using the plurality of prediction models;
an operating condition search unit for searching for operating conditions of the plant based on the index;
a control unit for controlling the plant based on the operating conditions;
The plant control assistance device according to claim 1 or 2, further comprising: The plant control assistance device according to claim 1 or 2, wherein the plant is a boiler system. 1. A plant control support method for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the method comprising:
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
A plant control support method comprising: 1. A plant control support program for supporting plant control using a plurality of process values of a plant predicted using a plurality of prediction models, the program comprising:
To the computer device,
learning a plurality of first prediction models as the plurality of prediction models using learning data that is operation data of the plant;
a step of re-learning a second prediction model using the driving data to which additional data has been added as learning data for a first prediction model having a prediction accuracy less than a reference value among the plurality of first prediction models;
re-learning a third prediction model using, as learning data, similar operating data that is similar to an operating point of the plant among the operating data of the second prediction model whose prediction accuracy is less than the reference value;
selecting, as the prediction model, one of the first prediction model, the second prediction model, and the third prediction model that has the best prediction accuracy;
A plant control support program that can execute the above.