Learning device, learning method, and learning program

Abstract

To avoid lowering of adequacy of an output of a model obtained by repetition of sequential learning by JIT method in imitation learning.SOLUTION: An assignment unit 134 assigns weight to each of pieces of first data which are combinations of explanatory variables and objective variables. An extracting unit 131 extracts second data from the first data based on distance between the explanatory variable and designated explanatory variable and the weight. An updating unit 133 updates a model for outputting the objective variable from the explanatory variable by using the second data.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a learning device, a learning method, and a learning program. [Background technology]

[0002] A technique known as imitation learning is known in the art, in which a machine learning model learns human behavior and the model is used to teach actions to humans or robots, etc.

[0003] Also, a technique known as the Just-In-Time (JIT) method is known in which a large amount of observed data is accumulated, data in the vicinity of a desired point is extracted from the accumulated data, and the extracted data is used to sequentially learn a model (see, for example, non-patent document 1).

[0004] Here, for example, in a chemical plant, environmental changes occur over time, such as aging of equipment, deterioration of catalysts, and changes in production load plans.

[0005] In response to this, it is conceivable to apply the JIT method to imitation learning, which learns how operators operate equipment in chemical plants, so that the model can adapt to changes in the environment. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2019-185194 A [Non-patent literature]

[0007] [Non-Patent Document 1] Shigeru Yamamoto, "Just-In-Time Predictive Control: Predictive Control Based on Accumulated Data," Instrumentation and Control, Vol. 52, No. 10, October 2013 (https: / / www.jstage.jst.go.jp / article / sicejl / 52 / 10 / 52_878 / _pdf / -char / ja) Summary of the Invention [Problem to be solved by the invention]

[0008] However, when the JIT method is applied to imitation learning, the problem is that as sequential learning is repeated, the operator skills reflected in the model at the initial stage are lost, and the validity of the model output decreases.

[0009] For example, if equipment is operated according to the output of a model that has learned the operations of an operator at an early stage, it is expected that the operational quality of the equipment and the plant in which the equipment is operated will improve, even if the operation is performed by an inexperienced operator. Therefore, the validity of the model's output can be said to be high.

[0010] On the other hand, as time passes, the history of actions taken by imitating operators is accumulated as training data and the model is learned sequentially, so the influence of the data learned in the early stages becomes weaker and the validity of the model output may decrease.

[0011] If equipment is operated in accordance with such an output whose validity has decreased, problems such as a decrease in the operating quality of the equipment and plant and an increase in costs may occur. [Means for solving the problem]

[0012] In order to solve the above-mentioned problems and achieve the objective, the learning device is characterized by having an assignment unit that assigns a weight based on any one of the production volume, yield, operating time, and energy consumption in the production process to each piece of first data, which is a combination of explanatory variables that represent a situation in a product production process and a target variable that represents the operation of equipment in the production process, an extraction unit that extracts second data from the first data based on the distance between the explanatory variables and a specified explanatory variable and the weight, and an update unit that uses the second data to update a model that outputs the target variable from the explanatory variables. Effect of the Invention

[0013] According to the present invention, it is possible to prevent a decrease in the validity of the model output when sequential learning is repeated using the JIT method in imitation learning. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating a plant operation system. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of a server according to the first embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the history DB. [Figure 4] FIG. 4 is a diagram illustrating the relationship between the prediction target and training data. [Diagram 5] FIG. 5 is a flowchart showing the flow of the learning process according to the first embodiment. [Figure 6] FIG. 6 is a diagram for explaining the classification method. [Figure 7] FIG. 7 is a flowchart showing the flow of the learning process according to the second embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a computer that executes a learning program. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a learning device, a learning method, and a learning program according to the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the following embodiments.

[0016] [First embodiment] [Configuration of the first embodiment] First, a plant operation system will be described with reference to Fig. 1. The plant operation system 1 is a system for managing and controlling a production process of a product in a plant. The plant includes a chemical plant for producing chemical products.

[0017] As shown in FIG. 1, the system includes a server 10, a terminal device 20, a terminal device 30, and a plant system 40.

[0018] The server 10 performs processing related to a model for performing imitation learning. The server 10 can function as a learning device.

[0019] Furthermore, the server 10, the terminal device 20, the terminal device 30, and the plant system 40 are connected to each other so as to be able to communicate data with each other via a network N. For example, the network N is the Internet and an intranet.

[0020] The terminal device 20 and the terminal device 30 are information processing devices such as a personal computer, a tablet terminal, a smartphone, etc. The terminal device 30 may be a dedicated terminal for operating equipment in the plant.

[0021] The plant system 40 may include equipment used in the production process and a distributed control system (DCS). For example, the equipment is a reactor, a cooler, a gas-liquid separator, etc.

[0022] The operator is a user who operates devices included in the plant system 40 via the terminal device 30. The staff is a user who manages models used in the server 10 via the terminal device 20.

[0023] The processing of each device in the plant operation system 1 will be described with reference to FIG.

[0024] First, the terminal device 20 manages the model in response to operations by the staff (step S1). For example, the terminal device 20 can instruct the server 10 to change the model and to execute a learning process and an inference process. The terminal device 20 can also output information acquired from the server 10 and present it to the staff.

[0025] The terminal device 30 operates the equipment of the plant system 40 in response to an operation by an operator (step S2). For example, the terminal device 30 sets the temperature and pressure inside the equipment, the target value of the production amount in the production process, the amount of raw materials to be input into the equipment, and the like, through the operation.

[0026] The plant system 40 operates in accordance with an operation from the terminal device 30 (step S3). Then, the plant system 40 provides an operation history to the server 10 (step S4).

[0027] For example, the history includes sensor values ​​of sensors installed at various locations in the plant system 40 and setting values ​​set by operations from the terminal device 30. The history may also be time-series data in which a time (time stamp) is added to each record.

[0028] The server 10 performs model learning, inference using the model, and weighting for data extraction (step S5). Each process of the server 10 will be described in detail later.

[0029] Furthermore, the server 10 provides the inference result to the operator (step S6). For example, the inference result is an operation content predicted from the situation. The operator operates the plant system 40 according to the provided operation content.

[0030] The model learns the operations of the operator through imitation learning, so other operators can imitate the operations by following the operations obtained as a result of inference by the model.

[0031] The server 10 will be described in detail with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the server according to the first embodiment.

[0032] As shown in FIG. 2, the server 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0033] The communication unit 11 performs data communication with other devices via a network. For example, the communication unit 11 is a network interface card (NIC).

[0034] The storage unit 12 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 12 may be a semiconductor memory in which data can be rewritten, such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM).

[0035] The storage unit 12 stores an OS (Operating System) and various programs executed by the server 10. The storage unit 12 stores model information 121 and a history DB 122.

[0036] The model information 121 is information such as parameters for constructing a model. For example, if the model is a neural network, the model information 121 is the weight and bias of each layer. Furthermore, the model information 121 includes parameters such as the order of preprocessing, the window width (window size) in moving average processing, etc.

[0037] The history DB 122 is information including history provided from the plant system 40. Fig. 3 is a diagram showing an example of the history DB. As shown in Fig. 3, the history DB 122 includes a list of explanatory variables such as time, a first temperature, a second temperature, a first pressure, a second pressure, a flow rate, a set value, and a CO2 concentration, as well as a set value that is a response variable, and a weight.

[0038] The first temperature, the second temperature, the first pressure, the second pressure, and the flow rate are sensor values ​​of sensors installed at various locations in the plant system 40, respectively.

[0039] The first temperature, the second temperature, the first pressure, the second pressure, and the flow rate are explanatory variables of the model, and are examples of explanatory variables that represent a situation in the production process of a product.

[0040] The setting value is a value that is set by an operation from the terminal device 30. The setting value may be a normalized value of an actually set value. The setting value corresponds to a response variable of the model.

[0041] The set value is an example of a response variable of the model, which represents the operation of equipment in a production process.

[0042] The CO2 concentration is the concentration of CO2 generated in the production process, and is used as an index in the weighting process described below.

[0043] The weight is a value that is assigned to each record in the history DB. The process of assigning weights and the process of extracting data using weights will be described later.

[0044] The times are time stamps indicating the dates and times when the first temperature, the second temperature, the first pressure, the second pressure, the flow rate, and the CO2 concentration were acquired.

[0045] For example, Figure 3 shows that at the time "2021 / 11 / 5 13:30:01", the first temperature is "40°C", the second temperature is "241°C", the first pressure is "501 hPa", the second pressure is "119 hPa", the flow rate is "12 m3 / s", the set value is "0.2", and the CO2 concentration is "700 ppm".

[0046] Furthermore, Figure 3 shows that the record with the time “2021 / 11 / 5 13:30:01” was assigned a weight of “1.11”.

[0047] The control unit 13 controls the entire server 10. The control unit 13 is, for example, an electronic circuit such as a central processing unit (CPU), a micro processing unit (MPU), or a graphics processing unit (GPU), or an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0048] The control unit 13 also has an internal memory for storing programs and control data that define various processing procedures, and executes each process using the internal memory. The control unit 13 also functions as various processing units by the operation of various programs. For example, the control unit 13 has an extraction unit 131, a calculation unit 132, an update unit 133, an assignment unit 134, and a display control unit 135.

[0049] The extraction unit 131 extracts data from the data included in the history DB 122 based on the distance between the explanatory variable and the specified explanatory variable and the weight. The data included in the history DB 122 is an example of first data. The data extracted by the extraction unit 131 is an example of second data.

[0050] The specified explanatory variable is called a request point. For example, the request point is an explanatory variable (corresponding to each sensor value in the history DB 122) at a predetermined time. In addition, the objective variable (setting value) at the request point may be unknown.

[0051] Here, in the JIT method, data is extracted based on the Euclidean distance between the training data (corresponding to the history DB 122 in this embodiment) which is a multidimensional vector and the request point which is a multidimensional vector. Note that the distance between the training data and the request point is not limited to the Euclidean distance, and may be, for example, the Mahalanobis distance, the cosine similarity, or the like.

[0052] On the other hand, the server 10 (learning device) of this embodiment extracts data using not only the distance between the training data and the request point but also the weight.

[0053] First, the extraction unit 131 calculates the Euclidean distance between the request point and each record of the history DB 122. Since the request point and each record of the history DB 122 are represented by vectors, the extraction unit 131 may calculate the Euclidean norm by the method described in Non-Patent Document 2.

[0054] In the conventional JIT method, k-Nearest Neighbors (k-NN) are extracted, which are k (k is an integer) records with small calculated Euclidean distance.

[0055] On the other hand, the extraction unit 131 extracts records by referring to the weights in the history DB 122 in addition to the calculated Euclidean distances.

[0056] Here, the larger the weight, the more desirable the data is to be extracted. At this time, the extracting unit 131 preferentially extracts data from the history DB 122 that has a small value that increases as the distance increases and decreases as the weight increases.

[0057] For example, the extraction unit 131 extracts k (for example, 1,000) records from the history DB 122 in ascending order of the value obtained by multiplying the Euclidean distance by the inverse of the weight.

[0058] Also, for example, the extraction unit 131 may extract only k records from the history DB 122 whose weights are equal to or greater than a threshold value in ascending order of Euclidean distance.

[0059] Also, for example, the extraction unit 131 may extract only k records from the history DB 122 whose Euclidean distance is equal to or smaller than a threshold, in descending order of weight.

[0060] The calculation unit 132 calculates the objective variables by inputting the explanatory variables to the model constructed from the model information 121. That is, the calculation unit 132 performs inference processing.

[0061] The update unit 133 uses the data extracted by the extraction unit 131 to update a model that outputs a response variable from an explanatory variable.

[0062] For example, the update unit 133 calculates an objective function that represents the difference between the objective variable calculated by the calculation unit 132 and the objective variable included in the data extracted by the extraction unit 131, and repeatedly updates the model parameters, i.e., the model information 121, so that the objective function becomes smaller until a learning termination condition is satisfied.

[0063] 4 is a diagram for explaining the relationship between the prediction target and training data. The training data, which is data up to time t-1, is a record in which the setting values ​​in the history DB 122 have been registered. On the other hand, the data of the prediction target at time t corresponds to the request point. For example, the period from time 0 to time t-1 is the target period for searching for training data. Therefore, as time passes (as t increases), the target period for searching for training data increases.

[0064] The assignment unit 134 assigns a weight to each of the data included in the history DB 122, which is a combination of an explanatory variable and a target variable.

[0065] For example, the weighting unit 134 assigns a larger weight to each piece of data included in the history DB 122 as the contribution of the data to bringing the index closer to the target value increases. In this embodiment, the larger the weight, the more desirable the data is as an extraction target.

[0066] It is believed that indicators can be improved by operating equipment according to the output of a model that has been trained on data extracted based on such weights.

[0067] For example, the assignment unit 134 assigns a weight to each piece of data included in the history DB 122, which is a combination of explanatory variables representing the situation in the product production process and objective variables representing the operation of equipment in the production process, such that the weight decreases as the concentration of a specified substance discharged in the production process increases.

[0068] In addition, the assignment unit 134 assigns a weight obtained from the closeness of an index based on an event observed at a first time to a target value to data included in the history DB 122 that is associated with a second time that is a predetermined time in the past from the first time.

[0069] Furthermore, when the index is a positive value and a smaller value is more desirable (for example, the target value is 0), the assigning unit 134 assigns the inverse of the index as the weight.

[0070] An example of a specific substance emitted in a production process is CO2. From the perspective of reducing greenhouse gases, it is preferable that the concentration of CO2 emitted is small.

[0071] In addition, in the plant system 40 of this embodiment, it is assumed that it is known that it takes about 20 minutes for the effect of the operation of setting the set value (set value) to be reflected in the concentration of CO2.

[0072] For example, the assignment unit 134 assigns a weight that is a normalized value of the inverse of the CO2 concentration in the record for the first time to a record for a time 20 minutes before the first time in the history DB 122. Since the CO2 concentration is always equal to or greater than 0, the closer the CO2 concentration is to the target value of 0, the larger the inverse of the CO2 concentration becomes.

[0073] In the example of FIG. 3, the assignment unit 134 assigns (adds) the normalized value of the inverse 1 / 900 of the CO2 concentration at the time "2021 / 11 / 5 14:00:02" to the weight of the time "2021 / 11 / 5 13:40:02".

[0074] Furthermore, here, it is considered that the impact on the set CO2 concentration begins to occur 30 minutes before, and the assignment unit 134 assigns (adds) the weighting obtained from the CO2 concentration at the time "2021 / 11 / 5 14:00:02" to the weighting from the time "2021 / 11 / 5 13:30:02" to "2021 / 11 / 5 13:40:02".

[0075] The index is not limited to the CO2 concentration, but may be production volume, yield, operating time, energy consumption, etc.

[0076] Also, if it is desired that the state is stable, the weight may be a value that increases as the variance of the index decreases.

[0077] [Processing of the first embodiment] The flow of the learning process according to the first embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the flow of the learning process according to the first embodiment.

[0078] 5, first, the server 10 assigns weights to history records based on evaluation variables (step S101). The evaluation variables are indices such as CO2 concentration. The evaluation variables may be included in the explanatory variables or the objective variables.

[0079] Next, the server 10 extracts records from the history based on the distance from a predetermined record and the weight (step S102). For example, the server 10 extracts a predetermined number of records in ascending order of the value obtained by multiplying the Euclidean distance from the record that is the request point by the inverse of the weight.

[0080] Here, the server 10 updates the model based on the extracted records (step S103). For example, the server 10 updates the model so that an error in the setting value obtained by inputting each sensor value of the extracted records into the model is minimized.

[0081] The server 10 can update the model using linear methods such as Ridge and Lasso, or non-linear methods such as deep learning.

[0082] [Advantages of the First Embodiment] As described above, the assigning unit 134 assigns a weight to each of the first data, which is a combination of an explanatory variable and a target variable. The extracting unit 131 extracts the second data from the first data based on the distance between the explanatory variable and a specified explanatory variable and the weight. The updating unit 133 uses the second data to update the model that outputs the target variable from the explanatory variable.

[0083] In this way, the server 10 can extract data for learning by considering not only the distance from the request point but also the weighting. As a result, according to this embodiment, it is possible to prevent the validity of the model output from decreasing when sequential learning is repeated by the JIT method in imitation learning.

[0084] The assigning unit 134 assigns a weight to each piece of first data that increases with the degree of contribution to bringing the index closer to the target value. The extracting unit 131 preferentially extracts data from the first data that has a small value that increases with the distance and decreases with the weight.

[0085] This makes it possible to easily extract data that takes into account both the distance from the requested point and the weight.

[0086] The assignment unit 134 assigns a weight obtained from the closeness of an index based on an event observed at a first time to a target value to data of the first data that is associated with a second time that is a predetermined time in the past from the first time.

[0087] This makes it possible to extract data that will improve the index with high accuracy, even if there is a time lag before the data is reflected in the index.

[0088] When the index is a positive value and a smaller value is more desirable, the assignment unit 134 assigns the inverse of the index as a weight. This reverses the magnitude relationship of the index, making it easy to use it as a weight.

[0089] The assignment unit 134 assigns a weight to each of the first data, which is a combination of an explanatory variable representing a situation in the production process of a product and a target variable representing the operation of equipment in the production process, such that the weight decreases as the concentration of a specified substance discharged in the production process increases.

[0090] This makes it possible to train the model on operations that can suppress the emission of substances whose concentrations are desirable to be small.

[0091] The display control unit 135 causes the terminal device 20 to display a screen for instructing execution of a model learning process, a screen for browsing the contents of the history DB, or the like.

[0092] [Second embodiment] In the second embodiment, an example will be described in which the server 10 uses a plurality of models depending on the characteristics of the data. The second embodiment is implemented by a server 10 having a similar configuration to that of the first embodiment.

[0093] In the second embodiment, the extraction unit 131 extracts data based on the distance between the request point and the explanatory variable from among data belonging to any one of a plurality of clusters into which the history DB 122, which is a combination of explanatory variables and objective variables, is classified.

[0094] The extraction unit 131 extracts past records in each cluster by the JIT method. When extracting data, the extraction unit 131 may or may not take into account the weighting applied in the first embodiment.

[0095] Furthermore, the update unit 133 uses the data extracted by the extraction unit 131 to update a model corresponding to a cluster from which data has been extracted by the extraction unit 131, among the models corresponding to each of the multiple clusters.

[0096] The extraction unit 131 classifies each record of the history DB 122 into a plurality of clusters by the method of Fig. 6. Fig. 6 is a diagram for explaining the classification method.

[0097] The extraction unit 131 may perform classification using a statistical clustering method, or may perform classification on a rule basis.

[0098] As shown in FIG. 6, the extraction unit 131 calculates the cross-correlation between two variables at each lag number for a group of records in the history DB 122 whose time falls within a predetermined period.

[0099] For example, the extraction unit 131 calculates the cross-correlation between the first temperature and the second temperature. When the number of lags is 0, the cross-correlation is the cross-correlation between the first temperature and the second temperature at the same time, that is, in the same record.

[0100] Furthermore, for example, the cross-correlation when the number of lags is 10 is the cross-correlation between a first temperature at a certain time and a second temperature 10 seconds after that time.

[0101] Moreover, the cross-correlation when the lag number is −10 is the cross-correlation between the first temperature at a certain time and the second temperature 10 seconds before that time.

[0102] Then, the extraction unit 131 classifies the record group into any one of cluster A, cluster B, and cluster C depending on the number of lags at which the cross-correlation reaches its peak.

[0103] For example, if the lag number at which the cross-correlation peaks is equal to or greater than −10 and less than 0, the extraction unit 131 classifies the record group into cluster A.

[0104] For example, the extraction unit 131 classifies the record group into cluster B when the lag number at which the cross-correlation peaks is equal to or greater than -20 and less than -10.

[0105] For example, the extraction unit 131 classifies the record group into cluster C when the lag number at which the cross-correlation peaks is equal to or greater than -30 and less than -20.

[0106] Here, the models corresponding to each cluster have different learning methods. For example, the explanatory variables and hyperparameters used are different for each model. The hyperparameters are, for example, the rounding width, time width (window size), prediction destination, number of steps, number of layers of DNN, number of nodes, activation function, etc.

[0107] The window size is the size of the sliding window when learning time-series data.

[0108] The window size for training the model corresponding to cluster A is 10 minutes. The window size for training the model corresponding to cluster B is 20 minutes. The window size for training the model corresponding to cluster C is 30 minutes.

[0109] [Processing of the second embodiment] The flow of the learning process according to the second embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the flow of the learning process according to the second embodiment.

[0110] As shown in FIG. 7, first, the server 10 calculates the cross-correlation between two pre-specified variables at each lag number (step S201).

[0111] Next, the server 10 clusters the records based on the cross-correlation (step S202). For example, the server 10 performs clustering based on the number of lags at which the cross-correlation has a peak.

[0112] The server 10 executes model learning by a method determined for each cluster (step S203). The model learning is performed by the calculation unit 132 and the update unit 133.

[0113] [Effects of the second embodiment] As described above, the extraction unit 131 extracts data based on the distance between the request point and the explanatory variable from among data belonging to any of a plurality of clusters into which the history DB 122, which is a combination of explanatory variables and objective variables, is classified. In addition, the update unit 133 uses the data extracted by the extraction unit 131 to update a model corresponding to the cluster from which the data was extracted by the extraction unit 131, among the models corresponding to each of the plurality of clusters.

[0114] In this way, by preparing multiple models with different learning methods in advance and combining them with the JIT method, it is possible to respond to major changes in the environment (operating conditions, etc.) that require the model to be changed.

[0115] [System configuration, etc.] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of it can be functionally or physically distributed or integrated in any unit according to various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or can be realized as hardware by wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0116] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0117] [program] As an embodiment, the server 10 can be implemented by installing a learning program that executes the above learning process as package software or online software on a desired computer. For example, the above learning program can be executed by an information processing device, causing the information processing device to function as the server 10. The information processing device here includes desktop or notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as tablet terminals, smartphones, mobile phones and PHS (Personal Handyphone System), and even slate terminals such as PDA (Personal Digital Assistant).

[0118] The server 10 may also be implemented as a server that provides a service related to the above learning process to a client, the client being a terminal device used by a user. For example, the server is implemented as a server device that provides a learning service that uses a request point specification as an input and a trained model as an output. In this case, the server may be implemented as a Web server or as a cloud that provides a service related to the above learning process by outsourcing.

[0119] 8 is a diagram showing an example of a computer that executes a learning program. The computer 1000 has, for example, a memory 1010 and a CPU 1020. The computer 1000 also has a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. Each of these components is connected by a bus 1080.

[0120] The memory 1010 includes a read only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0121] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the server 10 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the server 10 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

[0122] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0123] Note that the program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or wide area network (WAN)). The program module 1093 and the program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]

[0124] 1 Plant operation system 10 Server 20, 30 Terminal equipment 40 Plant Systems 11 Communications Department 12 Storage section 13 Control section 121 Model Information 122 History DB 131 Extraction part 132 Calculation section 133 Update Department 134 Granting Department 135 Display control unit

Claims

1. an assigning unit that assigns a weight based on any one of a production volume, a yield, an operating time, and an energy consumption in the production process to each of first data that is a combination of an explanatory variable that represents a situation in a production process of a product and a target variable that represents an operation of a device in the production process; an extraction unit that extracts second data from the first data based on a distance between the explanatory variable and a designated explanatory variable and the weight; an update unit that updates a model that outputs the objective variable from the explanatory variables by using the second data; A learning device comprising:

2. A learning method performed by a learning device, comprising: an assigning step of assigning a weight based on any one of a production volume, a yield, an operating time, and an energy consumption in the production process to each of first data, which is a combination of an explanatory variable representing a situation in a production process of a product and a target variable representing an operation of a device in the production process; an extraction step of extracting second data from the first data based on a distance between the explanatory variable and a designated explanatory variable and the weight; an updating step of updating a model that outputs the objective variable from the explanatory variables by using the second data; A learning method comprising:

3. a weighting step of weighting each of first data, which is a combination of explanatory variables representing a situation in a production process of a product and a response variable representing an operation of a device in the production process, based on any one of a production volume, a yield, an operating time, and an energy consumption in the production process; an extraction step of extracting second data from the first data based on a distance between the explanatory variable and a specified explanatory variable and the weight; an updating step of updating a model that outputs the objective variable from the explanatory variables by using the second data; A learning program characterized by causing a computer to execute the above.

Images