Learning apparatus, inference apparatus, learning method, inference method, learning program, and inference program

Abstract

To implement an operation support system of a batch-type plant using a machine learning model for imitation learning.SOLUTION: A processing apparatus 10 includes a collection unit 1311, a conversion unit 1313, and a learning unit 1314. The collection unit 1311 collects histories which are combinations of an explanatory variable representing status in a production process of a product and including data identifying the process, and an objective variable representing operation of a device in the process. The conversion unit 1313 converts the data identifying the process into numerical data represented by one or more numerical values. The learning unit 1314 optimizes a parameter of a model configured to output an objective variable from an explanatory variable, using the histories and the numerical data as learning data.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] BACKGROUND ART A technique known as imitation learning is known in the past, in which a machine learning model (hereinafter, referred to as a model) learns human behavior and then uses the model to teach behavior to humans, robots, or the like.

[0003] Here, an operation support system for continuous plants using a model that performs imitation learning has been proposed. For example, in a continuous plant such as a chemical plant, imitation learning is performed by having a model learn the operations actually performed by an operator (plant operation imitation learning). Note that a continuous plant, for example, a heat treatment furnace, is a system in which the heat treatment furnace is operated at all times, and products are fed into the heat treatment furnace to perform heat treatment continuously.

[0004] Using a model that performs this type of imitation learning, it is possible not only to assist plant operation with recommended values, but also to autopilot operations. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7335414 Summary of the Invention [Problem to be solved by the invention]

[0006] In contrast to continuous plants, there is a system called a batch plant, which is a plant in which each production process, such as material input, heating, and cooling, is carried out in sequence in one furnace.

[0007] There are some problems when applying plant operation imitation learning to build a model for a batch plant.

[0008] In batch plants, the operating methods differ depending on the production process. For example, the required operations differ depending on the production process, such as cooling and heating processes, making it difficult to perform consistent control using a single model.

[0009] Furthermore, because batch plants have multiple production processes, creating separate models for each production process in a batch plant would require insufficient data corresponding to each production process, resulting in inaccurate models.

[0010] The present invention has been made in consideration of the above, and aims to provide a learning device, an inference device, a learning method, an inference method, a learning program, and an inference program that realize an operation support system for a batch plant using a machine learning model that performs imitation learning. [Means for solving the problem]

[0011] In order to solve the above-mentioned problems and achieve the objectives, the learning device of the present invention is characterized by having a collection unit that collects history, which is a combination of explanatory variables that represent the situation in a product production process, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion unit that converts the data that identifies the process into numerical data represented by one or more numerical values; and a learning unit that uses the history and the numerical data as learning data and optimizes parameters of a model that outputs the objective variable from the explanatory variables.

[0012] In order to solve the above-mentioned problems and achieve the object, the inference device of the present invention is characterized by having a collection unit that collects history, which is a combination of explanatory variables that represent a situation in a product production process, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion unit that converts the data that identifies the process into numerical data represented by one or more numerical values; and an inference unit that uses a trained model to infer the objective variables that represent the operation of equipment in the process based on the explanatory variables including the numerical data. [Effects of the Invention]

[0013] According to the present invention, an operation support system for a batch plant is realized using a machine learning model that performs imitation learning. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating a plant operation system. [Figure 2] FIG. 2 is a diagram illustrating an outline of model learning according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the processing device according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of data registered in the history database (DB) shown in FIG. [Figure 5] FIG. 5 is a flowchart of the learning process according to the first embodiment. [Figure 6] FIG. 6 is a flowchart of the inference process according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a computer that implements a processing device by executing a program. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, embodiments of a learning device, an inference device, a learning method, an inference program, and an inference 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 embodiments described below.

[0016] [Embodiment 1] [Configuration of the First Embodiment] First, the plant operation system will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining the plant operation system.

[0017] The plant operation system 1 is a system for managing and controlling a product production process (hereinafter referred to as a production process) in a plant. The plant includes a chemical plant for producing chemical products. In this embodiment, a plant operation system applied to a batch plant will be described. A batch plant is a plant in which, for example, each production process, such as material input, heating, and cooling, is performed in sequence for one piece of equipment (e.g., a furnace).

[0018] As shown in FIG. 1, the plant operation system 1 includes a processing device 10, a terminal device 20, and a plant system 30.

[0019] The processing device 10 performs processing related to a model for performing imitation learning (machine learning model), and can function as a learning device and an inference device.

[0020] The processing device 10 and the plant system 30 are connected to each other via a network so that they can communicate data with each other. For example, the network is the Internet and an intranet. The processing device 10 uses the model to present recommended operation values ​​to an operator of the plant system 30, thereby supporting plant operation. Furthermore, when the processing device 10 satisfies predetermined autopilot conditions set by the operator or the like and receives an autopilot command from the operator, it uses the model to perform autopilot control of the plant system 30.

[0021] The plant system 30 may include equipment used in the production process and a distributed control system (DCS). For example, the equipment is a furnace or a reactor, and each production process, such as material input, heating, and cooling, is performed in sequence for one furnace.

[0022] The terminal device 20 is an information processing device such as a personal computer, a tablet terminal, or a smartphone, or a dedicated terminal for operating equipment in the plant.

[0023] The operator is a user who operates the devices included in the plant system 30 via the terminal device 20. The operator also instructs the processing device 10 to start or stop the autopilot. The models used in the processing device 10 are managed appropriately by a system administrator or the like.

[0024] The processing of each device in the plant operation system 1 will be described with reference to FIG.

[0025] The terminal device 20 operates the equipment of the plant system 30 in response to an operation by an operator (step S1). For example, the terminal device 20 operates to set the temperature inside one piece of equipment (e.g., a furnace) of a batch plant, the 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, etc.

[0026] The plant system 30 operates in accordance with the operation from the terminal device 20 (step S2). Then, the plant system 30 transmits the operation history to the processing device 10 (step S3).

[0027] For example, the history may include sensor values ​​of various sensors installed in the furnace of the plant system 30 and setting values ​​set by operation from the terminal device 20. The history may also be time-series data in which a time (time stamp) is assigned to each record. The history may also include, for example, information indicating multiple production processes that were executed sequentially on the equipment.

[0028] The processing device 10 registers the history collected (acquired) from the plant system 30 in a history database (DB) (step S3).

[0029] Next, the processing device 10 acquires learning data to be used for learning (e.g., machine learning) of the model (machine learning model) from the history, learns the model, and performs inference and system application using the model (step S4).

[0030] The processing device 10 uses predetermined autopilot conditions to determine, for example, whether or not autopilot is possible by the processing device 10. Details of each process of the processing device 10 will be described later.

[0031] Furthermore, the processing device 10 presents a guidance screen 21 showing the inference result and the autopilot implementation determination result to the operator's terminal device 20 (step S6). When the autopilot conditions are satisfied, the processing device 10 displays on the guidance screen 21 that it is now possible to start the autopilot. When the terminal device 20 instructs the processing device 10 to start the autopilot, the processing device 10 performs autopilot control of the plant system 30 using the model (step S5).

[0032] Furthermore, if the autopilot conditions are not satisfied while the autopilot is in operation, the processing device 10 displays an instruction to stop the autopilot on the guidance screen 21. When an instruction to stop the autopilot is received from the terminal device 20, the processing device 10 stops the autopilot control of the plant system 30. Then, the terminal device 20 operates the equipment of the plant system 30 in response to an operation by the operator (step S1).

[0033] The model learns the operations of the operators through imitation learning, so other operators can imitate the operations by following the operations obtained as inference results from the model.

[0034] [Model Training] In a batch plant to which the first embodiment is applied, the operation method differs depending on the production process. In this batch plant, the required operations, such as a cooling process and a heating process, differ depending on the production process. In this embodiment, the following model learning is performed to enable consistent control of a batch plant with a single model. Figure 2 is a diagram illustrating an overview of model learning in the first embodiment.

[0035] 2, the processing device 10 constructs a model using the history. Specifically, the processing device 10 learns the model using the history as learning data. Furthermore, the processing device 10 infers (predicts, estimates) the objective variable using the learned model based on the explanatory variables included in the history.

[0036] The history is time-series data stored in the history DB 121, which will be described later. The history includes N records. In the example of FIG. 2, the history includes N records from time t n , operation value Y n , process information, process variable X n where n is a subscript to identify the record.

[0037] The process variable X has items such as the temperature at one or more locations of an equipment (e.g., a furnace), the flow rate at one or more locations, the pressure at one or more locations, and the concentration of gases generated in the production process. The values ​​of these items are detected by sensors installed in the equipment. The time t is a timestamp indicating the date and time when the temperature, pressure, flow rate, and gas concentration were acquired.

[0038] Here, the processing device 10 numerically encodes the process information included in the history and inputs it to the model as an explanatory variable. For example, the processing device 10 converts the process information represented by the text "hoge" into a vector (a n ,b n ,c n ) for example, a n ,b n ,c nare all real values. Data conversion using numerical encoding can also be described as data mapping.

[0039] The model accepts inputs of time t, process variable X, and numerically encoded process information (a, b, c), and outputs manipulated value Y.

[0040] The operation value Y, which is the objective variable, is the operation performed, and is, for example, a set value set by an operation from the terminal device 20. The operations are various operations performed in the production process, such as material input operations, heating operations, cooling operations, valve operations, etc. The set value may be a normalized value of an actually set value.

[0041] [Processing equipment] Next, the processing device 10 will be described in detail. Fig. 3 is a diagram showing an example of the configuration of the processing device 10 according to embodiment 1. As shown in Fig. 3, the processing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0042] 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).

[0043] The storage unit 12 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. Note that the storage unit 12 may also be a data-rewritable semiconductor memory such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM).

[0044] The storage unit 12 stores an OS (Operating System) and various programs executed by the processing device 10. The storage unit 12 includes a history DB 121 and model information 122.

[0045] The history DB 121 is information including history provided from the plant system 30. For example, records are accumulated in the history DB 121 every minute or every second.

[0046] Fig. 4 is a diagram showing an example of data registered in the history DB 121 shown in Fig. 3. As shown in Fig. 4, the history DB 121 includes a time, a process, a first temperature, a second temperature, a first pressure, a second pressure, a flow rate, and a set value.

[0047] The time, process, first temperature, second temperature, first pressure, second pressure, and flow rate are explanatory variables of the model, and are examples of explanatory variables that represent the status of the product production process. The explanatory variables may include pressure at one or more locations, the concentration of gas generated in the production process, etc.

[0048] 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 30. The time is a timestamp indicating the date and time when the sensor value was acquired or the date and time when an operation was performed in accordance with a set value. The process is data identifying the process in which the operation was performed.

[0049] The set value indicates the content of the operation to be performed. For example, the set value is set by an operation from the terminal device 20, such as the opening degree of a valve. The set value may be a normalized value of the actually set value.

[0050] The set value is an objective variable of the model, and is an example of an objective variable that represents the operation of equipment in the production process.

[0051] The model information 122 is information such as parameters for constructing a model. For example, if the model is a neural network, the model information 122 is the weight and bias of each layer.

[0052] The control unit 13 controls the entire processing device 10. The control unit 13 is, for example, an electronic circuit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0053] The control unit 13 also has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory. The control unit 13 also functions as various processing units by running various programs.

[0054] For example, the control unit 13 includes a learning unit 131 (learning device) and an inference unit 132 (inference device). The learning unit 131 executes model learning. The inference unit 132 performs inference using the learned model. The inference unit 132 also applies the obtained objective variables to the plant system 30.

[0055] The learning unit 131 includes a collection unit 1311, a learning data reading unit 1312, a conversion unit 1313, and a learning unit 1314. For example, the learning unit 1314 employs sequential learning using the JIT method.

[0056] The collection unit 1311 collects the history of each production process in the plant system 30. The history is a combination of explanatory variables that represent the status of the product production process and objective variables that represent the operation of equipment in the production process. The collection unit 1311 registers the collected history in the history DB 121.

[0057] The learning data reading unit 1312 reads out history as learning data from the history DB 121. The learning data reading unit 1312 outputs the read learning data to the learning unit 1314. However, for the learning data for the process, the data after being converted by the conversion unit 1313 is input to the learning unit 1314.

[0058] The conversion unit 1313 converts part of the learning data by numerical encoding. The conversion unit 1313 converts the process information into a numerical value or a set of numerical values ​​(for example, a vector with numerical values ​​as elements) by numerical encoding. In this way, the conversion unit 1313 converts data specifying a process into numerical data represented by one or more numerical values.

[0059] 4, the "Process" column in the history DB 121 corresponds to process information. The processes in the history DB 121 are values ​​determined by the user or the system. The processes are represented by symbols such as "A," "B," and "C."

[0060] The conversion unit 1313 converts the processes into pre-associated numerical values. For example, if the processes are represented by alphabets from "A" to "Z," there are 26 types of processes. Each alphabet is associated with a numerical value according to its order. For example, "1.0" is associated with process "A," "2.0" is associated with process "B," and "26" is associated with process "Z."

[0061] In this case, the conversion unit 1313 converts the step "A" into a numerical value "1.0." The conversion unit 1313 also converts the step "B" into a numerical value "2.0." The conversion unit 1313 converts the step "Z" into a numerical value "26."

[0062] Furthermore, the conversion unit 1313 may perform numerical encoding using Onehot Encoding. That is, the conversion unit 1313 can convert data that identifies a process into a Onehot vector. In this case, the conversion unit 1313 converts the process information into a Onehot vector. A Onehot vector has elements equal to or greater than the number of process types. A Onehot vector is a vector in which one element takes "1" and the other elements take "0".

[0063] Here, it is assumed that there are four processes, "A," "B," "C," and "D," and the number of elements of the Onehot vector is four. The conversion unit 1313 converts the process "A" into the vector (1,0,0,0) using Onehot Encoding. The conversion unit 1313 also converts the process "B" into the vector (0,1,0,0) using Onehot Encoding. The conversion unit 1313 also converts the process "C" into the vector (0,0,1,0) using Onehot Encoding. The conversion unit 1313 also converts the process "D" into the vector (0,0,0,1) using Onehot Encoding.

[0064] Furthermore, the process may be expressed as a text in a natural language that describes the process, such as a "heating process," a "cooling process," or a "cutting process." In this case, the conversion unit 1313 can convert keywords included in the text, which is data that identifies the process, into numerical values ​​associated with the keywords. The conversion unit 1313 may convert keywords that appear in the text into numerical values. For example, the conversion unit 1313 converts the keyword "heating" to "1," the keyword "cooling" to "2," and the keyword "cutting" to "3."

[0065] Alternatively, the conversion unit 1313 may perform encoding using a neural network. For example, the conversion unit 1313 performs conversion using a neural network that receives process information as input and outputs a vector with a predetermined number of dimensions, with numerical values ​​as elements.

[0066] If the dimension of the vector output by the neural network is 3, for example, the conversion unit 1313 converts step "A" to (1.0, 2.3, √3) and step "B" to (2.0, -4.5, log2).

[0067] The conversion unit 1313 may also create a model for numeric encoding by performing pre-learning of an unsupervised learning model such as contrastive learning. For example, the conversion unit 1313 converts data identifying a process into a vector having numerical values ​​as elements using contrastive learning. When contrastive learning is used, the more similar the processes are, the closer the distance between the vectors will be, and the more dissimilar the processes are, the farther the distance between the vectors will be.

[0068] The learning unit 1314 optimizes the parameters of a model that outputs a target variable from an explanatory variable. The learning unit 1314 updates the model information 122 using the optimized parameters. For the process, the learning unit 1314 uses data converted by the conversion unit 1313, rather than using the data in the history DB 121 as is.

[0069] The inference unit 132 includes a data acquisition unit 1321 , a conversion unit 1322 , an inference unit 1323 , and a system application unit 1324 .

[0070] The data acquisition unit 1321 acquires explanatory variables of the inference target. The explanatory variables of the inference target are each sensor value at a process and a predetermined time. The objective variable corresponding to the explanatory variables of the inference target may be unknown.

[0071] The converter 1322 performs numerical encoding of the process in the same manner as the converter 13131 .

[0072] The inference unit 1323 infers a response variable corresponding to an explanatory variable of an inference target, using a model constructed from the model information 122. For the process, the inference unit 1323 uses data converted by the conversion unit 1322, rather than using the data in the history DB 121 as is.

[0073] The system application unit 1324 applies the objective variables inferred by the inference unit 1323 as operation values ​​of the plant system 30. Alternatively, the system application unit 1324 presents the objective variables inferred by the inference unit 1323 to an operator.

[0074] [Learning process] Next, a description will be given of the learning process according to Embodiment 1. Fig. 5 is a flowchart of the learning process according to Embodiment 1.

[0075] 5, the processing device 10 collects history of each production process in the plant system 30 (step S11) and registers the collected history in the history DB 121. The processing device 10 reads out the history from the history DB 121 as learning data (step S12). For example, the learning data is a record in the history DB 121 in which a setting value has been registered.

[0076] Here, the processing device 10 converts part of the read learning data by numerical encoding (step S13). That is, the processing device 10 converts data that specifies a process among the data included in the history DB 121 by numerical encoding.

[0077] The processing device 10 uses the training data to train the model (step S14) and optimizes the model parameters. Here, the processing device 10 uses converted data for the data that was the target of conversion in step S13 among the training data. That is, the processing device 10 uses numerically encoded data as training data.

[0078] As described above, the conversion unit 1313 can perform numerical encoding using a model such as a neural network. The model used by the conversion unit 1313 to perform numerical encoding is called a numerical encoding model, to distinguish it from the model for imitation learning, which is the learning target in Fig. 5. Furthermore, since the output of the numerical encoding model is input to the model for imitation learning, the two models can be connected in series and regarded as a single model.

[0079] The numerical encoding model may be trained in advance by self-supervised learning or the like before the model for imitation learning is trained. Furthermore, the numerical encoding model may be trained simultaneously with the model for imitation learning. For example, the parameters of the numerical encoding model may be optimized simultaneously with the parameters of the model for imitation learning in step S14 of FIG. 5. Furthermore, the previously trained numerical encoding model may be additionally trained simultaneously with the model for imitation learning, using the previously trained parameters as initial values.

[0080] [Inference processing] Next, a description will be given of the inference processing according to embodiment 1. Fig. 6 is a flowchart of the inference processing according to embodiment 1.

[0081] 6, the processing device 10 acquires input data (step S21). The input data is explanatory variables of an inference target. For example, the input data is a record in the history DB 121 in which a setting value is not registered.

[0082] Here, the processing device 10 converts a part of the read input data by numerical encoding (step S22). That is, the processing device 10 converts data specifying a process among the data included in the history DB 121 by numerical encoding.

[0083] The processing device 10 performs inference processing using the input data (step S23). The processing device 10 inputs explanatory variables included in the input data into a model to obtain a target variable. Here, the processing device 10 uses converted data for the input data that was the target of conversion in step S22. That is, the processing device 10 uses numerically encoded data as input data.

[0084] The processing device 10 applies the response variable inferred in step S24 as an operation value of the plant system 30 or a value presented to an operator (step S24).

[0085] [Effects of the First Embodiment] As explained above, the collection unit 1311 collects history data, which is a combination of explanatory variables that represent the status of a product production process and include data that identify the process, and objective variables that represent the operation of equipment in the process. The conversion unit 1313 converts the data that identify the process into numerical data represented by one or more numerical values. The learning unit 1314 uses the history data and numerical data as learning data to optimize parameters of a model that outputs an objective variable from the explanatory variables.

[0086] In this way, by converting the information specifying the process into numerical data in advance, the model can handle the process information as information with physical meaning through numerical representation, compared to when the process is specified in an ambiguous manner such as natural language. As a result, according to the embodiment, imitation learning can be realized with particularly high accuracy in batch plants where the operation methods differ depending on the process.

[0087] The conversion unit 1313 converts the data specifying the process into a one-hot vector, which allows the processing device 10 to clearly express the differences between the processes.

[0088] The conversion unit 1313 converts keywords contained in text, which is data specifying a process, into numerical values ​​associated with the keywords. This allows the model to handle process information as information with physical meaning via numerical expressions, compared to when a process is specified from text.

[0089] The conversion unit 1313 converts data identifying a process into a vector with numerical values ​​as elements using a numerical encoding model that has been trained in advance using a self-supervised method such as contrastive learning. This allows the physical information of the process to be reflected in the numerical encoding through learning, allowing the model to more clearly identify the process.

[0090] [System configuration of the embodiment] The processing device 10 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 the functions of the processing device 10 is not limited to that shown in the figure, and all or part of it can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc.

[0091] Furthermore, all or any part of the processes performed by the processing device 10 may be realized by a CPU, a GPU (Graphics Processing Unit), and a program analyzed and executed by the CPU and the GPU. Furthermore, each process performed by the processing device 10 may be realized as hardware using wired logic.

[0092] Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually. Alternatively, all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters described above and illustrated can be changed as appropriate unless otherwise specified.

[0093] [program] 7 is a diagram showing an example of a computer in which a program is executed to realize the processing device 10. 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. These components are connected by a bus 1080.

[0094] The memory 1010 includes a ROM 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). 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 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.

[0095] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the processing device 10 is implemented as a program module 1093 in which code executable by the computer 1000 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 processing device 10 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0096] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in memory 1010 or hard disk drive 1090. Then, CPU 1020 reads program module 1093 and program data 1094 stored in memory 1010 or hard disk drive 1090 into RAM 1012 as necessary and executes them.

[0097] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also 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 program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or a wide area network (WAN)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0098] Although the present invention has been described above as an embodiment, the present invention is not limited to the descriptions and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention. [Explanation of symbols]

[0099] 1 Plant operation system 10 Processing equipment 11 Communications Department 12 Storage section 13 Control Unit 20 Terminal equipment 30 Plant Systems 121 History DB 122 Model Information 131 Learning Department 132 Reasoning part 1311 Collection Department 1312 Learning data reading unit 1313 Conversion Unit 1314 Learning Department 1321 Data Acquisition Department 1322 Conversion Unit 1323 Reasoning Department 1324 System Application Department

Claims

1. a collection unit that collects history data that is a combination of explanatory variables that represent a situation in a production process of a product, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion unit that converts the data specifying the process into numerical data represented by one or more numerical values; a learning unit that uses the history and the numerical data as learning data to optimize parameters of a model that outputs the objective variable from the explanatory variables; A learning device comprising:

2. The conversion unit converts the data specifying the process into a one-hot vector.

2. The learning device according to claim 1 .

3. The conversion unit converts a keyword included in text that is data specifying the process into a numerical value associated with the keyword.

2. The learning device according to claim 1 .

4. The conversion unit converts the data specifying the process into a vector having numerical values ​​as elements, using a numerical encoding model that has been trained in advance using a self-supervised method.

2. The learning device according to claim 1 .

5. The conversion unit converts the data specifying the process into a vector having numerical values ​​as elements, using a numerical encoding model that has been trained simultaneously with the model.

2. The learning device according to claim 1 .

6. a collection unit that collects history data that is a combination of explanatory variables that represent a situation in a production process of a product, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion unit that converts the data specifying the process into numerical data represented by one or more numerical values; an inference unit that infers a response variable representing an operation of a device in the process based on the explanatory variables including the numerical data using a trained model; An inference device comprising:

7. A learning method executed by a learning device, comprising: a collection procedure for collecting a history that is a combination of explanatory variables that represent a situation in a product production process, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion procedure for converting the process-specific data into numerical data represented by one or more numerical values; a learning procedure for optimizing parameters of a model that outputs the objective variable from the explanatory variables using the history and the numerical data as learning data; A learning method comprising:

8. An inference method executed by an inference device, comprising: a collection procedure for collecting a history that is a combination of explanatory variables that represent a situation in a product production process, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion procedure for converting the process-specific data into numerical data represented by one or more numerical values; an inference procedure for inferring a response variable representing an operation of a device in the process based on the explanatory variables including the numerical data using a trained model; 10. An inference method comprising:

9. a collection step of collecting a history that is a combination of explanatory variables that represent a situation in a production process of a product, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion step of converting the process-specific data into numerical data represented by one or more numerical values; a learning step of optimizing parameters of a model that outputs the objective variable from the explanatory variables using the history and the numerical data as learning data; A learning program that allows a computer to execute the above.

10. a collection step of collecting a history that is a combination of explanatory variables that represent a situation in a production process of a product, the explanatory variables including data that identify the process, and objective variables that represent the operation of equipment in the process; a conversion step of converting the process-specific data into numerical data represented by one or more numerical values; an inference step of inferring a response variable representing an operation of a device in the process based on the explanatory variables including the numerical data using the trained model; An inference program that allows a computer to execute the above.

Images