Plant model construction device, plant model construction method, and computer-readable storage medium

Abstract

A plant model construction device is provided with: a common model construction unit that constructs a common model that is a physical model based on plant data from a plurality of plants; and an individual model construction unit that constructs an individual model for controlling a predetermined target plant on the basis of the common model. The present invention provides a plant model construction method comprising: a step for constructing a common model, which is a physical model based on plant data from a plurality of plants; and a step of constructing individual models for controlling a predetermined target plant from the common model.

Description

Technical Field

[0001] The present invention relates to a plant model building device, a plant model building method and a computer-readable storage medium. Background Art

[0002] Patent document 1 describes "an information processing method that collects sensor value data of manufacturing equipment from multiple companies, prepares multiple learning models with rich variations and excellent detection accuracy, and can appropriately select and utilize the learning model or the optimal learning model required by each company that is a user of the information processing device." Prior art literature Patent Literature Patent Document 1: Japanese Patent Application Laid-Open No. 2022-128069 Patent Document 2: International Publication No. 2019 / 159883 Patent Document 3: Japanese Patent Application Laid-Open No. 2011-118574 Summary of the Invention

[0003] In a first aspect of the present invention, a plant model construction device is provided, comprising: a common model construction unit that constructs a common model, which is a physical model based on plant data from multiple plants; and an individual model construction unit that constructs individual models for controlling predetermined target plants based on the common model.

[0004] The plant model construction device may include a model updating unit configured to update the common model based on the plant data from the plurality of plants and to update the individual model based on the plant data from the target plant.

[0005] In any of the plant model construction devices, the model updating unit may update the common model when a predetermined first update condition is satisfied, and update the individual model based on the update of the common model.

[0006] In any of the plant model construction devices, the model updating unit may update the individual model instead of the common model when a predetermined second update condition is satisfied.

[0007] Any of the plant model construction devices may include an input unit that receives an instruction from an operator of the target plant. The model updating unit may update the individual model based on the instruction input from the operator.

[0008] Alternatively, any of the plant model construction devices may include an evaluation result receiving unit configured to receive, from the plurality of plants, evaluation results of the accuracy of the individual models of the plurality of plants. Alternatively, the model updating unit may update the common model or the individual models based on the evaluation results.

[0009] In any of the plant model construction devices, the individual model may include a hybrid model of a physical model and a machine learning model.

[0010] In any of the plant model construction devices, the individual model construction unit may execute machine learning using the plant data of the target plant to construct the individual model by changing internal parameters of the common model.

[0011] In any of the plant model construction devices, the individual model may include a machine learning model.

[0012] In any of the plant model construction devices, the individual model construction unit may construct the individual model that outputs an operation value for controlling the target plant based on the output of the common model input by performing machine learning using the plant data of the target plant and the output of the common model.

[0013] In any of the plant model construction devices, the individual model construction unit may construct an individual model that outputs a correction value for correcting the operating value output by the common model for controlling the target plant based on the plant data input to the target plant by performing machine learning using the plant data of the target plant and the output of the common model.

[0014] In any of the plant model construction devices, the individual model construction unit may construct a plurality of individual models for controlling the target plant.

[0015] In any of the plant model construction devices, the common model may include a plurality of common models corresponding to the plurality of individual models.

[0016] In any of the plant model construction devices, the common model construction unit may construct the common model based on the plant data and material information from the plurality of plants.

[0017] In any of the plant model construction devices, the individual model construction unit may construct the individual model based on the common model and the material information.

[0018] In any of the factory model building devices, the raw material information may also include at least one of information on the composition of the raw material, information related to the strength, purity, color or grade of the raw material, information on the raw material supplier, information on the original product of the raw material, information related to the usage status of the original product of the raw material, or information related to the storage of the raw material.

[0019] In any of the plant model construction devices, the common model may be a model that outputs an operating value for controlling the target plant based on the plant data input to the target plant. The common model may also calculate and output an intermediate variable that associates the plant data of the target plant with the operating value.

[0020] In any of the plant model construction devices, the individual model may be a model that outputs an operating value for controlling the target plant based on the plant data input to the target plant. Alternatively, the individual model may calculate and output an intermediate variable that associates the plant data of the target plant with the operating value.

[0021] In a second aspect of the present invention, a plant model construction method is provided, comprising: constructing a common model, which is a physical model based on plant data from a plurality of plants; and constructing individual models for controlling predetermined target plants based on the common model.

[0022] In a third embodiment of the present invention, a computer-readable storage medium is provided, which records a program, and the program is executed by a computer. The program causes the computer to act as a common model construction unit and an individual model construction unit, the common model construction unit constructs a common model, which is a physical model based on factory data from multiple factories, and the individual model construction unit constructs an individual model for controlling a predetermined object factory based on the common model.

[0023] The above summary of the invention does not list all the features of the present invention, and subcombinations of these feature groups may also constitute inventions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 An example of the configuration of the plant model construction device 100 is shown together with the plant 200 . Figure 2A An example of a method of constructing the individual model 122 is shown. Figure 2B An example of a method of constructing the individual model 122 is shown. Figure 2C An example of a method of constructing the individual model 122 is shown. Figure 3A This represents an example of an intermediate variable. Figure 3B This represents an example of an intermediate variable. Figure 4 This section shows an example of how to build a plant model. Figure 5 This section shows an example of a flow of a method for building a plant model. Figure 6 This section shows an example of how to use the factory model. Figure 7A This section shows an example of a flow for how to use a factory model. Figure 7B This section shows an example of a flow for how to use a factory model. Figure 8 A modified example of the plant model building device 100 is shown together with a plant 200 . Figure 9 This section shows an example of how to update a plant model. Figure 10 A modified example of the plant model construction device 100 is shown together with a plant 200 , a material information provider 300 , and a material provider 400 . Figure 11 An example of a computer 1000 capable of embodying the various aspects of the present invention in whole or in part is shown. DETAILED DESCRIPTION

[0025] The present invention will be described below by way of embodiments of the invention, but the following embodiments do not limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution provided by the invention.

[0026] Figure 1 An example of the configuration of a plant model construction device 100 is shown together with a plant 200. The blocks shown in the figure are functionally separate functional blocks and do not necessarily correspond to the actual device configuration. That is, a block shown as a single block in this figure does not necessarily consist of a single device. Furthermore, blocks shown as separate blocks in this figure do not necessarily consist of separate devices.

[0027] In this example, N factories are shown: factory 200-1, factory 200-2, ..., and factory 200-N. These N factories 200 may be of the same type. In the following description, when there is no need to distinguish each factory 200, they are simply referred to as factory 200. When it is necessary to distinguish each factory 200, they may be referred to as factory 200-1, etc. In other words, features described simply as factory 200 may be common to multiple factories 200-1, 200-2, ..., and 200-N, while features described as factory 200-1, etc. may be specific to a specific factory 200.

[0028] Factory 200 may be a recycling plant for recycling or regenerating waste, an industrial plant such as a chemical or biological plant, a plant that manages and controls the wellheads of gas or oil fields or their surrounding areas, a plant that manages and controls hydropower, thermal power, and / or nuclear power generation, a plant that manages and controls environmentally friendly power generation such as solar power or wind power, or a plant that manages and controls water supply and drainage systems or reservoirs. Factory 200 may include an acquisition unit 210, a control unit 220, and a model storage unit 230.

[0029] The acquisition unit 210 can acquire plant data of the plant 200. The plant data may include data indicating various internal and external states (physical quantities) of the plant 200, data indicating operation values ​​used to control the plant 200, operational data indicating the operational status of the plant 200 as a result of controlling the plant 200, consumption data indicating energy or raw material consumption by the plant 200, and interference environment data indicating physical quantities that may interfere with the control of the plant 200. However, the types of data included in the plant data are not limited to these.

[0030] For example, acquisition unit 210 may include one or more sensors capable of measuring various internal and external conditions of factory 200, and may acquire data representing various internal and external conditions of factory 200 through the one or more sensors. Acquisition unit 210 may acquire data representing operational values ​​used to control factory 200 from control unit 220. Thus, acquisition unit 210 may include a component for acquiring factory data based on the type of data included in the factory data, or may acquire factory data from another component that has factory data.

[0031] The physical quantities included in the factory data may include, for example, temperature, pressure, flow rate, level, speed, weight, molecular weight, and pH of objects in the process of the factory 200. However, the physical quantities included in the factory data are not limited to these.

[0032] The acquisition unit 210 may provide the acquired plant data to the plant model construction apparatus 100. The acquisition unit 210 may provide the acquired plant data to the control unit 220.

[0033] The control unit 220 controls the factory 200. The control unit 220 can control the factory 200 based on the factory data acquired by the acquisition unit 210 and the common model 112 and / or individual models 122 constructed by the plant model construction device 100. The common model 112 and individual models 122 will be described in detail later. The control unit 220 can control the factory 200 based on the output results of the common model 112 and / or individual models 122.

[0034] The control unit 220 can control the factory 200 using the individual model 122 corresponding to the factory 200 in which the control unit 220 is installed. For example, the control unit 220 installed in the factory 200-1 controls the factory 200-1 using the individual model 122-1 corresponding to the factory 200-1, the control unit 220 installed in the factory 200-2 controls the factory 200-2 using the individual model 122-2 corresponding to the factory 200-2, and the control unit 220 installed in the factory 200-N controls the factory 200-N using the individual model 122-N corresponding to the factory 200-N. The control unit 220 installed in each of the factories 200-1, 200-2, ..., 200-N can control each of the factories 200-1, 200-2, ..., 200-N using the same common model 112.

[0035] The control unit 220 can control the factory 200 by controlling the control object. The control object can be a device installed in the factory 200 that becomes the object of control. For example, the control object is an operating terminal that controls physical quantities in the process of the factory 200, including actuators such as valves, heaters, motors, fans, and switches. The control unit 220 can perform a given operation corresponding to the operation value. The control object can also be a controller that controls the operating terminal. That is, the term "control" used in this specification can be broadly interpreted to include not only direct control of the operating terminal, but also indirect control of the operating terminal through a controller.

[0036] The model storage unit 230 can store the common model 112 and / or the individual models 122. When only the common model 112 is used for controlling the plant 200, the model storage unit 230 may store only the common model 112 or both the common model 112 and the individual models 122. When only the individual model 122 is used for controlling the plant 200, the model storage unit 230 may store only the individual model 122 or both the common model 112 and the individual models 122. When both the common model 112 and the individual models 122 are used for controlling the plant 200, the model storage unit 230 may store both the common model 112 and the individual models 122.

[0037] The model storage unit 230 may store a plurality of common models 112 and / or a plurality of individual models 122. The control unit 220 may select a common model 112 and / or an individual model 122 corresponding to the operating state of the plant 200 from the plurality of common models 112 and / or the plurality of individual models 122 stored in the model storage unit 230, and control the plant 200 using the selected common model 112 and / or individual model 122. The control unit 220 may input plant data into the common model 112 and / or the individual model 122.

[0038] The plant model construction device 100 generates a plant model based on plant data from multiple plants 200. The plant model construction device 100 can be a computer such as a PC (personal computer), a tablet computer, a smartphone, a workstation, a server computer, or a general-purpose computer, or a computer system obtained by connecting multiple computers. Such a computer system is also a computer in a broad sense. In addition, the plant model construction device 100 can be installed in a computer through one or more executable virtual computer environments. Instead of this method, the plant model construction device 100 can be a dedicated computer designed for building a plant model, or it can be dedicated hardware implemented by a dedicated circuit. In addition, if it can be connected to the Internet, the plant model construction device 100 can be implemented through cloud computing.

[0039] The plant model construction apparatus 100 includes a common model construction unit 110 and an individual model construction unit 120 . The plant model construction apparatus 100 may include a storage unit 130 .

[0040] The common model construction unit 110 constructs a common model 112, a physical model based on plant data from multiple plants 200. Common model 112 can be a model that outputs operational values ​​for controlling the target plant based on the plant data input to the target plant. The target plant is the plant 200 that is the target of control among the multiple plants 200. For example, if plant 200-1 is being controlled, the target plant is plant 200-1. In this case, common model 112 can output operational values ​​for controlling plant 200-1 based on the plant data input to plant 200-1. However, the target plant is not limited to this.

[0041] For example, the common model 112 estimates or predicts the state of the target plant based on the plant data of the target plant. The common model 112 can output information necessary for supporting the operation of the target plant.

[0042] The common model construction unit 110 in this example constructs a common model 112 based on plant data from multiple plants 200. This allows common model 112 to be constructed based on a rich amount of data, resulting in a more accurate common model 112 than when a physical model is constructed based on plant data from a single plant 200. Even when common model 112 is used in any of plants 200-1, 200-2, ..., and 200-N, appropriate operational support for the plants 200 can be achieved.

[0043] The common model 112 can calculate and output intermediate variables that associate the plant data of the target plant with the operation value. Intermediate variables can be variables that represent the process of deriving the operation value from the plant data. The details of intermediate variables will be described later.

[0044] In the plant model construction device 100 of this example, since the common model construction unit 110 constructs a common model 112 as a physical model, the interpretability of the operation support for the plant 200 can be improved. For example, when using a machine learning model that outputs an operation value based on input plant data, the process leading up to the operation value being derived from the plant data is black-boxed, making it difficult for operators to interpret the reason for the output of that operation value. In contrast, since the plant model construction device 100 of this example constructs a common model 112 as a physical model, operators can interpret the reason for the output of that operation value by appropriately referencing the intermediate variables calculated by the common model 112. For example, when the operation value output from the common model 112 defies the operator's intuitive understanding based on their experience, explaining the reason for the output of that operation value may be important.

[0045] In this example, common model 112 is described as a physical model, but common model 112 may also be a hybrid model of a physical model and a machine learning model. Even in this case, the operator can interpret the reason for outputting the operation value by appropriately referring to the intermediate variables calculated by common model 112.

[0046] Based on the common model 112, the individual model construction unit 120 constructs an individual model 122 for controlling a predetermined target plant. Similar to the common model 112, the individual model 122 can output an operational value for controlling the target plant, or it can be a model for correcting the operational value output by the common model 112. Details of the individual model 122 will be described later.

[0047] The individual model construction unit 120 can construct a plurality of individual models 122 corresponding to each of the plurality of plants 200. In this example, the individual model construction unit 120 constructs a plurality of individual models 122-1, 122-2, ..., 122-N corresponding to the plurality of plants 200-1, 200-2, ..., 200-N. The individual model construction unit 120 can construct an individual model 122 corresponding to a target plant based on the common model 112 and plant data from the target plant. For example, the individual model construction unit 120 constructs an individual model 122-1 corresponding to plant 200-1 based on the common model 112 and plant data from plant 200-1; constructs an individual model 122-2 corresponding to plant 200-2 based on the common model 112 and plant data from plant 200-2; and constructs an individual model 122-N corresponding to plant 200-N based on the common model 112 and plant data from plant 200-N.

[0048] The plant data from the target plant used to construct the individual model 122 may be included in the plant data from the multiple plants 200 used to construct the common model 112, or may not be included in the plant data from the multiple plants 200 used to construct the common model 112. For example, if the target plant is plant 200-1, the common model construction unit 110 may construct the common model 112 based on the plant data from the multiple plants 200-1, 200-2, ..., 200-N, or may construct the common model 112 based on the plant data from the multiple plants 200-2, ..., 200-N.

[0049] The individual model construction unit 120 of this example constructs an individual model 122 for controlling the target plant based on the common model 112. Thus, the plant model construction device 100 of this example can implement appropriate operation support according to the target plant.

[0050] As described above, the plant model construction device 100 of this example includes a common model construction unit 110 and an individual model construction unit 120. This allows for appropriate operational support of the plant 200 based on the highly accurate common model 112 and improved interpretability of the operational support for the plant 200, while also enabling appropriate operational support tailored to the target plant based on the individual model 122.

[0051] While this example describes operational support using individual models 122, operational support can also be implemented using only the common model 112. For example, at the start of operation of a target plant, individual models 122 may not be constructed because there is no or little plant data from the target plant. Even in this case, the common model construction unit 110 constructs the common model 112 based on plant data from multiple plants 200, enabling highly accurate operational support for the target plant.

[0052] The plant model construction apparatus 100 can provide the common model 112 and / or the individual model 122 to the plant 200. The model storage unit 230 of the plant 200 can store the common model 112 and / or the individual model 122 provided by the plant model construction apparatus 100. In other words, the common model 112 and the individual model 122 can be constructed by the plant model construction apparatus 100 during the construction phase, or stored in each plant 200 during the operation phase.

[0053] Furthermore, while this example describes a case where the common model 112 and / or individual model 122 are stored in each plant 200 during the operational phase, the common model 112 and / or individual model 122 may also be stored in the plant model construction device 100 during the operational phase. In this case, the target plant (e.g., plant 200-1) can provide the acquired plant data to the plant model construction device 100, which then executes model calculation using the corresponding individual model 122 (e.g., individual model 122-1), and provides the target plant (e.g., plant 200-1) with information necessary for operational support as the output of the model.

[0054] The storage unit 130 may store factory data from a plurality of factories 200. The storage unit 130 may store the factory data from the plurality of factories 200 in association with each factory 200. For example, the storage unit 130 may store the factory data from the factory 200-1 together with an identifier indicating that the factory data is from the factory 200-1, store the factory data from the factory 200-2 together with an identifier indicating that the factory data is from the factory 200-2, and store the factory data from the factory 200-N together with an identifier indicating that the factory data is from the factory 200-N.

[0055] The common model construction unit 110 can construct the common model 112 based on the plant data stored in the storage unit 130. The individual model construction unit 120 can construct the individual model 122 based on the plant data stored in the storage unit 130. For example, when the individual model construction unit 120 constructs the individual model 122-1 corresponding to the plant 200-1, the individual model construction unit 120 constructs the individual model 122-1 based on the common model 112 and the plant data stored in association with the plant 200-1.

[0056] Figure 2A This shows an example of a method for constructing the individual model 122. The individual model 122 may include a hybrid model of a physical model and a machine learning model. For example, the individual model 122 may include a hybrid model that combines the common model 112, which is a physical model, with a machine learning model.

[0057] The individual model construction unit 120 can construct an individual model 122 by performing machine learning using the target plant's plant data, thereby modifying the internal parameters of the common model 112. For example, if the target plant is plant 200-1, the individual model construction unit 120 can perform machine learning using the plant data of plant 200-1 to construct an individual model 122-1 by modifying the internal parameters of the common model 112. This allows the construction of an individual model 122-1 suitable for plant 200-1. The individual model 122 can be a model that outputs operational values ​​for controlling the target plant based on the input plant data.

[0058] The individual model construction unit 120 of this example uses the plant data of the target plant to construct the individual model 122. This allows the individual model 122 to more accurately represent the characteristics of the target plant, and the plant model construction apparatus 100 of this example can provide appropriate operational support tailored to the target plant.

[0059] The individual model 122 calculates and outputs intermediate variables that associate the plant data of the target plant with the operation value. In the plant model construction device 100 of this example, because the individual model construction unit 120 constructs the individual model 122 as a hybrid model of a physical model and a machine learning model, the interpretability of the operation support for the plant 200 can be improved. Specifically, because the plant model construction device 100 of this example constructs the individual model 122 as a hybrid model of a physical model and a machine learning model, operators can interpret the reason for the output of the operation value by appropriately referring to the intermediate variables calculated by the individual model 122.

[0060] Furthermore, the individual model construction unit 120 of this example constructs an individual model 122 by modifying the internal parameters of the common model 112. This allows for a deeper understanding of the characteristics of the plant 200 by comparing the parameters of the common model 112 and the individual model 122, thereby improving the interpretability of the operational support for the plant 200. This allows operators to gain a deeper understanding of the processes within the plant 200.

[0061] Figure 2B An example of a method for constructing the individual model 122 is shown. The individual model 122 may include a machine learning model or a statistical model. As an example, the individual model includes a machine learning model.

[0062] The individual model construction unit 120 can execute machine learning using the target plant's plant data and the output of the common model 112 to construct an individual model 122 that outputs operational values ​​for controlling the target plant based on the output of the common model 112. Specifically, the individual model 122 can be a model that receives operational values ​​as outputs of the common model 112 and outputs operational values ​​more appropriate for the target plant. For example, if the target plant is plant 200-1, the individual model construction unit 120 can execute machine learning using the plant data of plant 200-1 and the output of the common model 112 to construct an individual model 122-1 that outputs operational values ​​for controlling plant 200-1 based on the output of the common model 112. This allows the construction of an individual model 122-1 that is appropriate for plant 200-1.

[0063] The individual model construction unit 120 of this example uses the plant data of the target plant to construct the individual model 122. This allows the individual model 122 to more accurately represent the characteristics of the target plant, and the plant model construction apparatus 100 of this example can provide appropriate operational support tailored to the target plant.

[0064] Furthermore, the individual model construction unit 120 of this example constructs an individual model 122 that outputs an operational value for controlling the target plant based on the output of the common model 112. Thus, by analyzing the individual model 122, it is possible to understand the characteristics of errors in the common model 112, thereby improving the interpretability of the operational support provided for the plant 200.

[0065] Figure 2C An example of a method for constructing the individual model 122 is shown. The individual model 122 may include a machine learning model or a statistical model. As an example, the individual model includes a machine learning model.

[0066] The individual model construction unit 120 can execute machine learning using the target plant's plant data and the output of the common model 112 to construct an individual model 122 that outputs a correction value for correcting the operational value output by the common model 112 for controlling the target plant, based on the input plant data. Specifically, the individual model 122 can receive the target plant's plant data as input and, given the same input plant data, output a correction value for correcting the operational value output by the common model 112 to an operational value more appropriate for the target plant. For example, if the target plant is plant 200-1, the individual model construction unit 120 can execute machine learning using the plant data of plant 200-1 and the output of the common model 112 to construct an individual model 122-1 that outputs a correction value for correcting the operational value output by the common model 112 for controlling plant 200-1, based on the input plant data of plant 200-1. This allows the construction of an individual model 122-1 that is appropriate for plant 200-1.

[0067] The individual model construction unit 120 of this example uses the plant data of the target plant to construct the individual model 122. This allows the individual model 122 to more accurately represent the characteristics of the target plant, and the plant model construction apparatus 100 of this example can provide appropriate operational support tailored to the target plant.

[0068] Furthermore, the individual model construction unit 120 of this example constructs an individual model 122 based on the input plant data of the target plant. This model outputs a correction value for correcting the operational value output by the common model 112 for controlling the target plant. Thus, by analyzing the individual model 122, it is possible to understand the characteristics of errors in the common model 112, thereby improving the interpretability of the operational support provided for the plant 200.

[0069] use Figures 2A to 2C The individual model 122 construction method is described as an example, but the individual model 122 construction method is not limited to this. The individual model construction unit 120 can also be combined with Figures 2A to 2C The individual model 122 is constructed using at least two methods of the method for constructing the individual model 122 described above.

[0070] Figure 3A This represents an example of an intermediate variable. Factory 200 in this example is a waste plastic recycling plant. Factory 200 heats the waste plastic in a decomposition layer to produce dissolved plastic. The vaporized oil generated by the dissolution of the waste plastic can be recovered as liquid oil in a recovery tank.

[0071] For example, the plant data input into shared model 112 includes data related to the material of waste plastics, data indicating heating-related operating conditions, and other data. Based on this input plant data, shared model 112 can output operational values ​​for improving waste plastic decomposition efficiency. In deriving operational values ​​from the input plant data, shared model 112 calculates various intermediate variables. For example, shared model 112 calculates the molecular weight distribution of oil (vapor) and the molecular weight distribution of dissolved plastics as intermediate variables.

[0072] In this way, common model 112, acting as a physical model, calculates intermediate variables representing the process leading to the derivation of operational values ​​from plant data. This allows operators to interpret the reason for outputting operational values ​​by appropriately referencing the intermediate variables calculated by common model 112. Consequently, the plant model construction apparatus 100 of this example can improve the interpretability of operational support for plant 200.

[0073] Furthermore, when individual model 122 includes a hybrid model of a physical model and a machine learning model, individual model 122 can also calculate the same intermediate variables as common model 112. Thus, by appropriately referring to the intermediate variables calculated by individual model 122, operators can interpret the reason for outputting the corresponding operation value. Therefore, the plant model construction apparatus 100 of this example can improve the interpretability of the operation support for the plant 200.

[0074] Figure 3B An example of an intermediate variable is shown. The common model 112 in this example calculates a predicted value of the intermediate variable based on or instead of the current value of the intermediate variable. For example, the intermediate variable is the molecular weight distribution.

[0075] exist Figure 3B In FIG, the molecular weight distribution represented by the solid line is the current value of the intermediate variable. The molecular weight distribution represented by the dotted line is the predicted value of the intermediate variable when the current operating value is continued for a predetermined time. The molecular weight distribution represented by the single-dot chain line is the predicted value of the intermediate variable when the operating value output by the common model 112 is continued for a predetermined time.

[0076] Common model 112 can calculate the current value of the intermediate variable based on the plant data input to the target plant. Common model 112 can also calculate the predicted value of the intermediate variable if the current operating value is used for a predetermined period of time. Common model 112 can also calculate the predicted value of the intermediate variable if the operating value output by common model 112 is used for a predetermined period of time.

[0077] In this example, the common model 112 calculates predicted values ​​for intermediate variables. This allows operators to verify the validity of the operational values ​​output by the common model 112 based on the calculated predicted values. Consequently, the plant model construction device 100 in this example can improve the interpretability of operational support for the plant 200. This also applies to cases where the individual model 122 includes a hybrid model that combines a physical model with a machine learning model.

[0078] Figure 4 This section shows an example of a method for constructing a plant model. In step S110, a common model 112 is constructed as a physical model based on plant data from multiple plants 200. For example, the common model construction unit 110 constructs the common model 112. In step S120, based on the common model 112, individual models 122 for controlling predetermined target plants are constructed. For example, the individual model construction unit 120 constructs the individual models 122. The details of the construction of each model are as described above.

[0079] Figure 5 An example of a flow of a method for constructing a plant model is shown below: In step S110 , the common model 112 is constructed in the plant model construction apparatus 100 .

[0080] In step S112, the operator of the target plant specifies the plant data of the target plant for constructing the individual model 122. In step S114, the operator of the target plant specifies the construction method of the individual model 122. For example, the operator can select Figures 2A to 2C Any one of the above-described methods for constructing the individual model 122 may be used, or any combination thereof may be selected.

[0081] Furthermore, the order of steps S112 and S114 is not limited. The operator can specify the plant data for the target plant before or after specifying the method for building the individual model 122. Furthermore, the order of steps S110, S112, and S114 is also not limited. The operator can specify the plant data and the method for building the individual model 122 before or after the common model 112 is built in the plant model building device 100.

[0082] In step S120, the individual model 122 is constructed in the plant model construction device 100. The individual model construction unit 120 can construct the individual model 122 using the plant data specified by the operator and the method specified by the operator.

[0083] In step S130, the plant model construction apparatus 100 sends the model to the plant 200. The plant model construction apparatus 100 selects the model to be sent according to the construction method of the individual model 122. For example, Figure 2A When the individual model 122 is constructed by the method described above, the plant model construction apparatus 100 may send only the individual model 122 to the plant 200. As another example, in the case of Figure 2B or Figure 2C When the individual model 122 is constructed by the method described above, the plant model construction apparatus 100 can send the common model 112 and the individual model 122 to the plant 200. Figure 2A When the individual model 122 is constructed using the method described above, the plant model construction apparatus 100 may transmit the common model 112 and the individual model 122 to the plant 200 .

[0084] In step S132, the plant 200 receives the plant model. The model storage unit 230 may store the received plant model.

[0085] Figure 6 An example of a method for operating a plant model is shown. In step S210 , plant data is acquired. For example, the acquisition unit 210 acquires plant data of the plant 200 .

[0086] In step S220, an operation value for controlling the plant 200 is output. Figure 2A When the individual model 122 is constructed by the method described above, the individual model 122 outputs an operation value for controlling the plant 200 based on the plant data acquired by the input acquisition unit 210. Figure 2B When the individual model 122 is constructed by the method described above, the common model 112 outputs the operation value based on the plant data acquired by the input acquisition unit 210, and the individual model 122 outputs the operation value for controlling the target plant based on the output of the common model 112. Figure 2C When the individual model 122 is constructed using the described method, the common model 112 outputs an operation value based on the plant data obtained by the input acquisition unit 210, and the individual model 122 outputs a correction value for correcting the operation value output by the common model 112 based on the plant data obtained by the input acquisition unit 210.

[0087] In step S230 , the plant 200 is controlled. For example, the control unit 220 controls the plant 200 using the output results of the common model 112 and / or the individual model 122 .

[0088] Figure 7AAn example of a flow of a method for operating a plant model is shown. In step S210 , plant data is acquired in the plant 200 . For example, the acquisition unit 210 acquires the plant data of the plant 200 . The acquisition unit 210 may transmit the acquired plant data to the plant model construction device 100 .

[0089] In step S212, the plant data is stored. For example, the storage unit 130 stores the plant data of the plant 200. The plant data stored in the storage unit 130 can be used to construct and / or update the common model 112 and / or the individual models 122. The updating of each model will be described later.

[0090] In step S220, an operation value for controlling the plant 200 is output. In step S222, the operator confirms the output operation value. The operator can confirm the output operation value together with the intermediate variables calculated by the common model 112 and / or the individual model 122.

[0091] In step S224, the operator inputs an operation value. The operator can input the operation value output by the model or another operation value. For example, the operator confirms the intermediate variable of the process that outputs the operation value. If the output operation value is determined to be appropriate, the operator inputs the operation value output by the model. If the output operation value is determined to be inappropriate, the operator inputs another operation value.

[0092] In step S230, the plant 200 is controlled. For example, the control unit 220 controls the plant 200 using the operation value input by the operator.

[0093] Figure 7B This example shows an example of a process for operating a plant model. In this example, there is no step for the operator to confirm the operation value. Figure 7A The process is different. Other Figure 7A The process is the same.

[0094] For example, in step S224, the operation value output by the model in step S220 is directly input for control in step S230. As an example, if the reliability of the operation value output by the plant model is high enough, it can be used Figure 7B As another example, before inputting the operation value in step S224, a process of determining the validity of the operation value output in step S222 may be implemented separately. Figure 7A In the process, the operator determines the validity of the operation value by interpreting the output operation value, but the process of determining the validity of the operation value may be automatically executed in the factory 200.

[0095] Figure 8A modified example of the plant model construction device 100 is shown together with the plant 200. The plant model construction device 100 of this example is different from the plant model construction device 100 in that it includes a model updating unit 140, an input unit 150, an evaluation result receiving unit 160, and a notification unit 170. Figure 1 In this example, Figure 1 The differences between the embodiments are particularly described, and the other Figure 1 The same as the embodiment.

[0096] The model updating unit 140 can update the common model 112 based on plant data from multiple plants 200, and can update the individual model 122 based on plant data from a target plant. The model updating unit 140 can update the common model 112 based on plant data from multiple plants 200 acquired after the common model building unit 110 has built the common model 112. The model updating unit 140 can update the individual model 122 based on plant data from a target plant acquired after the individual model building unit 120 has built the individual model 122.

[0097] The model updating unit 140 can update the common model 112 when a predetermined first update condition is satisfied. The first update condition can include at least one of a condition related to the amount of plant data from multiple plants 200 accumulated in the storage unit 130 after the common model building unit 110 built the common model 112, a condition related to the amount of plant data from multiple plants 200 accumulated in the storage unit 130 after the model updating unit 140 updated the common model 112, a condition related to the period of time that has elapsed since the common model building unit 110 built the common model 112, a condition related to the period of time that has elapsed since the model updating unit 140 updated the common model 112, a condition related to the presence or absence of an instruction from an operator, and a condition related to the evaluation results of the individual models 122. However, the types of first update conditions are not limited to these.

[0098] For example, the first update condition includes a condition related to the amount of plant data from the plurality of plants 200 accumulated in the storage unit 130 after the common model construction unit 110 constructs the common model 112. The model updating unit 140 may update the common model 112 if the amount of plant data from the plurality of plants 200 accumulated in the storage unit 130 after the common model construction unit 110 constructs the common model 112 exceeds a predetermined reference amount.

[0099] For example, the first update condition includes a condition related to the amount of plant data from the plurality of plants 200 accumulated in the storage unit 130 after the model updating unit 140 updates the common model 112. The model updating unit 140 may update the common model 112 if the amount of plant data from the plurality of plants 200 accumulated in the storage unit 130 exceeds a predetermined reference amount after the model updating unit 140 updates the common model 112.

[0100] Thus, when sufficient data to update the common model 112 is accumulated after the common model 112 is constructed or updated, the model updating unit 140 can update the common model 112. The reference amount after the common model 112 is constructed and the reference amount after the common model 112 is updated may be the same or different.

[0101] For example, the first update condition includes a condition related to the period that has passed since the common model construction unit 110 constructed the common model 112. The model update unit 140 may update the common model 112 if the period that has passed since the common model construction unit 110 constructed the common model 112 exceeds a predetermined reference period.

[0102] For example, the first update condition includes a condition regarding the period that has passed since the model updater 140 updated the common model 112. The model updater 140 may update the common model 112 if the period that has passed since the model updater 140 updated the common model 112 exceeds a predetermined reference period.

[0103] In this manner, if a sufficient period has elapsed since the common model 112 was constructed or updated, the model updating unit 140 can update the common model 112. Specifically, if a sufficient period has elapsed since the common model 112 was constructed or updated, it can be estimated that a sufficient amount of data has been accumulated to update the common model 112. The base period after the common model 112 was constructed and the base period after the common model 112 was updated may be the same or different.

[0104] For example, the first update condition includes a condition regarding the presence or absence of an instruction from an operator. The model updating unit 140 may update the common model 112 when there is an instruction from the operator to update the content of the common model 112 .

[0105] For example, the first update condition includes a condition related to the evaluation result of the individual model 122. The details of the update based on the evaluation result of the individual model 122 will be described later.

[0106] The model updating unit 140 can update the individual model 122 based on the update of the common model 112. The individual model 122 is constructed based on the common model 112. When the common model 112 is updated, the individual model 122 can be updated based on the updated common model 112.

[0107] If a predetermined second update condition is satisfied, the model updating unit 140 may update the individual model 122 instead of the common model 112. In other words, the second update condition may be a condition for updating only the individual model 122. The second update condition may include at least one of a condition related to the amount of plant data from the target plant accumulated in the storage unit 130 after the individual model building unit 120 built the individual model 122, a condition related to the amount of plant data from the target plant accumulated in the storage unit 130 after the model updating unit 140 updated the individual model 122, a condition related to the period of time that has elapsed since the individual model building unit 120 built the individual model 122, a condition related to the period of time that has elapsed since the model updating unit 140 updated the individual model 122, a condition related to the presence or absence of an operator's instruction, and a condition related to the evaluation results of the individual model 122. However, the types of second update conditions are not limited to these.

[0108] For example, the second update condition includes a condition related to the amount of plant data from the target plant accumulated in the storage unit 130 after the individual model construction unit 120 constructs the individual model 122. The model updating unit 140 may update the individual model 122 if the amount of plant data from the target plant accumulated in the storage unit 130 after the individual model construction unit 120 constructs the individual model 122 exceeds a predetermined reference amount.

[0109] For example, the second update condition includes a condition related to the amount of plant data from the target plant accumulated in the storage unit 130 after the model updating unit 140 updates the individual model 122. The model updating unit 140 may update the individual model 122 if the amount of plant data from the target plant accumulated in the storage unit 130 exceeds a predetermined reference amount after the model updating unit 140 updates the individual model 122.

[0110] Thus, when sufficient data to update the individual model 122 is accumulated after the individual model 122 is constructed or updated, the model updating unit 140 can update the individual model 122. The reference amount after the individual model 122 is constructed and the reference amount after the individual model 122 is updated may be the same or different.

[0111] The reference amount used to update the common model 112 may be different from the reference amount used to update the individual models 122. The reference amount used to update the common model 112 may be greater than the reference amount used to update the individual models 122. For example, if the amount of plant data from the plurality of plants 200 is less than the reference amount used to update the common model 112, but the amount of plant data from the target plant is greater than the reference amount used to update the individual models 122, the common model 112 is not updated, and the individual models 122 corresponding to the target plant are updated.

[0112] For example, the second update condition includes a condition related to the period that has passed since the individual model construction unit 120 constructed the individual model 122. The model update unit 140 may update the individual model 122 if the period that has passed since the individual model construction unit 120 constructed the individual model 122 exceeds a predetermined reference period.

[0113] For example, the second update condition includes a condition regarding the period that has passed since the model updater 140 updated the individual model 122. The model updater 140 may update the individual model 122 if the period that has passed since the model updater 140 updated the individual model 122 exceeds a predetermined reference period.

[0114] In this way, if a sufficient period has elapsed since the individual model 122 was constructed or updated, the model updating unit 140 can update the individual model 122. In other words, if a sufficient period has elapsed since the individual model 122 was constructed or updated, it can be estimated that a sufficient amount of data has been accumulated to update the individual model 122. The reference period after the individual model 122 was constructed and the reference period after the individual model 122 was updated may be the same or different.

[0115] The base period for updating the common model 112 and the base period for updating the individual models 122 can be the same or different. The common model 112 is updated based on plant data from multiple plants 200, while the individual models 122 are updated based on plant data from target plants. Therefore, because the speed at which plant data from multiple plants 200 is accumulated to update the common model 112 differs from the speed at which plant data from target plants is accumulated to update the individual models 122, appropriate base periods can be set for the common model 112 and the individual models 122, respectively.

[0116] For example, the second update condition includes a condition regarding the presence or absence of an instruction from an operator. The model updating unit 140 may update the individual model 122 when there is an instruction from the operator to update the content of the individual model 122 .

[0117] For example, the second update condition includes a condition related to the evaluation result of the individual model 122. The update based on the evaluation result of the individual model 122 will be described in detail later.

[0118] The input unit 150 can input instructions from the operator of the target plant. For example, the input unit 150 can display a screen for inputting instructions from the operator on a display device of the target plant, and input the instructions from the operator.

[0119] The model updating unit 140 can update the common model 112 based on an instruction input from the operator. The model updating unit 140 can also update the individual model 122 based on an instruction input from the operator. That is, the first update condition and / or the second update condition may include a condition related to the presence or absence of an instruction from the operator.

[0120] The plant model construction device 100 of this example can improve the interpretability of the operation support of the plant 200. This allows the operator of the target plant to appropriately instruct the update of the model based on the interpretation result.

[0121] The evaluation result receiving unit 160 can receive, from the plurality of factories 200, evaluation results obtained by evaluating the accuracy of the individual models 122 of each of the plurality of factories 200. For example, the evaluation result receiving unit 160 receives the evaluation results obtained by evaluating the accuracy of the individual model 122-1 from the factory 200-1, receives the evaluation results obtained by evaluating the accuracy of the individual model 122-2 from the factory 200-2, and receives the evaluation results obtained by evaluating the accuracy of the individual model 122-N from the factory 200-N.

[0122] Plant 200 may include an evaluation unit 240 that evaluates the accuracy of individual model 122. Evaluation unit 240 may evaluate the accuracy of individual model 122 by comparing the output of individual model 122 with the actual operating conditions of the target plant. Evaluation unit 240 may transmit the evaluation results of the accuracy of individual model 122 to evaluation result receiving unit 160.

[0123] The model updating unit 140 may update the common model 112 or the individual model 122 based on the evaluation result. The first update condition and the second update condition may include a condition related to the evaluation result of the individual model 122.

[0124] For example, if the proportion of evaluation results indicating low accuracy for the individual models 122 of the multiple plants 200 exceeds a predetermined reference ratio, the model updating unit 140 may update the common model 112. Specifically, since the individual models 122 of the multiple plants 200 are constructed based on the common model 112, if the proportion of evaluation results indicating low accuracy for the individual models 122 is high, the common model 112 may have low accuracy. Therefore, if the proportion of evaluation results indicating low accuracy for the individual models 122 is high, the model updating unit 140 may update the common model 112.

[0125] For example, if the proportion of evaluation results obtained from evaluating the accuracy of the individual models 122 of each of the multiple plants 200 indicating that the accuracy of the individual models 122 is high exceeds a predetermined reference proportion, and the accuracy of the individual model 122 of the target plant is evaluated as low, the model updating unit 140 may update the individual model 122 of the target plant. In other words, if the proportion of evaluation results indicating that the accuracy of the individual model 122 is high is high, it is presumed that the accuracy of the common model 112 is also high. Therefore, if the accuracy of the individual model 122 of the target plant is evaluated as low, the model updating unit 140 may update the individual model 122 evaluated as low.

[0126] When the common model 112 or the individual model 122 is updated, the notification unit 170 may notify the operator of the update. For example, the notification unit 170 may notify the operator of the update. This can reduce confusion that may occur when the common model 112 or the individual model 122 is updated.

[0127] The plant model construction device 100 of this example includes a model updating unit 140 that updates the common model 112 and the individual models 122. This allows each model to be maintained in an updated state based on factors such as the amount of accumulated data, the period of data accumulation, operator instructions, and the accuracy of the individual models 122. Furthermore, since each model can be maintained in an updated state, the plant model construction device 100 of this example can provide appropriate operational support for the plant 200.

[0128] Figure 9 An example of a method for updating a plant model is shown below. In step S310, it is determined whether a predetermined first update condition is satisfied. The details of the first update condition are as described above.

[0129] If the predetermined first update condition is satisfied in step S310 (Yes), the common model 112 is updated in step S312. For example, the model updating unit 140 updates the common model 112. In step S314, the individual models 122 are updated. For example, the model updating unit 140 updates the individual models 122 based on the update of the common model 112. The model updating unit 140 may update the individual models 122 based on the updated common model 112.

[0130] If the predetermined first update condition is not satisfied in step S310 (No), it is determined whether the predetermined second update condition is satisfied in step S320. The details of the second update condition are as described above.

[0131] If the predetermined second update condition is satisfied in step S320 (Yes), the individual model 122 is updated in step S322. For example, the model updating unit 140 updates the individual model 122 instead of the common model 112. If the predetermined second update condition is not satisfied in step S320 (No), neither model is updated, and the process ends.

[0132] Figure 10 A modified example of the plant model construction device 100 is shown together with a plant 200. The plant model construction device 100 of this example is different from the plant model construction device 100 in that the individual model construction unit 120 constructs a plurality of individual models 122 for the control target plant. Figure 1 In this example, in particular Figure 1 The differences between the embodiments are described below, and other Figure 1 In addition, in this example, due to the limitation of space, only one factory 200-1 is shown, but the multiple factories 200 may include factories 200-2, ..., factories 200-N, and Figure 1 It's the same.

[0133] The raw material supplier 400 supplies raw materials to the factory 200. Different raw materials may be supplied from a plurality of raw material suppliers 400. The raw material supplier 400 provides raw material information to the raw material information supplier 300.

[0134] Raw material information may include at least one of information on the composition of the raw material, information regarding the strength, purity, color, or grade of the raw material, information about the raw material supplier 400, information about the original product of the raw material, information regarding the usage status of the original product of the raw material, and information regarding the storage of the raw material. However, the types of information included in the raw material information are not limited to these.

[0135] The material information provider 300 collects material information from the material provider 400. The material information provider 300 may provide the plant model construction apparatus 100 with the collected material information.

[0136] The individual model construction unit 120 can construct a plurality of individual models 122 for controlling the target plant. Figure 1 In the embodiment described above, the individual model construction unit 120 constructs multiple individual models 122. This is because the individual model construction unit 120 constructs an individual model 122 corresponding to each of the multiple plants 200. In this example, the individual model construction unit 120 constructs multiple individual models 122 corresponding to the target plant. In other words, the individual model construction unit 120 can construct multiple individual models 122 corresponding to each of the multiple plants 200.

[0137] For example, the individual model construction unit 120 constructs M individual models 122-1-1, ..., 122-1-M for the plant 200-1, and M individual models 122-N-1, ..., 122-NM for the plant 200-N. Furthermore, the number of individual models 122 corresponding to each of the multiple plants 200 can be the same or different. That is, while this example describes the individual model construction unit 120 constructing M individual models 122 for each of the plants 200-1 and 200-N, the individual model construction unit 120 can also construct a different number of individual models 122 for each plant 200.

[0138] The individual model construction unit 120 can construct multiple individual models 122 tailored to the operating conditions of the target plant. For example, the individual model construction unit 120 can construct a different individual model 122 for each raw material processed by the target plant, a different individual model 122 for each raw material supplier 400 of the raw materials processed by the target plant, a different individual model 122 for each season of operation of the target plant, or a different individual model 122 for each environment in which the target plant is installed. However, the types of individual models 122 constructed by the individual model construction unit 120 are not limited to these.

[0139] During the plant model application phase, for example, the operator of the target plant can select and apply an individual model 122 suitable for the operating conditions of the target plant from among multiple individual models 122. For example, if the season is summer, the operator of the target plant can select and apply an individual model 122 suitable for summer from among multiple individual models 122.

[0140] The common model 112 may include a plurality of common models 112 corresponding to a plurality of individual models 122. The common model 112 in this example includes, for example, M common models 112-1, ..., 112-M corresponding to M individual models 122-1-1, ..., 122-1-M.

[0141] The common model construction unit 110 can construct multiple common models 112 tailored to the operating conditions of the target plant. For example, the common model construction unit 110 can construct a different common model 112 for each raw material processed by the target plant, a different common model 112 for each raw material supplier 400 of the raw materials processed by the target plant, a different common model 112 for each season of operation of the target plant, or a different common model 112 for each environment in which the target plant is installed. However, the types of common models 112 constructed by the common model construction unit 110 are not limited to these.

[0142] The individual model construction unit 120 of this example constructs multiple individual models 122 for controlling the target plant. This allows operators of the target plant to select and use the appropriate individual model 122 that suits the operating conditions, and thus the plant model construction device 100 of this example can provide appropriate operational support for the plant 200.

[0143] The common model construction unit 110 can construct a common model 112 based on plant data and material information from a plurality of plants 200. The individual model construction unit 120 can construct an individual model 122 based on the common model 112 and the material information.

[0144] The plant model construction device 100 can access raw material information stored in the company's factory 200 or in an external platform. Specifically, the raw material information used by the common model construction unit 110 to construct the common model 112 can include raw material information stored in the company's factory 200, raw material information stored in an external platform, or both. The same applies to the raw material information used by the individual model construction unit 120 to construct the individual model 122.

[0145] In this example, the common model construction unit 110 constructs a common model 112 based on the raw material information, and the individual model construction unit 120 constructs individual models 122 based on the raw material information. This allows the plant model to output appropriate operational values ​​corresponding to the raw material information, enabling the plant model construction device 100 of this example to provide appropriate operational support for the plant 200. Furthermore, since the raw material information in this example is provided by the raw material information provider 300, the cost of providing appropriate operational support can be reduced compared to a case where raw material sensing is performed within the plant 200.

[0146] In this example, the raw material information includes various information, including information on the raw material's composition, the strength, purity, color, or grade of the raw material, information on the raw material supplier 400, information on the raw material's original product, information on the usage status of the original raw material product, and information on the storage of the raw material. This includes information that cannot be obtained through raw material sensing. This allows for more appropriate operational support compared to raw material sensing within factory 200.

[0147] In this example, the individual model construction unit 120 also constructs the individual model 122 based on the raw material information. However, the individual model construction unit 120 may construct the individual model 122 based solely on the common model 112. Specifically, since the common model construction unit 110 constructs the common model 112 based on the raw material information, it is assumed that even when the individual model construction unit 120 constructs the individual model 122 based solely on the common model 112, the individual model 122 will output an operation value or correction value that fully reflects the raw material information.

[0148] use Figure 1 、 Figure 8 as well as Figure 10 Each feature described in FIG can be implemented together with the features described in other figures. That is, the plant model construction device 100 of the present invention can have Figure 1 、 Figure 8 as well as Figure 10 All or any combination of the described features.

[0149] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where a module may represent (1) a stage of a process for performing an operation or (2) a portion of a device having the function of performing an operation. Specific stages and portions may be implemented by dedicated circuits, programmable circuits provided together with computer-readable instructions stored on a computer-readable medium, and / or processors provided together with computer-readable instructions stored on a computer-readable medium. Dedicated circuits may include digital and / or analog hardware circuits, and may also include integrated circuits (ICs) and / or discrete circuits. Programmable circuits may include reconfigurable hardware circuits that include logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and other memory elements.

[0150] A computer-readable medium may include any tangible device capable of storing instructions for execution by an appropriate device. Consequently, a computer-readable medium having instructions stored therein includes an article containing instructions that can be executed to produce a means for performing the operations specified by the flowchart or block diagram. Examples of computer-readable media include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable media include floppy disks, magnetic disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disks (DVD), Blu-ray discs (RTM), memory sticks, integrated circuit cards, and the like.

[0151] Computer-readable instructions include any of source code and object code described by any combination of one or more programming languages ​​including assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or object-oriented programming languages ​​such as Smalltalk (registered trademark), JAVA (registered trademark), C++, and existing procedural programming languages ​​such as the "C" programming language or similar programming languages.

[0152] Computer-readable instructions can be provided to a processor or programmable circuit of a programmable data processing device such as a computer via a local or local area network (LAN), a wide area network (WAN) such as the Internet, and the computer-readable instructions are executed in order to make a means for performing the operations specified by the flowchart or block diagram. Here, the computer can be a PC (personal computer), a tablet computer, a smart phone, a workstation, a server computer, a general-purpose computer or a special-purpose computer, etc., or a computer system obtained by connecting multiple computers. Such a computer system obtained by connecting multiple computers is also called a distributed computing system, which is a computer in a broad sense. In a distributed computing system, each of the multiple computers executes a part of the program, and the data in the program execution is handed over between the computers as needed, so that the multiple computers collectively execute the program.

[0153] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like. A computer may have one processor or multiple processors. In a multi-processor system having multiple processors, each processor executes a portion of a program, and data in program execution is handed over between processors as needed, so that multiple processors collectively execute the program. For example, in the execution of multiple tasks, each of the multiple processors can perform task switching for each time slice, thereby executing a portion of each task piecemeal. In this case, which portion of a program is executed by each processor changes dynamically. Which portion of a program is executed by each of the multiple processors can be statically determined by programming with multi-processor awareness.

[0154] Figure 11 This figure illustrates an example of a computer 1000 capable of implementing various aspects of the present invention in whole or in part. Programs installed on computer 1000 enable computer 1000 to perform operations associated with apparatuses according to embodiments of the present invention or functions of one or more components of such apparatuses, or to execute such operations or such one or more components, and / or enable computer 1000 to perform processes according to embodiments of the present invention or stages of such processes. Such programs may be executed by CPU 1012 to cause computer 1000 to perform specific operations associated with some or all of the modules in the flowcharts and block diagrams described herein.

[0155] The computer 1000 of this embodiment includes a CPU 1012, a RAM 1014, a graphics controller 1016, and a display device 1018, which are interconnected via a main controller 1010. The computer 1000 also includes input / output units such as a communication interface 1022, a hard disk drive 1024, a DVD-ROM drive 1026, and an IC card drive, which are connected to the main controller 1010 via an input / output controller 1020. The computer also includes conventional input / output units such as a ROM 1030 and a keyboard 1042, which are connected to the input / output controller 1020 via an input / output chip 1040.

[0156] The CPU 1012 controls each unit by operating according to programs stored in the ROM 1030 and the RAM 1014. The graphics controller 1016 acquires image data generated by the CPU 1012 from a frame buffer or the like provided in the RAM 1014 or from the graphics controller 1016 itself, and displays the image data on the display device 1018.

[0157] The communication interface 1022 enables communication with other electronic devices via a network. The hard disk drive 1024 stores programs and data used by the CPU 1012 within the computer 1000. The DVD-ROM drive 1026 reads programs or data from the DVD-ROM 1027 and provides the programs or data to the hard disk drive 1024 via the RAM 1014. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0158] The ROM 1030 stores therein a boot program and the like executed by the computer 1000 upon activation and / or programs dependent on the hardware of the computer 1000. The input / output chip 1040 can also connect various input / output units to the input / output controller 1020 via a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0159] The program is provided on a computer-readable medium such as a DVD-ROM 1027 or an IC card. The program is read from the computer-readable medium, installed in the hard disk drive 1024, RAM 1014, or ROM 1030, also examples of computer-readable media, and executed by the CPU 1012. The information processing described in these programs is read into the computer 1000, thereby enabling the program to cooperate with the various types of hardware resources described above. A device or method can be constructed by implementing information manipulation or processing with the use of the computer 1000.

[0160] For example, when communication is performed between the computer 1000 and an external device, the CPU 1012 can execute a communication program loaded in the RAM 1014 and instruct the communication interface 1022 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1012, the communication interface 1022 reads transmission data stored in a transmission buffer area provided in the RAM 1014, the hard disk drive 1024, the DVD-ROM 1027, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area provided on the recording medium.

[0161] Furthermore, the CPU 1012 can read all or a necessary portion of a file or database stored in an external recording medium such as the hard disk drive 1024, the DVD-ROM drive 1026 (DVD-ROM 1027), or an IC card into the RAM 1014, and perform various types of processing on the data in the RAM 1014. The CPU 1012 then writes the processed data back to the external recording medium.

[0162] Various types of information such as various types of programs, data, tables, and databases can be stored in a recording medium and subjected to information processing. CPU1012 performs various types of processing described in various places of this disclosure on the data read from RAM1014 and writes the results back to RAM1014. The various types of processing include various types of operations specified by the instruction sequence of the program, information processing, conditional judgment, conditional branching, unconditional branching, information retrieval / replacement, etc. In addition, CPU1012 can retrieve information from files, databases, etc. in the recording medium. For example, in the case where multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, CPU1012 can retrieve an entry that is consistent with the condition specifying the attribute value of the first attribute from the multiple entries, and read the attribute value of the second attribute stored in the entry, thereby obtaining the attribute value of the second attribute associated with the first attribute that meets the predetermined condition.

[0163] The programs or software modules described above may be stored in a computer-readable medium on or near the computer 1000. In addition, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as the computer-readable medium, thereby providing the program to the computer 1000 via the network.

[0164] While the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various modifications or improvements can be made to the above embodiments. As can be seen from the claims, embodiments with such modifications or improvements are also included in the technical scope of the present invention.

[0165] The order of execution of actions, processes, steps, and stages, etc., in the apparatus, system, program, and method described in the claims, specifications, and drawings is not specifically indicated as "before," "before," or the like. Furthermore, it should be noted that the actions, processes, steps, and stages may be executed in any order as long as the output of the previous process is not used in the subsequent process. Even if the action flow in the claims, specifications, and drawings is described using the phrases "first," "next," or the like for ease of explanation, it does not necessarily mean that the actions must be executed in that order. Description of reference numerals:

[0166] 100: Factory model building device; 110: Common model building unit; 112: Common model; 120: Individual model building unit; 122: Individual model; 130: Storage unit; 140: Model updating unit; 150: Input unit; 160: Evaluation result receiving unit; 170: Notification unit; 200: Factory; 210: Acquisition unit; 220: Control unit; 230: Model storage unit; 240: Evaluation unit; 300: Raw material information provider; 400: Raw material provider; 1000: Computer; 1010: Main controller; 1012: CPU; 1014: RAM; 1016: Graphics controller; 1018: Display device; 1020: Input / output controller; 1022: Communication interface; 1024: Hard disk drive; 1026: DVD-ROM drive; 1027: DVD-ROM; 1030: ROM; 1040: Input / output chip; 1042: Keyboard.

Claims

1. A plant model building device, characterized in that: have: a common model construction unit that constructs a common model that is a physical model based on plant data from a plurality of plants; and The individual model construction unit constructs an individual model for controlling a predetermined target plant based on the common model.

2. The plant model building device according to claim 1, characterized in that: The plant model construction device includes a model updating unit configured to update the common model based on the plant data from the plurality of plants and to update the individual model based on the plant data from the target plant.

3. The plant model building device according to claim 2, characterized in that: The model updating unit updates the common model when a predetermined first update condition is satisfied. The model updating unit updates the individual model according to the update of the common model.

4. The plant model building device according to claim 2, characterized in that: The model updating unit updates the individual model instead of the common model when a predetermined second update condition is satisfied.

5. The plant model building device according to claim 4, characterized in that: The plant model construction device includes an input unit for inputting instructions from an operator of the target plant. The model updating unit updates the individual model based on an instruction input from the operator.

6. The plant model building device according to claim 2, characterized in that: The plant model construction device includes an evaluation result receiving unit configured to receive, from the plurality of plants, evaluation results obtained by evaluating the accuracy of the individual models of the respective plants. The model updating unit updates the common model or the individual model based on the evaluation result.

7. The plant model construction device according to any one of claims 1 to 6, characterized in that: The individual models include hybrid models of physical models and machine learning models.

8. The plant model building device according to claim 7, characterized in that: The individual model construction unit executes machine learning using the plant data of the target plant to construct the individual model by changing internal parameters of the common model.

9. The plant model construction device according to any one of claims 1 to 6, characterized in that: The individual models include machine learning models.

10. The plant model building device according to claim 9, characterized in that: The individual model construction unit executes machine learning using the plant data of the target plant and the output of the common model to construct the individual model that outputs an operation value for controlling the target plant based on the output of the common model input.

11. The plant model building device according to claim 9, characterized in that: The individual model construction unit constructs the individual model by executing machine learning using the plant data of the target plant and the output of the common model, and outputs a correction value for correcting an operation value output by the common model for controlling the target plant based on the plant data input to the target plant.

12. The plant model construction device according to any one of claims 1 to 6, characterized in that: The individual model construction unit constructs a plurality of individual models for controlling the target factory.

13. The plant model building device according to claim 12, characterized in that: The common model includes a plurality of common models corresponding to the plurality of individual models.

14. The plant model construction device according to any one of claims 1 to 6, characterized in that: The common model construction unit constructs the common model based on the plant data and raw material information from the plurality of plants.

15. The plant model building device according to claim 14, characterized in that: The individual model construction unit constructs the individual model based on the common model and the material information.

16. The plant model building device according to claim 14, characterized in that: The raw material information includes at least one of information on the composition of the raw material, information related to the strength, purity, color or grade of the raw material of the raw material, information on the raw material supplier, information on the original product of the raw material, information related to the usage status of the original product of the raw material and information related to the storage of the raw material.

17. The plant model construction device according to any one of claims 1 to 6, characterized in that: The common model is a model that outputs an operation value for controlling the target plant based on the plant data input to the target plant. The common model calculates and outputs an intermediate variable that associates the plant data of the target plant with the operation value.

18. The plant model construction device according to any one of claims 1 to 6, characterized in that: The individual model is a model that outputs an operation value for controlling the target plant based on the plant data input to the target plant. The individual model calculates and outputs an intermediate variable that associates the plant data of the target plant with the operation value.

19. A method for constructing a factory model, characterized in that: include: The phase of building a physical model based on plant data from multiple plants, i.e., a common model; as well as A stage in which individual models for controlling a predetermined target plant are constructed based on the common model.

20. A computer-readable storage medium, characterized in that The computer readable storage medium has a program recorded thereon. The program is executed by a computer, The program causes the computer to operate as a common model construction unit and an individual model construction unit. The common model construction unit constructs a common model that is a physical model based on plant data from a plurality of plants. The individual model construction unit constructs an individual model for controlling a predetermined target plant based on the common model.

Images