Simulation system, simulation device, simulation method, and simulation program

Abstract

To provide a simulation system capable of reducing a burden of work for creating a simulation scenario which is an input in simulation.SOLUTION: The simulation system 1 includes a time-series data acquisition unit 11 that acquires time-series data including a control value used to operate a plant and a measurement value measured in the plant, a classification unit 15 that classifies a plurality of section data obtained by dividing the time-series data into a plurality of patterns based on similarity between the section data, and a simulation execution unit 28 that simulates operation of the plant by executing a simulation using, as an input, a simulation scenario obtained by picking up section data classified into the same pattern as section data designated by a user from the plurality of section data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a simulation system, a simulation device, a simulation method, and a simulation program for simulating plant operation. [Background technology]

[0002] A simulation system may be attached to a monitoring and control device that monitors and controls a plant to simulate the operation of the plant. Such a simulation system calculates evaluation indexes related to the operation efficiency by executing a simulation based on the plant operation plan or the plant operation record. The operation efficiency of the plant can be improved by applying an operation method discovered based on the simulation results to the plant control.

[0003] Patent Document 1 discloses a system that includes a simulation unit that simulates the operation of a manufacturing site, a monitor unit that monitors the actual operation of the manufacturing site, and a calibration unit that calibrates a simulation model based on the difference between the operation simulated by the simulation unit and the monitored operation. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-56733 Summary of the Invention [Problem to be solved by the invention]

[0005] The above-mentioned Patent Document 1 does not describe a method for creating a simulation scenario, which is an input for the simulation. When a simulation is performed according to a driving situation, if a simulation scenario is to be created manually, the workload of creating the simulation scenario increases as the period to be simulated becomes longer.

[0006] The present disclosure has been made in view of the above, and aims to provide a simulation system that can reduce the workload of creating a simulation scenario, which is an input in a simulation. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the objectives, the simulation system according to the present disclosure includes a time-series data acquisition unit that acquires time-series data including control values ​​used in plant operation and measurement values ​​measured in the plant; a classification unit that classifies a plurality of section data obtained by dividing the time-series data at a set period into a plurality of patterns based on similarities between the section data; and a simulation execution unit that simulates plant operation by executing a simulation using as input a simulation scenario obtained by picking out section data that has been classified into the same pattern as section data specified by a user from the plurality of section data. [Effects of the Invention]

[0008] The simulation system according to the present disclosure has the effect of reducing the workload of creating a simulation scenario, which is an input for a simulation. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a simulation system according to a first embodiment; [Figure 2]FIG. 1 is a diagram showing an example of a plant to be simulated by the simulation system according to the first embodiment; [Figure 3] FIG. 1 is a diagram for explaining a simulation performed by a simulation device according to a first embodiment. [Figure 4] 1 is a flowchart showing an example of an operation procedure of the simulation system according to the first embodiment; [Figure 5] FIG. 1 is a diagram for explaining input / output relationships among a plurality of micro models used in the simulation system according to the first embodiment. [Figure 6] FIG. 1 is a diagram for explaining a cascade operation of constraint conditions executed by the simulation system according to the first embodiment. [Figure 7] FIG. 1 is a diagram showing an example of a hardware configuration for realizing a simulation device included in a simulation system according to a first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] A simulation system, a simulation device, a simulation method, and a simulation program according to embodiments will be described in detail below with reference to the accompanying drawings.

[0011] Embodiment 1 1 is a diagram showing an example of the configuration of a simulation system 1 according to the embodiment 1. In FIG. 1, the simulation system 1, a monitoring control device 2, and an input / output device 3 are shown.

[0012] The simulation system 1 is a system that simulates the operation of a plant. The monitoring and control device 2 monitors and controls the plant. The input / output device 3 is operated by a user of the simulation system 1 to input information to the simulation system 1. The input / output device 3 also outputs information from the simulation system 1. The input / output device 3 also inputs information to the monitoring and control device 2.

[0013] The simulation system 1, the monitoring control device 2, and the input / output device 3 are connected via a network. The simulation system 1, the monitoring control device 2, and the input / output device 3 communicate with each other via the network. The network is, for example, a WAN (Wide Area Network) such as the Internet, but may also be a LAN (Local Area Network).

[0014] The plant may be a water treatment plant, a power plant, a chemical plant, a building facility, or a factory where FA (Factory Automation) has been introduced. The plant may be any plant that can be monitored and controlled by the monitoring and control device 2, and is not limited to the examples given here.

[0015] The simulation system 1 includes a preprocessing device 4 and a simulation device 5. The preprocessing device 4 processes data acquired from the monitoring and control device 2 and sends the processed data to the simulation device 5. The simulation device 5 uses the data from the preprocessing device 4 to perform a simulation of the operation of the plant.

[0016] The data from the pre-processing device 4 is data that indicates the operating history of the plant. The simulation device 5 acquires the data from the pre-processing device 4 and executes a simulation based on the operating history of the plant. The simulation device 5 may also acquire an operation plan for future operation of the plant and execute a simulation based on the operation plan. An example in which the simulation device 5 executes a simulation based on the operating history of the plant will be described below.

[0017] The preprocessing device 4 includes a time series data acquisition unit 11, a first time series data storage unit 12, a feature calculation unit 13, a second time series data storage unit 14, a classification unit 15, and a third time series data storage unit 16.

[0018] The monitoring and control device 2 transmits time series data including control values ​​used in plant operation and measurement values ​​measured in the plant to the preprocessing device 4. The control values ​​included in the time series data are values ​​related to the operation of the plant. The measurement values ​​included in the time series data are values ​​indicating the results of measuring the state of the plant. The time series data acquisition unit 11 receives the time series data from the monitoring and control device 2. As a result, the time series data acquisition unit 11 acquires time series data including control values ​​used in plant operation and measurement values ​​measured in the plant. The time series data acquisition unit 11 outputs the acquired time series data to the first time series data storage unit 12. The first time series data storage unit 12 stores the time series data.

[0019] The feature amount calculation unit 13 reads out time series data from the first time series data storage unit 12. The feature amount calculation unit 13 performs a calculation to extract feature amounts from the read out time series data. The feature amount calculation unit 13 outputs the time series data to which the feature amounts have been added to the second time series data storage unit 14. The second time series data storage unit 14 stores the time series data to which the feature amounts have been added.

[0020] The classification unit 15 reads the time series data to which the feature values ​​have been assigned from the second time series data storage unit 14. The classification unit 15 obtains a plurality of interval data by dividing the time series data to which the feature values ​​have been assigned at a predetermined period. The classification unit 15 classifies the plurality of interval data into a plurality of patterns based on the similarity between the interval data. The classification unit 15 assigns pattern information indicating the classified pattern to each interval data. The classification unit 15 outputs the time series data to which the feature values ​​and pattern information have been assigned to the third time series data storage unit 16. The third time series data storage unit 16 stores the time series data to which the feature values ​​and pattern information have been assigned.

[0021] The simulation device 5 includes a simulation scenario definition unit 21, a simulation data storage unit 22, a micromodel selection unit 23, a simulation micromodel storage unit 24, a simulation scenario editing unit 25, a constraint condition editing unit 26, a simulation condition creation unit 27, a simulation execution unit 28, and an evaluation value calculation unit 29. The simulation device 5 also includes a micromodel relationship storage unit 30, a cascade calculation condition specification unit 31, a constraint condition determination unit 32, a constraint condition cascade calculation unit 33, and a simulation scenario management unit 34.

[0022] The simulation device 5 reads the time series data stored in the third time series data storage unit 16 of the preprocessing device 4. The time series data read into the simulation device 5 is time series data to which feature quantities and pattern information have been added. The simulation data storage unit 22 stores the time series data to which feature quantities and pattern information have been added.

[0023] The simulation scenario definition unit 21 executes processing to define a simulation scenario, which is an input in a simulation. The user specifies the period to be simulated by operating the input / output device 3. The user also specifies, by operating the input / output device 3, section data to be included in the simulation scenario from the time-series data separated into the specified period.

[0024] The simulation scenario definition unit 21 picks out section data that is classified into the same pattern as the section data specified by the user from the time-series data for the period specified by the user. The simulation scenario definition unit 21 defines the section data specified by the user and the picked-up section data as a simulation scenario.

[0025] The simulation device 5 stores a plurality of micro models created in advance. A means for storing the plurality of micro models is not shown. Each of the plurality of micro models is a model that simulates a part of a plant. The micro model selection unit 23 selects a micro model to be used for simulation from the plurality of micro models. The simulation micro model storage unit 24 stores the micro model selected by the micro model selection unit 23.

[0026] The simulation scenario editing unit 25 edits the simulation scenario defined by the simulation scenario definition unit 21. Editing a simulation scenario refers to changing the section data defined as the simulation scenario. The user instructs the simulation device 5 to edit the simulation scenario by operating the input / output device 3. The simulation scenario editing unit 25 edits the simulation scenario in accordance with the user's operation on the input / output device 3.

[0027] The constraint condition editing unit 26 edits the constraint conditions of the micro model. In the first embodiment, the constraint conditions are conditions that indicate the allowable range of values ​​output from the micro model. The constraint conditions can be set for each of a plurality of pre-set micro models. The set constraint conditions are associated with each micro model. The user instructs the input / output device 3 to edit the constraint conditions associated with the micro model stored in the simulation micro model storage unit 24. The constraint condition editing unit 26 edits the constraint conditions in accordance with the user's operation on the input / output device 3.

[0028] The simulation condition creating unit 27 reads out a simulation scenario from the time-series data stored in the simulation data storage unit 22. When the simulation scenario editing unit 25 edits the simulation scenario, the simulation condition creating unit 27 acquires, from the simulation scenario editing unit 25, a simulation scenario in which the editing by the simulation scenario editing unit 25 is reflected. The simulation condition creating unit 27 reads out a micro model stored in the simulation micro model storage unit 24. When the constraint condition editing unit 26 edits the constraint conditions, the simulation condition creating unit 27 acquires, from the constraint condition editing unit 26, constraint conditions in which the editing by the constraint condition editing unit 26 is reflected. The simulation condition creating unit 27 outputs the simulation conditions, which are the information input to the simulation condition creating unit 27, to the simulation executing unit 28.

[0029] The simulation execution unit 28 executes a simulation based on the simulation conditions. The simulation execution unit 28 inputs a simulation scenario into a micro model included in the simulation conditions, and obtains a simulation result, which is an output from the micro model. In this way, the simulation execution unit 28 executes a simulation using as input a simulation scenario obtained by picking out section data that is classified into the same pattern as the section data specified by the user from among multiple section data. In this way, the simulation execution unit 28 simulates the operation of the plant. The simulation execution unit 28 outputs the simulation scenario and the simulation result to the evaluation value calculation unit 29.

[0030] The evaluation value calculation unit 29 calculates various evaluation values ​​based on the simulation results input to the evaluation value calculation unit 29. The input / output device 3 displays the various evaluation values ​​obtained by calculations by the evaluation value calculation unit 29. The evaluation value calculation unit 29 outputs the simulation scenario input to the evaluation value calculation unit 29 to the simulation scenario management unit 34.

[0031] The micro model relationship storage unit 30 stores micro model relationship information indicating the input / output relationships between multiple micro models. The input / output relationships between micro models are such that the output of one micro model corresponds to the input of another micro model. The input / output relationships can also be said to indicate the relationships between parts that are connected to each other in a plant.

[0032] In the first embodiment, the cascade operation of constraints refers to an operation that reflects the constraints of one micromodel on other micromodels. The cascade operation condition designation unit 31 designates the boundaries of the range of constraints to be reflected on other micromodels using time-series data based on the input / output data that are the simulation results. The cascade operation condition designation unit 31 outputs the designated time-series data to the constraint cascade operation unit 33 as cascade operation conditions.

[0033] The constraint cascade calculation unit 33 receives the simulation results from the simulation execution unit 28. The constraint cascade calculation unit 33 reads out micro model relationship information from the micro model relationship storage unit 30. The constraint cascade calculation unit 33 receives the cascade calculation conditions from the cascade calculation condition specification unit 31. The constraint cascade calculation unit 33 executes a cascade calculation of constraints using the simulation results, the micro model relationship information, and the cascade calculation conditions. The constraint cascade calculation unit 33 calculates time series data indicating the boundaries of the ranges to be used as constraint conditions for other micro models having input / output relationships with the micro model, based on the time series data indicated in the cascade calculation conditions based on the constraint conditions for the micro model. The constraint cascade calculation unit 33 outputs the calculated constraints to the simulation scenario management unit 34.

[0034] The user confirms the constraint conditions calculated by the cascade operation as the constraint conditions of the micro model by operating the input / output device 3. The constraint condition confirmation unit 32 confirms the constraint conditions calculated by the cascade operation as the constraint conditions of the micro model in accordance with the user's operation. The user can adjust the constraint conditions calculated by the cascade operation by operating the input / output device 3. The user can also confirm the constraint conditions adjusted by the user's operation as the constraint conditions of the micro model.

[0035] A simulation scenario is input to the simulation scenario management unit 34 from the evaluation value calculation unit 29. The simulation scenario management unit 34 stores the input simulation scenario. The user instructs the input / output device 3 to read out a simulation scenario stored in the simulation scenario management unit 34. When the instruction to read out a simulation scenario is given, the simulation scenario management unit 34 outputs the simulation scenario instructed to be read out to the simulation data storage unit 22. The simulation scenario instructed to be read out is used in a simulation by the simulation execution unit 28. This allows the simulation device 5 to read out a simulation scenario used in a past simulation and execute the simulation.

[0036] The simulation scenario management unit 34 receives constraint conditions calculated by the cascade operation from the constraint condition cascade operation unit 33. The simulation scenario management unit 34 stores the constraint conditions determined by the constraint condition determination unit 32. The user instructs the input / output device 3 to read out the constraint conditions stored in the simulation scenario management unit 34. When the instruction to read out the constraint conditions is given, the simulation scenario management unit 34 outputs the constraint conditions instructed to be read out to the simulation data storage unit 22. The constraint conditions instructed to be read out are used in the simulation by the simulation execution unit 28. This allows the simulation device 5 to execute a simulation applying the constraint conditions obtained by the cascade operation.

[0037] Next, the input / output relationships between the micro models will be described, assuming that the simulation system 1 according to the first embodiment is applied to the simulation of a sewage treatment system.

[0038] Fig. 2 is a diagram showing an example of a plant that is the target of a simulation by the simulation system 1 according to the embodiment 1. Fig. 2 shows a simplified configuration of a general sewage treatment system.

[0039] A sewage treatment system comprises a sewer pipe through which sewage flows, an inlet conduit into which the sewage flows after passing through the sewer pipe, a grit basin into which the sewage flows from the inlet conduit, and a pump well into which the sewage flows from the grit basin. The grit basin is a pond used to remove sediment and debris mixed in the sewage by settling it out. Once the sewage reaches the pump well, it is sent by a lift pump to the primary sedimentation basin, which is the next treatment facility. The lift pump pumps up the sewage at a set pumping rate. The amount of sewage treated by the sewage treatment system is controlled by the pumping rate set for the lift pump.

[0040] In the primary settling tank, the sewage flows gently, allowing small pieces of garbage and mud contained in the sewage to settle. As a result, the primary settling tank removes small pieces of garbage and mud that were not removed in the grit tank. After being treated in the primary settling tank, the sewage flows into the reaction tank. In the reaction tank, activated sludge is mixed into the sewage to treat it. The sewage containing activated sludge is sent from the reaction tank to the final settling tank. In the final settling tank, the sewage flows gently, allowing the activated sludge to settle, and clean water is extracted. After being treated in the final settling tank, the water is disinfected in disinfection equipment. Water that has been disinfected in the disinfection equipment is released into rivers and other places as treated water.

[0041] In this way, a sewage treatment system treats sewage using multiple facilities such as an inlet drain, a grit basin, a pump well, a lift pump, a primary sedimentation tank, a reaction tank, a final sedimentation tank, and a disinfection facility. For example, a micromodel simulating each of these multiple facilities is created as a micromodel used for simulating water volume.

[0042] For example, in the case of two interconnected facilities, an inlet conduit and a grit basin, the amount of sewage outflow from the inlet conduit corresponds to the amount of sewage inflow into the grit basin. Therefore, the micro model representing the inlet conduit and the micro model representing the grit basin have an input-output relationship in which the output of the micro model representing the inlet conduit corresponds to the input of the micro model representing the grit basin. In this way, an input-output relationship holds between facilities interconnected in a sewage treatment system in which the output of a micro model representing one facility corresponds to the input of a micro model representing the other facility. The constraint cascade calculation unit 33 performs a cascade calculation of constraints based on this input-output relationship.

[0043] Here, the micro model used for simulating the water volume has been described, but a micro model used for simulating a state quantity other than the water volume may also be created for each of the multiple pieces of equipment. The state quantity other than the water volume may be, for example, a state quantity related to power consumption or a state quantity related to sludge treatment. The constraint cascade calculation unit 33 may also perform a cascade calculation of constraints on the micro models for the state quantities other than the water volume based on the input / output relationships between the micro models.

[0044] Next, a simulation performed by the simulation device 5 according to the first embodiment will be described. Fig. 3 is a diagram for explaining a simulation performed by the simulation device 5 according to the first embodiment. Fig. 3 shows an example of a screen for displaying a simulation result. The screen shown in Fig. 3 is displayed on the input / output device 3.

[0045] Here, we will explain the configuration of the screen shown in Fig. 3. The screen is provided with a selection operation section 41 that accepts selection of the simulation period and the equipment to be simulated, a section data display section 42 that displays information about section data, a micro model input display section 43 that displays the input of the micro model, a micro model output display section 44 that displays the output of the micro model, and an evaluation value display section 45 that displays the evaluation value.

[0046] The selection operation unit 41 has a field for inputting the date to be used as the first day of the period and a field for inputting the date to be used as the last day of the period. The selection operation unit 41 also has a field for accepting the selection of equipment. By inputting the dates of the first and last days in the selection operation unit 41, selecting the equipment, and pressing the enter button, the period to be simulated and the equipment on which the simulation will be performed are specified.

[0047] In the example described here, it is assumed that the time series data is divided into one-day periods in the classification unit 15 of the preprocessing device 4. That is, the section data is time series data divided into one-day periods.

[0048] For example, performance information of a sewage treatment system shown in FIG. 2 is expressed by time-series data for each of multiple data items, such as the inflow water volume, pumping volume, and main water level of a certain facility. Here, the data items are measurement value items or control value items. The classification unit 15 performs clustering of section data, which is time-series data divided into daily intervals. The classification unit 15 obtains state transition information indicating each of the multiple clusters through clustering. Based on the state transition information, the classification unit 15 treats section data whose states indicated by the multiple data items are similar as the same cluster. The classification unit 15 classifies each section data into multiple patterns using a clustering algorithm such as the k-means method or Ward's method. The classification unit 15 assigns pattern information indicating the pattern of the section data to each section data.

[0049] The section data display unit 42 displays section data for the period specified in the selection operation unit 41. In the section data display unit 42, a graph 46 displays an evaluation value calculated from each section data. When an evaluation value item such as inflow water volume or burdened power amount is selected in the section data display unit 42, the evaluation value for the selected item is displayed in the graph 46. In the graph 46, the horizontal axis represents the date and the vertical axis represents the evaluation value.

[0050] In the interval data display unit 42, a graph 47 displays objects representing the states of multiple data items for each interval data during a specified period. Here, the values ​​of the inflow water volume, pumping volume, and main water level are each ranked as "low," "normal," or "high." In the graph 47, each interval data item is represented by a columnar object colored according to the rank of each data item. In FIG. 3, the color coding is represented by outlined or hatched areas. In the graph 47, the horizontal axis represents the date, and the vertical axis represents the time. In the classification unit 15, interval data with similar color coding patterns in the columnar objects are classified into the same pattern. From the display in the interval data display unit 42, the user can easily understand the content of each interval data item during a specified period.

[0051] A micro model to be used in the simulation is selected according to the equipment and the evaluation value item by specifying the equipment in the selection operation unit 41 and selecting the evaluation value item in the section data display unit 42. In this way, the micro model selection unit 23 selects a micro model according to the equipment specification and the selection of the evaluation value item by the user's operation.

[0052] The user specifies the section data to be included in the simulation scenario by clicking on the display portion for a certain section data in graph 46 or graph 47. The micro model input display section 43 displays the values ​​of each of the multiple items included in the section data specified by the user. The micro model input display section 43 displays a graph 48 for each of the items, and the graph 48 shows the transition of the value for each of the items. In graph 48, the horizontal axis represents time and the vertical axis represents value.

[0053] The simulation execution unit 28 executes a simulation by inputting the section data shown in the micro model input display unit 43 into the micro model selected as described above. The micro model output display unit 44 displays the simulation results output by the simulation. The micro model output display unit 44 displays the values ​​of each of the multiple items included in the simulation results. The micro model output display unit 44 displays a graph 49 for each item, and the graph 49 shows the transition of the value for each item. In the graph 49, the horizontal axis represents time and the vertical axis represents value.

[0054] An object 52 representing the constraint condition is displayed on the graph 49. In the example shown in Fig. 3, the object 52 is a strip-shaped figure representing an area outside the range of the constraint condition. The object 52 is colored. In Fig. 3, the coloring is expressed by halftone tones.

[0055] As described above, section data to be included in the simulation scenario is specified by clicking on the display portion for a certain section data in graph 46 or graph 47. The simulation scenario definition unit 21 selects section data that is classified into the same pattern as the section data specified by the user from the section data in the period specified as the target of the simulation.

[0056] When the cursor is placed on a columnar object representing the section data specified by the user in the graph 47 displayed in the section data display unit 42, an object 51 is displayed for the section data specified by the user in the graphs 46 and 47. In addition, the same object 51 as the section data specified by the user is displayed for section data classified into the same pattern as the section data specified by the user. For example, the interior surrounded by the object 51 is colored with transparency.

[0057] The simulation execution unit 28 executes a simulation using as input the simulation scenario defined by the simulation scenario definition unit 21. By checking the objects 51 in the section data display unit 42, the user can easily understand the section data included in the simulation scenario.

[0058] The simulation execution unit 28 outputs the results of the simulation using the simulation scenario as input to the evaluation value calculation unit 29. The evaluation value calculation unit 29 calculates various evaluation values ​​based on the simulation results input to the evaluation value calculation unit 29. As an example, the evaluation value calculated by the evaluation value calculation unit 29 represents the results of evaluating the operation of the plant over a year.

[0059] The evaluation value display unit 45 displays various evaluation values ​​calculated by the evaluation value calculation unit 29. In the example shown in FIG. 3, the evaluation value display unit 45 displays evaluation values ​​for items selected by the user from among multiple items to be evaluated. In the example shown in FIG. 3, two items are selected in the evaluation value display unit 45. A graph 50 displayed in the evaluation value display unit 45 shows the distribution of evaluation values ​​for each of the two items. The user selects two items by selecting an item whose evaluation value is indicated on the vertical axis of the graph 50 and an item whose evaluation value is indicated on the horizontal axis of the graph 50. When the user switches between the two items, the content of the graph 50 also switches. The user can easily check the evaluation values ​​calculated by the evaluation value calculation unit 29 from the display in the evaluation value display unit 45.

[0060] Suppose that the user specifies one piece of section data in the section data display unit 42, and then performs an operation to specify another piece of section data while the display is being performed in each section of the screen as shown in FIG. 3. The display in the micro model input display unit 43 is switched to a display of the newly specified section data. The simulation execution unit 28 executes a simulation using the newly specified section data as input. The display in the micro model output display unit 44 is switched to a simulation result for the newly specified section data.

[0061] The simulation scenario definition unit 21 also updates the simulation scenario by picking up section data that are classified into the same pattern as the newly specified section data. The simulation execution unit 28 executes a simulation using the updated simulation scenario as input. The evaluation value calculation unit 29 calculates various evaluation values ​​based on the simulation results. The display on the evaluation value display unit 45 is switched to display the evaluation values ​​based on the updated simulation scenario. This allows the user to easily check the impact on the evaluation values ​​when the simulation scenario is changed.

[0062] The input / output device 3 accepts operations for editing the simulation scenario in the micro model input display unit 43. For example, the input / output device 3 is capable of freely changing the shape of a graph 48 in accordance with operations by the user. The simulation scenario editing unit 25 changes the contents of the section data shown in the graph 48, i.e., the contents of the input to the micro model, in accordance with the change in the shape of the graph 48. When the contents of the input to the micro model are changed, the simulation execution unit 28 executes a simulation based on the changed input. The display in the micro model output display unit 44 is switched to the simulation results based on the changed input. This allows the user to easily check the effect on the output when adjusting the input.

[0063] Furthermore, the simulation scenario editing unit 25 reflects changes to the section data shown in the graph 48 in all section data included in the simulation scenario. That is, the simulation scenario editing unit 25 changes the contents of all section data included in the simulation scenario in accordance with an operation that changes the shape of the graph 48. In this way, the simulation scenario editing unit 25 changes the simulation scenario. The simulation execution unit 28 executes a simulation based on the changed simulation scenario. The evaluation value calculation unit 29 calculates various evaluation values ​​based on the simulation results. The display in the evaluation value display unit 45 is switched to display evaluation values ​​based on the changed simulation scenario. The user can change the simulation scenario with simple operations on the screen. Furthermore, the user can easily check the impact on the evaluation values ​​when a pattern is changed.

[0064] The input / output device 3 accepts operations for editing the constraint conditions in the micro model output display unit 44. For example, the input / output device 3 is capable of freely changing the vertical width of the object 52 in accordance with an operation by the user. The constraint condition editing unit 26 changes the constraint conditions in accordance with the change in the vertical width of the object 52. This allows the user to easily change the constraint conditions.

[0065] The types and forms of the graphs 46, 47, 48, 49, and 50 displayed on the screen are not limited to those described above and may be any.Furthermore, the forms of the objects 51 and 52 displayed on the screen are not limited to those described above and may be any.

[0066] Next, a description will be given of the operation of the simulation system 1. Here, an example of an operation procedure for executing a simulation by inputting a simulation scenario will be described. Fig. 4 is a flowchart showing an example of the operation procedure of the simulation system 1 according to the first embodiment.

[0067] Steps S1 to S4 are operations performed by the preprocessing device 4. In step S1, the time-series data acquisition unit 11 acquires time-series data including control values ​​used in plant operation and measurement values ​​measured in the plant. The time-series data is stored in the first time-series data storage unit 12.

[0068] In step S2, the feature amount calculation unit 13 calculates feature amounts from the time series data acquired in step S1. The time series data to which feature amounts have been added is stored in the second time series data storage unit .

[0069] In step S3, the classification unit 15 divides the time series data to which the feature amounts have been assigned into a plurality of section data, and classifies the plurality of section data into a plurality of patterns. In step S4, the third time series data storage unit 16 stores the plurality of section data to which the feature amounts and pattern information have been assigned.

[0070] Steps S5 to S7 are operations performed by the simulation device 5. In step S5, the simulation scenario definition unit 21 defines a simulation scenario. The simulation scenario definition unit 21 defines the simulation scenario by picking out, from among the multiple section data, section data that is classified into the same pattern as the section data specified by the user.

[0071] In step S6, the simulation execution unit 28 executes a simulation using the simulation scenario defined in step S5 as an input, and outputs the simulation result to the evaluation value calculation unit 29.

[0072] In step S7, the evaluation value calculation unit 29 calculates an evaluation value based on the simulation result. The evaluation value calculation unit 29 outputs the calculation result of the evaluation value to the input / output device 3. With the above, the simulation system 1 ends the operation according to the procedure shown in FIG.

[0073] Next, the input / output relationships in a plurality of micro models will be described. FIG. 5 is a diagram for explaining the input / output relationships in a plurality of micro models used in the simulation system 1 according to the first embodiment. FIG. 5 shows examples of the input / output relationships in five micro models. In FIG. 5, rectangles in which mathematical expressions are written represent micro models. In FIG. 5, arrows connecting rectangles indicate that the output from the micro model at the origin of the arrow becomes the input to the micro model at the destination of the arrow. That is, in FIG. 5, the arrows represent the input / output relationships.

[0074] Figure 5 can be said to represent an example of a network structure formed by a chain of input / output relationships among multiple micro models used in a simulation. A plant is represented by a network structure consisting of micro models and the input / output relationships between the micro models. Note that the number of micro models and the form of the network structure in the network structure representing a plant are arbitrary.

[0075] In Figure 5, f i (x i (t),u i (t)) represents a micromodel. i is a number representing a micromodel and is an integer from 1 to 5. In the following description, a micromodel is referred to as f i It is written as u i (t) represents the input of the micro model. i (t) represents the output of the micromodel. x i (t) represents the state variable. x i (t) can be said to be an internal variable of the micromodel. i (t) includes the inputs u that can be directly controlled in the plant. i cont (t) and the input u, which is not directly controllable in the plant. i uncont(t) and (t). Inputs that can be directly controlled within the plant include the amount of water pumped by a water pump. Inputs that cannot be directly controlled within the plant include inputs from outside the plant, such as the amount of sewage inflow from sewer pipes.

[0076] In the example shown in Figure 5, f 1 The output of f 2 and f 3 is used for each input of f 2 , f 3 , and f 4 Each output of f 5 Used to input.

[0077] Next, the cascade calculation of constraint conditions will be described. Fig. 6 is a diagram for explaining the cascade calculation of constraint conditions executed by the simulation system 1 according to the first embodiment.

[0078] Here, one of the multiple micromodels is defined as a first micromodel, and a micromodel among the multiple micromodels to which data output from the first micromodel is input is defined as a second micromodel. The constraint cascade calculation unit 33 calculates a range of values ​​output from the first micromodel that can satisfy the constraints set in the second micromodel, and executes a cascade calculation to reflect the calculated range in the constraints set in the first micromodel.

[0079] In the first embodiment, the constraint is the output of each micro model, y i Let (t) be the time series data that represents the upper and lower limits of the range that can be taken. Here, the upper limit of the constraint condition of each micro model is C i U (t), the lower bound of the constraints of each micromodel is C i L (t). The constraints of each micro model are C i L (t) <y i (t) <C i U (t). The upper limit Ci U (t) and the lower bound C i L Each of (t) and (t) is represented by time series data.

[0080] Figure 6 shows two micromodels, f 1 and f 2 In Figure 6, f 1 corresponds to the first micromodel, and f 2 corresponds to the second micromodel, where f 2 The constraints set for f 1 Assume that a cascade operation is performed to reflect the constraints on

[0081] f 2 The constraints set for C 2 L (t) <y 2 (t) <C 2 U (t). Also, u 2 uncont (t)=y 1 (t) is defined as x 1 (t) and u 1 cont (t) and (t) are determined, then f 2 By using the inverse function of y 2 (t) to u 2 uncont (t) is obtained. f 2 The inverse function of C 2 U By entering (t), u 2 uncont (t)=y 1 From the relationship of (t), f 1 An additional condition on the upper limit of the constraint, C 1 U _ propagate (t) is obtained. Also, f 2 The inverse function of C 2 L By entering (t), u 2 uncont (t)=y1 From the relationship of (t), f 1 An additional condition on the lower bound of the constraint, C 1 L _ propagate (t) is required.

[0082] This allows f 1 The constraints on f 2 An additional condition, C, is added to reflect the constraints on 1 L _ propagate (t) <y 1 (t) <C 1 U _ propagate (t) is obtained. f 1 By finding the AND condition between the predefined constraints and the additional conditions, 1 The predefined constraint C 1 L (t) <y 1 (t) <C 1 U (t) to f 2 It is possible to reflect the constraints on f 1 The predefined constraints on f 1 f 1 Let f be the constraint. 1 The constraints on f 2 By reflecting the constraints on f 1 The output of f 1 As long as the constraints on 2 The output of f 2 The constraints on

[0083] In this way, the constraint cascade calculation unit 33 executes a cascade calculation that reflects the constraints set in the second micro model on the constraints set in the first micro model. The constraint cascade calculation unit 33 can execute such a cascade calculation for micro models that have an input / output relationship with each other in the above network structure. This allows the simulation device 5 to reflect the constraints set in each micro model in each of the multiple micro models in a chain reaction.

[0084] For example, when a simulation scenario of a certain micro model is changed, if the output satisfies the constraints, there is no need to recalculate other micro models linked to that micro model. This makes it possible to avoid the trouble of resimulating the entire plant when a simulation scenario is changed.

[0085] Next, a hardware configuration for realizing the simulation device 5 will be described. Fig. 7 is a diagram showing an example of a hardware configuration for realizing the simulation device 5 included in the simulation system 1 according to the first embodiment. The simulation device 5 is realized by a computer system including a processing circuit 61 and a communication device 62. The processing circuit 61 includes a processor 63 and a memory 64. The processing circuit 61 is a circuit on which the processor 63 executes software.

[0086] The processing functions of each component of the simulation apparatus 5 shown in FIG. 1 are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 64. In the processing circuit 61, the processor 63 reads and executes the program stored in memory 64, thereby realizing the processing functions of the simulation apparatus 5. That is, the processing circuit 61 includes memory 64 for storing a simulation program, which is a program that results in the processing of the simulation apparatus 5 being executed. It can also be said that the simulation program stored in memory 64 causes a computer to execute the procedures and methods of the simulation apparatus 5.

[0087] The storage function of the simulation device 5 is realized by using the memory 64. The simulation data storage unit 22, the simulation micro model storage unit 24, and the micro model relationship storage unit 30 shown in FIG.

[0088] The processor 63 is a CPU (Central Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a processor, or a DSP (Digital Signal Processor). The memory 64 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc).

[0089] The communication device 62 communicates with devices external to the simulation device 5. The communication function of the simulation device 5 is realized by using the communication device 62. The simulation device 5 may include an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0090] The preprocessing device 4 is realized by a hardware configuration similar to that shown in Fig. 7. Here, the hardware configuration that realizes the preprocessing device 4 will be described with reference to Fig. 7. The processing functions of each component of the preprocessing device 4 shown in Fig. 1 are realized by the processor 63 reading and executing a program stored in the memory 64 in the processing circuit 61. The storage function of the preprocessing device 4 is realized by using the memory 64. The first time series data storage unit 12, the second time series data storage unit 14, and the third time series data storage unit 16 are realized by using the memory 64.

[0091] The simulation program according to the first embodiment may be provided by being stored in a recording medium such as a CD (Compact Disc)-ROM or a DVD-ROM. Alternatively, the simulation program according to the first embodiment may be provided by being stored in a computer connected to a network such as the Internet and downloaded via the network such as the Internet. The simulation program according to the first embodiment may be provided or distributed via a network such as the Internet.

[0092] The components of the simulation system 1 do not necessarily have to be physically configured as shown in the figure. The specific form of distribution and integration of the components is not limited to that shown in the figure. The components may be configured in a functionally or physically distributed manner in any unit, or may be configured in an integrated manner. For example, the preprocessing device 4 and the simulation device 5 may be integrated into a single device.

[0093] According to the first embodiment, the simulation system 1 includes a time-series data acquisition unit 11 that acquires time-series data, a classification unit 15 that classifies a plurality of section data into a plurality of patterns based on the similarities between the section data, and a simulation execution unit 28 that simulates plant operation by executing a simulation using as input a simulation scenario obtained by picking out section data from the plurality of section data that has been classified into the same pattern as section data specified by a user. By classifying the plurality of section data by pattern and picking out section data of the same pattern to obtain a simulation scenario, the simulation system 1 can eliminate the need for manual creation of a simulation scenario. This has the effect of reducing the workload of creating a simulation scenario, which is an input for a simulation.

[0094] The simulation system 1 also includes a simulation scenario editing unit 25 that edits the simulation scenario. A simulation execution unit 28 executes a simulation based on the edited simulation scenario. This allows the simulation system 1 to allow the user to easily check the impact on the simulation results when the simulation scenario is changed.

[0095] The simulation execution unit 28 also executes simulations using multiple micro models, each of which simulates a part of the plant, allowing the simulation system 1 to perform simulations of the operation of each part of the plant and the operation of the entire plant.

[0096] The simulation system 1 also includes a constraint cascade calculation unit 33 that calculates a range of values ​​output from the first micro model that can satisfy the constraints set in the second micro model, and executes a cascade calculation to reflect the calculated range in the constraints set in the first micro model. This allows the simulation system 1 to avoid the hassle of re-simulating the entire plant when the simulation scenario is changed.

[0097] The configurations described in the above embodiments are examples of the contents of the present disclosure. The configurations of the embodiments can be combined with other known technologies. Part of the configurations of the embodiments can be omitted or modified without departing from the gist of the present disclosure. [Explanation of symbols]

[0098] 1 Simulation system, 2 Monitoring and control device, 3 Input / output device, 4 Preprocessing device, 5 Simulation device, 11 Time series data acquisition unit, 12 First time series data storage unit, 13 Feature calculation unit, 14 Second time series data storage unit, 15 Classification unit, 16 Third time series data storage unit, 21 Simulation scenario definition unit, 22 Simulation data storage unit, 23 Micromodel selection unit, 24 Simulation micromodel storage unit, 25 Simulation scenario editing unit, 26 Constraint condition editing unit, 27 Simulation condition creation unit, 28 Simulation execution unit, 29 Evaluation value calculation unit, 30 Micromodel relationship storage unit, 31 Cascade calculation condition specification unit, 32 Constraint condition determination unit, 33 Constraint condition cascade calculation unit, 34 Simulation scenario management unit, 41 Selection operation unit, 42 Section data display unit, 43 Micromodel input display unit, 44 Micromodel output display unit, 45 Evaluation value display unit, 46, 47, 48, 49, 50 Graph, 51, 52 Object, 61 Processing circuit, 62 Communication device, 63 Processor, 64 Memory.

Claims

1. a time-series data acquiring unit that acquires time-series data including control values ​​used in the operation of the plant and measurement values ​​measured in the plant; a classification unit that classifies a plurality of interval data obtained by dividing the time series data at a set period into a plurality of patterns based on similarities between the interval data; a simulation execution unit that executes a simulation using as input a simulation scenario obtained by picking out, from the plurality of section data, section data that is classified into the same pattern as the section data designated by a user, thereby simulating the operation of the plant. A simulation system comprising:

2. a simulation scenario editing unit that edits the simulation scenario, The simulation execution unit executes the simulation based on the edited simulation scenario.

2. The simulation system according to claim 1.

3. The simulation execution unit executes the simulation using a plurality of micromodels, each of which simulates a part of the plant.

3. The simulation system according to claim 1, wherein:

4. a condition indicating an allowable range for a value output from the micromodel is defined as a constraint condition, one of the plurality of micromodels is defined as a first micromodel, and one of the plurality of micromodels into which data output from the first micromodel is input is defined as a second micromodel; a constraint cascade calculation unit that calculates a range of values ​​output from the first micromodel that can satisfy the constraint set in the second micromodel, and executes a cascade calculation that reflects the calculated range in the constraint set in the first micromodel.

4. The simulation system according to claim 3.

5. The system includes a simulation execution unit that executes a simulation using as input a simulation scenario obtained by picking out section data that is classified into the same pattern as the section data designated by a user from among a plurality of section data that are classified into a plurality of patterns based on similarities between the section data, the section data being obtained by dividing time-series data that includes control values ​​used in the operation of the plant and measurement values ​​measured in the plant at a set period, and that simulates the operation of the plant. A simulation device characterized by:

6. A simulation method for simulating plant operation by a computer system, comprising: acquiring time-series data including control values ​​used in operation of the plant and measurement values ​​measured in the plant; classifying a plurality of interval data obtained by dividing the time series data at a set period into a plurality of patterns based on similarities between the interval data; and executing a simulation using as input a simulation scenario obtained by picking out, from the plurality of section data, section data that has been classified into the same pattern as the section data designated by a user, thereby simulating the operation of the plant. A simulation method comprising:

7. In the computer system, acquiring time-series data including control values ​​used in operating a plant and measurement values ​​measured in the plant; classifying a plurality of interval data obtained by dividing the time series data at a set period into a plurality of patterns based on similarities between the interval data; and simulating the operation of the plant by executing a simulation using as input a simulation scenario obtained by picking out, from the plurality of section data, section data that has been classified into the same pattern as the section data designated by the user. A simulation program characterized by:

Images