WO2019159280A1 - プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 - Google Patents
プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 Download PDFInfo
- Publication number
- WO2019159280A1 WO2019159280A1 PCT/JP2018/005252 JP2018005252W WO2019159280A1 WO 2019159280 A1 WO2019159280 A1 WO 2019159280A1 JP 2018005252 W JP2018005252 W JP 2018005252W WO 2019159280 A1 WO2019159280 A1 WO 2019159280A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- values
- plant
- regression model
- unit
- value
- Prior art date
Links
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 description 23
- 230000005540 biological transmission Effects 0.000 description 7
- 239000000047 product Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 3
- 239000012467 final product Substances 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000010977 unit operation Methods 0.000 description 2
- 238000010923 batch production Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/37—Measurements
- G05B2219/37591—Plant characteristics
Definitions
- the present invention relates to a plant operation condition setting support system for supporting setting of a plant operation condition, and a learning apparatus and an operation condition setting support apparatus that can be used in the plant operation condition setting support system.
- a series of processes are executed by a large number of devices such as reactors and heating furnaces, and a large amount of operation is required to control each of the large numbers of devices. Operating conditions are set.
- a plant where a multi-stage process is executed many manipulated variables can interact in a complex manner, so it is not easy to predict the effects of changes in manipulated variables. The plant is in operation.
- the simulation model Since the simulation model is adjusted manually, it requires a lot of man-hours and the accuracy of reproducing the actual process can be influenced by the experience and skill of the adjuster. In addition, since there may be an event that is difficult to reproduce by a process simulator, it has been difficult to construct a simulation model that accurately reproduces the actual operation state of the plant.
- the present invention has been made in view of such circumstances, and an object of the present invention is to provide a technology that supports setting of operating conditions capable of realizing a suitable operation of a plant.
- a plant operation condition setting support system for supporting setting of a plant operation condition, and includes a plurality of plant operation conditions.
- a learning device for learning a regression model for calculating a predicted output value indicating the operation result of the plant, and a plurality of settings to be set for controlling the operation of the plant using the regression model learned by the learning device And an operation condition setting support device that calculates the value of the operation amount.
- the learning device indicates the operation result of the plant when a plurality of operation amount values are set under operation conditions indicated by a plurality of state amount values, a plurality of operation amount values, and a plurality of state amount values.
- An actual value acquisition unit that acquires an actual value of a combination with an output value, a learning unit that learns a regression model based on a plurality of actual values acquired by the actual value acquisition unit, and a regression that is learned by the learning unit
- a regression model providing unit that provides the model to the driving condition setting support device.
- the driving condition setting support device includes a regression model acquisition unit that acquires the regression model learned by the learning device, a state quantity acquisition unit that acquires values of a plurality of state quantities, and a plurality of states acquired by the state quantity acquisition unit When operating the plant under the operation condition indicated by the quantity, an operation quantity calculation unit that uses a regression model to calculate a plurality of manipulated variable values whose output values satisfy a predetermined condition, and an operation quantity An operation amount output unit that outputs a plurality of operation amount values calculated by the calculation unit.
- the operation amount calculator may calculate a plurality of operation amount values by applying an optimization problem solving algorithm to the output value.
- the apparatus includes a plurality of state quantity values indicating plant operating conditions, a plurality of manipulated variable values set to control the operation of the plant, and a plurality of operating conditions indicated by the plurality of state quantity values.
- a learning unit for learning a regression model for calculating a predicted value of an output indicating an operation result of a plant when a plurality of operation amount values are set under an operation condition indicated by a plurality of state quantity values;
- a regression model providing unit that provides the operating model setting support device that calculates the values of a plurality of manipulated variables to be set for controlling the operation of the plant.
- Still another aspect of the present invention is an operating condition setting support device.
- This device is based on a plurality of state quantity values indicating a plant operating condition and a plurality of manipulated variable values set for controlling the operation of the plant.
- Regression model acquisition that acquires the regression model learned by the learning device from the learning device that learns the regression model for calculating the predicted value of the output indicating the operation result of the plant when multiple manipulated variable values are set
- An operation amount calculation unit that calculates a plurality of operation amount values that satisfy the predetermined condition using a regression model, and outputs a plurality of operation amount values calculated by the operation amount calculation unit Manipulation amount It comprises a part, a.
- FIG. 1 shows an overall configuration of a plant operation condition setting support system according to an embodiment.
- the plant operating condition setting support system 1 for supporting the setting of the operating conditions of the plant 3 includes a plant 3 for producing chemical products, industrial products, and the like, and a plurality of state quantity values indicating the operating conditions of the plant 3, The operation of the plant 3 when a plurality of manipulated variable values are set under the operation conditions indicated by the plurality of state variable values from the plurality of manipulated variable values set to control the operation of the plant 3. And a learning device 4 for learning a regression model 8 for calculating a predicted output value indicating the result.
- Each plant 3 includes a control target device 10 such as a reactor or a heating furnace installed in the plant 3, a control device 20 that sets an operation amount for controlling the operation of the control target device 10, and a learning device 4.
- An operation condition setting support device 30 that calculates values of a plurality of operation amounts to be set for controlling the operation of the plant 3 using the learned regression model 8 is provided.
- Each plant 3 and learning device 4 are connected via the Internet 2.
- the learning device 4 includes a result value acquisition unit 5, a learning unit 6, a regression model providing unit 7, and a regression model 8.
- these configurations are realized by a CPU of a computer, a memory, a program loaded in the memory, and the like, but here, functional blocks realized by their cooperation are illustrated. Accordingly, those skilled in the art will understand that these functional blocks can be realized in various forms by hardware only, software only, or a combination thereof.
- the regression model 8 is based on a plurality of state quantity values based on a plurality of state quantity values indicating the operation conditions of the plant 3 and a plurality of manipulated variable values set to control the operation of the plant 3. It is a model for calculating the predicted value of the output which shows the operation result of plant 3 when the value of a plurality of manipulated variables is set on the indicated operation condition. That is, the regression model 8 does not simulate individual processes executed in the plant 3, but calculates a predicted output value by a calculation using a plurality of state quantity values and a plurality of manipulated variable values. Is.
- the regression model 8 may calculate a predicted output value by a calculation using a plurality of state quantity values and a plurality of manipulated variable values and a calculation parameter for calculating a predicted output value. Good.
- the output value may be an arbitrary value indicating the operation result of the plant 3, and may be, for example, the amount of product produced by the plant 3, quality such as purity, yield, etc. It may be the amount, concentration, etc. of exhaust gas, etc. It may be the time, energy, amount, quality, temperature, etc. of the production of the product, and the production efficiency of the plant 3 etc. It may be a key performance evaluation index (KPI: Key Performance Indicator).
- KPI Key Performance Indicator
- the actual value acquisition unit 5 receives from the plant 3 a plurality of state quantity values indicating the operation conditions of the plant 3, a plurality of manipulated variable values set to control the operation of the plant 3, and a plurality of state quantities.
- the learning unit 6 learns the regression model 8 based on the plurality of actual values acquired by the actual value acquiring unit 5.
- the learning unit 6 inputs the values of the plurality of state quantities and the values of the plurality of manipulated variables acquired by the result value acquiring unit 5 to the regression model 8, the actual value of the output paired with those values
- the value of the calculation parameter may be adjusted so that a value close to is calculated.
- the learning unit 6 may learn the regression model 8 by supervised learning using the actual value of the output of the plant 3 as teacher data, or may learn the regression model 8 by any other known machine learning technique. Good.
- the accuracy of the regression model 8 can be improved by learning the regression model 8 using a large number of actual values, it is possible to calculate a predicted output value indicating the operation result of the plant 3 more accurately.
- a regression model 8 can be generated.
- the time and load required to generate the regression model 8 can be greatly reduced.
- the predicted output value can be calculated more accurately.
- Different regression models 8 may be learned for each plant 3, and regression models 8 common to a plurality of plants 3 may be learned using actual values from a plurality of plants 3 that execute the same type of process. .
- the regression model providing unit 7 provides the operating model setting support device 30 with the regression model 8 learned by the learning unit 6.
- the learning device 4 is shown as a single device, but the learning device 4 is realized by a plurality of servers using cloud computing technology, distributed processing technology, or the like. May be. Thereby, since a large amount of information collected from the plant 3 can be processed at high speed and the regression model 8 can be learned, the time required to improve the accuracy of the regression model 8 can be greatly shortened.
- FIG. 2 shows the configuration of the operating condition setting support device and the control device according to the embodiment.
- the control device 20 includes a control unit 21 and an operation panel 22.
- the operation panel 22 displays various state quantity values indicating the operation status of the plant 3, various operation amount set values set by the control device 20, and output values indicating the operation results of the plant 3 on the display device. In addition to the display, input of various set values of the operation amount is accepted from the operator.
- the control unit 21 includes an operation amount setting unit 23, a state amount acquisition unit 24, a state amount transmission unit 25, and a result value transmission unit 26. These functional blocks can also be realized in various forms by hardware only, software only, or a combination thereof.
- the operation amount setting unit 23 sets various operation amount setting values received from the operator through the operation panel 22, controls the control target device 10, and displays it on the display device of the operation panel 22.
- the state quantity acquisition unit 24 acquires various state quantity values indicating the operation status and operation result of the plant 3 from various sensors and measuring devices provided in the control target device 10 and the like, and displays the operation panel 22 on the display. Display on the device.
- the state quantity transmission unit 25 transmits the value of the state quantity acquired by the state quantity acquisition unit 24 to the driving condition setting support device 30.
- the actual value transmission unit 26 transmits the operation amount value set by the operation amount setting unit 23, the state amount value acquired by the state amount acquisition unit 24, and the output value to the learning device 4.
- the operating condition setting support device 30 includes a control unit 31 and a regression model 38.
- the control unit 31 includes a state amount acquisition unit 32, an operation amount calculation unit 33, an operation amount output unit 34, a regression model acquisition unit 35, a predicted value calculation unit 36, and a predicted value presentation unit 37. These functional blocks can also be realized in various forms by hardware only, software only, or a combination thereof.
- the regression model acquisition unit 35 acquires the regression model 8 learned by the learning device 4 and stores it as a regression model 38 in the storage device.
- the state quantity acquisition unit 32 acquires a plurality of state quantity values from the state quantity transmission unit 25 of the control device 20.
- the operation amount calculating unit 33 has a plurality of operation amounts such that the output value satisfies a predetermined condition. Is calculated using regression model 38.
- the operation amount output unit 34 outputs a plurality of operation amount values calculated by the operation amount calculation unit 33 to the control device 20.
- the output operation amount value may be presented on the operation panel 22 for reference when the operator manually inputs the operation amount value, or may be automatically input to the operation amount setting unit 23. Good.
- the operation amount calculation unit 33 calculates a plurality of operation amount values that can optimize the output value by applying an algorithm for solving the optimization problem to the output value according to the purpose. For example, when it is desired to obtain an optimum operation set point capable of maximizing the production efficiency of the final product, a plurality of state quantities acquired by the state quantity acquiring unit 32 are set as fixed values, and a plurality of operation amount values are set. As a variable, a plurality of manipulated variable values that maximize the predicted value of the KPI calculated by inputting to the regression model 8 for calculating the KPI indicating the production efficiency of the final product are obtained by an optimization problem solving algorithm. calculate. As an algorithm for solving the optimization problem, any known algorithm such as a gradient method or a Nelder-Meade method may be used.
- a predicted value such as KPI When a predicted value such as KPI is calculated by a simulator, it requires a considerable amount of calculation and time just to calculate a KPI value corresponding to one set of a plurality of state quantity values and a plurality of manipulated variable values. . Therefore, to calculate a large amount of predicted values of KPI over all the manipulated values of all the manipulated variables, and to search for a plurality of manipulated variable values that maximize the predicted value of KPI, May take weeks to months. In order to shorten the period required for the search, it is necessary to reduce the set for calculating the predicted value of KPI. Therefore, there is a possibility that a truly optimal operation set point cannot be searched.
- a highly accurate regression model 8 since a highly accurate regression model 8 can be obtained by machine learning, it corresponds to one set of a plurality of state quantity values and a plurality of manipulated variable values.
- the output value can be calculated quickly and accurately. Therefore, it is possible to search for and output a plurality of manipulated variable values that provide an output value that satisfies a predetermined condition in a short period of time. Can be set, and the operation of the plant 3 can be optimized.
- the predicted output value since a predicted output value corresponding to one set of a plurality of state quantity values and a plurality of manipulated variable values can be calculated in a short time, the predicted output value is calculated for a larger number of sets. The optimum operation set point can be searched. As a result, regardless of the optimization algorithm for any optimization problem, the global maximum value or the minimum value can be searched without being caught by the local extreme value, so that a true optimal solution can be calculated.
- the predicted value calculation unit 36 calculates an output predicted value by substituting a plurality of state quantities and a plurality of manipulated variables into the regression model 38.
- the predicted value presentation unit 37 presents the predicted output value calculated by the predicted value calculation unit 36 on the operation panel 22. For example, based on the value of the current state quantity acquired by the state quantity acquisition unit 32 and the setting values of a plurality of operation amounts actually set by the operation amount setting unit 23 of the control device 20, the current KPI and the like The output value may be calculated and presented.
- a predicted value for future output is calculated based on the state quantity value after the change and the current manipulated variable setting value. May be presented.
- the predicted output value after the change is calculated based on the current state value and the manipulated variable set value after the change. May be presented. Thereby, the setting of the operating condition by the operator can be appropriately supported.
- FIG. 3 shows an example of a display screen displayed on the display device of the operation panel.
- the process flow diagram of the plant 3 the value of the state quantity related to the operation condition, the value of the state quantity related to the operation result, and a set value of a plurality of manipulated variables are displayed.
- the operation amount calculation unit 33 uses the regression model 38 to calculate an optimal operation amount value that satisfies the condition.
- the operation amount output unit 34 displays the calculated operation amount value on the display screen. Further, the operation amount output unit 34 displays on the display screen a graph showing the change over time in the output value indicating the operation result of the plant 3 when the operation amount is changed to the calculated operation amount value and when the operation amount is not changed.
- the operation amount output unit 34 may display the value so as to be identifiable as to whether the value corresponds to the actual value or the predicted value.
- the operator determines a set value of the operation amount with reference to the presented value of the operation amount, and inputs it to the operation panel 22.
- the operation amount setting unit 23 controls the control target device 10 based on the input set value.
- the value of the operation amount output by the operation amount output unit 34 may be directly input to the operation amount setting unit 23 and automatically set in the control target device 10. In this case, the value of the operation amount automatically set in the control target device 10 may be presented on the operation panel 22 or may not be presented.
- the operation mode may be switchable between a manual mode in which the operator manually inputs.
- the technology of the present invention can be applied to both a continuous process plant and a batch process plant.
- 1 plant operation condition setting support system 3 plant, 4 learning device, 5 actual value acquisition unit, 6 learning unit, 7 regression model providing unit, 8 regression model, 10 controlled device, 20 control device, 22 operation panel, 23 operation Quantity setting part, 24 state quantity acquisition part, 25 state quantity transmission part, 26 actual value transmission part, 30 operating condition setting support device, 32 state quantity acquisition part, 33 manipulated variable calculation part, 34 manipulated variable output part, 35 regression model Acquisition unit, 36 predicted value calculation unit, 37 predicted value presentation unit, 38 regression model.
- the present invention can be used in a plant operating condition setting support system for supporting setting of operating conditions of a plant.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Manufacturing & Machinery (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Lifting Devices For Agricultural Implements (AREA)
- Control Of Turbines (AREA)
Abstract
Description
Claims (4)
- プラントの運転条件の設定を支援するためのプラント運転条件設定支援システムであって、
前記プラントの運転条件を示す複数の状態量の値、及び、前記プラントの運転を制御するために設定される複数の操作量の値から、前記複数の状態量の値により示される運転条件で前記複数の操作量の値が設定された場合の前記プラントの運転結果を示す出力の予測値を算出するための回帰モデルを学習させる学習装置と、
前記学習装置により学習された前記回帰モデルを使用して、前記プラントの運転を制御するために設定すべき前記複数の操作量の値を算出する運転条件設定支援装置と、
を備え、
前記学習装置は、
前記複数の状態量の値と、前記複数の操作量の値と、前記複数の状態量の値により示される運転条件で前記複数の操作量の値が設定された場合の前記プラントの運転結果を示す出力の値との組合せの実績値を取得する実績値取得部と、
前記実績値取得部により取得された複数の実績値に基づいて、前記回帰モデルを学習させる学習部と、
前記学習部により学習された前記回帰モデルを前記運転条件設定支援装置に提供する回帰モデル提供部と、
を備え、
前記運転条件設定支援装置は、
前記学習装置により学習された前記回帰モデルを取得する回帰モデル取得部と、
前記複数の状態量の値を取得する状態量取得部と、
前記状態量取得部により取得された前記複数の状態量により示される運転条件で前記プラントを運転する場合に、前記出力の値が所定の条件を充足するような前記複数の操作量の値を、前記回帰モデルを使用して算出する操作量算出部と、
前記操作量算出部により算出された前記複数の操作量の値を出力する操作量出力部と、
を備えることを特徴とするプラント運転条件設定支援システム。 - 前記操作量算出部は、最適化問題の解法アルゴリズムを前記出力の値に適用することにより、前記複数の操作量の値を算出することを特徴とする請求項1に記載のプラント運転条件設定支援システム。
- プラントの運転条件を示す複数の状態量の値と、前記プラントの運転を制御するために設定される複数の操作量の値と、前記複数の状態量の値により示される運転条件で前記複数の操作量の値が設定された場合の前記プラントの運転結果を示す出力の値との組合せの実績値を取得する実績値取得部と、
前記実績値取得部により取得された複数の実績値に基づいて、前記複数の状態量の値により示される運転条件で前記複数の操作量の値が設定された場合の前記プラントの運転結果を示す出力の予測値を算出するための回帰モデルを学習させる学習部と、
前記学習部により学習された前記回帰モデルを、前記プラントの運転を制御するために設定すべき前記複数の操作量の値を算出する運転条件設定支援装置に提供する回帰モデル提供部と、
を備えることを特徴とする学習装置。 - プラントの運転条件を示す複数の状態量の値、及び、前記プラントの運転を制御するために設定される複数の操作量の値から、前記複数の状態量の値により示される運転条件で前記複数の操作量の値が設定された場合の前記プラントの運転結果を示す出力の予測値を算出するための回帰モデルを学習させる学習装置から、前記学習装置により学習された回帰モデルを取得する回帰モデル取得部と、
プラントの運転条件を示す複数の状態量の値を取得する状態量取得部と、
前記状態量取得部により取得された前記複数の状態量により示される運転条件で前記プラントを運転する場合に、前記出力の値が所定の条件を充足するような前記複数の操作量の値を、前記回帰モデルを使用して算出する操作量算出部と、
前記操作量算出部により算出された前記複数の操作量の値を出力する操作量出力部と、
を備えることを特徴とする運転条件設定支援装置。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019571877A JP7144462B2 (ja) | 2018-02-15 | 2018-02-15 | プラント運転条件設定支援システム及び運転条件設定支援装置 |
RU2020128158A RU2767009C1 (ru) | 2018-02-15 | 2018-02-15 | Система поддержки установки условий работы завода, устройство обучения и устройство поддержки установки условий работы |
PCT/JP2018/005252 WO2019159280A1 (ja) | 2018-02-15 | 2018-02-15 | プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 |
AU2018408886A AU2018408886A1 (en) | 2018-02-15 | 2018-02-15 | Plant operation condition setting support system, learning device, and operation condition setting support device |
TW108105066A TWI801502B (zh) | 2018-02-15 | 2019-02-15 | 廠房運轉條件設定支援系統、學習裝置以及運轉條件設定支援裝置 |
US16/995,031 US11320811B2 (en) | 2018-02-15 | 2020-08-17 | Plant operating condition setting support system, learning device, and operating condition setting support device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2018/005252 WO2019159280A1 (ja) | 2018-02-15 | 2018-02-15 | プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/995,031 Continuation US11320811B2 (en) | 2018-02-15 | 2020-08-17 | Plant operating condition setting support system, learning device, and operating condition setting support device |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019159280A1 true WO2019159280A1 (ja) | 2019-08-22 |
Family
ID=67618913
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2018/005252 WO2019159280A1 (ja) | 2018-02-15 | 2018-02-15 | プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 |
Country Status (6)
Country | Link |
---|---|
US (1) | US11320811B2 (ja) |
JP (1) | JP7144462B2 (ja) |
AU (1) | AU2018408886A1 (ja) |
RU (1) | RU2767009C1 (ja) |
TW (1) | TWI801502B (ja) |
WO (1) | WO2019159280A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023119544A1 (ja) * | 2021-12-23 | 2023-06-29 | 千代田化工建設株式会社 | プログラム、情報処理装置、及び方法 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11868098B2 (en) * | 2021-11-12 | 2024-01-09 | Phaidra, Inc. | Chiller and pump control using customizable artificial intelligence system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11325433A (ja) * | 1998-05-15 | 1999-11-26 | Kobe Steel Ltd | 流動床式焼却炉の制御方法及びその装置 |
JP2001242905A (ja) * | 2000-02-28 | 2001-09-07 | Hitachi Ltd | プロセス制御方法および装置 |
JP2002091505A (ja) * | 2000-09-14 | 2002-03-29 | Toshiba Corp | モデル同定装置 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4017272B2 (ja) * | 1998-12-16 | 2007-12-05 | 中国電力株式会社 | プラント状態推定・予測装置及び方法 |
JP3712329B2 (ja) * | 1999-02-03 | 2005-11-02 | 株式会社日立製作所 | プロセスの制御装置 |
EP1288757A1 (de) * | 2001-08-07 | 2003-03-05 | Siemens Aktiengesellschaft | Verfahren und Prozessleitsystem zum Betrieb einer technischen Anlage |
CN107004060B (zh) * | 2014-11-25 | 2022-02-18 | Pdf决策公司 | 用于半导体制造工艺的经改进工艺控制技术 |
JP6501593B2 (ja) * | 2015-04-03 | 2019-04-17 | 住友化学株式会社 | 予測ルール生成システム、予測システム、予測ルール生成方法及び予測方法 |
US10671131B2 (en) * | 2015-06-05 | 2020-06-02 | Apple Inc. | Predictive control systems and methods |
MY190843A (en) | 2016-03-10 | 2022-05-12 | Jgc Corp | Method of determining mixed refrigerant composition for natural gas liquefying apparatus |
EP3364519A1 (en) * | 2017-02-15 | 2018-08-22 | ABB Schweiz AG | Method for controlling electric power conversion system and control arrangement for electric power conversion system |
WO2018149898A2 (en) * | 2017-02-16 | 2018-08-23 | Alcatel-Lucent Ireland Ltd | Methods and systems for network self-optimization using deep learning |
US10084805B2 (en) * | 2017-02-20 | 2018-09-25 | Sas Institute Inc. | Computer system to identify anomalies based on computer-generated results |
DE102017203836A1 (de) * | 2017-03-08 | 2018-09-13 | Siemens Aktiengesellschaft | Verfahren und System zum Bestimmen einer erwarteten Lebensdauer eines elektrischen Betriebsmittels |
US20190165966A1 (en) * | 2017-11-25 | 2019-05-30 | Ruptub Solutions Private Limited | Method and system for quality control of a facility based on machine learning |
GB201800473D0 (en) * | 2018-01-11 | 2018-02-28 | Microsoft Technology Licensing Llc | Knowledge base construction |
US10664999B2 (en) * | 2018-02-15 | 2020-05-26 | Adobe Inc. | Saliency prediction for a mobile user interface |
-
2018
- 2018-02-15 JP JP2019571877A patent/JP7144462B2/ja active Active
- 2018-02-15 WO PCT/JP2018/005252 patent/WO2019159280A1/ja active Application Filing
- 2018-02-15 RU RU2020128158A patent/RU2767009C1/ru active
- 2018-02-15 AU AU2018408886A patent/AU2018408886A1/en active Pending
-
2019
- 2019-02-15 TW TW108105066A patent/TWI801502B/zh active
-
2020
- 2020-08-17 US US16/995,031 patent/US11320811B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11325433A (ja) * | 1998-05-15 | 1999-11-26 | Kobe Steel Ltd | 流動床式焼却炉の制御方法及びその装置 |
JP2001242905A (ja) * | 2000-02-28 | 2001-09-07 | Hitachi Ltd | プロセス制御方法および装置 |
JP2002091505A (ja) * | 2000-09-14 | 2002-03-29 | Toshiba Corp | モデル同定装置 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023119544A1 (ja) * | 2021-12-23 | 2023-06-29 | 千代田化工建設株式会社 | プログラム、情報処理装置、及び方法 |
WO2023119711A1 (ja) * | 2021-12-23 | 2023-06-29 | 千代田化工建設株式会社 | プログラム、情報処理装置、及び方法 |
JPWO2023119544A1 (ja) * | 2021-12-23 | 2023-06-29 | ||
JP7354477B1 (ja) | 2021-12-23 | 2023-10-02 | 千代田化工建設株式会社 | プログラム、情報処理装置、及び方法 |
Also Published As
Publication number | Publication date |
---|---|
RU2767009C1 (ru) | 2022-03-16 |
AU2018408886A1 (en) | 2020-08-20 |
US11320811B2 (en) | 2022-05-03 |
JPWO2019159280A1 (ja) | 2021-01-28 |
US20200379452A1 (en) | 2020-12-03 |
JP7144462B2 (ja) | 2022-09-29 |
TWI801502B (zh) | 2023-05-11 |
TW201937319A (zh) | 2019-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11022965B2 (en) | Controlling multi-stage manufacturing process based on internet of things (IOT) sensors and cognitive rule induction | |
Zhu et al. | Toward a low cost and high performance MPC: The role of system identification | |
WO2019098158A1 (ja) | プラント管理システム及び管理装置 | |
WO2020039683A1 (ja) | 細胞培養支援装置の作動プログラム、細胞培養支援装置、細胞培養支援装置の作動方法 | |
CN112100916A (zh) | 用于构建强化学习模型的方法、装置、电子设备及介质 | |
CN105103059B (zh) | 用于在plc中实现模型预测性控制的系统和方法 | |
WO2019159280A1 (ja) | プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置 | |
JPWO2019234913A1 (ja) | 支援装置、学習装置、及びプラント運転条件設定支援システム | |
Lopez-Guede et al. | On the influence of the prediction horizon in dynamic matrix control | |
WO2016203757A1 (ja) | 制御装置、それを使用する情報処理装置、制御方法、並びにコンピュータ・プログラムが格納されているコンピュータ読み取り可能な記憶媒体 | |
JP2010146137A (ja) | パラメータ調整支援装置 | |
TWI833666B (zh) | 支援方法、支援裝置以及支援程式 | |
TWI830193B (zh) | 預測系統、資訊處理裝置以及資訊處理程式 | |
Muldbak et al. | Digital Twin of a pilot-scale bio-production setup | |
JP7384311B1 (ja) | 運転支援装置、運転支援方法及びプログラム | |
CN117930767A (zh) | 一种基于云边协同和hils的大型焙烧炉模拟装置 | |
JP2022148258A (ja) | シミュレーション装置、シミュレーションシステム、シミュレーション方法、およびシミュレーションプログラム | |
US20230138268A1 (en) | Control system, control method, and control program | |
JP2023019825A (ja) | 情報処理装置、表示制御方法および表示制御プログラム | |
JP2023019824A (ja) | 情報処理装置、情報処理方法、情報処理プログラム、モデル生成方法およびモデル生成プログラム | |
JP2023063039A (ja) | 火力発電プラントの運転支援装置、及び運転支援方法 | |
TW202411798A (zh) | 支援方法、支援裝置以及支援程式 | |
JP2023078710A (ja) | 装置、方法およびプログラム | |
JP2023019823A (ja) | 情報処理装置、情報処理方法、情報処理プログラム、モデル生成方法およびモデル生成プログラム | |
JP2023078694A (ja) | 装置、方法およびプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18906576 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2019571877 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2018408886 Country of ref document: AU Date of ref document: 20180215 Kind code of ref document: A |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18906576 Country of ref document: EP Kind code of ref document: A1 |