The present invention provides novel techniques for graphically modeling, displaying, and interacting with parametric hybrid models used to optimize and control components of industrial plants and enterprises. In particular, a graphical modeling tool of a control/optimization system for controlling
The present invention provides novel techniques for graphically modeling, displaying, and interacting with parametric hybrid models used to optimize and control components of industrial plants and enterprises. In particular, a graphical modeling tool of a control/optimization system for controlling a plant or enterprise is configured to transmit a graphical user interface to a user, wherein the graphical user interface enables a plurality of command inputs relating to a plurality of parametric hybrid models based on a security access level of the user. The parametric hybrid models may be displayed by the graphical user interface as nodes of a network with connections connecting the nodes. The user may graphically manipulate the nodes and connections associated with the parametric hybrids models to either modify optimization constraints of the model network, or actually modify the manner in which the parametric hybrid models function (e.g., inputs, outputs, parameters, and so forth, of the parametric hybrid models), depending on the access level of the user.
대표청구항▼
1. An enterprise-integrated system optimizer, comprising a non-transitory computer-readable medium having computer instructions encoded thereon, wherein the computer instructions comprise instructions for: transmitting a graphical representation of a well-posed optimization problem comprising an int
1. An enterprise-integrated system optimizer, comprising a non-transitory computer-readable medium having computer instructions encoded thereon, wherein the computer instructions comprise instructions for: transmitting a graphical representation of a well-posed optimization problem comprising an interconnected network of nodes and connections to a remote electronic device, wherein the optimization problem relates to an enterprise-integrated system and comprises a parametric objective function, one or more decision variables, and one or more parametric constraints, wherein at least one of the nodes comprises a parametric hybrid model whose output is a decision variable in the parametric objective function, and at least one connection comprises a parametric hybrid model that describes parametric constraints on at least one decision variable in the optimization problem, and the graphical representation of the optimization problem enables graphically modifying at least one of the parametric objective function, a decision variable, and a parametric constraint of the optimization problem by interaction with a node or a connection, wherein the parametric hybrid model for a node or connection comprises: an empirical model configured to generate a parameter model input based at least in part on a variable input to the node or connection;a parameter model configured to generate a fundamental model parameter based at least in part on the parameter model input and the variable input; anda parametric first principles model configured to generate a variable output of the node or connection based at least in part on the variable input and the fundamental model parameter;receiving a user command input relating to a node or connection in the graphical representation of the optimization problem;processing the user command input, wherein processing the user command input comprises modifying the optimization problem; andexecuting the optimizer with the modified optimization problem to determine current and future values of decision variables to implement in the enterprise-integrated system. 2. The system optimizer of claim 1, wherein executing the optimizer with the modified optimization problem comprises modifying at least one decision variable to adjust operation of the enterprise-integrated system. 3. The system optimizer of claim 1, wherein receiving the user command input comprises receiving a user command input to add or delete a node or connection. 4. The system optimizer of claim 1, wherein modifying the optimization problem comprises modifying a node parametric hybrid model, a connection parametric hybrid model, or both, wherein the node parametric hybrid model is configured to model a component in the enterprise-integrated system and the connection parametric hybrid model is configured to model a constraint in the optimization problem. 5. The system optimizer of claim 1, wherein the computer instructions comprise instructions for determining an access level of a user, wherein receiving the user command input comprises receiving a user command input from an engineer-level user of the enterprise, and processing the user command input comprises modifying one or more parametric hybrid models. 6. The system optimizer of claim 1, wherein the computer instructions comprise instructions for determining an access level of a user, wherein receiving the user command input comprises receiving a user command input from a manager-level user of the enterprise, and processing the user command input comprises modifying a constraint of the optimization problem. 7. The system optimizer of claim 1, wherein the computer instructions comprise instructions for determining an access level of a user, and receiving approval of modifications to the optimization problem committed by the user from another appropriately authorized user. 8. The system optimizer of claim 1, wherein executing the optimizer with the modified optimization problem comprises automatically modifying at least one parametric hybrid model along a predicted operation trajectory of the enterprise-integrated system modifying the optimization problem to adjust operation of the enterprise-integrated system, wherein a cost of adjusting operation is presented. 9. The system optimizer of claim 1, wherein executing the optimizer with the modified optimization problem comprises determining an optimization solution based at least in part on a previous optimization solution. 10. The system optimizer of claim 1, wherein modifying the optimization problem comprises convexification of one or more of the parametric hybrid models along a predicted operation trajectory of the enterprise-integrated system, wherein the parameter model, the parametric first-principles model, or both are convexified around the predicted operation trajectory. 11. The system optimizer of claim 1, wherein processing the user command input comprises determining model quality of one or more models of components in the enterprise-integrated system. 12. A method, comprising: transmitting a graphical representation of awell-posed optimization problem comprising an interconnected network of nodes and connections to an electronic device, wherein the optimization problem relates to a plant in an enterprise-integrated system and comprises a parametric objective function, one or more decision variables, and one or more parametric constraints, wherein at least one of the nodes comprises a parametric hybrid model that describes how decision variables influence the parametric objective function, at least one connection comprises a parametric hybrid model that describes parametric constraints on decision variables in connected nodes, and the graphical representation of the optimization problem enables graphically modifying at least one of the parametric objective function, a decision variable, and a parametric constraint of the optimization problem by interaction with a node or a connection, wherein the parametric hybrid model for a node or connection comprises: an empirical model configured to generate a parameter model input based at least in part on a variable input to the node or connection;a parameter model configured to generate a fundamental model parameter based at least in part on the parameter model input and the variable input; anda parametric first principles model configured to generate a variable output of the node or connection based at least in part on the variable input and the fundamental model parameter;receiving a user command input relating to a node or connection in the graphical representation of the optimization problem;processing the user command input, wherein processing the user command input comprises modifying the optimization problem; andexecuting optimization with the modified optimization problem to determine current and future values of decision variables to implement in the plant. 13. The method of claim 12, wherein receiving the user command input comprises receiving a user command input to add or delete a node or connection. 14. The method of claim 12, wherein modifying the optimization problem comprises modifying a node parametric hybrid model, a connection parametric hybrid model, or both, wherein the node parametric hybrid model is configured to model a component in the plant and the connection parametric hybrid model is configured to model a constraint in the optimization problem. 15. The method of claim 12, comprising determining an access level of a user, wherein receiving the user command input comprises receiving a user command input from an engineer-level user of the plant, and processing the user command input comprises modifying one or more parametric hybrid models. 16. The method of claim 12, comprising determining an access level of a user, wherein receiving the user command input comprises receiving a user command input from a manager-level user of the plant, and processing the user command input comprises modifying a constraint of the optimization problem. 17. The method of claim 16, comprising receiving approval of the modified constraint from an engineer-level user of the enterprise prior to modifying an optimization solution of the optimization problem. 18. The method of claim 12, wherein executing the optimization with the modified optimization problem comprises automatically modifying at least one parametric hybrid model along a predicted operation trajectory of the plant modifying the optimization problem to adjust operation of the plant, wherein modifying the optimization problems comprises convexification of one or more of the parametric hybrid models along the predicted operation trajectory, wherein the parameter model, the parametric first-principles model, or both are convexified around the predicted operation trajectory. 19. The method of claim 12, wherein executing the optimization with the modified optimization problem comprises determining an optimization solution based at least in part on a previous optimization solution. 20. A non-transitory computer-readable medium having computer instructions encoded thereon, wherein the computer instructions comprise instructions for: determining an access level of a user operating an electronic device;transmitting a graphical representation of awell-posed optimization problem comprising an interconnected network of nodes and connections to an electronic device, wherein the optimization problem relates to an enterprise-integrated system and comprises a parametric objective function, one or more decision variables, and one or more parametric constraints, wherein at least one of the nodes comprises a parametric hybrid model that describes how decision variables influence the parametric objective function, and at least one connection comprises a parametric hybrid model that describes parametric constraints on decision variables in connected nodes, and the graphical representation of the optimization problem enables graphically modifying at least one of the parametric objective function, a decision variable, and a parametric constraint of the optimization problem by interaction with a node or a connection, wherein the parametric hybrid model for a node or connection comprises: an empirical model configured to generate a parameter model input based at least in part on a variable input to the node or connection;a parameter model configured to generate a fundamental model parameter based at least in part on the parameter model input and the variable input; anda parametric first principles model configured to generate a variable output of the node or connection based at least in part on the variable input and the fundamental model parameter;receiving a user command input relating to a node or connection in the graphical representation of the optimization problem; andprocessing the user command input according to the access level of the user, wherein processing the user command input comprises modifying the optimization problem by convexification of a node parametric hybrid model, a connection parametric hybrid model, or both, along a predicted operation trajectory of the enterprise-integrated system, wherein the parameter model, the parametric first-principle model, or both are convexified along the predicted operation trajectory; andexecuting optimization with the modified optimization problem without adjusting the objective function and the constraints to determine current and future values for decision variables to implement in the enterprise-integrated system during the predicted operation trajectory.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (22)
Chia, Tien-Li; Lefkowitz, Irving; Brosilow, Coleman B.; Haji-Valizadeh, Alireza; Parvez, Shahid; Nagle, John T., Apparatus and method for model-based control.
Berger,Torsten; Payne,Bradley A.; Shannon, III,Walter C., Apparatus and methods for modifying a model of an object to enforce compliance with a manufacturing constraint.
Liebl Ronald J. (Mukwonago WI) Bronikowski Alan J. (South Milwaukee WI) Holdorf Thomas C. (Mukwonago WI) Strojny Lawrence J. (Oostburg WI) Tellier Mark W. (Milwaukee WI), Energy control system.
Ristanovic,Petar; Bjelogric,Milan; Frame,James G.; Aganagic,Mohammed; Shahidehpour,Mohammed, Exchange, scheduling and control system for electrical power.
Mehta,Ashish; Wojsznis,Peter; Wojsznis,Wilhelm K.; Blevins,Terrence L.; Thiele,Dirk; Ottenbacher,Ron; Nixon,Mark, Integrated model predictive control and optimization within a process control system.
Castelli, Gennaro; Hackett, Michael; Howard, Michael Quinn; Jones, Lawrence Edmund; Shung, HuiChu Su; Brand, Heath Daniel, Methods for assessing reliability of a utility company's power system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.