Model based optimization of multiple power generating units
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G05D-003/12
G05B-013/02
출원번호
UP-0547558
(2009-08-26)
등록번호
US-7844351
(2011-01-31)
발명자
/ 주소
Piche, Stephen
출원인 / 주소
Pegasus Technologies, Inc.
대리인 / 주소
Kusner & Jaffe
인용정보
피인용 횟수 :
16인용 특허 :
21
초록▼
A method and apparatus for optimizing the operation of a single or multiple power generating units using advanced optimization, modeling, and control techniques. In one embodiment, a plurality of component optimization systems for optimizing power generating unit components are sequentially coordina
A method and apparatus for optimizing the operation of a single or multiple power generating units using advanced optimization, modeling, and control techniques. In one embodiment, a plurality of component optimization systems for optimizing power generating unit components are sequentially coordinated to allow optimized values determined by a first component optimization system to be fed forward for use as an input value to a subsequent component optimization system. A unit optimization system may be provided to determine goals and constraints for the plurality of component optimization systems in accordance with economic data. In one embodiment of the invention, a multi-unit optimization system is provided to determine goals and constraints for component optimization systems of different power generating units. Both steady state and dynamic models are used for optimization.
대표청구항▼
Having described the invention, the following is claimed: 1. A computer system programmed to optimize operation of a plurality of power generating units, each of said plurality of power generating units comprised of a plurality of components, the computer system comprising: a plurality of multi-com
Having described the invention, the following is claimed: 1. A computer system programmed to optimize operation of a plurality of power generating units, each of said plurality of power generating units comprised of a plurality of components, the computer system comprising: a plurality of multi-component optimization systems, each multi-component optimization system respectively associated with one of said plurality of power generating units, wherein each multi-component optimization system is comprised of a plurality of component optimization systems, each component optimization system associated with optimizing one component of the respective power generating unit, wherein each component optimization system includes: a model of the component, said model receiving input values associated with manipulated variables and disturbance variables, and predicting an output value for at least one controlled variable associated with operation of said component, wherein the manipulated variables are variables changeable by an operator or a component optimization system to affect the at least one controlled variable, and an optimizer for determining optimal setpoint values for manipulated variables associated with control of the component, said optimal setpoint values determined in accordance with one or more goals and constraints; said plurality of multi-component optimization systems in communication with a respective distributed control system (DCS) to provide optimal setpoint values thereto, wherein the respective DCS provides regulation control of the respective power generating unit; and a multi-unit optimization system for determining optimal values of said one or more goals and said constraints for operation of each of the component optimization system associated with each of said plurality of power generating units, wherein the multi-unit optimization system includes: a multi-unit model for each of said components, each said multi-unit model receiving input values associated with manipulated variables and disturbance variables and predicting an output value for at least one controlled variable associated with operation of said component, and a multi-unit optimizer for determining optimal setpoint values for manipulated variables and controlled variables associated with control of the component, said optimal setpoint values determined in accordance with one or more goals associated with operation of the power generating units and constraints associated with operation of the power generating units, wherein said optimal setpoint values determined by the multi-unit optimizer are used to determine said one or more goals and said constraints for each of the component optimization systems associated with each of said plurality of power generating units. 2. A computer system according to claim 1, wherein said multi-unit model and said model of each component optimization system are selected from the group consisting of the following: a steady state model and a dynamic model. 3. A model computer system according to claim 1, wherein said multi-unit model and said model of each component optimization system are selected from the group consisting of the following: a neural network model, an empirically developed model, a model developed using “first principles,” a support vector machine (SVM) model, a model developed by linear regression and a model based upon heuristics. 4. A computer system according to claim 1, wherein said multi-unit optimizer and said optimizer of each component optimization system are selected from the group consisting of: linear programming, quadratic programming, mixed integer non-linear programming (NLP), stochastic programming, global non-linear programming, genetic algorithms, and particle/swarm techniques. 5. A computer system according to claim 1, wherein said optimizer of each component optimization system determines said optimal setpoint values for said manipulated variables by accessing said model to minimize a cost value of a cost function while observing said constraints, said cost value affected by the value of said manipulated variables. 6. A computer system according to claim 1, wherein said constraints include at least one of the following: a limit on emissions of NOx, a limit on emissions of SO2, a limit on emissions of CO2, a limit on emissions of CO, a limit on emissions of mercury, a limit on ammonia slip, and a limit on emissions of particulate matter. 7. A computer system according to claim 1, wherein said plurality of components includes at least one of the following: a fuel blending system, a boiler, a selective catalytic reduction (SCR) system, an electro-static precipitator (ESP) and a flue gas desulfurization (FGD) system. 8. A computer system according to claim 1, wherein said computer system further comprises a control system for each power generating unit, each said control system providing regulatory control of said respective power generating unit, said control system receiving said optimal setpoint values from each of said plurality of component optimization systems. 9. A computer system according to claim 1, wherein said multi-unit optimizer determines said optimal setpoint values by accessing said multi-unit model to minimize a cost value of a unit cost function while observing said constraints, said unit cost function including economic data associated with operation of said plurality of power generating units. 10. A computer system according to claim 9, wherein said economic data associated with operation of said plurality of power generating units relates to at least one of the following: cost of fuels, cost of additives, cost of ammonia, cost of limestone used in an FGD, cost of internal electric power for the power generating unit, price of electricity, cost of NOx credits, cost of SO2 credits and price of gypsum. 11. A computer system according to claim 9, wherein said multi-unit model is selected from the group consisting of the following: a steady state model and a dynamic model. 12. A method for optimizing operation of a plurality of power generating units, each of said plurality of power generating units comprised of a plurality of components, the method comprising: determining one or more goals and constraints associated with operation of the plurality of power generating units using a multi-unit optimization system; and providing said one or more goals and constraints to a plurality of multi-component optimization systems, each multi-component optimization system respectively associated with one of said plurality of power generating units, wherein each multi-component optimization system is comprised of a plurality of component optimization systems, each component optimization system associated with optimizing one component of the respective power generating unit, wherein each component optimization system includes: a model of the component, said model receiving input values associated with manipulated variables and disturbance variables, and predicting an output value for at least one controlled variable associated with operation of the component, wherein the manipulated variables are variables changeable by an operator or a component optimization system to affect the at least one controlled variable, and an optimizer for determining optimal setpoint values for manipulated variables associated with control of the component, said optimal setpoint values determined in accordance with one or more goals and constraints determined by the multi-unit optimization system; said plurality of multi-component optimization systems in communication with a respective distributed control system (DCS) to provide optimal setpoint values thereto, wherein the respective DCS provides regulation control of the respective power generating unit, operating said components of each of said plurality of power generating units in accordance with the optimal setpoint values. 13. A method according to claim 12, wherein said multi-unit optimization system includes: a multi-unit model for each of said components, each said multi-unit model receiving input values associated with manipulated variables and disturbance variables and predicting an output value for at least one controlled variable associated with operation of said component, and a multi-unit optimizer for determining optimal values for at least one of manipulated variables and controlled variables associated with control of the component, said optimal values determined in accordance with one or more goals associated with operation of the power generating unit and constraints associated with operation of the power generating unit. 14. A method according to claim 13, wherein said multi-unit model and said model of each component optimization system are selected from the group consisting of the following: a steady state model and a dynamic model. 15. A method according to claim 13, wherein said multi-unit model and said model of each component optimization system are selected from the group consisting of the following: a neural network model, an empirically developed model, a model developed using “first principles,” a support vector machine (SVM) model, a model developed by linear regression and a model based upon heuristics. 16. A method according to claim 13, wherein said multi-unit optimizer and said optimizer of each component optimization system are selected from the group consisting of: linear programming, quadratic programming, mixed integer non-linear programming (NLP), stochastic programming, global non-linear programming, genetic algorithms, and particle/swarm techniques. 17. A method according to claim 13, wherein said optimizer of each component optimization system determines said optimal setpoint values for said manipulated variables by accessing said model to minimize a cost value of a cost function while observing said constraints, said cost value affected by the value of said manipulated variables. 18. A method according to claim 13, wherein said multi-unit optimizer determines said optimal setpoint values by accessing said multi-unit model to minimize a cost value of a multi-unit cost function while observing said constraints, said multi-unit cost function including economic data associated with operation of said plurality of power generating units. 19. A method according to claim 18, wherein said economic data associated with operation of said plurality of power generating units relates to at least one of the following: cost of fuels, cost of additives, cost of ammonia, cost of limestone used in an FGD, cost of internal electric power for the power generating unit, price of electricity, cost of NOx credits, cost of SO2 credits and price of gypsum. 20. A method according to claim 13, wherein said multi-unit model is selected from the group consisting of the following: a steady state model and a dynamic model. 21. A method according to claim 12, wherein said constraints include at least one of the following: a limit on emissions of NOx, a limit on emissions of SO2, a limit on emissions of CO2, a limit on emissions of CO, a limit on emissions of mercury, a limit on ammonia slip, and a limit on emissions of particulate matter. 22. A method according to claim 12, wherein said plurality of components includes at least one of the following: a fuel blending system, a boiler, a selective catalytic reduction (SCR) system, an electro-static precipitator (ESP) and a flue gas desulfurization (FGD) system.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (21)
Hartman, Eric Jon; Peterson, Carsten; Piche, Stephen, Bayesian neural networks for optimization and control.
Keeler James David ; Hartman Eric J. ; Liano Kadir, Method and apparatus for determining the sensitivity of inputs to a neural network on output parameters.
Martin Gregory D. ; Boe Eugene ; Piche Stephen ; Keeler James David ; Timmer Douglas ; Gerules Mark ; Havener John P., Method and apparatus for dynamic and steady state modeling over a desired path between two end points.
Gregory D. Martin ; Eugene Boe ; Stephen Piche ; James David Keeler ; Douglas Timmer ; Mark Gerules ; John P. Havener, Method and apparatus for modeling dynamic and steady-state processes for prediction, control and optimization.
Ferguson, Ralph Bruce; Hartman, Eric J.; Johnson, William Douglas; Hurley, Eric S., System and method for historical database training of support vector machines.
Keeler James D. (Austin TX) Havener John P. (Austin TX) Godbole Devendra (Austin TX) Ferguson Ralph B. (Austin TX), Virtual continuous emission monitoring system with sensor validation.
Wichmann, Lisa Anne; Pandey, Achalesh Kumar; Pool, Eric Thomas; Raczynski, Christopher Michael; Pamujula, Suresh, Methods and systems for enhancing control of power plant generating units.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.