A controller for a building system receives training data that includes input data and output data. The output data measures a state of the building system affected by both the input data and an extraneous disturbance. The controller performs a two-stage optimization process to identify system param
A controller for a building system receives training data that includes input data and output data. The output data measures a state of the building system affected by both the input data and an extraneous disturbance. The controller performs a two-stage optimization process to identify system parameters and Kalman gain parameters of a dynamic model for the building system. During the first stage, the controller filters the training data to remove an effect of the extraneous disturbance from the output data and uses the filtered training data to identify the system parameters. During the second stage, the controller uses the non-filtered training data to identify the Kalman gain parameters. The controller uses the dynamic model with the identified system parameters and Kalman gain parameters to generate a setpoint for the building system. The building system uses the setpoint to affect the state measured by the output data.
대표청구항▼
1. A controller for a building system, the controller comprising: a communications interface configured to receive training data comprising input data and output data, the output data indicative of a state of the building system affected by both the input data and an extraneous disturbance comprisin
1. A controller for a building system, the controller comprising: a communications interface configured to receive training data comprising input data and output data, the output data indicative of a state of the building system affected by both the input data and an extraneous disturbance comprising an uncontrolled input to the building system; anda processing circuit comprising a processor and memory, wherein the processing circuit is configured to perform a two-stage optimization process to identify system parameters and Kalman gain parameters of a dynamic model for the building system, the two-stage optimization process comprising: a first stage in which the processing circuit is configured to filter the training data to remove an effect of the extraneous disturbance from the output data and uses the filtered training data to identify the system parameters, anda second stage in which the processing circuit is configured to use the non-filtered training data to identify the Kalman gain parameters;wherein the processing circuit is configured to use the dynamic model to generate a setpoint for the building system and the building system is configured to use the setpoint to affect the state indicated by the output data. 2. The controller of claim 1, wherein the extraneous disturbance comprises an uncontrolled thermal input to the building system. 3. The controller of claim 1, wherein the system parameters describe energy transfer characteristics of the building system and are independent of the extraneous disturbance. 4. The controller of claim 1, wherein the Kalman gain parameters account for the extraneous disturbance. 5. The controller of claim 1, wherein the state of the building system comprises at least one of a temperature of the building system, a power use of the building system, a humidity of the building system, an enthalpy of the building system, and a flow rate within the building system. 6. The controller of claim 1, wherein the dynamic model is a physics-based parameterization of the building system. 7. The controller of claim 1, wherein the first stage of the two-stage optimization process comprises: filtering the input data to create filtered input data and filtering the output data to create filtered output data;generating model-predicted filtered output data based on a set of estimated system parameters and the filtered input data;generating a first error cost function that defines a first error cost based on a difference between the filtered output data and the model-predicted filtered output data;adjusting the estimated system parameters to minimize the first error cost. 8. The controller of claim 1, wherein: the extraneous disturbance comprises a slowly changing disturbance to the building system; andthe processing circuit is configured to filter the training data using a high-pass filter to remove an effect of the slowly changing disturbance from the output data. 9. The controller of Claim 7, wherein the second stage of the two-stage optimization process comprises: generating model-predicted output data based on a set of estimated Kalman gain parameters and the non-filtered input data;generating a second error cost function that defines a second error cost based on a difference between the output data and the model-predicted output data;adjusting the estimated Kalman gain parameters to minimize the second error cost. 10. The controller of claim 1, wherein the processing circuit identifies the Kalman gain parameters during the second stage of the two-stage optimization process while holding the system parameters at constant values identified during the first stage of the two-stage optimization process. 11. A controller for a building system, the controller comprising: a communications interface configured to receive training data comprising input data and output data, the output data indicative of a state of the building system affected by both the input data and an extraneous disturbance comprising an uncontrolled input to the building system; anda processing circuit comprising a processor and memory, wherein the processing circuit is configured to perform a two-stage optimization process to identify parameters of a dynamic model for the building system, the two-stage optimization process comprising: a first stage in which the processing circuit is configured to identify system parameters of the dynamic model, anda second stage in which the processing circuit is configured to identify Kalman gain parameters of the dynamic model while holding the system parameters at constant values identified during the first stage;wherein the processing circuit is configured to use the dynamic model to generate a setpoint for the building system and the building system is configured to use the setpoint to affect the state indicated by the output data. 12. The controller of claim 11, wherein: the extraneous disturbance comprises a slowly changing disturbance to the building system; andthe processing circuit is configured to filter the training data using a high-pass filter to remove an effect of the slowly changing disturbance from the output data. 13. The controller of claim 11, wherein the extraneous disturbance comprises an uncontrolled thermal input to the building system. 14. The controller of claim 11, wherein the first stage of the two-stage optimization process comprises: filtering the training data to remove an effect of the extraneous disturbance from the output data; andusing the filtered training data to identify the system parameters. 15. The controller of claim 11, wherein the system parameters describe energy transfer characteristics of the building system and are independent of the extraneous disturbance. 16. The controller of claim 11, wherein: the Kalman gain parameters account for the extraneous disturbance; andthe second stage of the two-stage optimization process comprises using non-filtered training data to identify the Kalman gain parameters. 17. The controller of claim 11, wherein the state of the building system comprises at least one of a temperature of the building system, a power use of the building system, a humidity of the building system, an enthalpy of the building system, and a flow rate within the building system. 18. A computer-implemented method for identifying parameters of a dynamic model for a building system, the method comprising: receiving, at a controller for the building system, training data comprising input data and output data, the output data indicative of a state of the building system affected by both the input data and an extraneous disturbance comprising an uncontrolled input to the building system;performing, by the controller, a two-stage optimization process to identify system parameters and Kalman gain parameters of the dynamic model, the two-stage optimization process comprising: a first stage in which the controller filters the training data to remove an effect of the extraneous disturbance from the output data and uses the filtered training data to identify the system parameters, anda second stage in which the controller uses the non-filtered training data to identify the Kalman gain parameters; andusing the dynamic model to generate, by the controller, a setpoint for the building system, wherein the building system is configured to use the setpoint to affect the state indicated by the output data. 19. The method of claim 18, wherein the state of the building system comprises at least one of a temperature of the building system, a power use of the building system, a humidity of the building system, an enthalpy of the building system, and a flow rate within the building system. 20. The method of claim 18, wherein: the system parameters describe energy transfer characteristics of the building system and are independent of the extraneous disturbance; andthe Kalman gain parameters account for the extraneous disturbance.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (101)
Fan,Junqiang; Backstrom,Johan U., Apparatus and method for coordinating controllers to control a paper machine or other machine.
Gloudeman Jeffrey J. ; Gottschalk Donald A. ; Kraemer C. Richard ; Rasmussen David E., Common object architecture supporting application-centric building automation systems.
Morshedi Abdol M. (Houston TX) Cutler Charles R. (Houston TX) Fitzpatrick Thomas J. (Katy TX) Skrovanek Thomas A. (Houston TX), Dynamic process control.
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.
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.
Vouzis, Panagiotis; Bleris, Leonidas; Arnold, Mark G.; Kothare, Mayuresh V., Iterative matrix processor based implementation of real-time model predictive control.
Boe, Eugene; Piche, Stephen; Martin, Gregory D., Method and apparatus for attenuating error in dynamic and steady-state processes for prediction, control, and optimization.
Davis Glenn A. ; Poche David M., Method and apparatus using distributed intelligence for applying real time pricing and time of use rates in wide area network including a headend and subscriber.
Pekar, Jaroslav; Strewart, Greg; Kihas, Dejan; Borrelli, Francesco, Method and system for combining feedback and feedforward in model predictive control.
Lu Zhuxin J. (Glendale AZ) MacArthur J. Ward (Scottsdale AZ) Horn Brian C. (Phoenix AZ), Method of multivariable predictive control utilizing range control.
Pekar, Jaroslav; Borralli, Francesco; Stewart, Gregory, Methods and systems for the design and implementation of optimal multivariable model predictive controllers for fast-sampling constrained dynamic systems.
Stewart,Gregory E.; Kolavennu,Soumitri N.; Borrelli,Francesco; Hampson,Gregory J.; Shahed,Syed M.; Samad,Tariq; Rhodes,Michael L., Multivariable control for an engine.
Sloop, Christopher Dale; Oberholzer, David; Marshall, Robert S.; Kim, Jungho; Siemann, Michael, Optimizing and controlling the energy consumption of a building.
Bohrer, Philip J.; Merten, Gregory J.; Schnell, Robert J.; Atlass, Michael B., Profile based method for deriving a temperature setpoint using a `delta` based on cross-indexing a received price-point level signal.
MacArthur J. Ward (Minneapolis MN) Wahlstedt David A. (Minneapolis MN) Woessner Michael A. (Minneapolis MN) Foslien Wendy K. (Minneapolis MN), Receding horizon based adaptive control having means for minimizing operating costs.
Lu, Joseph; Morningred, John Duane, System and method for continuous supply chain control and optimization using stochastic calculus of variations approach.
Plumer, Edward Stanley; Sayyar-Rodsari, Bijan; Schweiger, Carl Anthony; Ferguson, II, Ralph Bruce; Johnson, William Douglas; Axelrud, Celso, System and method for enterprise modeling, optimization and control.
Das,Indraneel; Rey,Gonzalo, System and method for exploiting a good starting guess for binding constraints in quadratic programming with an infeasible and inconsistent starting guess for the solution.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.