Data-driven approach to modeling sensors wherein optimal time delays are determined for a first set of predictors and stored as a second set of predictors

• US 8,577,822 B2
• Filed: 09/25/2009
• Issued: 11/05/2013
• Est. Priority Date: 09/25/2008
• Status: Active Grant

• Current Assignee: University of Iowa Research Foundation
• Original Assignee: University of Iowa Research Foundation
• Inventors: Kusiak, Andrew, Song, Zhe
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US12/567,380
• Publication Number:
  US 20100152905A1
• Time in Patent Office: 1,502 Days
• Field of Search: 706/12, 706/45, 706/62
• US Class Current: 706/45
• CPC Class Codes: G05B 17/02 electric

Abstract

A method, computer program product and system are provided for modeling non-controllable parameters affecting system performance. The method may include receiving historical values for each of a plurality of system parameters and grouping the system parameters into controllable, non-controllable, and performance parameters. The method may further include determining a first set of predictors from the non-controllable parameters using the historical values of these non-controllable parameters and, for each predictor in the first set, determining optimal time instances at which a value of each predictor is measured using non-uniform time scales. These optimal time instances may then be saved as a second set of predictors. One or more constraints may then be established for each of the controllable parameters. Finally, a dynamic model based on the second set of predictors, the controllable parameters, and the performance parameters may be constructed and optimized.

Claims

1. A method for optimizing a system, comprising:

receiving one or more historical values for each of a plurality of system parameters;

grouping the system parameters into controllable parameters, non-controllable parameters, and performance parameters;

determining a first set of predictors from the non-controllable parameters using the historical values of these non-controllable parameters;

for each predictor in the first set of predictors, determining one or more optimal time instances at which a value of each predictor in the first set of predictors is measured using non-uniform time scales;

storing the optimal time instances for each predictor in the first set of predictors as a second set of predictors;

establishing one or more constraints for each of the controllable parameters;

constructing a dynamic model based on the second set of predictors, the controllable parameters, and the performance parameters; and

optimizing the dynamic model with a non-gradient-based algorithm.

2. The method of claim 1, wherein establishing one or more constraints for each of the controllable parameters comprises applying one or more of physical constraints, historical values observed, and industrial practice.

3. The method of claim 1 further comprising determining accuracy of the dynamic model.

4. The method of claim 3, wherein if the accuracy of the dynamic model is not satisfactory, the method further comprises generating a plurality of dynamic models based at least in part on grouped historical values for the system parameters.

5. The method of claim 4, wherein grouped historical values are generated from an optimized subset of the controllable, non-controllable, and performance parameters.

6. The method of claim 1, wherein the non-gradient-based algorithm is an evolutionary computation algorithm.

7. The method of claim 1, wherein determining a first set of predictors comprises selecting one or more of the system parameters capable of being used to predict respective non-controllable parameters.

8. The method of claim 1 further comprising:

using the dynamic model to generate a value for at least one of the controllable parameters.

9. The method of claim 1, wherein the system is selected from a group consisting of a boiler-turbine system, a wind turbine, and a Heating, Ventilation and Air Conditioning system.

10. The method of claim 9, wherein the system comprises a boiler-turbine system, the non-controllable parameters comprise outside air temperature and river water temperature, and the performance parameters comprise one or more of temperature, megawatt load, unit heat rate, fuel electricity rate and turbine heat rate.

11. The method of claim 9, wherein the system comprises a wind turbine and the system parameters are selected from a group consisting of generator torque, wind speed, power produced, generator speed, generator bearing, blade pitch angle, yaw error and rotor speed.

12. The method of claim 9, wherein the system comprises a Heating, Ventilation and Air Conditioning system and the system parameters are selected from a group consisting of temperature, CO₂, relative humidity, light level, barometric pressure, relative humidity, dry-bulb temperature, direct normal solar irradiation, total horizontal irradiation, wind direction and wind speed.

13. A computer program product for optimizing a system, said computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, wherein the computer-readable program code portions comprise:

a first executable portion for receiving one or more historical values for each of a plurality of system parameters;

a second executable portion for grouping the system parameters into controllable parameters, non-controllable parameters, and performance parameters;

a third executable portion for determining a first set of predictors from the non-controllable parameters using the historical values of these non-controllable parameters;

a fourth executable portion for determining, for each predictor in the first set of predictors, one or more optimal time instances at which a value of each predictor in the first set of predictors is measured using non-uniform time scales;

a fifth executable portion for storing the optimal time instances for each predictor in the first set of predictors as a second set of predictors;

a sixth executable portion for establishing one or more constraints for each of the controllable parameters;

a seventh executable portion for constructing a dynamic model based on the second set of predictors, the controllable parameters, and the performance parameters; and

an eighth executable portion for optimizing the dynamic model with a non-gradient-based algorithm.

14. The computer program product of claim 13, wherein the sixth executable portion further comprises applying one or more of physical constraints, historical values observed, and industrial practice.

15. The computer program product of claim 13 further comprising:

a ninth executable portion for determining accuracy of the dynamic model.

16. The computer program product of claim 15, wherein if the accuracy of the dynamic model is not satisfactory, the computer program product further comprises:

a tenth executable portion for generating a plurality of dynamic models based at least in part on grouped historical values for the system parameters.

17. The computer program product of claim 16, wherein grouped historical values are generated from an optimized subset of the controllable, non-controllable, and performance parameters.

18. The computer program product of claim 13, wherein the non-gradient-based algorithm is an evolutionary computation algorithm.

19. The computer program product of claim 13, wherein the third executable portion further comprises selecting one or more of the system parameters capable of being used to predict respective non-controllable parameters.

20. A system comprising:

a processor configured to;

receive one or more historical values for each of a plurality of system parameters;

group the system parameters into controllable parameters, non-controllable parameters, and performance parameters;

determine a first set of predictors from the non-controllable parameters using the historical values of these non-controllable parameters;

for each predictor in the first set of predictors, determine one or more optimal time instances at which a value of each predictor in the first set of predictors is measured using non-uniform time scales;

store the optimal time instances for each predictor in the first set of predictors as a second set of predictors;

establish one or more constraints for each of the controllable parameters;

construct a dynamic model based on the second set of predictors, the controllable parameters, and the performance parameters; and

optimize the dynamic model with a non-gradient-based algorithm.