Systems and methods for condition-based power plant sensor calibration

• US 8,892,382 B2
• Filed: 09/26/2011
• Issued: 11/18/2014
• Est. Priority Date: 09/26/2011
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (GE Vernova, Inc.)
• Original Assignee: General Electric Company
• Inventors: Wang, Difei, Calleros, Erwing, Chillar, Rahul J., Mestroni, Julio
• Primary Examiner(s): Raymond, Edward
• Application Number:
  US13/245,486
• Publication Number:
  US 20130080100A1
• Time in Patent Office: 1,149 Days
• Field of Search: 702/117, 702/118, 702182-185, 702/188
• US Class Current: 702/85
• CPC Class Codes: G05B 23/0208 characterized by the configuration of the monitoring system

Abstract

Embodiments of the invention can provide systems and methods for condition-based power plant sensor calibration. According to one embodiment of the invention, a system can be provided. The system can include a computer processor. The system can also include a memory operable to store computer-executable instructions operable to: receive data from the one or more power plant sensors; reconcile detected errors within the data from the one or more power plant sensors; calibrate the one or more power plant sensors based at least in part on the detected errors within the data; generate at least one performance model based at least in part on the reconciled data from the one or more power plant sensors; detect anomalies within the at least one performance model; and tune the at least one performance model to account for the anomalies.

Claims

1. A method for condition-based power plant sensor calibration, comprising:

receiving data from one or more power plant sensors;

reconciling errors detected within the data from the one or more power plant sensors;

calibrating the one or more power plant sensors based at least in part on the errors detected within the data;

generating at least one performance model based at least in part on the reconciled data from the one or more power plant sensors, wherein the reconciling errors comprises giving more weight to the one or more power plant sensors that are known to be more reliable, based at least in part on at least one of a calibration history or trends of the one or more power plant sensors stored in a database;

detecting anomalies within the at least one performance model; and

tuning the at least one performance model to account for the anomalies.

2. The method of claim 1, wherein reconciling errors detected within the data from the one or more power plant sensors is based at least in part on accessing at least one database of calibration history and trends for the one or more power plant sensors.

3. The method of claim 1, wherein detecting anomalies within the at least one performance model is based at least in part on accessing at least one database of known performance models or actual power plant performance results.

4. The method of claim 1, wherein the detected anomalies within the at least one performance model are based at least in part on equipment performance degradation.

5. The method of claim 1, wherein the errors detected within the data from the one or more power plant sensors are based at least in part on sensor drifting.

6. The method of claim 1, further comprising:

determining an optimal calibration interval for the one or more power plant sensors based at least in part on the errors detected within the data.

7. The method of claim 1, wherein the data received from the one or more power plant sensors is from a power plant control system or a plant historian module.

8. A system for condition-based power plant sensor calibration, comprising:

a computer processor; and

a memory in communication with the computer processor operable to store computer-executable instructions operable to;

receive data from one or more power plant sensors;

reconcile errors detected within the data from the one or more power plant sensors;

calibrate the one or more power plant sensors based at least in part on the errors detected within the data;

generate at least one performance model based at least in part on the reconciled data from the one or more power plant sensors, wherein the reconciling errors comprises giving more weight to the one or more power plant sensors that are known to be more reliable, based at least in part on at least one of a calibration history or trends of the one or more power plant sensors stored in a database;

detect anomalies within the at least one performance model; and

tune the at least one performance model to account for the anomalies.

9. The system of claim 8, wherein reconciling errors detected within the data from the one or more power plant sensors is based at least in part on accessing at least one database of calibration history and trends for the one or more power plant sensors.

10. The system of claim 8, wherein detecting anomalies within the at least one performance model is based at least in part on accessing at least one database of known performance models or actual power plant performance results.

11. The system of claim 8, wherein the detected anomalies within the at least one performance model are based at least in part on equipment performance degradation.

12. The system of claim 8, wherein the errors detected within the data from the one or more power plant sensors are based at least in part on sensor drifting.

13. The system of claim 8, wherein the computer-executable instructions are further operable to determine an optimal calibration interval for the one or more power plant sensors based at least in part on the detected errors within the data.

14. The system of claim 8, wherein the data received from the one or more power plant sensors is from a power plant control system or a plant historian module.

15. A system for condition-based power plant sensor calibration, comprising:

one or more power plant sensors;

a computer processor; and

a memory in communication with the computer processor and operable to store computer-executable instructions operable to;

receive data from the one or more power plant sensors;

reconcile detected errors within the data from the one or more power plant sensors;

calibrate the one or more power plant sensors based at least in part on the detected errors within the data;

generate at least one performance model based at least in part on the reconciled data from the one or more power plant sensors, wherein the reconciling errors comprises giving more weight to the one ore more power plant sensors that are known to be more reliable, based at least in part on at least one of a calibration history or trends of the one or more power plant sensors stored in a database;

detect anomalies within the at least one performance model; and

tune the at least one performance model to account for the anomalies.

16. The system of claim 15, wherein reconciling errors detected within the data from the one or more power plant sensors is based at least in part on accessing at least one database of calibration history and trends for the one or more power plant sensors.

17. The system of claim 15, wherein detecting anomalies within the at least one performance model is based at least in part on accessing at least one database of known performance models or actual power plant performance results.

18. The system of claim 15, wherein the detected anomalies within the at least one performance model are based at least in part on equipment performance degradation.

19. The system of claim 15, wherein the errors detected within the data from the one or more power plant sensors are based at least in part on sensor drifting.

20. The system of claim 15, wherein the computer-executable instructions are further operable to determine an optimal calibration interval for the one or more power plant sensors based at least in part on the detected errors within the data.