ADAPTIVE PERFORMANCE MODEL AND METHODS FOR SYSTEM MAINTENANCE

• US 20100089067A1
• Filed: 10/10/2008
• Published: 04/15/2010
• Est. Priority Date: 10/10/2008
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Healy, Timothy Andrew, Wilkes, Kevin Wood, Rosson, Randy Scott
• Application Number:
  US12/249,176
• Publication Number:
  US 20100089067A1
• Time in Patent Office: Days
• US Class Current: 60/773
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks

Abstract

A system includes a correction factor module that receives modeled data generated from a simulation model and measured data, that determines a difference between the modeled data and the measured data, and that applies a filter to the difference to determine a correction value; and a performance monitoring module that analyzes the correction value, and that generates a component alert based on the analysis.

Claims

1. A system, the system comprising:

a correction factor module that receives modeled data generated from a simulation model and measured data, that determines a difference between the modeled data and the measured data, and that applies a filter to the difference to determine a correction value; and

a performance monitoring module that analyzes the correction value, and that generates a component alert based on the analysis.

2. The system of claim 1 further comprising a data modeling module that receives other measured data, and that generates the modeled data based on the other measured data and the simulation model.

3. The system of claim 2 wherein the data modeling module further generates modeled control data based on the simulation model.

4. The system of claim 1 wherein the correction factor module normalizes at least one of the modeled data and the measured data and wherein the difference between the modeled data and the measured data is determined based on the normalized at least one of modeled data and measured data.

5. The system of claim 1 wherein the analysis of the correction value includes at least one of a comparison to one or more pre-determined conditions and a comparison to a historical correction value.

6. The system of claim 5 wherein the comparison to the historical correction value includes comparing a rate-of-change of the correction value to a pre-determined threshold.

7. A system for monitoring the performance of a gas turbine engine, the system comprising:

a correction factor module that receives modeled data generated from a real-time gas turbine engine simulation model and measured data sensed from the gas turbine engine in real-time, that determines a difference between the modeled data and the measured data, and that applies a filter to the difference to determine a correction value; and

a performance monitoring module that analyzes the correction value, and that generates a component alert based on the analysis.

8. The system of claim 7 further comprising a data modeling module that receives other measured data sensed from the gas turbine engine in real-time, and that generates the modeled data based on the simulation model and the other measured data.

9. The system of claim 8 wherein the data modeling module further generates modeled control data based on the simulation model.

10. The system of claim 9 further comprising a component control module that receives the modeled control data and that controls at least one of a component and a sub-component of the gas turbine engine based on the modeled control data.

11. The system of claim 7 wherein the correction factor module normalizes at least one of the modeled data and the measured data and wherein the difference between the modeled data and the measured data is determined based on the normalized at least one of modeled data and measured data.

12. The system of claim 7 wherein the analysis of the correction value includes at least one of a comparison to one or more pre-determined conditions and a comparison to a historical correction value.

13. The system of claim 12 wherein the comparison to the historical correction value includes comparing a rate-of-change of the correction value to a pre-determined threshold.

14. A method for monitoring the performance of a gas turbine engine, the method comprising:

receiving measured data sensed from the gas turbine engine in real-time;

determining a difference between the measured data and modeled data generated from a real-time gas turbine engine simulation model;

applying a filter to the difference to determine a correction value;

performing an analysis of the correction value; and

generating a component alert based on the analysis.

15. The method of claim 14 further comprising generating modeled control data based on a predefined model and measured data.

16. The method of claim 15 further comprising controlling at least one of a component and a sub-component of the gas turbine engine based on the modeled control data.

17. The method of claim 14 further comprising normalizing at least one of the modeled data and the measured data and wherein the determining the difference between the modeled data and the measured data is based on the normalized at least one of modeled data and measured data.

18. The method of claim 14 wherein performing the analysis of the correction value includes performing a comparison of the correction value with a pre-determined condition.

19. The method of claim 14 wherein the performing the analysis of the correction value includes performing a comparison of the correction value to with a historical correction value of the gas turbine engine.

20. The method of claim 19 wherein the performing the comparison of the correction value with the historical correction value includes comparing a rate-of-change of the correction value to a pre-determined threshold.