ASSET DEGRADATION MODEL BASELINENING SYSTEM AND METHOD

• US 20170300018A1
• Filed: 04/19/2016
• Published: 10/19/2017
• Est. Priority Date: 04/19/2016
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (General Electric Company)
• Original Assignee: General Electric Company
• Inventors: Block, Frederick William, Szepek, Scott William, Seely, William Forrester, Dokucu, Mustafa Tekin, Raffensperger, John Joseph
• Granted Patent: US 10,358,983 B2
• Time in Patent Office: Days
• CPC Class Codes: F02C 9/00 Controlling gas-turbine plants; Controlling fuel supply in air- breathing jet-propulsion plants controlling air intakes F02C7/057; controlling turbines F01D; controlling compressors F04D27/00; controlling in general G05
• CPC Class Codes: F05D 2260/81 Modelling or simulation
• CPC Class Codes: G05B 19/4065 Monitoring tool breakage, life or condition
• CPC Class Codes: G05B 2219/37255 Using fuzzy logic techniques

Abstract

A system includes a model-based control system configured to receive data relating to parameters of a machinery via a plurality of sensors coupled to the machinery and select one or more models configured to generate a desired parameter of the machinery based on a determined relationship between the parameters and the desired parameter. The one or more models represent a performance of a device of the machinery. The model-based control system is configured to generate the desired parameter using the data and the one or more models control a plurality of actuators coupled to the machinery based on the desired parameter. Further, the model-based control system is configured to empirically tune the one or more models based on the data, the one or more parameters, and the desired parameter, compare the empirical tuning to a baseline tuning, and determine an operational state of the device based on the comparison.

Claims

1. A system, comprising:

a model-based control system configured to;

receive data relating to one or more parameters of a machinery via a plurality of sensors coupled to the machinery;

select one or more models configured to generate a desired parameter of the machinery based on a determined relationship between the one or more parameters and the desired parameter, wherein the one or more models represent a performance of a device of the machinery;

generate the desired parameter using the data and the one or more models;

control a plurality of actuators coupled to the machinery based on the desired parameter;

empirically tune the one or more models based on the data, the one or more parameters, and the desired parameter;

compare the empirical tuning to a baseline tuning; and

determine an operational state of the device based on the comparison.

2. The system of claim 1, wherein the one or more parameters comprise one or more surrogate parameters.

3. The system of claim 1, wherein empirically tuning the one or more models comprises performing regression analysis.

4. The system of claim 1, wherein the baseline tuning comprises a model, a set of coefficients derived during an empirical tuning, or any combination thereof.

5. The system of claim 1, wherein the control system is configured to store the empirically tuned one or more models, a set of coefficients derived during the empirical tuning, or any combination thereof as the baseline tuning.

6. The system of claim 1, wherein the control system is configured to store the empirical tuning and the baseline tuning, and use the stored empirical tuning and baseline tuning to predict a future operational state of the device.

7. The system of claim 6, wherein the control system is configured to determine a suggested replacement date for the device.

8. A method, comprising:

receiving data from a plurality of sensors coupled to machinery configured to produce power, the data corresponding to one or more parameters of the machinery;

selecting one or more models configured to generate a desired parameter of the machinery based on a determined relationship between the one or more parameters and the desired parameter, the one or more models representing a performance of a device of the machinery;

generating the desired parameter using the data and the one or more models;

performing regression analysis to update the one or more models using the data, the one or more models, and the desired parameter, wherein performing the regression analysis comprises calculating one or more coefficients;

comparing the updated one or more models, the one or more coefficients, or any combination thereof to a baseline tuning;

determining an operational state of the device based on the comparison.

9. The method of claim 8, comprising using one or more surrogate parameters as the one or more parameters.

10. The method of claim 8, comprising adjusting the baseline tuning based on a result of the regression analysis.

11. The method of claim 8, comprising predicting a future operational state of the device based, at least in part, on the comparison.

12. The method of claim 8, wherein the baseline tuning comprises a model, a set of coefficients derived during an empirical tuning, or any combination thereof.

13. The method of claim 8, comprising storing a result of the regression analysis, the baseline tuning, or any combination thereof and performing a historical analysis based on, at least in part, the stored result and the stored baseline tuning.

14. The method of claim 8, comprising determining whether a portion of the received data is unsuitable and discarding the unsuitable portion.

15. A non-transitory, computer-readable medium comprising computer executable code comprising instructions configured to:

receive one or more parameters of a machinery configured to produce power, one or more desired parameters of the machinery, and one or more models that represent a determined relationship between the one or more parameters and the one or more desired parameters and a performance of one or more devices of the machinery;

perform regression analysis to determine one or more coefficients to apply to the one or more models and adjust the one or more models using the one or more parameters, the one or more desired parameters, and the one or more models;

compare the one or more adjusted models, the one or more coefficients, or any combination thereof to a baseline model, a baseline set of coefficients, or any combination thereof;

determine an operational state of the one or more devices based on the comparison;

adjust the baseline model, the baseline set of coefficients, or any combination thereof based on a result of the regression analysis;

store the adjusted one or more models, the one or more coefficients, the adjusted baseline model, the adjusted baseline set of coefficients, or any combination thereof.

16. The non-transitory, computer-readable medium of claim 15, comprising instructions configured to perform a historical analysis based, at least in part, on the stored adjusted one or more models, the stored one or more coefficients, the stored adjusted baseline model, the stored adjusted baseline set of coefficients, or any combination thereof.

17. The non-transitory, computer-readable medium of claim 16, comprising instructions configured to predict a future operational state of the one or more devices.

18. The non-transitory, computer-readable medium of claim 16, comprising instructions configured to determine a suggested replacement date for the one or more devices based on the historical analysis.

19. The non-transitory, computer-readable medium of claim 15, comprising instructions to use one or more surrogate parameters as the one or more parameters.

20. The non-transitory computer-readable medium of claim 15, comprising instructions configured to determine whether a portion of the one or more parameters is unsuitable and discard the unsuitable portion.