Systems and methods for gas turbine operational impact modeling using statistical and physics-based methodologies

• US 9,852,240 B2
• Filed: 07/23/2014
• Issued: 12/26/2017
• Est. Priority Date: 07/23/2014
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (General Electric Company)
• Original Assignee: General Electric Company
• Inventors: Chopra, Seema, Purnell, David, Powar, Shridhar Raghuvir, Korsedal, John Robert, Farral, Christopher, Yau, Jenfu
• Primary Examiner(s): Dorais, Craig
• Application Number:
  US14/338,912
• Publication Number:
  US 20160026739A1
• Time in Patent Office: 1,252 Days
• Field of Search: None
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G07C 3/00 Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
• CPC Class Codes: G07C 3/14 Quality control systems

Abstract

Systems and methods for gas turbine operational impact modeling using statistical and physics-based methodologies are disclosed. According to one embodiment of the disclosure, a method can include receiving, by one or more processors, operational conditions data associated with a hardware component of a gas turbine; based at least in part on the operational variation data, applying, by one or more processors, statistical methods to establish an operational profile of the hardware component; receiving, by one or more processors, operating parameters and operational conditions data associated with the hardware component; based at least in part on the operating parameters and the operational conditions data, applying, by one or more processors, physics-based methods to establish an operational impact factor of the hardware component; and based at least in part on the operational profile and the operational impact factor determining, by one or more processors, a probability of a failure of the hardware component within a time period.

Claims

1. A method for operational impact modeling, the method comprising:

receiving, by one or more processors, operational conditions data associated with a hardware component of a gas turbine;

based at least in part on operational variation data, applying, by the one or more processors, statistical methods to establish an operational profile of the hardware component wherein establishing the operational profile comprises;

receiving historical operational variation data associated with reference hardware components;

comparing, using one or more statistical algorithms, the operational variation data associated with the hardware component to the historical operational variation data associated with the reference hardware components; and

based at least in part on the comparison, profiling the hardware component, the profiling including attributing hardware failures of the reference hardware components operating under substantially similar operational variations to the hardware component;

receiving, by the one or more processors, operating parameters data-associated with the hardware component;

based at least in part on the operating parameters and the operational conditions data, applying, by the one or more processors, physics-based methods to establish an operational impact factor of the hardware component;

based at least in part on the operational profile and the operational impact factor determining, by the one or more processors, a probability of a failure of the hardware component within a time period; and

based on the probability of the failure, adjusting the operating parameters associated with the hardware component.

2. The method of claim 1, further comprising:

triggering, by the one or more processors, one or more remedial actions to lower the probability of the failure.

3. The method of claim 2, wherein the one or more remedial actions include activating one or more inlet chillers associated with the gas turbine.

4. The method of claim 1, wherein the operational conditions data is received from one or more sensors installed in the gas turbine.

5. The method of claim 1, wherein the operational conditions data comprises one or more of the following:

a compressor discharge temperature, an ambient temperature, DRY load NOx mode of operation, firing temperature, and load of the gas turbine.

6. The method of claim 1, wherein the failure of the hardware component comprises one or more of the following:

an airslot cracking, an inner tang cracking, a combustor liner deformation, a combustor liner cracking, and a lockwire tap.

7. The method of claim 1, wherein establishing the operational impact factor comprises:

receiving, by the one or more processors, historical operational conditions data;

based on the historical operational conditions data, determining, by the one or more processors using statistical methods, representative operational cycles;

matching operational cycles of the hardware component to the representative operational cycles; and

computing a value of the operational impact factor, the operational impact factor being a proportion of a rate of failure of the reference hardware components in the matching operational cycles to a rate of failure in the reference hardware component.

8. The method of claim 7, wherein the reference operational cycles include a base load.

9. The method of claim 1, further comprising:

determining, based on the probability of a failure of the hardware component within a time period, a hardware component inspection frequency.

10. The method of claim 1, wherein the operating parameters comprise fuel pattern variations.

11. The method of claim 1, further comprising:

applying, by the one or more processors, a cluster analysis to identify similar types of clusters to determine a mission profile.

12. A system for operational impact modeling, the system comprising:

one or more processors operable to;

receive operational conditions data from one or more sensors associated with a gas turbine; and

based on a probability of the failure, adjust operating parameters associated with a hardware component;

a physics based analysis technique operable to generate an operational impact factor based at least in part on the operational conditions data;

a database and real time operational model including historical operational conditions data associated with the hardware component of the gas turbine;

a comparison module operable to generate operational variation data based at least on the operational conditions data and the historical operational conditions data and real-time operational conditions data;

a statistical methods module operable to generate an operational profile based at least in part on the operational variation data, wherein, when generating the operational profile, the statistical methods module is operable to;

receive historical operational variation data associated with reference hardware components;

compare, using one or more statistical algorithms, the operational variation data associated with the hardware component to the historical operational variation data associated with the reference hardware components; and

based at least in part on the comparison, profile the hardware component, the profiling including attributing hardware failures of the reference hardware components operating under substantially similar operational variations to the hardware component; and

a prediction module operable to generate the probability of a failure of the hardware component within a specified time period based at least in part on the operational impact factor and the operational profile.

13. The system of claim 12, wherein:

the one or more processors are further operable to receive the operating parameters from one or more controllers associated with the gas turbine; and

the physics based methods module is further operable to compute the operational impact factor based on the operating parameters.

14. The system of claim 13, further comprising:

a feedback module operable to provide feedback to a control module based at least in part on one or more of the operational conditions data, the operational impact factor, and the operational profile.

15. The system of claim 12, further comprising:

a database of historical operational conditions data, the physics-based methods module being further operable to incorporate the historical operational conditions data into the generation of the operational impact factor.

16. The system of claim 12, further comprising:

a database of the historical operational variation data, the statistical methods module being further operable to incorporate the historical operational variation data into the generation of the operational profile.

17. The system of claim 12, wherein the operational conditions data comprise one or more of the following:

a compressor discharge temperature, an ambient temperature, DRY load NOx mode of operation, firing temperature, and a load of the gas turbine.

18. The system of claim 12, wherein the failure of the hardware component comprises one or more of the following:

an airslot cracking, an inner tang cracking, a combustor liner deformation, a combustor liner cracking, and a lockwire tap.

19. A non-transitory computer-readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for operational impact modeling, the method comprising:

receiving, by one or more processors, operational variation data associated with a hardware component of a gas turbine;

based at least in part on the operational variation data, applying, by the one or more processors, statistical methods to establish an operational profile of the hardware component, wherein establishing the operational profile comprises;

receiving historical operational variation data associated with reference hardware components;

comparing, using one or more statistical algorithms, the operational variation data associated with the hardware component to the historical operational variation data associated with the reference hardware components; and

based at least in part on the comparison, profiling the hardware component, the profiling including attributing hardware failures of the reference hardware components operating under substantially similar operational variations to the hardware component;

receiving, by the one or more processors, operating parameters data and operational conditions data associated with the hardware component;

based at least in part on the operating parameters data and the operational conditions data, applying, by the one or more processors, physics-based methods to establish an operational impact factor of the hardware component; and

based at least in part on the operational profile and the operational impact factor determining, by the one or more processors, a probability of a failure of the hardware component within a time period; and

based on the probability of the failure, adjusting the operating parameters associated with the hardware component.