System and method for condition based monitoring of a gas turbine filter house

Patent metadata

Field	Value
Publication number	US-10612412-B2
Application number	US-201615136535-A
Country	US
Kind code	B2
Filing date	Apr 22, 2016
Priority date	Apr 22, 2016
Publication date	Apr 7, 2020
Grant date	Apr 7, 2020

Abstract

In one embodiment, a computing device includes one or more processors configured to execute instructions that cause the one or more processors to acquire pressure data measured by at least one pressure sensor disposed proximate to a filter house in an intake of a gas turbine engine system, derive an airflow or an air mass flow through a duct of the intake using a thermodynamic model of the gas turbine engine system based at least on the pressure data, derive an intake pressure drop in the duct using at least the pressure data, derive a loss parameter of the filter house by combining the air mass or air mass flow, and the intake pressure drop, derive a pressure loss model based on the loss parameter over a period of time, and determine a condition of the filter house based on the pressure loss model.

First claim

The invention claimed is:

1. A computing device, comprising:
one or more processors configured to execute instructions that cause the one or more processors to:
acquire pressure data measured by at least one pressure sensor disposed proximate to a filter house in an intake of a gas turbine engine system;
derive an airflow or an air mass flow through a duct of the intake using a thermodynamic model of the gas turbine engine system based at least on the pressure data, wherein the thermodynamic model comprises a physics-based model of the gas turbine engine configured to estimate the airflow or the air mass based on at least the pressure data;
derive an intake pressure drop in the duct using at least the pressure data;
derive a loss parameter of the filter house by combining the air mass or air mass flow, and the intake pressure drop;
derive a pressure loss model based on the loss parameter over a period of time; and
determine a condition of the filter house based on the pressure loss model.

2. The computing device of claim 1 , wherein the one or more processors are configured to execute the instructions that cause the one or more processors to determine the filter house is degraded when a subsequently derived loss parameter differs from the pressure loss model by a threshold.

3. The computing device of claim 1 , wherein the one or more processors are configured to execute the instructions that cause the one or more processors to perform a preventative action when the condition of the filter house comprises degradation.

4. The computing device of claim 3 , wherein the preventative action comprises outputting an advisory including a recommendation to replace the filter house when the cost of replacing the filter house is less than the cost associated with power output lost by continuing operating the gas turbine engine system.

5. The computing device of claim 3 , wherein the preventative action comprises outputting an advisory, shutting down the gas turbine engine system, automatically scheduling replacement of the filter house, or some combination thereof.

6. The computing device of claim 1 , wherein the pressure data is obtained by the at least one pressure sensor during startup, base load operation, shutdown, or some combination thereof, of the gas turbine engine system.

7. The computing device of claim 1 , wherein the at least one pressure sensor comprises a single pressure sensor.

8. The computing device of claim 1 , wherein the at least one pressure sensor is located directly behind the filter house.

9. The computing device of claim 1 , wherein the one or more processors are configured to execute the instructions that cause the one or more processors to determine an engineering impact, a financial impact, or a combination thereof, of power output lost due to operating the gas turbine engine system with the filter house in the condition.

10. The computing device of claim 1 , wherein the one or more processors are configured to execute the instructions that cause the one or more processors to:
derive a plurality of loss parameters of a plurality of filter houses included in a plurality of gas turbine engine systems in a fleet;
average the plurality of loss parameters over time; and
derive a fleet baseline pressure loss model based at least on the averaged plurality of loss parameters over time.

11. The computing device of claim 10 , wherein the one or more processors are configured to execute the instructions that cause the one or more processors to:
determine the condition of the filter house by comparing a subsequently derived loss parameter for the filter house of the gas turbine engine system to the fleet baseline pressure loss model; and
perform a preventative action when the condition comprises degradation.

12. A method, comprising:
acquiring, via a processor, pressure data measured by at least one pressure sensor disposed proximate to a filter house in an intake of a gas turbine engine system;
deriving, via the processor, an air mass or an air mass flow through a duct of the intake using a thermodynamic model of the gas turbine engine system based at least on the pressure data, wherein the thermodynamic model comprises a physics-based model of the gas turbine engine configured to estimate the airflow or the air mass based on at least the pressure data;
deriving, via the processor, an intake pressure drop in the duct using at least the pressure data;
deriving, via the processor, a loss parameter of the filter house by combining the air mass or air mass flow, and the intake pressure drop;
deriving, via the processor, a pressure loss model based on the loss parameter over a period of time; and
determining, via the processor, a condition of the filter house based on the pressure loss model.

13. The method of claim 12 , wherein determining the condition of the filter house based on the pressure loss model comprises determining that the filter house is degraded when a subsequently derived loss parameter differs from the pressure loss model by a threshold.

14. The method of claim 12 , comprising performing a preventative action when the condition comprises degradation, wherein the preventative action comprises shutting down the gas turbine engine system, outputting an advisory to replace the filter house, scheduling replacement of the filter house, or some combination thereof.

15. The method of claim 12 , comprising:
deriving a plurality of loss parameters of a plurality of filter houses included in a plurality of gas turbine engine systems in a fleet;
averaging the plurality of loss parameters over time; and
deriving a fleet baseline pressure loss model based at least on the averaged plurality of loss parameters over time.

16. The method of claim 15 , comprising:
determining the condition of the filter house by comparing a subsequently derived loss parameter for the filter house of the gas turbine engine system to the fleet baseline pressure loss model; and
performing a preventative action when the condition comprises degradation.

17. The method of claim 12 , wherein acquiring the pressure data comprises acquiring the pressure data from a database stored on a remote server or stored in a memory located in a same computing device as the processor.

18. A tangible, non-transitory computer readable medium storing computer instructions that, when executed by one or more processors, cause the one or more processors to:
acquire pressure data measured by at least one pressure sensor disposed behind a filter house in an intake of a gas turbine engine system;
derive an air mass or an air mass flow through a duct of the intake using a thermodynamic model of the gas turbine engine system based at least on the pressure data, wherein the thermodynamic model comprises a physics-based model of the gas turbine engine configured to estimate the airflow or the air mass based on at least the pressure data;
derive an intake pressure drop in the duct using at least the pressure data;
derive a loss parameter of the filter house by combining the air mass or air mass flow, and the intake pressure drop;
derive a pressure loss model based on the loss parameter over a period of time; and
determine a condition of the filter house based on the pressure loss model.

19. The computer readable medium of claim 18 , wherein the computer instructions, when executed by the one or more processors, cause the one or more processors to derive the air mass or air mass flow using the thermodynamic model to derive performance of the gas turbine

Assignees

• Gen Electric

Inventors

• Vega Jose L
• Escobedo Hernandez Ernesto Heliodoro
• Mendoza Jose

Classifications

• B01D46/446

  by pressure measuring · CPC title

• B01D46/0086

  Filter condition indicators · CPC title

• F05B2270/3015

  differential · CPC title

• F02C7/052

  with dust-separation devices · CPC title

• F01D21/003 Primary

  Arrangements for testing or measuring (for measuring vibrations G01H) · CPC title