Methods and apparatus for monitoring gas turbine engine operation

• US 6,466,858 B1
• Filed: 11/02/2000
• Issued: 10/15/2002
• Est. Priority Date: 11/02/2000
• Status: Expired due to Fees

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Adibhatla, Sridhar, Ashby, Malcolm John
• Primary Examiner(s): Camby, Richard M.
• Application Number:
  US09/705,131
• Time in Patent Office: 712 Days
• Field of Search: 607/72, 607/73, 60/393.4, 415/27, 415/28, 701/100
• US Class Current: 701/100
• 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: F02C 9/28 Regulating systems responsive to plant or ambient parameters, e.g. temperature, pressure, rotor speed F02C9/30 - F02C9/38, F02C9/44 take precedence
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: F05D 2260/81 Modelling or simulation
• CPC Class Codes: F05D 2260/82 Forecasts
• 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 model-based trending process for a gas turbine engine that generates, in real-time, engine trend parameters from engine sensor data and ambient flight condition data to assess engine condition is described. The engine includes a plurality of sensors that are responsive to engine operations. The trending process is implemented using a commercially available processor coupled to the engine to monitor the engine operations, and having the desired processing speed and capacity. Engine health parameters are estimated and adjusted in a model for component diagnostics and fault detection and isolation. The trend parameters generated are retained.

Claims

1. A method for identifying trends in engine operation, the engine having a plurality of sensors responsive to engine operations, said method comprising the steps of:

obtaining outputs from at least some of the sensors when the engine is operating;

obtaining ambient flight condition data; and

using an engine model to generate normalized engine trend parameters using the engine sensor data and ambient flight condition data, wherein engine component efficiencies and flow functions in the engine model are adjusted to account for engine faults, engine quality, and engine deterioration effects.

2. A method in accordance with claim 1 wherein said step of generating normalized engine trend parameters further comprises the step of:

using the engine model to generate additional trend parameters or normalized virtual sensors.

3. A method in accordance with claim 2 wherein said step of generating normalized engine trend parameters further comprising the step of normalizing engine trend parameters in real-time during engine operation.

4. A method in accordance with claim 2 wherein said step of generating normalized engine trend parameters further comprises the step of using at least one of a physics-based, regression-fit, or a neural-net engine model to normalize engine trend parameters.

5. A method according to claim 2 wherein said step of adjusting engine component efficiencies and flow functions further comprises the step of using a parameter estimation algorithm to adjust engine component efficiencies and flow functions.

6. A method according to claim 5 wherein said step of using a parameter estimation algorithm further comprises the step of using at least one of a linear regression scheme or a Kalman filter to adjust engine component efficiencies and flow functions.