← Back to Patent Explorer
EP1103926A2 Expired / Lapsed EP ⏱️ 0.0 years remaining

Methods and apparatus for model-based diagnostics

Assignee: General Electric Co
•
Filing: 2000-09-20
•
Granted: —
•
Expires: 2020-09-20
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract Systems (100) and methods for performing module-based diagnostics are described. In an exemplary embodiment, sensor values (12) from an actual engine plant are input to an engine component quality estimator (14) which generates performance estimates of major rotating components. Estimated performance differences are generating by comparing the generated performance estimates to a nominal quality engine. The estimated performance differences, which are indicative of component quality, are continuously updated and input to a real-time model (16) of the engine. The model receives operating conditional data and the quality estimates are used to adjust the nominal values in the model to more closely match the model values to the actual plant. Outputs from the engine model are virtual parameters, such as stall margins, specific fuel consumption, and fan/compressor/turbine efficiencies. The virtual parameters are combined with the sensor values from the actual engine plant in a fault detection and isolation classifier (22) to identify abnormal conditions and/or specific fault classes, and output a diagnosis (108).

Inventors

  • 👤 Malcolm John Ashby
  • 👤 Sridhar Adibhatla

Bibliographic Details

Application Number —
Jurisdiction EP
Data Source google_patents
Last Synchronized 2026-11-03 10:38
CPC Classifications
G; G05; G05B; G05B23/00; G05B23/02; G05B23/0205; G05B23/0218; G05B23/0243; G05B23/0254; G05B23/0259; G05B23/0275; F; F02; F02C; F02C9/00; F05; F05D; F05D2270/00; F05D2270/70; F05D2270/71

Claims Analysis

Total Claims: 10
Claim 1
Independent Claim 43 words
A system (10) for monitoring engine performance, said system comprising: an engine model (16): a component quality estimator (14) coupled to said engine model; and a fault detection and isolation classifier (22) coupled to said engine model and to said component quality estimator.
Claim 2
Dependent Claim 20 words
A system (10) in accordance with Claim 1 wherein said model comprises a component level model (16) of an engine.
Claim 3
Dependent Claim 20 words
A system (10) in accordance with Claim 1 or 2 wherein said component quality estimator (14) comprises a linear regressor.
Claim 4
Dependent Claim 25 words
A system (10) in accordance with Claim 1, 2 or 3, wherein said fault detection and isolation classifier (22) comprises a feed-forward neural network (80).
Claim 5
Dependent Claim 24 words
A system (10) in accordance with Claim 1, 2 or 3, wherein said fault detection and isolation classifier (22) comprises a linear regressor (90).
Claim 6
Independent Claim 36 words
A system (10) in accordance with any preceding Claim wherein said engine component quality estimator (14) generates performance estimates, and said model (16) generates virtual parameters (20) based on the performance estimates and engine operating conditions.
Claim 7
Dependent Claim 30 words
A system (10) in accordance with Claim 6 wherein said fault detection and isolation classifier (22) identifies fault conditions based on said virtual parameters (20) and engine sensor values (12).
Claim 8
Dependent Claim 34 words
A system (100) in accordance with Claim 6 wherein said engine virtual parameters are subtracted from engine sensor values (102) to generate sensor deltas (106) supplied to said fault detection and isolation classifier (22).
Claim 9
Dependent Claim 38 words
A system (300) in accordance with Claim 8 wherein reference sensor deltas (308) are generated and are compared to later obtained sensor deltas (308) to generate sensor delta-deltas (318) supplied to said fault detection and isolation classifier (22).
Claim 10
Dependent Claim 41 words
A system (10) in accordance with Claim 1 wherein said model generates virtual sensor values (20) based on engine operating conditions, and said component quality estimator (14) generates quality estimates based on said virtual sensor values and engine sensor values (12).

References Cited (Backward Citations)

No citation records indexed.

USPTO Annuity & Maintenance Windows

Maintenance schedule is calculated for granted US utility patents.

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag