In this paper, we present a unified framework for sensor validation, which is an extremely important module in the engine health management system. Our approach consists of several key ideas. First, we applied nonlinear minor component analysis (NLMCA) to capture the analytical redundancy between sensors. The obtained NLMCA model is data driven, does not require faulty data, and only utilizes sensor measurements during normal operations. Second, practical fault detection and isolation indices based on Squared Weighted Residuals (SWR) are employed to detect and classify the sensor failures. The SWR yields more accurate and robust detection and isolation results as compared to the conventional Squared Prediction Error (SPE). Third, an accurate fault size estimation method based on reverse scanning of the residuals is proposed. Extensive simulations based on a nonlinear prototype non-augmented turbofan engine model have been performed to validate the excellent performance of our approach.
[1]
Erkki Oja,et al.
Neural fitting: Robustness by anti-Hebbian learning
,
1996,
Neurocomputing.
[2]
William W. Hsieh,et al.
Nonlinear principal component analysis by neural networks
,
2001
.
[3]
Jie Chen,et al.
Robust Model-Based Fault Diagnosis for Dynamic Systems
,
1998,
The International Series on Asian Studies in Computer and Information Science.
[4]
Marios M. Polycarpou,et al.
Sensor bias fault isolation in a class of nonlinear systems
,
2005,
IEEE Transactions on Automatic Control.
[5]
M. Kramer.
Nonlinear principal component analysis using autoassociative neural networks
,
1991
.
[6]
Robert E. Uhrig,et al.
Use of Autoassociative Neural Networks for Signal Validation
,
1998,
J. Intell. Robotic Syst..
[7]
William Cheetham,et al.
Case-Based Reasoning for Gas Turbine Diagnostics
,
2005,
FLAIRS Conference.