An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis

To improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The contribution of this paper is to develop an iterative reduced kernel principal component analysis (IRKPCA) algorithm to extract fault features from original high-dimension observation without large additional calculation load and combine it with the HMM for engine gas-path fault diagnosis. The optimal kernel features are obtained by iterative sequential forward selection of the IRKPCA, and the features with lower dimensions are contracted through a trade-off between the fault information and modeling data scale in reduced kernel space. The similarity degree is designed to simplify the HMM modeling data using fault kernel features. Test results show that the proposed methodology brings a significant improvement in diagnostic confidence and computational efforts in the applications of a turbofan engine fault diagnosis during its steady and dynamic process.