Abstract:

To deal with the health performance degradation of electronic equipment, a new health evaluation and fault prognostics  method based on improved manifold learning algorithm and hidden semiMarkov model(HSMM) is proposed. Firstly, according  to the supervised neighborhood preserving projection (SNPP) algorithm, a kernel supervised uncorrelated neighborhood  preserving projection (KSUNPP) algorithm is proposed by introducing an uncorrelated constraint and kernel method, and the  improved algorithm is used for feature extraction. Secondly, the health evaluation and fault prognostics model of  electronic equipment is constructed. Then, by calculating Kullback Leibler (KL) distance which can measure the fault  degradation, the model can evaluate the health performance degradation. And according to the dwell time of every  state, it can also predict the time that faults occur. Finally, the proposed method is applied to the health evaluation  and fault prognostics of electronic equipment of a certain type of missile. Experiment results demonstrate that the  method is effective.