Method of Health Performance Evaluation and Fault Prognostics for Electronic Equipment
To deal with the health performance degradation of electronic equipment, a new health evaluation method based on improved manifold learning algorithm and HMM is proposed in this paper. Firstly, according to SNPP algorithm KSUNPP is proposed by introducing an uncorrelated constraint and kernel method, and the improved algorithm is used for feature extraction. Secondly, the health evaluation model of electronic equipment is constructed. Then, by calculating KL distance which can measure the fault degradation, the model can evaluate the health performance degradation. Finally, the proposed method is applied to health evaluation of electronic equipment which belongs to one type of missile, experiment results demonstrate that the method is effective.
F. X. Lou et al., "Method of Health Performance Evaluation and Fault Prognostics for Electronic Equipment", Applied Mechanics and Materials, Vols. 229-231, pp. 1343-1346, 2012