Health assessment for hydraulic servo system using manifold learning based on EMD

This study proposes a health assessment method for the hydraulic servo system using manifold learning based on empirical mode decomposition (EMD). An RBF neural network is adopted as a fault observer for the hydraulic servo system to generate a residual error signal. Then, the residual error signal is decomposed by EMD to form the initial feature matrix. To extract more sensitive features and reduce time consumption, isometric mapping algorithm is introduced to reduce the dimensionality of the initial feature matrix. Furthermore, the singular values of the reduced feature matrix are extracted for the subsequent health assessment. Considering the traditional Euclidean distance metric can only reflect local consistency, this study utilizes manifold distance (ManiD) to measure the health condition of the hydraulic servo system. Finally, the ManiD is converted into a confidence value, which directly represents the health status. Experiment results demonstrate the effectiveness of the proposed method.