A Fault Diagnosis Approach for Rolling Bearing Integrated SGMD, IMSDE and Multiclass Relevance Vector Machine.

摘要: The vibration signal induced by bearing local fault has strong nonstationary and nonlinear property, which indicates that the conventional methods are difficult to recognize patterns effectively. Hence, obtain an efficient diagnosis result, paper proposes intelligent approach for rolling integrated symplectic geometry mode decomposition (SGMD), improved multiscale symbolic dynamic entropy (IMSDE) multiclass relevance vector machine (MRVM). Firstly, SGMD is employed decompose original into several components (SGC), aimed at reconstructing achieving purpose of noise reduction. Secondly, bat algorithm (BA)-based optimized IMSDE presented evaluate complexity reconstruction extract features, can solve problems missing partial information existing in (MSDE). Finally, IMSDE-based features fed MRVM identification categories. validity proposed method verified experimental contrastive analysis. results show our precisely identify different bearings. Moreover, achieve higher recognition accuracy than involved this paper. This study provides a new research idea improvement identification.