LAUSR

Intelligent fault diagnosis of rotating machinery is a key topic for industrial equipment maintenance and fault prevention. In this study, an intelligent diagnosis approach of rotating machinery via enhanced hierarchical symbolic sample entropy (EHSSE) is proposed. Firstly, a novel indicator termed symbolic sample entropy (SSE) is proposed for complexity measure and representation of fault information. By using symbolic dynamic filtering, the raw continuous time-series will be discretized into symbolic data, and analysis of symbolic data is less sensitive to measurement noise, resulting in superior robustness. Secondly, SSE is combined with enhanced hierarchical analysis to further extract fault characteristics hidden in both low- and high-frequency components. To study the performance of SSE and EHSSE, multiple simulated signals and experimental studies are constructed and three widely used entropy methods are employed to present a comprehensive comparison. The comparison results show that EHSSE performs best in diagnosing various faults of planetary gearbox and rotor system with highest identification accuracy compared with other entropy-based approaches.