Refined time-shift multiscale diversity entropy: a novel feature extraction algorithm for fault diagnosis of planetary gearbox

Abstract

Planetary gearboxes play a critical role in aerospace and heavy industry fields, such as wind turbines, heavy vehicles and construction machines. Intelligent fault diagnosis is significant for safe operation and fault prevention of planetary gearboxes. Recently, multiscale diversity entropy and related entropy methods are proposed to extract features of time series and applied for the fault diagnosis. However, there are still some limitations in fault feature representation and stability for multiscale diversity entropy. To solve the problem, in this paper, a novel planetary gearboxes fault diagnosis method via refined time-shift multiscale diversity entropy (RTSMDE) is proposed. First, a novel entropy algorithm called RTSMDE is proposed to measure the complexity of time series and extract fault features of the vibration signals, which is robust and efficient in performance. Then, the obtained features are utilized to fulfil automatically the fault pattern identifications using support vector machine. To confirm the superiority of the RTSMDE-based fault diagnosis method, simulated signals and experimental studies are constructed and three used widely methods are employed to present a comprehensive comparison. The results indicate that RTSMDE performs best and obtains the highest accuracy.