Gearbox fault diagnosis based on local mean decomposition, permutation entropy and extreme learning machine

This paper presents a fault diagnosis method for gearbox based on local mean decomposition (LMD), permutation entropy (PE) and extreme learning machine (ELM). LMD, a new self-adaptive time-frequency analysis method, is applied to decompose the vibration signal into a set of product functions (PFs). Then, PE values of the first five PFs (PF-PE) are calculated to characterize the complexity of the vibration signal. Finally, for the purpose of less time-consuming and higher accuracy, ELM is used to identify and classify of gearbox in different fault types. The experimental results demonstrate that the proposed method is effective in diagnosing and classifying different states of gearbox in short time.