Fault diagnosis of planetary gear based on wavelet real modulation zooming and resonance demodulation

Shi, Xianjiang; Cao, Yi; Wang, Zhenmeng; Li, Kai; Si, Junshan

doi:10.1109/icinfa.2017.8078911

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, traditional MCT blade fault diagnosis methods are predominantly based on electrical and mechanical signal analysis. Previous studies [4][5][6] use time-frequency analysis methods to detect fault. Sapena-Bano et al 4 propose a method based on timefrequency analysis of rotor current signals to conduct condition monitoring on a wind turbine without using speed sensors.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al 5 use time and multidomain features to detect the faults of MCTs under complex working conditions. Shi et al, 6 on the other hand, employ wavelet packet decomposition and reconstruction to extract resonant frequency components caused by the local fault of gears. However, time-frequency analysis methods require choosing a suitable size of analyzing window when using short-time Fourier transform (STFT) and basic function of wavelet transform.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A diagnosis method based on depthwise separable convolutional neural network for the attachment on the blade of marine current turbine

Xin

Zheng

Wang

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

To diagnose the attachment of marine current turbine, this article proposes a method based on convolutional neural network and the concepts of depthwise separable convolution to achieve feature extraction. The method consists of three steps: data preprocessing, feature extraction and fault diagnosis. This method can diagnose the fault degree of blade imbalance and uniform attachment in underwater environment with strong currents and complex spatiotemporal variability. It can extract distinct image feature in harsh marine environments by using a convolutional neural network. In addition, this method is robust for the recognition of blurred pictures under high-speed rotation.

show abstract