Research Article
Research on Fast Separation Method of Motor Fault Signal Based on Wavelet Entropy
@INPROCEEDINGS{10.1007/978-3-031-28867-8_2, author={Jintian Yin and Li Liu and Junfei Nie and Zhihua Peng and Riheng Chen}, title={Research on Fast Separation Method of Motor Fault Signal Based on Wavelet Entropy}, proceedings={Advanced Hybrid Information Processing. 6th EAI International Conference, ADHIP 2022, Changsha, China, September 29-30, 2022, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2023}, month={3}, keywords={Wavelet entropy Motor failure Fault signal Rapid separation Signal separation Fault diagnosis}, doi={10.1007/978-3-031-28867-8_2} }- Jintian Yin
Li Liu
Junfei Nie
Zhihua Peng
Riheng Chen
Year: 2023
Research on Fast Separation Method of Motor Fault Signal Based on Wavelet Entropy
ADHIP PART 2
Springer
DOI: 10.1007/978-3-031-28867-8_2
Abstract
The extraction of motor signals by traditional methods will be affected by multi-component signals and non-stationary signals, and the separation effect of motor fault signals is poor. Therefore, a fast separation method of motor fault signals based on wavelet entropy is proposed. Obtain the motor fault vibration signal, convert it to the frequency domain for solution, and denoise the motor fault vibration signal through three-layer wavelet packet decomposition. Based on wavelet entropy, the sliding window is set for simulation, and the optimal features are selected for extraction to quantitatively describe the time-frequency and energy distribution of motor fault transient vibration signal. The second-order VKF filter is selected to extract multiple components at the same time, so as to realize the separation of multi-component signals. Experimental results show that this method can effectively separate and extract motor fault signals, and can achieve good results under high noise intensity.
