A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Feature Extraction using Wavelet Transform for Multi-class Fault Detection of Induction Motor
Abstract In this paper the theoretical aspects and feature extraction capabilities of continuous wavelet transform (CWT) and discrete wavelet transform (DWT) are experimentally verified from the point of view of fault diagnosis of induction motors. Vertical frame vibration signal is analyzed to develop a wavelet based multi-class fault detection scheme. The redundant and high dimensionality information of CWT makes it computationally in-efficient. Using greedy-search feature selection technique (Greedy-CWT) the redundancy is eliminated to a great extent and found much superior to the widely used DWT technique, even in presence of high level of noise. The results are verified using MLP, SVM, RBF classifiers. The feature selection technique has enabled determination of the most relevant CWT scales and corresponding coefficients. Thus, the inherent limitations of CWT like proper selection of scales and redundant information are eliminated. In the present investigation ‘db8’ is found as the best mother wavelet, due to its long period and higher number of vanishing moments, for detection of motor faults.
Feature Extraction using Wavelet Transform for Multi-class Fault Detection of Induction Motor
Abstract In this paper the theoretical aspects and feature extraction capabilities of continuous wavelet transform (CWT) and discrete wavelet transform (DWT) are experimentally verified from the point of view of fault diagnosis of induction motors. Vertical frame vibration signal is analyzed to develop a wavelet based multi-class fault detection scheme. The redundant and high dimensionality information of CWT makes it computationally in-efficient. Using greedy-search feature selection technique (Greedy-CWT) the redundancy is eliminated to a great extent and found much superior to the widely used DWT technique, even in presence of high level of noise. The results are verified using MLP, SVM, RBF classifiers. The feature selection technique has enabled determination of the most relevant CWT scales and corresponding coefficients. Thus, the inherent limitations of CWT like proper selection of scales and redundant information are eliminated. In the present investigation ‘db8’ is found as the best mother wavelet, due to its long period and higher number of vanishing moments, for detection of motor faults.
Feature Extraction using Wavelet Transform for Multi-class Fault Detection of Induction Motor
Chattopadhyay, P. (author) / Konar, P. (author)
2014-01-01
9 pages
Article (Journal)
Electronic Resource
English
Discrete Wavelet Transform for Stator Fault Detection in an Induction Motor
| Springer Verlag | 2023
Fault Detection in a Water Hydraulic Motor Using a Wavelet Transform
| British Library Online Contents | 2006
Feature Extraction from Acoustic Emission Waveforms using a Discrete Wavelet Transform
| British Library Conference Proceedings | 2008