Gearbox Fault Diagnosis Based on Polynomial Chirplet Transform and Support Vector Machine

Qing Xu, Zhongyan Li

2023

Abstract

In order to effectively extract gearbox signal features from complex vibration signals with interference from small samples and diagnose faults, this article proposes a gearbox fault diagnosis method based on polynomial chirplet transform and support vector machine. Firstly, via the polynomial chirplet transform for time-frequency analysis of vibration signals, a set of transformation kernel parameters that can centrally and accurately represent the time-frequency characteristics of the vibration signal are proposed as features to distinguish different states of the gearboxes. Secondly, this research combines the transform kernel parameters with time-domain and frequency-domain features to form feature vector groups. Then we use the feature vector group as the input set of the support vector machine to classify the feature vector group and obtain the state judgment of gearbox vibration signals. It’s found that transformation kernel parameters have a significant positive effect on improving the accuracy of model faults diagnosis after multiple experimental comparisons and this algorithm has generalization.

Paper Citation

in Harvard Style

Xu Q. and Li Z. (2023). Gearbox Fault Diagnosis Based on Polynomial Chirplet Transform and Support Vector Machine. In Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT; ISBN 978-989-758-677-4, SciTePress, pages 468-473. DOI: 10.5220/0012286100003807

in Bibtex Style

@conference{anit23,
author={Qing Xu and Zhongyan Li},
title={Gearbox Fault Diagnosis Based on Polynomial Chirplet Transform and Support Vector Machine},
booktitle={Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT},
year={2023},
pages={468-473},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012286100003807},
isbn={978-989-758-677-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT
TI - Gearbox Fault Diagnosis Based on Polynomial Chirplet Transform and Support Vector Machine
SN - 978-989-758-677-4
AU - Xu Q.
AU - Li Z.
PY - 2023
SP - 468
EP - 473
DO - 10.5220/0012286100003807
PB - SciTePress