Fault diagnosis for planetary gearboxes using multi-criterion fusion feature selection framework

作者：Liu, Zhiliang^*; Zuo, Ming J.; Xu, Hongbing

来源：Proceedings of the Institution of Mechanical Engineers - Part C: Journal of Mechanical Engineering Science , 2013, 227(9): 2064-2076.

DOI：10.1177/0954406212468407

• Fault diagnosis
• multi-criterion fusion
• feature selection
• gear fault
• planetary gearbox

Feature selection has been used to achieve dimension reduction in the field of fault diagnosis. This article introduces a multi-criterion fusion framework for feature selection that takes into account three aspects of features: effectiveness, correlation, and classification performance. This framework enables a more comprehensive evaluation of features than does a single criterion. The proposed framework is implemented using five effectiveness criteria and a correlation criterion. It is used to diagnose eight failure modes of a planetary gearbox. The experimental results demonstrate that the proposed multi-criterion framework outperforms many well-studied single criteria.

• 出版日期2013-9
• 单位电子科技大学