A new support vector data description method for machinery fault diagnosis with unbalanced datasets

作者：

Highlights：

• Binary Tree is integrated with Support Vector Data Description to address multi-classification issues with unbalanced datasets.

• Separability measure based on Mahalanobis distance is proposed to construct Binary Tree.

• The parameters of Support Vector Data Description are optimized using Particle Swarm Optimization to eliminate the error caused by manually selection.

摘要

•Binary Tree is integrated with Support Vector Data Description to address multi-classification issues with unbalanced datasets.•Separability measure based on Mahalanobis distance is proposed to construct Binary Tree.•The parameters of Support Vector Data Description are optimized using Particle Swarm Optimization to eliminate the error caused by manually selection.

论文关键词：Fault diagnosis,Unbalanced datasets,Support vector data description,Binary tree,Mahalanobis distance

论文评审过程：Received 25 February 2016, Revised 6 June 2016, Accepted 26 July 2016, Available online 27 July 2016, Version of Record 3 August 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.039