A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM

In the condition monitoring of gear reducer, the labeled fault samples are sparse and expensive, while the unlabeled samples are plentiful and cheap. How to diagnose the faults occurring in complex and special gear reducer effectively becomes a troublesome problem in case of insufficient labeled samples or excess unlabeled samples. This paper presents a novel model for fault diagnosis based on empirical mode decomposition (EMD) and multi-class transductive support vector machine (TSVM), which is applied to diagnose the faults of the gear reducer. The experimental results obtain a very high diagnosis accuracy. Even though the number of unlabeled samples is 50 times as that of labeled samples, the mean of testing accuracy of the proposed novel method can reach at 91.62%, which distinctly precedes the testing success rates of the other similar models in the same experimental condition.

► Multi-class transductive support vector machine (TSVM) is constructed.
► The novel diagnose fault model based on EMD and multi-class TSVM is proposed.
► The troublesome problem of insufficient labeled fault samples is effectively solved.
► The testing accuracy of novel model is high when the unlabeled samples are too many.
► The efficiency of EMD and multi-class TSVM is verified through the contrast tests.