Support vector machines for detection and characterization of rolling element bearing faults

L.B. Jack, Asoke K. Nandi

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · 2001 · 101 citations · 18 references

Concepts

Abstract

Artificial neural networks (ANNs) have been used to detect faults in rotating machinery for a number of years, using statistical estimates of the vibration signal as input features, and they have been shown to be highly successful in this type of application. Support vector machines (SVMs) are a more recent development, and little use has been made of them in the condition monitoring (CM) arena. The availability of a limited amount of training data creates some problems for the use of SVMs, and a strategy is offered that improves the generalization performance significantly in cases where only limited training data are available. This paper examines the performance of both types of classifier in one given scenario—a multiclass fault characterization example.

References

18