Abstract
In allusion to the lack of a large number of fault data samples in machinery fault diagnosis, the thesis put forward a new method of machinery fault diagnosis based on support vector machine. And the principle and algorithm of the method has been introduced. Then the multi-fault classifier has been built using simulative fault data. This diagnostic method only need a small amount of time-domain fault data samples to train the fault classification, and don't need to extract the feature amount. In addition, we verify the correctness of this fault classifier through the application of fault classification in steam turbine generator set. The diagnostic method is simple and has strong ability of fault classification.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have