On-line fault diagnosis of electric machine based on the Hidden Markov Model

Extensive work has been presented in the literature related to fault diagnosis and prognosis of machines and related components. With machine learning and statistics applied, methods are proposed in a novel perspective. In this work, the statistics model based on Hidden Markov Model(HMM) is selected because of its wide and strong applications on fault diagnostics in the industry. Based on this method, with the model well-trained, it can encompass the traditional difficulties such as building an exact mathematical model or complex parameters estimation. As the machine fault progresses, the fault features are projected on a certain class and therefore the fault and its severity are identified. Its theoretical base and practical performance are presented and its strength on fault tolerant operation are further come up with.