Faults Diagnosis of Rotor Machine in Whole Running-up Process Based on Hybrid SVVM/HMM Architecture

A new architecture for diagnosis of rotor machine in whole running-up process is proposed. This architecture converts the output of support vector machine (SVM) into the form of posterior probability which is computed by the combining use of sigmoid function and Gauss model, and it acts as a probability evaluator in the hidden states of hidden Markov models (HMM). Experiments show that the architecture is very effective.