Title :
Faults Diagnosis of Rotor Machine in Whole Running-up Process Based on Hybrid SVVM/HMM Architecture
Author :
Feng Changjian ; Wu Bin ; Kangjing Shaoqiang
Author_Institution :
Dalian nationalities Univ., Dalian
fDate :
May 30 2007-June 1 2007
Abstract :
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.
Keywords :
electric machine analysis computing; fault diagnosis; hidden Markov models; machine control; rotors; support vector machines; Gauss model; HMM architecture; SVM; faults diagnosis; hidden Markov model; posterior probability; rotor machine; sigmoid function; support vector machine; Computer architecture; Fault diagnosis; Gaussian processes; Hidden Markov models; Mechanical engineering; Probability; Sequences; Support vector machines; Vibrations; Yttrium; HMM; SVM; faults diagnosis; rotor machine;
Conference_Titel :
Control and Automation, 2007. ICCA 2007. IEEE International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4244-0818-4
Electronic_ISBN :
978-1-4244-0818-4
DOI :
10.1109/ICCA.2007.4376523
