Application of Hidden Markov Model to Fault Diagnosis of Power Electronic Circuit

Author

Yan Ren-Wu ; Cai Jin-Ding

Author_Institution

Electr. Eng. & Automatization Coll., Fuzhou Univ., Fuzhou

fYear

2009

fDate

28-29 April 2009

Firstpage

1

Lastpage

4

Abstract

This paper presents a new method of applying auto-regressive (AR) model and hidden Markov model (HMM) to fault diagnosis of power electronic circuit. AR coefficients is used as Exacting the features of the states of the circuit firstly .Then fault modes are trained and recognized by hidden Markov model. Finally, a three-phase SCR rectifier circuit with inductive load is used as an example to illustrate the new approach of fault diagnosis. The experimental results show that the method is feasible and effective.

Keywords

autoregressive processes; fault diagnosis; hidden Markov models; power electronics; rectifying circuits; thyristor circuits; autoregressive model; fault diagnosis; hidden Markov model; inductive load; power electronic circuit; three-phase SCR rectifier circuit; Circuit faults; Educational institutions; Electrical fault detection; Equations; Fault diagnosis; Hidden Markov models; Neural networks; Power electronics; Power system reliability; Predictive models;

fLanguage

English

Publisher

ieee

Conference_Titel

Testing and Diagnosis, 2009. ICTD 2009. IEEE Circuits and Systems International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-2587-7

Type

conf

DOI

10.1109/CAS-ICTD.2009.4960787

Filename

4960787