Title :
PPN: A probabilistic model for fault detection and diagnosis
Author :
Wei She ; Yangdong Ye
Author_Institution :
Sch. of Inf. Eng., Zhengzhou Univ., Zhengzhou, China
Abstract :
To analyze the composite fault in Discrete Event System (DES), a Probabilistic Petri net (PPN) and a fault diagnosis method for power system are proposed. Firstly, the PPN models are established on every fault spread direction. Secondly, the failed component is determined by the application of Petri net reasoning and probabilistic calculation. At last, the result is given by fusing all parties´ results using mean method. Diagnosis analysis shows that the method can adapt to topology changes and obtain satisfying diagnosis results with incomplete information. In the PPN reasoning, calculating the fault probability of component is based on the prior probability from statistics, so the subjectivity of setting related parameters can be avoided.
Keywords :
Petri nets; discrete event systems; fault diagnosis; inference mechanisms; power systems; probability; topology; PPN models; PPN reasoning; Petri net reasoning; discrete event system; fault detection; fault diagnosis; fault diagnosis method; fault probability; mean method; power system; probabilistic Petri net; probabilistic calculation; probabilistic model; Adaptation models; Bayesian methods; Cognition; Fault diagnosis; Petri nets; Probabilistic logic; discrete event system; fault diagnosis; fault tolerance; power system; probabilistic Petri nets;
Conference_Titel :
Intelligent Systems Design and Applications (ISDA), 2012 12th International Conference on
Conference_Location :
Kochi
Print_ISBN :
978-1-4673-5117-1
DOI :
10.1109/ISDA.2012.6416676