A Novel Intuitionistic Fuzzy Inhibitor Arc Petri Net With Error Back Propagation Algorithm and Application in Fault Diagnosis

The setting and adjustment of the weight parameters in the traditional fault diagnosis method depend entirely on personal experience, and the parameter setting lacks regularity. To reduce the fault diagnosis errors caused by human subjective factors and improve the speed and accuracy of power grid f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE access Ročník 7; s. 115978 - 115988
Hlavní autori: Tan, Mingyue, Li, Jiming, Xu, Guangyuan, Cheng, Xuezhen
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Back propagation
Back propagation networks
BP algorithm
Circuit breakers
Diagnostic systems
Fault diagnosis
grid fault diagnosis
Human error
inhibitor arc Petri net
Inhibitors
Intuitionistic fuzzy set
Mathematical models
Network topologies
Neural networks
Parameters
Petri nets
Weight
ISSN:2169-3536, 2169-3536
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The setting and adjustment of the weight parameters in the traditional fault diagnosis method depend entirely on personal experience, and the parameter setting lacks regularity. To reduce the fault diagnosis errors caused by human subjective factors and improve the speed and accuracy of power grid fault diagnosis, we propose a method for power grid fault diagnosis using intuitionistic fuzzy inhibitor arc Petri net (IFIAPN) with error back propagation (BP) algorithm. Firstly, according to the network topology analysis and relay protection configuration setting rules, the inhibitor arc (IA) tuple is introduced into the model structure of the intuitionistic fuzzy Petri net to reduce the ambiguity of protection and circuit breaker action. Then, the weight parameters in the model are trained using a BP neural network algorithm to enhance the objectivity of the parameters. Finally, a simulation of an IEEE-39 node system and a real case study using the Hou-zhong line local grid were used to verify the effectiveness of the fault diagnosis method. The results show that the method can effectively deal with the refusal and mis-operation of multiple circuit breakers and improve the diagnostic efficiency under complex data environment.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2936212