Abstract
AbstractDue to the advantages of Fuzzy reasoning Petri-nets(FPN)on uncertain and incomplete information processing. It is a promising technique to solve the complex power system fault-section estimation problem. Therefore, we propose a novel estimation method based on Adaptive Fuzzy Petri Nets (AFPN), in this algorithm, the AFPN is used to build a dynamic fault diagnosis fuzzy reasoning model, where the weights in fuzzy reasoning are decided by the incomplete and uncertain alarm information of protective relays and circuit breakers. The validity and feasibility of this method is illustrated by simulation examples. Results show that the fault section can be diagnosed correctly through fuzzy reasoning models for ten cases, and the AFPN not only takes the descriptive advantages of fuzzy Petri net, but also has learning ability as neural network..
Highlights
The aim of fault section estimation is identifying faulty components in power system based on the operation information of protective relays and circuit breakers
Case 1 to case 5 are used in Adaptive Fuzzy Petri Nets (AFPN) improved models and AFPN classical models simulation; the results show that the proposed method can give more accurate results
With fuzzy petri nets as basic tool, and according to fault diagnosis characteristics, a new improved type of diagnosis analysis method using self-adaptive petri nets with fuzzy logic is presented in this paper
Summary
The aim of fault section estimation is identifying faulty components in power system based on the operation information of protective relays and circuit breakers. The Petri net shows the characteristics of parallel information processing and concurrent operating function, and the ability of clearly describing the relation of protective relays, circuit breakers and concurrent operating mechanism can be got in the Petri net It is a very suitable and useful modeling tool for fault diagnosis. The fault diagnosis method based on FPN can provide correct diagnostic result, especially, compared with other methods [1]-[6], it can perfectly process the problem of information uncertain and data incompleteness [18]-[19] It has no ability of adjusting its weights and threshold value according to the knowledge updating or the network topology changing.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Computational Intelligence Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
