Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/103136
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | A fault diagnosis method of power systems based on an improved Adaptive fuzzy spiking neural P systems and PSO algorithms |
Author: | Wang, J. Peng, H. Tu, M. Perez-Jimenez, J. Shi, P. |
Citation: | Chinese Journal of Electronics, 2016; 25(2):320-327 |
Publisher: | Chinese Institute of Electronics |
Issue Date: | 2016 |
ISSN: | 1022-4653 2075-5597 |
Statement of Responsibility: | Jun Wang, Hong Peng, Min Tu, J. Mario Pérez-Jiménez, Peng Shi |
Abstract: | A new fault diagnosis method based on improved Adaptive fuzzy spiking neural P systems (in short, AFSN P systems) and Particle swarm optimization (PSO) algorithm is presented to improve the efficiency and accuracy of diagnosis for power systems in this paper. AFSN P systems are a novel kind of computing models with parallel computing and learning ability. Based on our previous works, this paper focuses on AFSN P systems inference algorithms and learning algorithms and builds the fault diagnosis model using improved AFSN P systems for diagnosing effectively. The process of diagnosis based on AFSN P systems is expressed by matrix successfully to improve the rate of diagnosis eminently. Furthermore, particle swarm optimization algorithm is introduced into the learning algorithm of AFSN P systems, thus the convergence speed of diagnosis has a big progress. An example of 4-node system is given to verify the effectiveness of this method. Compared with the existing methods, this method has faster diagnosis speed, higher accuracy and strong ability to adapt to the grid topology changes. |
Rights: | © Chinese Institute of Electronics |
DOI: | 10.1049/cje.2016.03.019 |
Published version: | http://dx.doi.org/10.1049/cje.2016.03.019 |
Appears in Collections: | Aurora harvest 7 Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.