PSO–SOM Neural Network Algorithm for Series Arc Fault Detection

• Published in: Advances in Mathematical Physics Vol. 2020; no. 2020; pp. 1 - 8
• Main Authors: Liu, Jinhai, Zuo, Jiankai, Chen, Jiatong, Qu, Na
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 2020; Hindawi; John Wiley & Sons, Inc; Wiley
• Subjects: Algorithms; Circuits; Classification; Electric properties; Fault detection; Feature maps; Mathematical optimization; Neural networks; Particle swarm optimization; Power supply; Standard deviation; Support vector machines; Unsupervised learning; Vector quantization; Wavelet transforms; Weight; Iran; China
• ISSN: 1687-9120; 1687-9139; 1687-9139
• DOI: 10.1155/2020/6721909

Self-organizing feature map (SOM) neural network is a kind of competitive neural network with unsupervised learning. It has the strong abilities of self-organization and self-learning. However, the classification accuracy of SOM neural network may decrease when the features of tested object are not obvious. In this paper, the particle swarm optimization (PSO) algorithm is used to optimize the weight values of SOM network. Three indexes, i.e., intra-class density, standard deviation and sample difference, are used to judge the weight value, which can improve the classification accuracy of the SOM network. PSO–SOM network is applied to the detection of series arc fault in electrical circuits and compared with conventional SOM network and learning vector quantization (LVQ) network. The detection accuracy of the PSO–SOM network is 95%, which is higher than conventional SOM network and LVQ network.