Particle swarm optimization pattern recognition neural network for transmission lines faults classification

被引:3
|
作者
Zhang, Liang [1 ]
Zhao, Zhengang [1 ,2 ]
Zhang, Dacheng [1 ,2 ]
Luo, Chuan [1 ]
Li, Chuan [1 ]
机构
[1] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming 650500, Yunnan, Peoples R China
[2] Kunming Univ Sci & Technol, Yunnan Key Lab Comp Technol Applicat, Kunming 650500, Yunnan, Peoples R China
基金
中国国家自然科学基金;
关键词
Transmission lines; voltage phase loss; phase break; particle swarm optimization; pattern recognition neural network; RELIABILITY; METER;
D O I
10.3233/IDA-205695
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The operating conditions of the transmission lines can be assessed through the information measured by the smart meters in the power supply bureau. Accurate classification of transmission line faults can be helpful to improve the maintenance strategy of smart grids. This paper analyzes the mechanism of the voltage loss and the phase fault of the transmission line by using the operation data collected by the smart meters from three power supply bureaus (named Bureau A, B and C), where the faults are labeled by expert systems. In this work, a novel Particle Swarm Optimization Pattern Recognition Neural Network (PSO-PRNN) classifier is built to accurately categorize the faults and its classification performance is compared with the ones of traditional K-Nearest Neighbor (KNN), Decision Tree (DT), PSO-KNN and PSO-DT classifiers. The results show that the classification accuracy of PSO-PRNN outperforms traditional classifiers when being applied to the data collected from all three bureaus. In the A power supply bureau are 83.0%, 88.7%, 82.0%, 86.9% and 96.1%, and the classification accuracy rates are 55.7%, 68.7%, 56.6%, 68.7% and 82.5%, when used to process the data of the bureau B. The classification accuracy is 57.1%, 66.4%, 57.2%, 69.0% and 82.1%, when processing the data of bureau C. The results show that the PSO-PRNN classifier is superior to the others in terms of accuracy and applicability.
引用
收藏
页码:189 / 203
页数:15
相关论文
共 50 条
  • [1] Emg pattern recognition based on particle swarm optimization and recurrent neural network
    Kan X.
    Zhang X.
    Cao L.
    Yang D.
    Fan Y.
    [J]. Kan, Xiu (xiu.kan@sues.edu.cn), 1600, Totem Publishers Ltd (16): : 1404 - 1415
  • [2] Pattern classification and prediction of water quality by neural network with particle swarm optimization
    Zhou, Chi
    Gao, Liang
    Gao, Haibing
    Peng, Chuanyong
    [J]. WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS, 2006, : 2864 - +
  • [3] The application of neural network based on particle swarm optimization in pattern recognition of flatness signal
    Liu, Jianchang
    Chen, Yingying
    [J]. WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS, 2006, : 6592 - +
  • [4] Novel flatness pattern recognition using neural network based on adaptive particle swarm optimization
    Xu Lin
    Sun Shu-fang
    Wang Jian-hui
    Fang Xiao-ke
    Gu Shu-sheng
    [J]. PROCEEDINGS OF 2005 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1 AND 2, 2005, : 550 - +
  • [5] Power System Faults Classification with Pattern Recognition Using Neural network
    Karimi, M.
    Banejad, M.
    Hassanpuor, H.
    Moeini, A.
    [J]. 2010 INTERNATIONAL COLLOQUIUM ON COMPUTING, COMMUNICATION, CONTROL, AND MANAGEMENT (CCCM2010), VOL IV, 2010, : 553 - 556
  • [6] Neural Network Classification for Iris Recognition using both Particle Swarm Optimization and Gravitational Search Algorithm
    Rizk, Mohamed R. M.
    Farag, Hania H. A.
    Said, Lamiaa A. A.
    [J]. 2016 WORLD SYMPOSIUM ON COMPUTER APPLICATIONS & RESEARCH (WSCAR), 2016, : 12 - 17
  • [7] Application of Particle Swarm Optimization Based Neural Network to Fault Classification
    Sahel, Salah Sabry Daiboun
    Boudour, Mohamed
    [J]. 2015 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2015, : 33 - U385
  • [8] Particle Swarm Optimization Based Higher Order Neural Network for Classification
    Nayak, Janmenjoy
    Naik, Bighnaraj
    Behera, H. S.
    Abraham, Ajith
    [J]. COMPUTATIONAL INTELLIGENCE IN DATA MINING, VOL 1, 2015, 31 : 401 - 414
  • [9] Image feature classification based on particle swarm optimization neural network
    Wang, Yifang
    [J]. Metallurgical and Mining Industry, 2015, 7 (07): : 328 - 334
  • [10] Particle Swarm Optimization Neural Network based Classification of Mental Tasks
    Hema, C. R.
    Paulraj, M. P.
    Yaacob, S.
    Adom, A. H.
    Nagarajan, R.
    [J]. 4TH KUALA LUMPUR INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING 2008, VOLS 1 AND 2, 2008, 21 (1-2): : 883 - 888