Shipboard power quality disturbance recognition based on a two dimensional residual network

被引：0
|
作者：
Song T. [1 ]
Shi W. [1 ]
Bi Z. [1 ]
Xie J. [1 ]
机构：
[1] Department of Electrical Automation, Shanghai Maritime University, Shanghai
来源：
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2022年 / 50卷 / 10期
关键词：
disturbance identification; multi-label classification; power quality; shipboard power system; single-label classification; two dimensional residual network;
D O I：
10.19783/j.cnki.pspc.211021
中图分类号：
学科分类号：
摘要：
For accurate classification, a power quality disturbance recognition method of a shipboard power system based on a two dimensional residual network (2D-ResNet) is proposed. First, the one-dimensional power quality time series is transformed into a two-dimensional image by a distance matrix, and then the image is sent to the proposed 2D-ResNet to extract features. Then an output feature map is used to obtain the recognition results through the linear layer classifier to realize on-line recognition of power quality disturbances in a shipboard power system. Compared with existing feature extraction methods, this method has the highest accuracy of disturbance recognition under different signal-to-noise ratio (SNR). When the SNR is 20 dB, the average accuracy of single-label classification is 93.86%, and the average F1-score of multi-label classification is 96.52%. This proves that the 2D-ResNet can effectively extract features and is robust to noise. A single-label classifier fails to recognize unknown compound disturbance, while the multi-label classifier accurately recognizes the unknown components in the disturbance signal, and the F1-score reaches 93%, which proves that the multi-label classification is suitable for the recognition of unknown compound disturbance. © 2022 Power System Protection and Control Press. All rights reserved.
引用
收藏
页码：94 / 103
页数：9
相关论文
共 23 条
  • [1] QIU Aichao, YUAN Chengqing, SUN Yuwei, Et al., Impact of photovoltaic penetration factor on the power quality of the photovoltaic system of ships, Journal of Harbin Engineering University, 39, 9, pp. 1532-1538, (2018)
  • [2] WANG Fei, QUAN Xiaoqing, REN Lintao, Review of power quality disturbance detection and identification methods, Proceedings of the CSEE, 41, 12, pp. 4104-4121, (2021)
  • [3] HUANG Jianming, QU Hezuo, LI Xiaoming, Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis, Power System Technology, 40, 10, pp. 3184-3191, (2016)
  • [4] ZHENG Shuhua, ZHANG Ningning, WANG Xiangzhou, A lifting wavelet and Hilbert transform fusion method for transient power quality detection, Transactions of Beijing Institute of Technology, 39, 2, pp. 162-168, (2019)
  • [5] YANG Xiaomei, GUO Linming, XIAO Xianyong, Et al., Classification of multiple power quality disturbances based on TQWT and random forest feature selection algorithm, Power System Technology, 44, 8, pp. 3014-3020, (2020)
  • [6] LIU Jun, HUANG Chun, JIANG Yaqun, Et al., Improved generalized S-transform algorithm for power quality disturbances analysis and its implementation, Proceedings of the CSU-EPSA, 29, 3, pp. 35-41, (2017)
  • [7] TIAN Zhenguo, FU Chenghua, WU Hao, Et al., Power quality disturbance for location and classification based on HHT, Power System Protection and Control, 43, 16, pp. 36-42, (2015)
  • [8] XU Changbao, GU Tingyun, GAO Yunpeng, Et al., Power quality disturbance detection based on improved wavelet threshold function and variational mode decomposition, Journal of Hunan University (Natural Science Edition), 47, 6, pp. 77-86, (2020)
  • [9] WANG Shouxiang, CHEN Haiwen, A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network, Applied Energy, (2019)
  • [10] WU Zhaoxu, YANG An, ZHU Longji, Power quality disturbance recognition based on recurrent neural network, Power System Protection and Control, 48, 18, pp. 88-94, (2020)
123