山东科学 ›› 2023, Vol. 36 ›› Issue (6): 68-73.doi: 10.3976/j.issn.1002-4026.2023.06.009

• 光纤与光子传感技术 • 上一篇    下一篇

基于生成对抗网络的有载调压开关故障检测研究

姜晓东1(), 王磊磊1, 孙鹏1, 杨光1, 耿俊琪1, 王家文2, 黄胜2, 渠帅2,*(), 王晨2, 尚盈2   

  1. 1.国网山东省电力公司淄博供电公司,山东 淄博 255000
    2.齐鲁工业大学(山东省科学院) 激光研究所,山东 济南 250104
  • 收稿日期:2022-12-29 出版日期:2023-12-20 发布日期:2023-12-07
  • 通信作者: * 渠帅,男,助理研究员,研究方向为光纤传感。Tel: 17861431855,E-mail: qushuai@sdlaser.cn
  • 作者简介:姜晓东(1991—),男,硕士,工程师,研究方向为电力系统。E-mail: 1016466541@qq.com
  • 基金资助:
    国网山东省电力公司科技项目(520603220003)

Fault detection of an on-load tap changer based on generative adversarial network

JIANG Xiaodong1(), WANG Leilei1, SUN Peng1, YANG Guang1, GENG Junqi1, WANG Jiawen2, HUANG Sheng2, QU Shuai2,*(), WANG Chen2, SHANG Ying2   

  1. 1. State Grid Shandong Electric Power Company Zibo Power Supply Company,Zibo 255000, China
    2. Laser Research Institute, Qilu University of Technology(Shandong Academy of sciences),Jinan 250014,China
  • Received:2022-12-29 Online:2023-12-20 Published:2023-12-07

摘要:

实际应用中电力变压器故障数据获取困难,导致在处理变压器故障数据时会由于存在不平衡数据对深入分析结果产生很大的影响。为了解决上述问题,结合对抗神经网络和人工神经网络对不平衡数据进行处理与判断,利用基于超弱光纤布拉格光栅的分布式声波传感技术对实验室搭建的变压器的模拟现场进行数据采集与分析,并在采集到的变压器故障模拟数据的检测上取得很好的效果。这种方法对基于对抗生成网络的有载变压器小样本故障识别系统具有重要的借鉴意义。

关键词: 人工神经网络, 点式传感器, 有载变压器, 故障检测, 模式识别, 对抗生成网络, 数据增强

Abstract:

The probability of power transformer failure is extremely low, which leads to a great impact on further in-depth analysis results due to unbalanced data when processing transformer fault data. To solve these problems, this study processes and judges the unbalanced data using an confrontation neural network combined with an artificial neural network, uses the distributed acoustic wave sensing technology based on ultraweak fiber Bragg gratings to collect and analyze the data of the simulation site of the transformer built in a laboratory, and achieves good results on the collected transformer fault simulation data. This method has an important referential significance for developing the small sample fault identification system of the on-load transformer using confrontation generation network.

Key words: artificial neural network, point sensor, on-load transformer, fault detection, pattern recognition, generative adversarial networks, data enhancement

中图分类号: 

  • TN247