湖南电力 ›› 2024, Vol. 44 ›› Issue (3): 15-24.doi: 10.3969/j.issn.1008-0198.2024.03.003

• 特约专栏: 输变电设备数字化运检技术 • 上一篇    下一篇

融合智能算法及频域介电谱法的变压器油纸绝缘状态评估研究

周煜健1, 丁哲时2   

  1. 1.国能广投北海发电有限公司,广西 北海 536017;
    2.广西大学电气工程学院,广西 南宁 530004
  • 收稿日期:2023-12-27 修回日期:2024-04-15 出版日期:2024-06-25 发布日期:2024-07-10
  • 通信作者: 丁哲时(1997),男,硕士研究生在读,主要研究方向为高电压与绝缘技术。
  • 作者简介:周煜健(1991),男,工程师,从事电厂设备电气管理工作。
  • 基金资助:
    国能广投北海发电有限公司科技项目(BHDC-2023-FW-033)

Research on Transformer Oil-Paper Insulation State Assessment by Integrating Intelligent Algorithm and Frequency Domain Dielectric Spectroscopy

ZHOU Yujian1, DING Zheshi2   

  1. 1. China Energy Investment Corporation Beihai Power Generation Co., Ltd.,Beihai 536017,China;
    2. Electrical Engineering Shool,Guangxi University, Nanning 530004, China
  • Received:2023-12-27 Revised:2024-04-15 Online:2024-06-25 Published:2024-07-10

摘要: 针对变压器绝缘状态评估提出一种结合非支配排序遗传算法(non-dominated sorting genetic algorithm Ⅱ,NSGA-Ⅱ)和扩展Cole-Cole模型的组合方法,提取特征参数并应用于实验室样本和变压器的绝缘状态评估工作。首先,收集不同状态绝缘样本的频域介电谱信息;然后,对扩展Cole-Cole模型进行解耦分析,以区分不同的介电响应行为;接着,使用NSGA-Ⅱ算法求解扩展Cole-Cole模型分离特征参数,并使用Pearson相关系数法获得所需的特征参数;最后,基于获得的特征参数,借助神经网络工具开展实验室样本和现场变压器的绝缘状态评估。结果表明,基于智能算法及频域介电谱法的变压器油纸绝缘状态评估具有较高的准确性和适用性。

关键词: 变压器, 频域介电谱法, 绝缘状态评估, 拓展Cole-Cole模型, NSGA-Ⅱ算法

Abstract: :This paper proposes a novel approach for assessing the insulation condition of transformers by combining the non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ) with an extended Cole-Cole model. The method is applied to extract feature parameters for the evaluation of insulation states in laboratory samples and transformers. Initially, frequency domain spectroscopy messages are collected from insulation samples in different states. Subsequently,uncoupling analysis is performed on the extended Cole-Cole model to distinguish various dielectric response behaviors. The NSGA-Ⅱ algorithm is then utilized to solve the extended Cole-Cole model and separate the feature parameters, which are further refined using the Pearson correlation coefficient method. Finally, based on the obtained feature parameters, insulation state assessments are conducted on laboratory samples and on-site transformers using neural network tools. The results demonstrate that this intelligent algorithm-based approach, coupled with frequency domain spectroscopy, has high accuracy and applicability in evaluating the insulation condition of transformer oil-paper insulation.

Key words: transformer, frequency domain dielectric spectroscopy, insulation state assessment, extended Cole-Cole model, NSGA-Ⅱ algorithm

中图分类号: