引用本文: | 包金山,杨定坤,张 靖,等.基于特征提取与INGO-SVM的变压器故障诊断方法[J].电力系统保护与控制,2024,52(7):24-32.[点击复制] |
BAO Jinshan,YANG Dingkun,ZHANG Jing,et al.Transformer fault diagnosis method based on feature extraction and INGO-SVM[J].Power System Protection and Control,2024,52(7):24-32[点击复制] |
|
摘要: |
针对使用支持向量机(support vector machine, SVM)对变压器进行故障诊断时有效特征提取困难、模型参数难以选择的问题,提出一种基于特征提取与INGO-SVM的变压器故障诊断方法。首先,使用核主成分分析(kernel principal component analysis, KPCA)方法对构建的21维待选特征进行特征融合和低维敏感特征提取。其次,使用佳点集、随机反向学习和维度交叉学习等策略对北方苍鹰优化算法(northern goshawk optimization, NGO)进行改进。通过2个典型测试对改进北方苍鹰优化算法(improved northern goshawk optimization, INGO)进行性能测试,验证了INGO算法的优越性。然后,基于KPCA提取的低维敏感特征,使用INGO对SVM的参数进行组合寻优,建立基于KPCA特征提取与INGO-SVM的变压器故障诊断模型。最后,对不同变压器故障诊断模型进行实例仿真对比实验。结果表明:所提方法故障诊断精度高、稳定性好,更适用于变压器的故障诊断。 |
关键词: 变压器 故障诊断 支持向量机 核主成分分析 北方苍鹰优化算法 |
DOI:10.19783/j.cnki.pspc.230936 |
投稿时间:2023-07-21修订日期:2023-10-05 |
基金项目:国家自然科学基金项目资助(52177016);贵州省科技计划项目资助(黔科合支撑[2021]365);贵州大学自然科学特别科学研究基金项目资助(2021-45) |
|
Transformer fault diagnosis method based on feature extraction and INGO-SVM |
BAO Jinshan1,YANG Dingkun2,ZHANG Jing1,ZHANG Ying1,3,YANG Jiarong1,HU Kelin1 |
(1. College of Electrical Engineering, Guizhou University, Guiyang 550025, China; 2. College of Advanced Manufacturing
Engineering, Chongqing University of Posts & Telecommunications, Chongqing 400065, China;
3. Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550002, China) |
Abstract: |
It is difficult to extract effective features and select model parameters when using a support vector machine (SVM) for transformer fault diagnosis. A transformer fault diagnosis method based on feature extraction and an improved northern goshawk optimization (INGO) algorithm optimized SVM is proposed. First, kernel principal component analysis (KPCA) is used to conduct feature fusion and low dimensional sensitive feature extraction for the 21 dimensional candidate feature. Secondly, strategies such as good point set, random opposition-based learning, and dimensional cross learning are used to improve the northern goshawk optimization (NGO) algorithm. The performance of the INGO algorithm is tested using two typical test functions, verifying its superiority. Then, based on the low dimensional sensitive feature extracted by KPCA, INGO is used to optimize the parameters of the SVM, and a transformer fault diagnosis model is established based on KPCA feature extraction and INGO-SVM. Finally, simulation and comparative experiments are conducted on different transformer fault diagnosis models. The results show that the proposed method has high accuracy and good stability in fault diagnosis, and is more suitable for transformer fault diagnosis. |
Key words: transformer fault diagnosis support vector machine kernel principal component analysis NGO |