作者:冯志亮, 肖涵麒, 任文凤, 杜艳丽
作者单位:北华大学电气与信息工程学院,吉林 吉林 132021
关键词:海鸥优化算法;支持向量机;PCA降维;变压器故障诊断
摘要:
针对支持向量机对变压器进行故障诊断时准确率较低的问题,提出一种海鸥算法优化支持向量机的方法。首先增加不同的气体分数比值特征,扩充变压器故障数据所包含的信息特征,然后采用主成分分析法(PCA)提取输入变量特征,降低特征变量的维数,降低变量之间的相关性,最后用海鸥优化算法(SOA)对支持向量机的核参数和惩罚因子进行优化,提高支持向量机建模准确度。仿真结果表明,与粒子群(PSO)、遗传算法(GA)相比,海鸥优化算法优化支持向量机(SOA-SVM)可以明显提高变压器故障诊断的准确率,并且可靠性和泛化性能表现也有提高。
Transformer fault diagnosis based on principal component analysis and seagull optimization support vector machine
FENG Zhiliang, XIAO Hanqi, REN Wenfeng, DU Yanli
School of Electrical and Information Engineering, Beihua University, Jilin 132021, China
Abstract: Aiming at the problem of low accuracy of support vector machine (SVM) in transformer fault diagnosis, a seagull algorithm is proposed to optimize SVM. Firstly, different gas fraction ratio features are added to expand the information features contained in transformer fault data. Then principal component analysis (PCA) is used to extract the features of input variables to reduce the dimension of feature variables and the correlation between variables. Finally, seagull optimization algorithm (SOA) is used to optimize the kernel parameters and penalty factors of support vector machine, Improve the accuracy of SVM modeling. Simulation results show that compared with particle swarm optimization (PSO) and genetic algorithm (GA), seagull optimization support vector machine (SOA-SVM) can significantly improve the accuracy of transformer fault diagnosis, and improve the reliability and generalization performance.
Keywords: seagull optimization algorithm;support vector machine;PCA dimension reduction;transformer fault diagnosis
2023, 49(2):99-105 收稿日期: 2021-03-24;收到修改稿日期: 2021-06-18
基金项目: 国家自然科学基金青年基金资助项目(61300098);吉林省教育厅“十三五”科学研究项目(JJKH20180340KJ)
作者简介: 冯志亮(1996-),男,山东青州市人,硕士研究生,专业方向为变压器故障诊断
参考文献
[1] FAIZ J, SOLEIMANI M. Assessment of computational intelligence and conventional dissolved gas analysis methods for transformer fault diagnosis[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2018, 25(5): 1798-1806
[2] KHAN S A, EQUBAL M D, ISLAM T I. A comprehensive comparative study of DGA based transformer fault diagnosis using fuzzy logic and ANFIS models[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2015, 22(1): 590-596
[3] 刘凯, 彭维捷, 杨学君. 特征优化和模糊理论在变压器故障诊断中的应用[J]. 电力系统保护与制, 2016, 44(15): 54-60
[4] WEN L, LI X, GAO L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998
[5] 邵宇鹰, 王枭, 彭鹏, 等. 基于声场听觉感知的变压器故障诊断方法研究[J]. 中国测试, 2021, 47(3): 92-97
[6] 陈尔奎, 韩清春, 周栾. 基于布谷鸟算法和BP神经网络的矿用变压器故障诊断[J]. 煤炭技术, 2018, 37(6): 223-224
[7] 陈欢, 彭辉, 舒乃秋, 等. 基于蝙蝠算法优化最小二乘双支持向量机的变压器故障诊断[J]. 高电压技术, 2018, 44(11): 3664-3671
[8] ALY S, MOHAMED A. Unknown-length handwritten numeral string recognition using cascade of pca-svmnet classifiers[J]. IEEE Access, 2019, 7: 52024-52034
[9] YUAN X, LIU Z, MIAO Z. Fault diagnosis of analog circuits based on ih-pso optimized support vector machine[J]. IEEE Access, 2019, 7: 137945-137958
[10] 唐勇波. 数据驱动的大型电力变压器故障诊断和预测研究[D]. 长沙: 中南大学, 2013.
[11] 张洋. 支持向量机和相关向量机在变压器油溶解气体分析中的应用研究[D]. 秦皇岛: 燕山大学, 2019.
[12] 孙琛. 基于机器学习算法的变压器故障诊断[D]. 上海: 上海交通大学, 2018
[13] 杨烨. 基于二进制海鸥优化算法的特征选择算法研究[D]. 南昌: 江西财经大学, 2020.
[14] 谢国民, 倪乐水. 基于IABC优化SVM的变压器故障诊断[J]. 电力系统保护与控制, 2020, 48(15): 156-163
[15] 党东升. 基于改进量子粒子群优化支持向量机的变压器故障诊断方法[J]. 电力科学与技术学报, 2019, 34(3): 108-113