一种用于变压器故障诊断的贝叶斯网络优化方法

doi:10.16180/j.cnki.issn1007-7820.2024.08.005

摘要/Abstract

摘要：

针对变压器故障诊断效率低的问题,文中将油中溶解气体分析与人工智能方法相结合,提出了一种改进蝗虫优化算法优化贝叶斯网络的变压器故障诊断方法。利用差分进化算法和与模拟退火算法对蝗虫算法进行改进,提高了算法的优化能力。将改进蝗虫算法应用于贝叶斯网络结构来学习构建变压器故障诊断模型,利用所提方法对变压器进行故障诊断。实验结果表明,该方法诊断正确率达到了92.7%,与其他算法所构建的诊断模型相比具有更高的故障诊断准确率。

关键词: 变压器, 蝗虫算法, 差分进化算法, 模拟退火算法, 油中溶解气体, 贝叶斯网络, 故障诊断, 结构学习

Abstract:

In view of the low efficiency of transformer fault diagnosis, an improved grasshopper optimization algorithm is proposed by combining dissolved gas analysis in oil with artificial intelligence method to optimize the transformer fault diagnosis method of Bayesian network. The differential evolution algorithm and simulated annealing algorithm are used to improve the locust algorithm, which improve the optimization ability of the algorithm. The improved locust algorithm is applied to the Bayesian network structure learning to construct the transformer fault diagnosis model, and the method proposed in this study is used to diagnose the transformer fault. The experimental results show that the diagnosis accuracy of this method is 92.7%, which is higher than that of other algorithms.

Key words: transformer, locust algorithm, differential evolution algorithm, simulated annealing algorithm, dissolved gas in oil, Bayesian network, fault diagnosis, structural learning

中图分类号:

TP18

仝兆景, 荆利菲, 兰孟月. 一种用于变压器故障诊断的贝叶斯网络优化方法[J]. 电子科技, 2024, 37(8): 34-39.

TONG Zhaojing, JING Lifei, LAN Mengyue. A Bayesian Network Optimization Method for Transformer Fault Diagnosis[J]. Electronic Science and Technology, 2024, 37(8): 34-39.

图/表 9

图1

图2

表1

表2

表3

图3

图4

图5

图6

参考文献 19

[1]	徐尧宇, 李元, 王怡静, 等. 信息缺失下变压器状态预警方法[J]. 高电压技术, 2020, 46(9):3062-3069.
	Xu Yaoyu, Li Yuan, Wang Yijing, et al. Early-warning methods of transformer conditions under information deficiency[J]. High Voltage Engineering, 2020, 46(9):3062-3069.
[2]	杨亚东. 基于DGA的电力变压器智能故障诊断研究[D]. 郑州: 郑州大学, 2020:1-75.
	Yang Yadong. Study on intelligent fault diagnosis of power transformer based on DGA[D]. Zhengzhou: Zhengzhou University, 2020:1-75.
[3]	朱保军, 咸日常, 范慧芳, 等. WRSR与改进朴素贝叶斯融合的变压器故障诊断技术研究[J]. 电力系统保护与控制, 2021, 49(20):120-128.
	Zhu Baojun, Xian Richang, Fan Huifang, et al. Transformer fault diagnosis technology based on the fusion of WRSR and improved naive Bayes[J]. Power System Protection and Control, 2021, 49(20):120-128.
[4]	林凡勤, 李明明, 郭红. 变压器故障诊断技术综述[J]. 计算机与现代化, 2022(3):116-126.
	Lin Fanqin, Li Mingming, Guo Hong. Review on fault diagnosis technology of transformer[J]. Computer and Modernization, 2022(3):116-126.
[5]	杨宇, 曾国辉, 黄勃. 基于人工鱼群算法和LS_SSVM的变压器故障诊断[J]. 电子科技, 2020, 33(11):36-40,45.
	Yang Yu, Zeng Guohui, Huang Bo. A transformer fault diagnosis method integrating artificial fish swarm algorithm with least square support vector machine[J]. Electronic Science and Technology, 2020, 33(11):36-40,45.
[6]	汪徐阳, 易映萍, 李田丰. 一种用于变压器故障诊断的卷积神经网络优化方法[J]. 电子科技, 2023, 36(12):79-86.
	Wang Xuyang, Yi Yingping, Li Tianfeng. A convolutional neural network optimization method for fault diagnosis of power transformer[J]. Electronic Science and Technology, 2023, 36(12):79-86.
[7]	张国治, 陈康, 方荣行, 等. 基于DGA与鲸鱼算法优化Logit Boost-决策树的变压器故障诊断方法[J]. 电力系统保护与控制, 2023, 51(7):63-72.
	Zhang Guozhi, Chen Kang, Fang Rongxing, et al. Transformer fault diagnosis method based on DGA and whale algorithm optimizing Logit Boost-decision tree[J]. Power System Protection and Control, 2023, 51(7):63-72.
[8]	王春明, 朱永利. 基于NSGA2优化正则极限学习机的变压器油色谱故障诊断[J]. 高压电器, 2020, 56(9):210-215.
	Wang Chunming, Zhu Yongli. Transformer oil chromatography fault diagnosis based on regularized extreme learning machine optimized by NSGA2[J]. High Voltage Apparatus, 2020, 56(9):210-215.
[9]	曹伟嘉, 杨留方, 徐天奇, 等. 基于IGA-XGBoost的变压器故障诊断研究[J]. 自动化与仪器仪表, 2022, 41(4):1-5.
	Cao Weijia, Yang Liufang, Xu Tianqi, et al. Transformer fault diagnosis based on IGA-X Goost[J]. Automation and Instrumentation, 2022, 41(4):1-5.
[10]	邓焱. 基于多维信息融合的变压器状态评估与故障诊断方法研究[D]. 广州: 华南理工大学, 2018:1-104.
	Deng Yan. A study transformer state evaluation and fault diagnosis based on multi-dimensional information fusion[D]. Guangzhou: South China University of Technology, 2018:1-104.
[11]	康佳宇, 张沈习, 张庆平, 等. 基于ANOVA和BO-SVM的变压器故障诊断方法[J]. 高电压技术, 2023, 49(5):1882-1891.
	Kang Jiayu, Zhang Shenxi, Zhang Qingping, et al. Fault diagnosis method of transformer based on ANOVA and BO-SVM[J]. High Voltage Engineering, 2023, 49(5):1882-1891.
[12]	曹伟嘉, 杨留方, 徐天奇, 等. 基于精英反策略麻雀搜索优化随机森林的变压器故障诊断[J]. 国外电子测量技术, 2022, 41(2):138-143.
	Cao Weijia, Yang Liufang, Xu Tianqi, et al. Transformer fault diagnosis based on elite counterstrategy sparrow search algorithm optimized random forest[J]. Foreign Electronic Measurement Technology, 2022, 41(2):138-143.
[13]	崔欢欢. 基于量子贝叶斯网络的电力变压器故障诊断方法研究[D]. 北京: 华北电力大学, 2015:1-55.
	Cui Huanhuan. The research of power transformer fault diagnosis method based on quantum Bayesian network[D]. Beijing: North China Electric Power University, 2015:1-55.
[14]	李兴东. 基于贝叶斯网络理论的变压器故障综合诊断方法的研究[D]. 武汉: 华中科技大学, 2012:1-44.
	Li Xingdong. Synthetic fault diagnosis of power transformer based on Bayesian network[D]. Wuhan: Huazhong University of Science and Technology, 2012:1-44.
[15]	陈学赓. 基于粗糙集理论和贝叶斯网络的变压器故障诊断方法研究[D]. 山东: 山东大学, 2018:1-60.
	Chen Xuegeng. Transformer fault diagnosis based on rough set theory and Bayesian network[D]. Shandong: Shandong University, 2018:1-60.
[16]	Saremi S, Mirjalili S, Lewis A. Grasshopper optimization algorithm:Theory and application[J]. Advances in Engineering Software, 2017, 10(5):30-47.
[17]	杨廷方, 张航, 黄立滨. 基于改进型主成分分析的电力变压器潜伏性故障诊断[J]. 电力自动化设备, 2015, 35(6):149-153.
	Yang Tingfang, Zhang Hang, Huang Libin. Incipient fault diagnosis based on improved principal component analysis for power transformer[J]. Electric Power Automation Equipment, 2015, 35(6):149-153.
[18]	朱永利, 尹金良. 组合核相关向量机在电力变压器故障诊断中的应用研究[J]. 中国电机工程学报, 2013, 33(22):68-74.
	Zhu Yongli, Yin Jinliang. Study on application of multikernel learning relevance vector machine in fault diagnosis of power transformers[J]. Proceedings of the CSEE, 2013, 33(22):68-74.
[19]	唐勇波, 桂卫华, 彭涛, 等. PCA和KICA特征提取的变压器故障诊断模型[J]. 高电压技术, 2014, 40(2):557-563.
	Tang Yongbo, Gui Weihua, Peng Tao, et al. Transformer fault diagnosis model based on PCA and KICA feature extraction[J]. High Voltage Engineering, 2014, 40(2):557-563.

状态编码	运行状态
F₀	正常
F₁	低温过热
F₂	中温过热
F₃	高温过热
F₄	局部放电
F₅	低能放电
F₆	高能放电

故障类型	样本数据	训练样本	测试样本
正常	48	38	10
低温过热	48	38	10
中温过热	52	41	11
局部放电	55	44	11
低能放电	96	77	19
高能放电	88	70	18
高温过热	58	46	12

故障类型	DESAGOA- BNs/%	GOA- BNs/%	GWO- BNs/%	PSO- BNs/%
正常	100.0	90.0	80.0	70.0
低温过热	100.0	80.0	70.0	70.0
中温过热	90.9	72.7	90.9	81.8
局部放电	90.9	90.9	72.7	72.7
低能放电	89.4	84.3	84.2	78.9
高能放电	94.4	88.9	83.3	77.8
高温过热	83.3	75.0	83.3	66.7