Oil-immersed transformer fault diagnosis method based on PCA and SSA-LightGBM

doi:10.3969/j.issn.2097-0706.2023.03.002

Abstract

Abstract:

In view of low diagnosis accuracy on oil-immersed transformer faults caused by the fault complexity at present，an oil-immersed transformer fault diagnosis method based on PCA and SSA-LightGBM is proposed.The data of dissolved gas in oil are collected，and a 17-dimensional fault feature matrix is constructed with codeless ratio method.The joint feature is obtained in the normalized matrix.Feature fusion is performed by using principal component analysis which can eliminate the redundant information between variables，and construct fusion features.The SSA-LightGBM transformer diagnosis model is constructed，and the ten-fold cross-validation method is used to verify the classification ability of the model.The experimental results show that the average fault diagnosis accuracy of the proposed model is 93.6%，which is 8.1 and 5.7 percentage points higher than that of GA-LightGBM and GWO-LightGBM fault diagnosis models，respectively， verifying that this method can effectively improve the fault diagnosis performance for transformers.

Key words: fault diagnosis, transformer, principal component analysis, sparrow search algorithm, LightGBM, sparrow search algorithm

CLC Number:

TK01：TM41

XIAO Honglei, LIU Yi, XIA Hongjun, MIAO Yufeng, YU Xiaoling, YANG Haiqi. Oil-immersed transformer fault diagnosis method based on PCA and SSA-LightGBM[J]. Integrated Intelligent Energy, 2023, 45(3): 9-16.

Figures/Tables 9

Table 1

Fig.1

Fig.2

Table 2

Fig.3

Table 3

Table 4

Table 5

Table 6

References 30

[1]	韩志远, 王广健, 张晓静, 等. 基于故障模型的大型变压器故障综合诊断方法与应用[J]. 华电技术, 2018, 40(10):22-26,77.
	HAN Zhiyuan, WANG Guangjian, ZHANG Xiaojing, et al. Application of large transformer comprehensive fault diagnosis based on fault model[J]. Huadian Technology, 2018, 40(10):22-26,77.
[2]	马金平. 变压器油中含气量超标检查与处理[J]. 华电技术, 2018, 40(7):35-37,78.
	MA Jinping. Inspection and processing of excessive gas content in transformer oil[J]. Huadian Technology, 2018, 40(7):35-37,78.
[3]	康振华. 大型电力变压器油色谱在线监测技术与案例分析[J]. 华电技术, 2018, 40(3):17-20,77.
	KANG Zhenhua. On‑line monitoring technology and case analysis of large power transformer oil chromatography[J]. Huadian Technology, 2018, 40(3):17-20,77.
[4]	吴鑫杰. 充氮气油浸式变压器取油样技术探讨[J]. 华电技术, 2018, 40(2):46-47,79.
	WU Xinjie. Discussion over oil sampling technique used in oil‑immersed transformer filled with nitrogen[J]. Huadian Technology, 2018, 40(2):46-47,79.
[5]	龙思成, 黄志鸿. 基于多尺度极限融合网络的电力变压器故障诊断方法研究[J]. 综合智慧能源, 2022, 44(9):78-83. doi: 10.3969/j.issn.2097-0706.2022.09.011
	LONG Sicheng, HUANG Zhihong. Research on fault diagnosis method of power transformers based on multi‑scale extreme fusion network[J]. Integrated Intelligent Energy, 2022, 44(9):78-83. doi: 10.3969/j.issn.2097-0706.2022.09.011
[6]	张镱议, 彭鸿博, 李昕, 等. 基于DGA特征量优选与改进磷虾群算法优化支持向量机的变压器故障诊断模型[J]. 电测与仪表, 2019, 56(21):110-116.
	ZHANG Yiyi, PENG Hongbo, LI Xin, et al. Fault diagnosis model of power transformers based on DGA features selection and improved krill herd algorithm optimization SVM[J]. Electrical Measurement & Instrumentation, 2019, 56(21):110-116.
[7]	李黄曼, 张勇, 张瑶. 基于ISSA优化SVM的变压器故障诊断研究[J]. 电子测量与仪器学报, 2021, 35(3):123-129.
	LI Huangman, ZHANG Yong, ZHANG Yao. Study of transformer fault diagnosis based on improved sparrow search algorithm optimized support vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(3):123-129.
[8]	余松, 胡东, 唐超, 等. 基于TLR-ADASYN平衡化数据集的MSSA-SVM变压器故障诊断[J]. 高电压技术, 2021, 47(11):3845-3853.
	YU Song, HU Dong, TANG Chao, et al. MSSA-SVM transformer fault diagnosis method based on TLR-ADASYN balanced data set[J]. High Voltage Engineering, 2021, 47(11):3845-3853.
[9]	朱瑞金, 郝东光, 胡石峰. 小样本条件下基于卷积孪生网络的变压器故障诊断[J]. 电力系统及其自动化学报, 2021, 33(1):64-69,84.
	ZHU Ruijin, HAO Dongguang, HU Shifeng. Transformer fault diagnosis based on convolutional siamese network with small samples[J]. Proceedings of the CSU-EPSA, 2021, 33(1):64-69,84.
[10]	禹建丽, 周瑞芳. 一种基于神经网络和模糊理论的变压器故障诊断[J]. 中南大学学报(自然科学版), 2013, 44(S1):243-247.
	YU Jianli, ZHOU Ruifang. Transformer fault diagnosis based on neural network and fuzzy theory[J]. Journal of Central South University(Science and Technology), 2013, 44(S1):243-247.
[11]	王晶, 许素安, 洪凯星, 等. 基于DGA特征量优选与GA-SVM的变压器故障诊断模型[J]. 变压器, 2020, 57(12):36-40,46.
	WANG Jing, XU Suan, HONG Kaixing, et al. Transformer based on DGA feature quantity optimization and GA-SVM fault diagnosis model[J]. Transformer, 2020, 57(12):36-40,46.
[12]	方涛, 钱晔, 郭灿杰, 等. 基于天牛须搜索优化支持向量机的变压器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(20):90-96.
	FANG Tao, QIAN Ye, GUO Canjie, et al. Research on transformer fault diagnosis based on a beetle antennae search optimized support vector machine[J]. Power System Protection and Control, 2020, 48(20):90-96.
[13]	谢国民, 倪乐水, 曹媛. 基于VSRP与β-GWO-SVM的变压器故障辨识方法[J]. 高电压技术, 2021, 47(10):3635-3641.
	XIE Guomin, NI Leshui, CAO Yuan. Transformer fault identification method based on VSRP and β-GWO-SVM[J]. High Voltage Engineering, 2021, 47(10):3635-3641.
[14]	刘华, 刘江永. 基于图卷积神经网络的电力变压器故障诊断[J]. 湖南科技大学学报(自然科学版), 2021, 36(3):75-81.
	LIU Hua, LIU Jiangyong. Fault diagnosis of power transformer based on graph convolutional network[J]. Journal of Hunan University of Science & Technology (Natural Science Edition), 2021, 36(3):75-81.
[15]	杨德昌, 廖文龙, 任翔, 等. 基于胶囊网络的电力变压器故障诊断[J]. 高电压技术, 2021, 47(2):415-424.
	YANG Dechang, LIAO Wenlong, REN Xiang, et al. Fault diagnosis of transformer based on capsule network[J]. High Voltage Engineering, 2021, 47(2):415-424.
[16]	王涤, 马爱军, 归宇, 等. 基于P‑CNN的局部放电绝缘故障融合诊断[J]. 高电压技术, 2020, 46(8):2897-2905.
	WANG Di, MA Aijun, GUI Yu, et al. Diagnosis of partial discharge insulation fault fusion based on P‑CNN[J]. High Voltage Engineering, 2020, 46(8):2897-2905.
[17]	吴瞻宇, 董明, 王健一, 等. 基于模糊关联规则挖掘的电力变压器故障诊断方法[J]. 高压电器, 2019, 55(8):157-163.
	WU Zhanyu, DONG Ming, WANG Jianyi, et al. Fault diagnosis of power transformer based on fuzzy association rules mining[J]. High Voltage Apparatus, 2019, 55(8):157-163.
[18]	谢松, 邹阳, 蔡金锭. 基于模糊粗糙集的变压器油纸绝缘状态评估[J]. 仪器仪表学报, 2017, 38(1):190-197.
	XIE Song, ZOU Yang, CAI Jinding. Assessment of transformer oil‑paper insulation status with fuzzy rough set[J]. Chinese Journal of Scientific Instrument, 2017, 38(1):190-197.
[19]	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]. 电力系统保护与控制, 2016, 44(15):54-60.
	LIU Kai, PENG Weijie, YANG Xuejun. Method of fault diagnosis for power transformer based on optimizing characteristics and the fuzzy theory[J]. Power System Protection and Control, 2016, 44(15):54-60.
[20]	王福忠, 邵淑敏. 基于模糊综合评价法的变压器运行状态评估[J]. 计算机仿真, 2015, 32(6):141-145.
	WANG Fuzhong, SHAO Shumin. Fuzzy strategy on running state evaluation of oil‑immersed power transformer[J]. Computer Simulation, 2015, 32(6):141-145.
[21]	柴琴琴, 陈舒迪, 王武, 等. 基于改进GWO-LightGBM的滚动轴承未知故障诊断[J]. 航空动力学报, 2022, 37(4):848-855.
	CHAI Qinqin, CHEN Shudi, WANG Wu, et al. Unknown fault diagnosis of rolling bearings based on improved GWO-LightGBM[J]. Journal of Aerospace Power, 2022, 37(4):848-855.
[22]	王凯. 基于集成学习的变压器故障预测方法研究[D]. 济南: 山东大学, 2021.
	WANG Kai. Research on transformer fault prediction method based on ensemble learning[D]. Jinan: Shandong University, 2021.
[23]	袁淼. 基于油中气体分析的变压器故障智能诊断方法研究[D]. 广州: 广东工业大学, 2021.
	YUAN Miao. Research on intelligent diagnosis method of transformer fault based on dissolved gas analysis[D]. Guangzhou: Guangdong University of Technology, 2021.
[24]	刘亚玲. 基于深度学习的10 kV馈线故障预测方法研究[D]. 重庆: 重庆大学, 2019.
	LIU Yaling. Research on 10 kV feeder fault prediction method based on deep learning[D]. Chongqing: Chongqing University, 2019.
[25]	覃煜, 黄慧红, 方健, 等. 基于FCM和改进PCA的变压器故障诊断[J]. 高压电器, 2018, 54(12):262-267.
	QIN Yu, HUANG Huihong, FANG Jian, et al. Fault diagnosis of transformer based on FCM and improved PCA[J]. High Voltage Apparatus, 2018, 54(12):262-267.
[26]	张育杰, 冯健, 李典阳, 等. 基于油色谱数据的变压器故障征兆新优选策略[J]. 电网技术, 2021, 45(8):3324-3331.
	ZHANG Yujie, FENG Jian, LI Dianyang, et al. New feature selection method for transformer fault diagnosis based on DGA data[J]. Power System Technology, 2021, 45(8):3324-3331.
[27]	白星振, 臧元, 葛磊蛟, 等. 变压器故障诊断用油中溶解气体征兆优选方法[J/OL]. 高电压技术:1-16(2022-09-08)[2022-10-04].https://doi.org/10.13336/j.1003-6520.hve.20220670.
	BAI Xingzhen, ZANG Yuan, GE Leijiao, et al. Selection method of feature derived from dissolved gas in oil for fault diagnosis of transformers[J/OL]. High Voltage Engineering:1-16(2022-09-08)[2022-10-04].https://doi.org/10.13336/j.1003-6520.hve.20220670.
[28]	张彼德, 梅婷, 王涛. 电力变压器故障诊断的k值自适应加权KNN算法研究[J]. 湖北电力, 2020, 44(2):6-12.
	ZHANG Bide, MEI Ting, WANG Tao. Research on adaptive k‑value weighted KNN algorithm for power transformer fault diagnosis[J]. Hubei Electric Power, 2020, 44(2):6-12.
[29]	刘裕舸, 黄忠辉. 基于SVM算法优化的变压器故障诊断研究[J]. 红水河, 2022, 41(2):89-93.
	LIU Yuge, HUANG Zhonghui. Transformer fault diagnosis based on SVM algorithm optimization[J]. HongShui River, 2022, 41(2):89-93.
[30]	王妍, 张太华. 基于数字孪生的优化概率神经网络变压器故障诊断[J]. 组合机床与自动化加工技术, 2020(11):20-23. doi: 10.13462/j.cnki.mmtamt.2020.11.005
	WANG Yan, ZHANG Taihua. Fault diagnosis of transformers based on optimal probabilistic neutral network based on digital twin[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(11):20-23.

编号	特征量	编号	特征量
1	φ（H₂）	10	φ（C₂H₆)/φ（TH）
2	φ（CH₄）	11	φ（H₂)/φ（TH）
3	φ（C₂H₄）	12	φ（CH₄)/φ（H₂）
4	φ（C₂H₂）	13	φ（C₂H₂)/φ（C₂H₆）
5	φ（C₂H₆）	14	φ（C₂H₄)/φ（C₂H₆）
6	φ（TH）	15	φ（C₂H₂)/φ（C₂H₄）
7	φ（CH₄)/φ（TH）	16	φ（H₂)/φ(H₂+TH)）
8	φ（C₂H₄)/φ（TH）	17	φ(CH₄+C₂H₄)/φ（TH)
9	φ（C₂H₂)/φ（TH）

参数名称	寻优范围	最优值
max_depth	(4,12)	6.000
feature_leaves	(0,1)	0.700
learning rate	(0,1)	0.814
subsample	(0,1)	0.632

工作状态	样本总数	测试样本数	诊断正确数量	准确率/%
正常状态	43	13	11	84.6
高温热故障	45	14	11	78.6
中温热故障	50	15	15	100.0
中低温热故障	128	39	38	97.4
低能放电	50	15	15	100.0
高能放电	78	23	23	100.0
局部放电	119	35	33	94.3
总体	513	154	146	94.8
平均	—	—	—	93.6

工作状态	诊断准确率
工作状态	GA-LightGBM	GWO-LightGBM	SSA-LightGBM
正常状态	82.2	75.9	84.6
高温热故障	77.4	78.1	78.6
中温热故障	89.6	95.9	100.0
中低温热故障	87.1	92.1	97.4
低能放电	88.1	94.3	100.0
高能放电	87.6	90.4	100.0
局部放电	87.3	89.5	94.3
平均	85.6	88.0	93.6