Research on Fault Diagnosis Method of Power Transformer Based on KPCA and IHHO-LSSVM

doi:10.11985/2022.01.013

Abstract

Abstract:

In order to improve the accuracy of power transformer fault identification, a power transformer fault diagnosis method based on kernel principal component analysis(KPCA) and improved Harris hawk algorithm(IHHO) optimized least square support vector machine(LSSVM) is proposed. First, use nuclear principal component analysis to preprocess the original fault data of the transformer to remove redundant data. Secondly, combine the Sigmoid deformation function and the point symmetry strategy to improve the traditional Harris hawk optimization(HHO), and combine with HHO and genetic algorithm(GA). The performance comparison proves that the accuracy of the solution and the speed of network convergence have been improved. Finally, IHHO is used to optimize the related hyperparameters of LSSVM to obtain a transformer fault diagnosis model combining KPCA and IHHO-LSSVM. The results show that the diagnosis accuracy of the proposed model is 95.6%, which is 8.9% and 16.7% higher than other fault diagnosis models, respectively, which proves that the proposed method can effectively improve the performance of transformer fault diagnosis.

Key words: Transformer, fault diagnosis, LDA, HHO, LSSVM

CLC Number:

TM41

SONG Liye, FAN Yiling, WANG Yizeng. Research on Fault Diagnosis Method of Power Transformer Based on KPCA and IHHO-LSSVM[J]. Journal of Electrical Engineering, 2022, 17(1): 95-103.

Figures/Tables 13

References 22

[1]	赵莉华, 徐立, 刘艳, 等. 基于点对称变换与图像匹配的变压器机械故障诊断方法[J]. 电工技术学报, 2021, 36(17):3614-3626.
	ZHAO Lihua, XU Li, LIU Yan, et al. Transformer mechanical fault diagnosis method based on point symmetry transformation and image matching[J]. Transactions of China Electrotechnical Society, 2021, 36(17):3614-3626.
[2]	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):3324-3332.
	ZHANG Yujie, FENG Jian, LI Dianyang, et al. New optimization strategy for transformer fault symptoms based on oil chromatographic data[J]. Power System Technology, 2021, 45(8):3324-3332.
[3]	KIM S, JO S H, KIM W, et al. A semi-supervised autoencoder with an auxiliary task (SAAT) for power transformer fault diagnosis using dissolved gas analysis[J]. IEEE Access, 2020, 8:178295-178310. doi: 10.1109/ACCESS.2020.3027830
[4]	谢国民, 蔺晓雨. 基于改进SSA优化MDS-SVM的变压器故障诊断方法[J/OL]. 控制与决策:1-9 [2021-12-03]. https://doi.org/10.13195/j.kzyjc.2021.1437.
	XIE Guomin, LIN Xiaoyu. Transformer fault diagnosis method based on improved SSA to optimize MDS-SVM[J/OL]. Control and Decision:1-9 [2021-12-03]. https://doi.org/10.13195/j.kzyjc.2021.1437.
[5]	黄新波, 王享, 田毅, 等. 基于PSO-ELM融合动态加权AdaBoost的变压器故障诊断方法[J]. 高压电器, 2020, 56(5):39-46.
	HUANG Xinbo, WANG Xiang, TIAN Yi, et al. Transformer fault diagnosis method based on PSO-ELM fusion dynamic weighted AdaBoost[J]. High Voltage Apparatus, 2020, 56(5):39-46.
[6]	LI Y, MA L. Fault diagnosis of power transformer based on improved particle swarm optimization OS-ELM[J]. Archives of Electrical Engineering, 2019, 68(1):161-172.
[7]	LI X, ZHU Y. Optimizing depth discrimination restricted boltzmann machine based on genetic algorithm for fault diagnosis of transformer[J]. International Core Journal of Engineering, 2019, 5(10):108-116.
[8]	TAHA I B M, IBRAHIM S, MANSOUR D E A. Power transformer fault diagnosis based on DGA using a convolutional neural network with noise in measurements[J]. IEEE Access, 2021(99):1-1.
[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 twin network under small sample conditions[J]. Proceedings of the CSU-EPSA, 2021, 33(1):64-69,84.
[10]	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. Research on transformer fault diagnosis based on ISSA optimized SVM[J]. Journal of Electronic Measurement and Instrument, 2021, 35(3):123-129.
[11]	SAHRI Z B, YUSOF R B. Support vector machine-based fault diagnosis of power transformer using k nearest-neighbor imputed DGA dataset[J]. Journal of Computer & Communications, 2018, 2(9):22-31.
[12]	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 chromatographic fault diagnosis based on NSGA2 optimized regular extreme learning machine[J]. High Voltage Apparatus, 2020, 56(9):210-215.
[13]	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):415-425.
	YANG Dechang, LIAO Wenlong, REN Xiang, et al. Power transformer fault diagnosis based on capsule network[J]. High Voltage Engineering, 2021, 47(2):415-425.
[14]	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 based on TLR-ADASYN balanced data set[J]. High Voltage Engineering, 2021, 47(11):3845-3853.
[15]	吴晓欣, 何怡刚, 段嘉珺, 等. 考虑复杂时序关联特性的Bi-LSTM变压器DGA故障诊断方法[J]. 电力自动化设备, 2020, 40(8):184-193.
	WU Xiaoxin, HE Yigang, DUAN Jiajun, et al. Bi-LSTM transformer DGA fault diagnosis method considering complex timing correlation characteristics[J]. Electric Power Automation Equipment, 2020, 40(8):184-193.
[16]	李一鸣, 白龙, 蒋周翔, 等. 基于EEMD-KPCA和KL散度的垮落煤岩识别[J]. 煤炭学报, 2020, 45(2):827-835.
	LI Yiming, BAI Long, JIANG Zhouxiang, et al. Caving coal and rock recognition based on EEMD-KPCA and KL divergence[J]. Acta China Coal Society, 2020, 45(2):827-835.
[17]	邵良杉, 徐波. 岩溶塌陷倾向性等级的KPCA-SVM预测模型[J]. 中国安全科学学报, 2015, 25(3):60-65.
	SHAO Liangshan, XU Bo. KPCA-SVM prediction model of karst collapse tendency grade[J]. China Safety Science Journal, 2015, 25(3):60-65.
[18]	温廷新, 孙红娟, 张波, 等. 煤与瓦斯突出预测的QGA-LSSVM模型[J]. 中国安全生产科学技术, 2015, 11(5):5-12.
	WEN Tingxin, SUN Hongjuan, ZHANG Bo, et al. QGA-LSSVM model for coal and gas outburst prediction[J]. Journal of Safety Science and Technology, 2015, 11(5):5-12.
[19]	温廷新, 陈晓宇, 杨红玉, 等. 基于优化Bagging-LSSVM模型的冲击地压预测[J]. 中国安全科学学报, 2017, 27(6):121-126.
	WEN Tingxin, CHEN Xiaoyu, YANG Hongyu, et al. Rockburst prediction based on optimized Bagging-LSSVM model[J]. China Safety Science Journal, 2017, 27(6):121-126.
[20]	VAPNIK V N. The nature of statistical learning theory[M]. New York: Springer-Verlag, 1998.
[21]	HEIDARI A A, MIRJALILI S, FARIS H, et al. Harris hawks optimization:Algorithm and applications[J]. Future Generation Computer Systems, 2019, 97:849-872. doi: 10.1016/j.future.2019.02.028
[22]	ZHAO W G, ZHANG Z X, WANG L Y. Manta ray foraging optimization:An effective bio-inspired optimizer for engineering applications[J]. Engineering Applications of Artificial Intelligence, 2020, 87:103300. doi: 10.1016/j.engappai.2019.103300

函数		HHO	GA	IHHO
F1	Min	6.35×10^-60	1.23×10²	5.43×10^-323
	Mean	2.07×10^-51	1.54×10²	7.41×10^-323
	Std	1.04×10^-50	1.04×10¹	0
F2	Min	8.88×10^-16	7.17×10^-1	8.88×10^-16
	Mean	8.88×10^-16	1.34×10⁰	8.88×10^-16
	Std	0	2.23×10¹	0
F3	Min	3.09×10^-4	4.67×10^-3	3.08×10^-4
	Mean	4.22×10^-4	9.90×10^-2	3.77×10^-4
	Std	3.49×10^-4	5.54×10^-2	2.29×10^-4

第一主单元	第二主单元	第三主单元
-0.064 6	0.153 3	-0.097 1
0.692 6	0.166 3	-0.058 4
0.095 2	-0.136 0	0.008 2
-0.028 1	0.503 1	0.105 4
1.077 0	-0.046 3	0.007 3
0.072 2	-0.144 9	0.002 8
-0.071 4	0.166 9	-0.025 3
0.279 2	-0.230 5	0.012 1
-0.045 6	-0.281 5	-0.001 0
-0.075 2	0.065 7	0.023 2

故障类型	KPCA特征提取前准确率(%)
故障类型	IHHO- LSSVM	GA- LSSVM	HHO- LSSVM
正常	86.7	80.0	80.0
高温过热	93.3	86.7	86.7
中低温过热	86.7	80.0	86.7
高能放电	86.7	73.3	80.0
低能放电	86.7	66.7	86.7
局部放电	80.0	73.3	80.0
总成功率	86.7	77.8	82.2

故障类型	KPCA特征提取后准确率(%)
故障类型	IHHO- LSSVM	GA- LSSVM	HHO- LSSVM
正常	93.3	80.0	86.7
高温过热	100.0	93.3	93.3
中低温过热	93.3	80.0	86.7
高能放电	100.0	80.0	86.7
低能放电	100.0	66.7	80.0
局部放电	86.7	73.3	86.7
总成功率	95.6	78.9	86.7