Transformer Fault Diagnosis Method Based on Data Equalization and Kernel-based Extreme Learning Machine of Improved Whale Algorithm
WANG Yuhong1, SUN Yuanxing1, BAO Weichuan2, CHEN Zichun1,3
1. School of Electrical and Control Engineering, Liaoning University of Engineering and Technology, Huludao 125105, China; 2. Substation Maintenance Work Area, State Grid Fuxin Power Supply Company, Fuxin 123000, China; 3. Kailuan Group Co, Ltd., Tangshan 063018, China
Abstract:In this study, we propose a transformer fault diagnosis model based on adaptive integrated oversampling (ADASYN) and kernel-based extreme learning machine of improved whale algorithm (IWOA-KELM). This model aims to examine the effect of transformer unbalanced data on the recognition accuracy of the transformer fault diagnosis model. The imbalance between transformer fault data sets results in a bias problem. So, to resolve this, we first use the ADASYN algorithm to optimize the equalization process of transformer fault data. Secondly, we use a multi-strategy combination to improve the search speed, convergence ability, and escape ability of local extremums of the whale optimization algorithm (WOA). Finally, the WOA is used to optimize the KELM regularization coefficient and kernel function parameters. It also constructs a fault diagnosis model of the optimized IWOA-KELM. When the model is applied to the field of transformer fault diagnosis, its diagnostic accuracy is found to improve by 14.17%, 12.5%, and 8.34%, respectively, for particle swarm algorithm KELM (PSO-KELM), gray wolf algorithm KELM (GWO-KELM), and WOA-KELM. Our findings proved that the proposed fault diagnosis model has higher breaking accuracy and generalization ability.
王雨虹, 孙远星, 包伟川, 陈子春. 基于数据均衡化与改进鲸鱼算法优化核极限学习机的变压器故障诊断方法[J]. 信息与控制, 2023, 52(2): 235-244,256.
WANG Yuhong, SUN Yuanxing, BAO Weichuan, CHEN Zichun. Transformer Fault Diagnosis Method Based on Data Equalization and Kernel-based Extreme Learning Machine of Improved Whale Algorithm. Information and control, 2023, 52(2): 235-244,256.
[1] ZHENG H B, ZHANG Y Y, LIU J F, et al. A novel model based on wavelet LS-SVM integrated improved PSO algorithm for forecasting of dissolved gas contentin power transformers[J]. Electric Power Systems Research, 2018, 155:196-205. [2] 周光宇, 马松玲. 基于机器学习与DGA的变压器故障诊断及定位研究[J]. 高压电器, 2020, 56(6):262-268. ZHOU G Y, MA S L. Study of transformer fault diagnosis and location based on machine learning and DGA[J]. High Voltage Apparatus, 2020, 56(6):262-268. [3] 李刚, 于长海, 刘云鹏, 等. 电力变压器故障预测与健康管理:挑战与展望[J]. 电力系统自动化, 2017, 41(23):156-167. LI G, YU C H, LIU Y P, et al. Fault prediction and health management of power transformers:Challenges and prospects[J]. Automation of Electric Power Systems, 2017, 41(23):156-167. [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[2022-02-03]. https://doi.org/10.13195/j.kzyjc.2021.1437. XIE G M, LIN X Y. Transformer fault diagnosis method based on improved SSA and optimized MDS-SVM[J/OL]. Control and Decision[2022-02-03]. https://doi.org/10.13195/j.kzyjc.2021.1437. [5] 赵文清, 严海, 周震东, 等. 基于残差BP神经网络的变压器故障诊断[J]. 电力自动化设备, 2020, 40(2):143-148. ZHAO W Q, YAN H, ZHOU Z D, et al. Transformer fault diagnosis based on residual BP neural network[J]. Electric Power Automation Equipment, 2020, 40(2):143-148. [6] 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 K, PENG W J, YANG X J. Application of feature optimization and fuzzy theory in transformer fault diagnosis[J]. Power System Protection and Control, 2016, 44(15):54-60. [7] 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 C M, ZHU Y L. Fault diagnosis of transformer oil chromatography based on NSGA2 optimized regular extreme learning machine[J]. High Voltage Electrical Apparatus, 2020, 56(9):210-215. [8] BEJ S, DAVTYAN N, WOLFIEN M, et al. LoRAS:An oversampling approach for imbalanced datasets[J]. Machine Learning, 2021, 110(2):279-301. [9] BECKMANN M, EBECKEN N F F, PIRES DE LIMA B S L, et al. A KNN undersampling approach for data balancing[J]. Journal of Intelligent Learning Systems and Applications, 2015, 7(4):104-116. [10] 李亮, 范瑾, 闫林, 等. 基于混合采样和支持向量机的变压器故障诊断[J]. 中国电力, 2021, 54(12):150-155. LI L, FAN J, YAN L, et al. Transformer fault diagnosis based on mixed sampling and support vector machine[J]. China Electric Power, 2021, 54(12):150-155. [11] 刘云鹏, 和家慧, 许自强, 等. 结合AdaBoost和代价敏感的变压器故障诊断方法[J]. 华北电力大学学报(自然科学版), 2022, 49(5):1-9. LIU Y P, HE J H, XU Z Q, et al. Transformer fault diagnosis method combining AdaBoost and cost-sensitive[J]. Journal of North China Electric Power University (Natural Science Edition), 2022, 49(5):1-9. [12] 刘云鹏, 和家慧, 许自强, 等. 基于SVM SMOTE的电力变压器故障样本均衡化方法[J]. 高电压技术, 2020, 46(7):2522-2529. LIU Y P, HE J H, XU Z Q, et al. Power transformer fault sample equalization method based on SVM SMOTE[J]. High Voltage Technology, 2020, 46(7):2522-2529. [13] HE H B, BAI Y, GARCIA E A, et al. ADASYN:Adaptive synthetic sampling approach for imbalanced learning[C]//2008 IEEE International Joint Conference on Neural Networks. Piscataway, USA:IEEE, 2008:1322-1328. [14] MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95:51-67. [15] 张珍珍, 贺兴时, 于青林, 等. 多阶段动态扰动和动态惯性权重的布谷鸟算法[J]. 计算机工程与应用, 2022, 58(1):79-88. ZHANG Z Z, HE X S, YU Q L, et al. Cuckoo algorithm for multi-stage dynamic disturbance and dynamic inertia weight[J]. Computer Engineering and Applications, 2022, 58(1):79-88. [16] ZHU Y L, YOUSEFI N. Optimal parameter identification of PEMFC stacks using adaptive sparrow search algorithm[J]. International Journal of Hydrogen Energy, 2021, 46(14):9541-9552. [17] 温泽宇, 谢珺, 谢刚, 等. 基于新型拥挤度距离的多目标麻雀搜索算法[J]. 计算机工程与应用, 2021, 57(22):102-109. WEN Z Y, XIE J, XIE G, et al. Multi-objective sparrow search algorithm based on a new crowding degree distance[J]. Computer Engineering and Applications, 2021, 57(22):102-109. [18] 寇英信, 奚之飞, 徐安, 等. 基于改进核极限学习机和集成学习理论的目标机动轨迹预测[J]. 国防科技大学学报, 2021, 43(5):23-35KOU Y X, XI Z F, XU A, et al. Target maneuver trajectory prediction based on improved nuclear extreme learning machine and integrated learning theory[J]. Journal of National University of Defense Technology, 2021, 43(5):23-35. [19] 徐睿, 梁循, 齐金山, 等. 极限学习机前沿进展与趋势[J]. 计算机学报, 2019, 42(7):1640-1670. XU R, LIANG X, QI J S, et al. Advances and trends in extreme learning machine[J]. Chinese Journal of Computers, 2019, 42(7):1640-1670. [20] 范君, 王新, 徐慧. 粒子群优化混合核极限学习机的构造煤厚度预测方法[J]. 计算机应用, 2018, 38(6):1820-1825, 1830. FAN J, WANG X, XU H. Tectonic coal thickness prediction method based on particle swarm optimization hybrid kernel extreme learning machine[J]. Journal of Computer Applications, 2018, 38(6):1820-1825, 1830. [21] 田晓飞. 基于改进蝙蝠算法优化支持向量机的变压器故障诊断研究[D]. 成都:西华大学, 2019. TIAN X F. Research on transformer fault diagnosis based on improved bat algorithm to optimize support vector machine[D]. Chengdu:Xihua University, 2019. [22] 尹金良. 基于相关向量机的油浸式电力变压器故障诊断方法研究[D]. 北京:华北电力大学, 2013. YIN J L. Research on fault diagnosis method of oil-immersed power transformer based on correlation vector machine[D]. Beijing:North China Electric Power University, 2013. [23] HUANG X Y, HUANG X L, WANG B R, et al. Fault diagnosis of transformer based on modified grey wolf optimization algorithm and support vector machine[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2020, 15(3):409-417. [24] 汪可, 李金忠, 张书琦, 等. 变压器故障诊断用油中溶解气体新特征参量[J]. 中国电机工程学报, 2016, 36(23):6570-6578, 6625. WANG K, LI J Z, ZHANG S Q, et al. New characteristic parameters of dissolved gas in oil for transformer fault diagnosis[J]. Proceedings of the Chinese Society of Electrical Engineering, 2016, 36(23):6570-6578, 6625.