摘要
为提高高压断路器故障诊断精度和效率以保障电力系统安全稳定运行,提出一种基于拉普拉斯分值法与改进的支持向量机(SVM)的智能故障诊断方法。首先,从高压断路器分合闸线圈电流中提取包括电流峰值、关键时间点及电流统计量等特征值,并建立故障样本集合;其次,采用拉普拉斯分值法筛选出关键特征,降低故障样本集合的维度;最后,采用灰狼算法(GWO)优化支持向量机(SVM)的关键参数,构建高效、准确的高压断路器故障诊断模型。基于实际故障样本的仿真测试结果表明:提出的采用特征选择及参数优化的故障诊断方法较其他传统方法具有更高的诊断精度及诊断效率,对实际工程应用具有一定的参考借鉴意义。
In order to improve the accuracy and efficiency of high-voltage circuit breaker fault diagnosis for keeping power grid stable and safe,an intelligent fault diagnosis approach based on Laplace score method and improved support vector machine(SVM)is present in this paper.First,a set of features including current peak values,key time points and statistics values from opening and closing coil current curves are extracted to establish fault samples.Then,the Laplacian score method is used to filter out the critical features to reduce the input dimension.Finally,the gray wolf algorithm(GWO)is used to optimize the key parameters of the support vector machine(SVM)to construct an efficient and accurate fault diagnosis model for high-voltage circuit breakers.Simulation results based on actual fault samples suggest that the presented approach combined with feature selection technique and parameter optimization has better fault diagnosis accuracy and diagnosis efficiency than that of conventional methods,which has certain guiding significance for actual engineering application.
作者
逯浩坦
伊力哈木•亚尔买买提
刘鹏伟
张鹏程
李振恩
吐松江•卡日
LU Hao-tan;YILIHAMU Yaermaimaiti;LIU Peng-wei;ZHANG Peng-cheng;LI Zhen-en;TUSONGJIANG Kari(School o£Electrical Engineering,Xinjiang University,Urumqi 800046,China;Shanghai Nyten Electrical Technology Co.,Ltd.,Shanghai 201100,China)
出处
《组合机床与自动化加工技术》
北大核心
2022年第1期103-107,共5页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金(52067021)
新疆维吾尔自治区优秀青年科技人才培养项目(2019Q012)
新疆大学博士启动基金(BS190221)。
关键词
高压断路器
线圈电流
故障诊断
支持向量机
特征选择
high voltage circuit breaker
coil current
fault diagnosis
support vector machine
feature selection
