Suzhou Electric Appliance Research Institute
期刊号: CN32-1800/TM| ISSN1007-3175

Article retrieval

文章检索

首页 >> 文章检索 >> 往年索引

基于改进极限学习机的高压断路器故障诊断

来源:电工电气发布时间:2022-10-24 15:24 浏览次数:285

基于改进极限学习机的高压断路器故障诊断

张莲1,贾浩2,张尚德2,赵梦琪2,赵娜2,黄伟2
(1 重庆市能源互联网工程技术研究中心,重庆 400054;
2 重庆理工大学 电气与电子工程学院,重庆 400054)
 
    摘 要:针对极限学习机连接权重和阈值随机选取存在的很大不确定性,提出将麻雀搜索算法与极限学习机结合搭建故障诊断模型(FASSA-ELM)。在原麻雀搜索算法的基础上引入 Sine 混沌映射优化初始种群,结合萤火虫算法 (FA) 对麻雀种群的位置以及最优解位置进行扰动更新,将改进后的麻雀搜索算法用于优化极限学习机的权值和阈值。采用集合经验模态方法提取出高压断路器分合闸线圈电流中的故障特征量,对断路器故障特征的仿真分析表明,FASSA-ELM 的诊断准确率达到了100%,将训练样本和测试样本互换后该模型诊断准确率为84.5%,与其他三种模型相比,该方法具有更高的准确率和更好的稳定性。
    关键词: 断路器;极限学习机;故障诊断;分合闸线圈电流
    中图分类号:TM561     文献标识码:B     文章编号:1007-3175(2022)10-0050-07
 
Fault Diagnosis of High Voltage Circuit Breaker Based on
Improved Extreme Learning Machine
 
ZHANG Lian1, JIA Hao2, ZHANG Shang-de2, ZHAO Meng-qi2, ZHAO Na2, HUANG Wei2
(1 Chongqing Energy Internet Engineering Technology Research Center, Chongqing 400054, China;
2 School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China)
 
    Abstract: This paper combined an improved sparrow search algorithm with the extreme learning machine to construct a fault diagnosis model (FASSA-ELM) for solving the uncertainty of the weight of connection of the extreme learning machine and the random threshold selection. This study introduced the Sine chaotic map based on the original sparrow search algorithm to optimize the initial population. It is combined with the firefly algorithm (FA) to disturb and update the position of the sparrow population and the optimal solution position.Moreover, it used the improved sparrow search algorithm to optimize the weights and thresholds of the extreme learning machine. This research employed the ensemble empirical mode method to extract the fault feature quantity of the switching coil current of the high voltage circuit breaker and conducted a simulation of the circuit breaker fault characteristic. The analysis results show that the diagnostic accuracy of the FASSA-ELM gets up to 100%. However, if exchanging the training sample for the test sample, the diagnostic accuracy of the model is 84.5%. Compared with the other 3 models, this method has higher accuracy and better stability.
    Key words: circuit breaker; extreme learning machine; fault diagnosis; switching coil current
 
参考文献
[1] 阙华坤,冯小峰,刘盼龙,等.Grassberger 熵随机森林在窃电行为检测的应用[J] . 计算机科学,2022,49(S1):790-794.
[2] 方喜峰,于超,章振,等. 基于支持向量机的船用柴油机装配质量预测[J] . 组合机床与自动化加工技术,2021(9):62-66.
[3] 张佳,陈志英,陈丽安,等. 基于粒子群优化极限学习机的断路器故障诊断方法研究[J] . 高压电器,2020,56(6):181-188.
[4] 黄南天,陈怀金,林琳,等. 基于 S 变换和极限学习机的高压断路器机械故障诊断[J] . 高压电器,2018,54(6):74-80.
[5] 于万国,隋丽娜. 基于支持向量机的软件工程实验智能评价分析方法研究[J] . 现代电子技术,2021,44(22):183-186.
[6] 何怡刚,陶琳,施天成,等. 基于改进 BREMD 与 ELM 的断路器机械故障诊断[J] . 电子测量技术,2018,41(21):81-88.
[7] 刘栋,魏霞,王维庆,等. 基于 SSA-ELM 的短期风电功率预测[J]. 智慧电力,2021,49(6):53-59.
[8] 于波,肖艳利,刘尚科,等. 基于 PSO-ELM 算法的输变电工程造价预测分析[J] . 信息技术,2019,43(4):148-151.
[9] 吕鑫,慕晓冬,张钧,等. 混沌麻雀搜索优化算法[J]. 北京航空航天大学学报,2021,47(8):1712-1720.
[10] 胡鸿志,覃畅,管芳,等. 基于麻雀搜索算法优化支持向量机的刀具磨损识别[J] . 科学技术与工程,2021,21(25):10755-10761.
[11] 邹东尧,李明,李军,等. 基于改进一维逻辑正弦混沌映射系统的图像加密算法[J] . 科学技术与工程,2021,21(28):12175-12184.
[12] 刘纲,陈奇,雷振博,等. 基于改进萤火虫算法的有限元模型修正[J] . 工程力学,2022,39(7):1-9.
[13] 朱旭辉,沈国娇,夏平凡,等. 基于螺旋进化萤火虫算法和 BP 神经网络的模型及其在 PPP 融资风险预测中的应用[J] . 计算机科学,2022,49(S1):667-674.
[14] 薛茂远,梅益,唐方艳,等. 基于 GA-ELM 及遗传算法的注塑件成型工艺优化[J] . 塑料,2022,51(1):56-61.