摘要
为实现高压断路器与负荷开关的故障诊断,提高设备安全可靠性,有必要深入研究电机电流特性与高压断路器、负荷开关的弹簧操作机构状态之间的关系。由于传统BP神经网络存在易陷入局部最小点及网络收敛速度慢等缺陷,采用遗传算法对于BP神经网络进行优化可以提高判断准确率及诊断效率。诊断结果表明,GA-BP算法可以根据断路器、负荷开关电机电流数据快速准确判断设备所处的运行状态,且精确度高,对于工程实际具有广泛应用前景。
For achieving the fault diagnosis of high voltage circuit breaker and load switch as well as improve their safety and reliability,it is necessary to deeply study the relationship between motor current characteristics and the state of spring operating mechanism for high voltage circuit breaker and load switch.Since the traditional BP neural network has such defects as easily falling into local minimum points and slow network convergence speed,the use of genetic algorithm to optimize BP neural network can improve the judgment accuracy and diagnosis efficiency.The diagnosis results show that GA-BP algorithm can quickly and accurately judge the operating state of the equipment in accordance with the current data of of motor for the circuit breaker and load,has high accuracy and wide application prospect for engineering practice.
作者
王佳灿
何志鹏
冀一玮
赵莉华
吴月峥
WANG Jiacan;HE Zhipeng;JI Yiwei;ZHAO Lihua;WU Yuezheng(Lijiang Power Supply Bureau of Yunnan Power Grid Co.,Ltd.,Yunnan Lijiang 674100,China;School of Automation,Northwest University of Technology,Xi’an 710072,China;School of Electrical Engineering,Sichuan University,Chengdu 610065,China)
出处
《高压电器》
CAS
CSCD
北大核心
2024年第5期39-45,共7页
High Voltage Apparatus
基金
国网黑龙江电力有限公司检修公司科技项目(SGHLJG00YJJS1400303)
中央高校基本科研业务费专项资金资助项目(YJ202070)。
关键词
负荷开关
高压断路器
电机电流
遗传算法
BP神经网络
故障诊断
load switch
high voltage circuit breaker
motor current
genetic algorithm
BP neural network
fault diagnosis