摘要
提高高压断路器故障诊断可靠性对于降低生产成本、提高运行可靠性具有重要作用。由于监测信号有限、信号之间为非线性关系,确定故障的来源非常困难,难以准确高效地诊断出故障。传统的诊断方法几乎都采用阈值的方法,缺乏数据管理和分析诊断平台,诊断时间长、效率低。为了提高诊断效率、提升故障诊断可靠性,提出了基于Matlab环境下的遗传算法(Genetic Algorithm,简称GA)优化的BP(Back Propagation)神经网络算法和径向基函数(RBF)神经网络算法的高压断路器故障诊断方法。仿真结果表明两种算法都具有很快的识别速度和较高的准确性,与标准BP算法模型诊断方法对比,两种模型均诊断能力更优、实用性均更强,其中RBF性能最好,两种算法均能有效地提高高压断路器可靠性。
Improving the fault diagnosis reliability of high voltage circuit breaker plays an important role in reduc- ing the production cost and improving the operation reliability. Because of the limited monitoring signals and the non- linear relationship between the signals, it is very difficult to determine the source of faults, so it is difficult to diag- nose the fault accurately and effectively. In order to improve the efficiency of diagnosis and enhance the reliability of fault diagnosis, based on genetic algorithm, BP neural network algorithm and radial basis function （RBF） neural net- work algorithm, a high voltage circuit breaker fault diagnosis method was proposed. The simulation results show that the two algorithms have fast recognition speed and high accuracy, can effectively improve the reliability of high - voltage circuit breakers.
作者
周康
刘惠康
ZHOU Kang Liu Hui -kang(College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan Hubei 430081, China)
出处
《计算机仿真》
北大核心
2017年第4期152-156,共5页
Computer Simulation
关键词
高压断路器
故障诊断
神经网络
遗传算法
径向基函数
High voltage circuit breaker
Fault diagnosis
Neural network
Genetic algorithm
RBF
