论文部分内容阅读
作为电力系统的一种重要设备,高压断路器的故障诊断一直是研究中的重点。针对传统神经网络收敛速度慢,容易陷入局部极小等不足,提出了一种基于小波神经网络的高压断路器故障诊断方法。首先利用特征熵方法提取振动信号的特征值,然后利用小波神经网络进行分类识别。同时还给出了一种小波神经网络的改进方法,提高了其收敛速度。实验结果表明,相比较于传统神经网络,改进的小波神经网络训练速度更快,分类准确率更高,对于高压断路器的故障诊断效果更佳。
As an important equipment of power system, the fault diagnosis of high voltage circuit breakers has been the research focus. Aiming at the shortcomings of traditional neural network, such as slow convergence speed and easy to fall into local minima, a fault diagnosis method of HV circuit breaker based on wavelet neural network is proposed. Firstly, the eigenvalues of vibration signals are extracted by using the feature entropy method, and then the wavelet neural network is used to classify and recognize the eigenvalues. At the same time, an improved method of wavelet neural network is given, which improves its convergence speed. The experimental results show that the improved wavelet neural network can train faster and have higher classification accuracy than the traditional neural network, and it is more effective in fault diagnosis of high voltage circuit breakers.