电力设备基于小波神经网络故障检测方法的仿真研究

Simulation Research on a Fault Detection Method Using Wavelet Neural Networks for Power Equipment

提出了一种基于小波神经网络非线性观测器的故障检测方法。它是将规范正交的小波函数作为基函数网络中的基函数,得到小波神经网络。通过小波的去噪和神经网络的自学习功能,获取系统输入输出的非线性动力学特性,进而实时计算出残差并进行逻辑判决,可提高故障检测的速度和准确率。对同步交流电机的结构损伤故障进行了仿真,结果表明了该方法的有效性。

In this paper,a method of fault detection based on nonlinear observer using wavelet neural networks is presented.In the method,wavelet is used as the basle of the basis neutral networks,which is called wavelet neural networks.By the denoising function of wavelet and the learning itself function of neural network,the input and output nonlinear dynamic characteristic of system is obtained. The output prediction error,generated from the real output and wavelet neural networks estimated output,is used as a residual error to execute logical judge,and this approach can improve the speed and accuracy rate of fault detection.Simulation for structural damage faults of nonlinear synchronous motors show that the fault detection approach is effective.