Matlab GUI小波神经网络回转窑故障诊断

Fault diagnosis of rotary kiln with Matlab GUI wavelet neural network

采用小波神经网络的方法实现回转窑故障诊断。选取回转窑主电机电流作为故障分类依据,用小波包特征向量提取的方法提取各故障情况下窑电流在不同频带上的能量特征。将提取的特征向量作为神经网络的输入,故障类型作为输出,训练概率神经网络,实现故障分类,并设置测试组对网络学习效果进行测试。设计Matlab GUI故障诊断界面,搭建了回转窑故障诊断平台,实现样本波形绘制、特征向量提取、故障诊断及提出解决方案等功能。仿真和实验结果证明提出的回转窑故障诊断方法是可行的,实现了对窑故障的分类,并实现了良好的人机交互。

The fault diagnosis of rotary kiln is realized by wavelet neural network. The main motor current of rotary kiln is selected as the basis of fault classification,and the energy characteristics of kiln current in different frequency bands are extracted by wavelet packet eigenvector extraction method. The extracted feature vector is used as the input of the neural network and the fault type is taken as the output. The probabilistic neural network is trained to realize the fault classification and the test group is set up to test the learning effect of the network. The Matlab GUI fault diagnosis interface is designed and the rotary kiln fault diagnosis platform is built. The functions of sample waveform drawing,feature vector extraction,fault diagnosis and solution are realized. Simulation and experimental results show that the proposed fault diagnosis method for rotary kiln is feasible. It completes the classification of kiln faults and realizes good man-machine interaction.