基于小波神经网络的陀螺仪故障诊断

Gyroscope Fault Diagnosis Based on Wavelet Neural Network

为了准确可靠地发现和预测陀螺仪的故障,提出了一种基于RBF小波神经网络的陀螺仪故障检测方法;该方法是将陀螺仪的输出信号进行三层小波包分解,再对分解得到的8个不同频段上的节点进行特征提取,将提取后的8维特征向量作为RBF神经网络的输入;当陀螺仪发生故障时,陀螺仪的输出信号中会产生突变成分,进行训练后的RBF神经网络可以准确地诊断出陀螺仪的故障类型;应用Matlab实现了RBF小波神经网络诊断陀螺仪故障类型的仿真;仿真结果表明,应用RBF小波神经网络进行陀螺仪故障诊断有很好的效果。

In order to accurately and reliably detect and predict the fault of gyroscope , a wavelet-based RBF neural network fault detection method is presented, decomposing the signal by three--layer wavelet packet. Feature is extracted after decomposition for eight nodes, then an 8--dimensional eigenvector is used as fault samples to train Radical Basis Function （RBF） neural network. When the gyroscope failure, the output signal of gyroscope will have mutations in components, after training the RBF neural network can accurately diagnose the type of gyroscope failures. Application of MATLAB helps to achieve RBF wavelet neural network fault diagnosis of the type of gyroscope simulation, simulation results show that the application of wavelet neural network RBF gyroscope fault diagnosis, there are very good results.