论文部分内容阅读
基于故障轴承的特征提取,提出一种基于小波包与径向基RBF神经网络相结合的故障诊断方法,克服了以往常用诊断方法中的小波BP神经网络网络收敛慢、训练时间长、而且常常陷入局部极小点的缺点。采用小波滤波技术对采集到的滚动轴承振动信号进行滤波处理,利用小波包分解获得滚动轴承振动信号的特征向量作为故障样本对RBF网络进行训练,进行了详细的故障诊断试验研究。实验结果表明训练好的RBF网络能够很好地诊断出轴承故障类型,故本方法在旋转机械故障诊断方面具有良好的应用价值。
Based on the feature extraction of faulty bearing, a fault diagnosis method based on wavelet packet and radial basis function RBF neural network is proposed, which overcomes the disadvantages of traditional BP neural network, such as slow convergence, long training time, Shortcomings of local minima. Wavelet filter is used to filter the vibration signal of the rolling bearing. The wavelet packet decomposition is used to get the eigenvector of the rolling bearing vibration signal as the fault sample to train the RBF network, and a detailed fault diagnosis test is carried out. Experimental results show that the trained RBF network can well diagnose the types of bearing faults, so this method has a good application value in fault diagnosis of rotating machinery.