基于神经网络与小波变换的滚动轴承故障诊断

Fault Diagnosis of Rolling Bearing Based on Neural Network and Wavelet Transform

神经网络是一种具有非线性映射能力强以及自学习、自组织、自适应等优点的智能方法,非常适合于滚动轴承的故障诊断。针对滚动轴承是机械设备重要的易损零件之一,大约有30%的故障是由轴承损坏引起的,提出了基于神经网络的滚动轴承故障诊断方法。以滚动轴承小波分解后的能量信息作为特征,通过神经网络作为分类器对滚动轴承故障进行识别、诊断。实验表明,该方法对于滚动轴承的故障诊断具有良好的效果和应用价值,并可方便地推广到其他类似的诊断领域。

Neural network is an kintelligent method with powerful nonlinear mapping capability and serf-learning, self-organizing, self-adoption etc. , so it is ideally used for roiling bearing foult diagnosis. Aiming at the roiling bearing which is one of the important but easy olamage pomponents in machinery equipment, and nearly 30% fault are caused by bearing damage, so a fault diagnonis method for rolling bearing based on neural network is proposed in this paper. Taking the anergy information obtained after decomposing the rolling bearing wavelet as a feature and through the neural network as a classifier then the rolling bearing fault is identified and diagnosed. Experiments show that this method has good effect and application value for roiling fault dianosis and can be easily extended to other similar diagnosis.