论文部分内容阅读
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 intelligent method with strong ability of non-linear mapping, self-learning, self-organizing and adaptive. It is very suitable for the fault diagnosis of rolling bearing. Aiming at the fact that rolling bearing is one of the most important wearing parts of mechanical equipment, about 30% of the failures are caused by bearing damage, and the fault diagnosis method of rolling bearing based on neural network is proposed. Taking the energy information of the wavelet decomposition of the rolling bearing as a feature, the neural network is used as a classifier to identify and diagnose rolling bearing faults. Experiments show that this method has a good effect and application value for the fault diagnosis of rolling bearings and can be easily extended to other similar diagnostic fields.