中文摘要：

内圈裂纹、外圈松动和掉渣是滚动轴承常见典型故障，为实现其快速、准确地诊断，本文提出基于振动信号小波能谱熵特征和神经网络相结合的滚动轴承诊断方法。首先对振动信号进行小波分解和重构，得到小波重构系数，利用重构系数的能谱熵特征作为神经网络输入进行滚动轴承的故障类型的识别，同时引入遗传算法对神经网络结构参数进行优化，以进一步提高故障识别诊断速度和准确率。结果表明：该方法用于轴承典型故障诊断有着更高的诊断速率和故障识别率。

英文摘要：

The inner crack, the outer loose and dregs are typical faults of rolling bearing. In order to diagnose these faults rapidly and accurately, the paper proposes a diagnosis method of rolling bearing based on the wavelet energy entropy characteristics of wavelet reconstruction coefficients and neural network established by using vibration sig- nal. The vibration signal is decomposed by wavelet decomposition, and the calculated wavelet energy entropy char- acteristics of wavelet reconstruction coefficients are inputted to the neural network to identify the type of rolling bear- ing faults. At the same time, the genetic algorithm is introduced to optimize the structure parameters of neural net- work, which improves diagnostic rate and accuracy of faults. The results show that this method has a high efficiency of diagnosis and recognition for the typical faults of rolling bearing.