小波变换和CNN涡旋压缩机故障诊断

Fault diagnosis of scroll compressor based on wavelet transform and CNN

针对传统单尺度信号分析难以有效解决涡旋压缩机故障诊断中的故障特征信息多尺度耦合问题,提出一种基于小波变换和卷积神经网络的涡旋压缩机故障诊断方法。首先将采集到的振动信号进行连续小波变换生成时频图,并对时频图进行网格化规范处理,将预处理后的时频图作为特征图输入Alexnet卷积神经网络,通过不断调节网络参数,得出最为理想的神经网络模型,以此实现对涡旋压缩机故障类型的辨识诊断。结果表明,该方法针对涡旋压缩机故障类型的识别准确率达到94.6%,与传统多尺度排列熵、信息熵熵距的故障诊断方法相比,该故障识别方法具有更高的准确率。

In order to solve the problem that traditional single-scale signal analysis is difficult to effectively solve the problem of multi-scale coupling of fault feature information in the fault diagnosis of scroll compressors,a fault diagnosis method based on wavelet transform and convolutional neural network(CNN)is proposed.Firstly,the collected vibration signal is analyzed by continuous wavelet transform to generate timefrequency diagram.And the generated time-frequency diagram is gridded and normalized.Then,it has to be inputtd to Alexnet convolutional neural network,and the network parameters are adjusted to obtain the most ideal network model,so as to realize the identification and diagnosis fault types of scroll compressors.The results show that the recognition accuracy reaches 94.6%,with higher accuracy than the traditional methods of multi-scale permutation entropy and distance of the information entropy.