基于EMD二值化图像和CNN的滚动轴承故障诊断

Fault Diagnosis for Rolling Bearing Based on EMD Binarization Image and CNN

针对传统故障诊断方法识别准确率低、泛化能力差,而基于深度学习的故障诊断普遍存在需要海量训练数据的问题,提出了一种基于经验模态分解(empirical mode decomposition,简称EMD)与卷积神经网络(convolutional neural networks,简称CNN)的滚动轴承智能故障诊断方法。首先,对轴承振动数据进行EMD,同时对相关系数最大的本征模函数(intrinsic mode function,简称IMF)分量进行频谱分析,获取频谱图,并将频谱图数据压缩成特征二值化图像作为CNN分类网络训练的输入数据;其次,将正常状态下和各类故障状态下的滚动轴承特征二值化图像作为CNN的输入得到训练模型,利用训练好的模型对各类故障进行分类识别。实验结果表明:在较少的训练数据下,轴承故障诊断准确率达到97.61%,远超过使用反向传播神经网络(back propagation,简称BP)和概率神经网络(probabilistic neural network,简称PNN)方法,证明了所提出方法与传统故障诊断方法相比能够更加准确地识别各类故障类别;对原始信号加入6 dB白噪声后的识别准确率也达到了96.19%,证明了所提出方法具有良好的泛化能力与抗噪性能。

The traditional fault diagnosis methods show low accuracy and poor generalization ability in identifica⁃tion,and the methods based on deep learning need huge amounts of training data.In light of these shortcom⁃ings,this paper proposes an intelligent rolling bearing fault diagnosis method based on the empirical mode de⁃composition(EMD)and convolution neural network(CNN).The bearing vibration data are decomposed by EMD.The intrinsic mode function(IMF)component with the largest correlation coefficient are analyzed for spectral images,which are compressed into characteristic binarization images to feed in the CNN training.Then,CNN yields a model that is used to classify and identify various faults based on the compressed images both under normal and various fault conditions.The experimental results show that the presented method sur⁃passes traditional fault diagnosis methods when the accuracy rate of the bearing fault diagnosis with less training data increased to 97.61%,which is much larger than that of the BP neural network and probabilistic neural net⁃work method.Besides,the method presents stronger generalization ability and better anti-noise performance with an accuracy rate of 96.19%when the original signals is superposed with a 6 dB white noise.