基于DCNN-SVM的滚动轴承故障诊断方法研究
|
摘要
针对传统深度学习方法在滚动轴承故障诊断中分类准确度相对较低的问题,提出了一种基于深度卷积模型(DCNN)和支持向量机(SVM)相结合的诊断模型。利用深度卷积模型对滚动轴承故障信号进行自适应特征提取,再将提取的特征输入到支持向量机中进行模式识别。使用经典深度卷积、BP神经网络和支持向量机三种模型进行了5组对比实验,并对自适应提取的特征与人工特征进行了PCA主成分分析。结果表明,利用该方法对滚动轴承内圈点蚀、滚珠点蚀和外圈点蚀等10类故障进行实验诊断,准确率达到99.25%,提高了故障诊断准确率。
Aiming at the relatively low accuracy of traditional deep learning method in rolling bearing fault diagnosis,the fault diagnosis method is proposed based on deep convolutional neural network(DCNN) and support vector machine(SVM).The feature of rolling bearing fault signal is extracted adaptively using deep convolutional neural network.Then,the features are input to support vector machine for pattern recognition.In order to verify the validity of this method for fault diagnosis of rolling bearings, five groups of comparative experiments were carried out using deep convolutional neural network, BP neural network and support vector machine. Principal component analysis(PCA) is used for adaptive extraction of features and artificial features.The results show that the ten kinds of faults are experimentally diagnosed by this method.The ten kinds of faults include pitting corrosion of inner ring,pitting corrosion of ball and pitting corrosion of outer ring. The accuracy is 99.25%, which improves the accuracy of fault diagnosis.
Aiming at the relatively low accuracy of traditional deep learning method in rolling bearing fault diagnosis,the fault diagnosis method is proposed based on deep convolutional neural network(DCNN) and support vector machine(SVM).The feature of rolling bearing fault signal is extracted adaptively using deep convolutional neural network.Then,the features are input to support vector machine for pattern recognition.In order to verify the validity of this method for fault diagnosis of rolling bearings, five groups of comparative experiments were carried out using deep convolutional neural network, BP neural network and support vector machine. Principal component analysis(PCA) is used for adaptive extraction of features and artificial features.The results show that the ten kinds of faults are experimentally diagnosed by this method.The ten kinds of faults include pitting corrosion of inner ring,pitting corrosion of ball and pitting corrosion of outer ring. The accuracy is 99.25%, which improves the accuracy of fault diagnosis.
引文
[1] 陈龙,谭继文,姜晓瑜.基于TESPAR和LS-SVM算法的滚动轴承退化趋势预测[J].煤矿机械,2017,38(8):18-20.
[2] Gou L,Gao H,Huang H,et al.Multifeatures fusion and nonlinear dimension reduction for intelligent bearing condition monitoring[J].Shock and Vibration,2016,16(6):895-914.
[3] Lu C,Wang Z Y,Qin W L,et al.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification [J].Signal Processing,2017,130:377-388.
[4] Janssens O,Slavkovikj V,Vervisch B,et al.Convolutional neural network based fault detection for rotating machinery[J].Journal of Sound and Vibration,2016,377:331-345.
[5] Zhang W,Peng G,Li C,et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J].Sensors,2017,17(2):425-446.
[6]乔风娟,郭红利,李伟,等.基于SVM的深度学习分类研究综述[J].齐鲁工业大学学报,2018,32(5):41-44.
[7] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[8] 时永刚,程坤,刘志文.结合深度学习和支持向量机的海马子区图像分割[J].中国图像图形学报,2018,23(4):542-551.
[9] Jing L Y,Zhao M,Li P,et al.A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox [J].Measurement,2017,111:1-10.
[10] 徐卫晓,谭继文,文妍.基于BP神经网络和改进D-S证据理论的滚动轴承故障诊断方法研究[J].机床与液压,2014,42(23):188-191.
[11] Jing L Y,Wang T Y,Zhao M,et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox [J].Sensors,2017,17(2):414-429.
[2] Gou L,Gao H,Huang H,et al.Multifeatures fusion and nonlinear dimension reduction for intelligent bearing condition monitoring[J].Shock and Vibration,2016,16(6):895-914.
[3] Lu C,Wang Z Y,Qin W L,et al.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification [J].Signal Processing,2017,130:377-388.
[4] Janssens O,Slavkovikj V,Vervisch B,et al.Convolutional neural network based fault detection for rotating machinery[J].Journal of Sound and Vibration,2016,377:331-345.
[5] Zhang W,Peng G,Li C,et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J].Sensors,2017,17(2):425-446.
[6]乔风娟,郭红利,李伟,等.基于SVM的深度学习分类研究综述[J].齐鲁工业大学学报,2018,32(5):41-44.
[7] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[8] 时永刚,程坤,刘志文.结合深度学习和支持向量机的海马子区图像分割[J].中国图像图形学报,2018,23(4):542-551.
[9] Jing L Y,Zhao M,Li P,et al.A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox [J].Measurement,2017,111:1-10.
[10] 徐卫晓,谭继文,文妍.基于BP神经网络和改进D-S证据理论的滚动轴承故障诊断方法研究[J].机床与液压,2014,42(23):188-191.
[11] Jing L Y,Wang T Y,Zhao M,et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox [J].Sensors,2017,17(2):414-429.