摘要
状态监测和故障诊断对于维护系统性能和保证运行安全具有重要意义.针对传统智能识别方法需要复杂的特征提取过程和大量的诊断经验等问题,结合振动信号自身的一维性的特点,提出一种基于一维卷积神经网络(1-Dimensional Convolutional Neural Network,1DCNN)的旋转机械智能故障诊断方法.首先将数据信号通过傅里叶变换转换成频域信号并进行预处理,然后训练卷积神经网络自动提取特征,最后通过Softmax回归进行分类.在基准数据集上的实验结果表明,1DCNN模型不仅能有效地从原始信号中进行多种工况、多种故障位置、多种故障程度的特征提取和诊断,而且具有很高的故障识别精度,获得了优于主流故障诊断方法的结果.
Condition monitoring and fault diagnosis are important for maintaining the system performance and guaranteeing the operational safety.The traditional intelligent identification method requires a complex feature extraction process and much diagnosis experience.Considering the characteristics of one dimension of vibration signals,a new method of intelligent fault diagnosis based on 1-Dimensional Convolutional Neural Network(1DCNN)is presented.Firstly,the data signal is converted into the frequency domain signal by Fourier Transformation and preprocessed.Then,the convolution neural network is trained to automatically extract the features,and finally the classification is made through Softmax regression.Experimental results on the benchmark datasets indicate that 1DCNN model cannot only effectively extract features and diagnosis of multiple working conditions,multiple fault locations and different health conditions,but also be able to achieve higher identification accuracy than existing methods.
引文
[1] Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks.Science,2006,313(5786):504-507.
[2] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks∥Proceedings of the 25thInternational Conference on Neural Information Processing Systems.Lake Tahoe,NV,USA:ACM,2012:1097-1105.
[3] Graves A,Mohamed A R,Hinton G.Speech recognitionwithdeeprecurrentneural networks∥Proceedings of 2013IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver,Canada:IEEE,2013:6645-6649.
[4] Sarikaya R,Hinton G E,Deoras A.Application of deep belief networks for natural language understanding.IEEE/ACM Transactions on Audio,Speech,and Language Processing,2014,22(4):778-784.
[5] Di Lena P,Nagata K,Baldi P.Deep architectures forproteincontactmapprediction.Bioinformatics,2012,28(19):2449-2457.
[6] Yu D,Deng L.Deep learning and its applications to signal and information processing.IEEE Signal Processing Magazine,2011,28(1):145-154.
[7] Tamilselvan P,Wang P F.Failure diagnosis using deep belief learning based health state classification.Reliability Engineering&System Safety,2013,115:124-135.
[8]赵光权,葛强强,刘小勇等.基于DBN的故障特征提取及诊断方法研究.仪器仪表学报,2016,37(9):1946-1953.(Zhao G Q,Ge Q Q,Liu X Y,et al.Fault feature extraction and diagnosis method based on deep belief network.Chinese Journal of Scientific Instrument,2016,37(9):1946-1953.)
[9]李巍华,单外平,曾雪琼.基于深度信念网络的轴承故障分类识别.振动工程学报,2016,29(2):340-347.(Li W H,Shan W P,Zeng X Q.Bearing fault identification based on deep belief network.Journal of Vibration Engineering,2016,29(2):340-347.)
[10]Tran V T,AlThobiani F,Ball A.An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks.Expert Systems with Applications,2014,41(9):4113-4122.
[11]Liao L X,Jin W J,Pavel R.Enhanced restricted Boltzmann machine with prognosability regularization for prognostics and health assessment.IEEE Transactions on Industrial Electronics,2016,63(11):7076-7083.
[12]雷亚国,贾峰,周昕等.基于深度学习理论的机械装备大数据健康监测方法.机械工程学报,2015,51(21):49-56.(Lei Y G,Jia F,Zhou X,et al. Adeeplearning-basedmethodfor machinery health monitoring with big data.Journal of Mechanical Engineering,2015,51(21):49-56.)
[13]Jia F,Lei Y G,Lin J,et al.Deep neural networks:Apromisingtoolforfault characteristic mining and intelligent diagnosis of rotatingmachinerywithmassivedata.Mechanical Systems and Signal Processing,2016,72-73:303-315.
[14]Sun W J,Shao S Y,Zhao R,et al.A sparse autoencoder-based deep neural network approach for inductionmotorfaultsclassification.Measurement,2016,89:171-178.
[15]Xia M,Li T,Liu L Z,et al.Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder.IET Science,Measurement&Technology,2017,11(6):687-695.
[16]Lecun Y,Bottou L,Bengio Y,et al.Gradientbased learning applied to document recognition.Proceedings of the IEEE,1998,86(11):2278-2324.
[17]周飞燕,金林鹏,董军.卷积神经网络研究综述.计算机学报,2017,40(6):1229-1251.(Zhou F Y,Jin L P,Dong J.Review of convolutional neural network.Chinese Journal of Computers,2017,40(6):1229-1251.)
[18]Chen Z Q,Li C,Sanchez R V.Gearbox fault identification and classification with convolutional neuralnetworks. ShockandVibration,2015:390134.
[19]Janssens O,Slavkovikj V,Vervisch B,et al.Convolutionalneuralnetworkbasedfault detection for rotating machinery.Journal of Sound and Vibration,2016,377:331-345.
[20]Guo X J,Chen L,Shen C Q.Hierarchical adaptive deep convolutionneuralnetworkandits application to bearing fault diagnosis.Measurement,2016,93:490-502.
[21]Zhang W,Peng G L,Li C H.Bearings fault diagnosis based on convolutional neural networks with 2-D representation of vibration signals as input. MATEC Web of Conferences,2017,95(8):13001.
[22]Sun W J,Zhao R,Yan R Q,et al.Convolutional discriminative feature learning for induction motor fault diagnosis.IEEE Transactions on Industrial Informatics,2017,13(3):1350-1359.
[23]Xia M,Li T,Xu L,et al.Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks.IEEE/ASME Transactions on Mechatronics,2018,23(1):101-110.
[24]Palaz D,Collobert R,Doss M M.Estimating phoneme class conditional probabilities from raw speechsignalusingconvolutionalneural networks.Computer Science,2013:1766-1770.
[25]Zeiler M D.ADADELTA:An adaptive learning rate method.2012,arXiv:1212.5701.
[26]Hinton G E,Srivastava N,Krizhevsky A,et al.Improvingneuralnetworksbypreventing co-adaptation of feature detectors.2012,arXiv:1207.0580.
[27]Lou X,Loparo K A.Bearing fault diagnosis based on wavelet transform and fuzzy inference.Mechanical Systems and Signal Processing,2004,18(5):1077-1095.
[28]Lu C,Wang Z Y,Zhou B.Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification.Advanced Engineering Informatics,2017,32:139-151.
[29]van der Maaten L,Hinton G.Visualizing data using t-SNE.Journal of Machine Learning Research,2008,9(11):2579-2605.
