A Bearing Fault Diagnosis Method Based on Spectrum Map Information Fusion and Convolutional Neural Network

With the development of information technology, it has become increasingly important to use intelligent algorithms to diagnose mechanical equipment faults based on vibration signals of rolling bearings. However, with the application of high-performance sensors in the Internet of Things, the complexity of real-time classification of multichannel, multidimensional sensor signals is increasing. In view of the need for intelligent methods for fault diagnosis methods of mechanical equipment, the generalization ability of fault diagnosis models also needs to be further strengthened. In this context, in order to make fault diagnosis intelligent and efficient, a bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network (CNN) is proposed. First, short-time Fourier transform (STFT) is used to analyze the multichannel vibration signal of the rolling bearing and obtain the frequency domain information of the signal over a period of time. Second, the information fusion is converted into two-dimensional (2D) images, which are input into CNN for training, and the bearing fault identification model is obtained. Next, the frequency domain information of each signal is converted into a 2D spectrum map, which is used as a CNN training dataset to train a bearing fault identification model. Finally, the diagnostic model is validated using the existing datasets. The results show that the accuracy of fault diagnosis using the proposed bearing is greater than 99.4% and can even reach 100%. The proposed method considerably reduces the workload of the diagnosis process, with strong robustness and generalization ability.

[1]  Xiang Li,et al.  Deep Learning-Based Partial Domain Adaptation Method on Intelligent Machinery Fault Diagnostics , 2021, IEEE Transactions on Industrial Electronics.

[2]  Wenhua Du,et al.  Data-driven fault diagnosis method based on the conversion of erosion operation signals into images and convolutional neural network , 2021, Process Safety and Environmental Protection.

[3]  Wentao Mao,et al.  A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis , 2021 .

[4]  Meng Ma,et al.  Deep-Convolution-Based LSTM Network for Remaining Useful Life Prediction , 2021, IEEE Transactions on Industrial Informatics.

[5]  Xuebao Wang,et al.  Spectrum Representation Based on STFT , 2020, 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[6]  Yixiang Huang,et al.  Actual bearing compound fault diagnosis based on active learning and decoupling attentional residual network , 2020 .

[7]  Jiafu Wan,et al.  Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images , 2020, IEEE Transactions on Industrial Informatics.

[8]  Yanhe Zhu,et al.  GADF/GASF-HOG:feature extraction methods for hand movement classification from surface electromyography , 2020, Journal of neural engineering.

[9]  Yaguo Lei,et al.  Applications of machine learning to machine fault diagnosis: A review and roadmap , 2020 .

[10]  Huimin Zhao,et al.  An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network , 2020, IEEE Transactions on Instrumentation and Measurement.

[11]  Carlos Scheidegger,et al.  Visualizing Neural Networks with the Grand Tour , 2020 .

[12]  Yaguo Lei,et al.  Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data , 2019, IEEE Transactions on Industrial Electronics.

[13]  Rui Yao,et al.  A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm , 2017, Soft Computing.

[14]  Hee-Jun Kang,et al.  A survey on Deep Learning based bearing fault diagnosis , 2019, Neurocomputing.

[15]  Adam Glowacz,et al.  Fault diagnosis of single-phase induction motor based on acoustic signals , 2019, Mechanical Systems and Signal Processing.

[16]  Serkan Kiranyaz,et al.  A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN Classifier , 2018, Journal of Signal Processing Systems.

[17]  Wei Zhang,et al.  Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction , 2019, Reliab. Eng. Syst. Saf..

[18]  Hee-Jun Kang,et al.  Rolling element bearing fault diagnosis using convolutional neural network and vibration image , 2019, Cognitive Systems Research.

[19]  Yaguo Lei,et al.  Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization , 2018, Mechanical Systems and Signal Processing.

[20]  Pietro Borghesani,et al.  Electrical Signature Analysis-Based Detection of External Bearing Faults in Electromechanical Drivetrains , 2018, IEEE Transactions on Industrial Electronics.

[21]  Wei Jiang,et al.  Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders. , 2018, ISA transactions.

[22]  Biao Wang,et al.  LiftingNet: A Novel Deep Learning Network With Layerwise Feature Learning From Noisy Mechanical Data for Fault Classification , 2018, IEEE Transactions on Industrial Electronics.

[23]  Alessandro Fasana,et al.  The Autogram: An effective approach for selecting the optimal demodulation band in rolling element bearings diagnosis , 2018 .

[24]  Wu Deng,et al.  A Novel Fault Diagnosis Method Based on Integrating Empirical Wavelet Transform and Fuzzy Entropy for Motor Bearing , 2018, IEEE Access.

[25]  Haidong Shao,et al.  A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders , 2018 .

[26]  Haidong Shao,et al.  Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network , 2018, IEEE Transactions on Industrial Electronics.

[27]  Yi Qin,et al.  A New Family of Model-Based Impulsive Wavelets and Their Sparse Representation for Rolling Bearing Fault Diagnosis , 2018, IEEE Transactions on Industrial Electronics.

[28]  Haidong Shao,et al.  Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing , 2018 .

[29]  Diego Cabrera,et al.  A review on data-driven fault severity assessment in rolling bearings , 2018 .

[30]  Haidong Shao,et al.  Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine , 2018, Knowl. Based Syst..

[31]  Liang Guo,et al.  A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines , 2018, Neurocomputing.

[32]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[33]  Xinyu Shao,et al.  Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network , 2021, Knowl. Based Syst..

[34]  Adam Glowacz,et al.  Novel Convolutional Neural Network (NCNN) for the Diagnosis of Bearing Defects in Rotary Machinery , 2021, IEEE Transactions on Instrumentation and Measurement.

[35]  Zepeng Liu,et al.  A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings , 2020 .

[36]  Ming J. Zuo,et al.  Dynamic modeling of gearbox faults: A review , 2018 .

[37]  Adam Glowacz,et al.  Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals , 2018 .

[38]  Mallat Stéphane,et al.  CHAPTER 4 – Time Meets Frequency , 2009 .

[39]  V. Rusu,et al.  EKG Analysis Using STFT Phase , 2009 .