Research on Bearing Fault Diagnosis Method for Drilling Pole Machine Based on IEC Module, TSCNN

doi:10.3969/j.issn.1008-0198.2025.05.018

Abstract

Abstract: To achieve efficient bearing fault diagnosis, a novel method based on the IEC module (integrating InceptionV2, Efficient Channel Attention, and Convolutional Block Attention Module) and a Two-stream Convolutional Neural Network(TSCNN) is proposed. First, raw vibration signals are converted into one-dimensional data and two-dimensional time-frequency images using Fast Fourier Transform(FFT) and Continuous Wavelet Transform(CWT). Subsequently, an improved TSCNN fusion model is constructed, and the obtained wavelet time-frequency images and FFT spectra are used as inputs to extract the spatial features of the time-frequency images by using InceptionV2 and ECANet-CBAM improvement module, and the resulting dual-layer feature information is fused into the Softmax layer to accomplish fault classification. Finally, comparative analysis based on a standard rolling bearing fault data set demonstrates that the proposed IEC-TSCNN method achieves superior diagnostic accuracy.

Key words: drilling pole machine, bearing, fault diagnosis, IEC module, TSCNN(two-stream convolutional neural network)

CLC Number:

TM754

YANG Miao, YIN Peng, ZENG Xiaojun, CHEN Ming, YANG Wen, HE Jilin. Research on Bearing Fault Diagnosis Method for Drilling Pole Machine Based on IEC Module, TSCNN[J]. Hunan Electric Power, 2025, 45(5): 133-140.

References

[1] SUN Y X,XIONG Z H.An optimal weighted wavelet packet entropy method with application to real-time chatter detection[J]. IEEE/ASME Transactions on Mechatronics,2016,21(4):2004-2014.
[2] 赵小强,张毓春. 基于双路并行多尺度ResNet的滚动轴承故障诊断方法[J]. 振动与冲击,2023,42(3):199-208.
[3] YANG Z X,WANG X B,WONG P K.Single and simultaneous fault diagnosis with application to a multistage gearbox:a versatile dual-ELM network approach[J]. IEEE Transactions on Industrial Informatics,2018,14(12): 5245-5255.
[4] 唐波,陈慎慎. 基于深度卷积神经网络的轴承故障诊断方法[J]. 电子测量与仪器学报,2020,34(3):88-93.
[5] ZHANG M,JIANG Z N,FENG K.Research on variational mode decomposition in rolling bearings fault diagnosis of the multistage centrifugal pump[J]. Mechanical Systems and Signal Processing,2017,93:460-493.
[6] BODA S,MAHADEVAPPA M,DUTTA P K.A hybrid method for removal of power line interference and baseline wander in ECG signals using EMD and EWT[J]. Biomedical Signal Processing and Control,2021,67:102466.
[7] GU Y K,ZHOU X Q,YU D P,et al.Fault diagnosis method of rolling bearing using principal component analysis and support vector machine[J]. Journal of Mechanical Science and Technology,2018,32(11):5079-5088.
[8] 谢扬筱,王国强,石念峰,等. 融合注意力机制的MSCNN-BiLSTM滚动轴承故障诊断方法[J]. 轴承,2024(8):86-94.
[9] SHAO S Y,MCALEER S,YAN R Q,et al.Highly accurate machine fault diagnosis using deep transfer learning[J]. IEEE Transactions on Industrial Informatics,2019,15(4):2446-2455.
[10] PENG D D,LIU Z L,WANG H,et al.A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains[J]. IEEE Access,2018,7:10278-10293.
[11] LI H,ZHANG Q,QIN X,et al.Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock,2018,37(19):124-131.
[12] 张立智,徐卫晓,井陆阳,等. 基于二维深度卷积网络的旋转机械故障诊断[J]. 机械强度,2020,42(5):1039-1044.
[13] XU Y,LI Z X,WANG S Q,et al.A hybrid deep-learning model for fault diagnosis of rolling bearings[J]. Measurement,2021,169(6):108502.
[14] SAID D,KAMEL M,KHALED K,et al.Deep transfer learning for bearing fault diagnosis using CWT time-frequency images and convolutional neural networks[J]. Journal of Failure Analysis and Prevention,2023,23(3):1046-1058.
[15] LU J Y,WANG K,CHEN C,et al.A deep learning method for rolling bearing fault diagnosis based on attention mechanism and graham angle field[J]. Sensors,2023,23(12):5487.
[16] ZHANG K,TANG B P,DENG L,et al.A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox[J]. Measurement,2021,179:109491.
[17] YU D,FU H Y,SONG Y C,et al.Deep transfer learning rolling bearing fault diagnosis method based on convolutional neural network feature fusion[J]. Measurement Science and Technology,2024,35(1):015013.
[18] DING S M,RUI Z Y,LEI C L,et al.A rolling bearing fault diagnosis method based on Markov transition field and multi-scale Runge-Kutta residual network[J]. Measurement Science and Technology,2023,34(12):125150.
[19] GU X J,XIE Y T,TIAN Y,et al.A lightweight neural network based on GAF and ECA for bearing fault diagnosis[J]. Metals,2023,13(4):822.
[20] WANG Q L,WU B G,ZHU P F,et al. ECA-net:Efficient channel attention for deep convolutional neural networks[EB/OL].2019:arXiv:1910.03151. https//arXiv.org/abs/1910.03151.
[21] DONG S J,WU W L,HE K,et al.Rolling bearing performance degradation assessment based on improved convolutional neural network with anti-interference[J]. Measurement,2020,151:107219.
[22] WU G X,WANG G,LIU X L,et al.Bearing fault diagnosis method based on STFT image and AlexNet network[C]//International Conference on the Efficiency and Performance Engineering Network. Cham:Springer Nature Switzerland,2022:1056-1068.
[23] HOU X L,GUO W C,REN S J,et al.Bolt-loosening detection using 1D and 2D input data based on two-stream convolutional neural networks[J]. Materials,2022,15(19):6757.
[24] ZHOU S,XIAO M H,BARTOS P,et al.Remaining useful life prediction and fault diagnosis of rolling bearings based on short-time Fourier transform and convolutional neural network[J]. Shock and Vibration,2020,2020(1):8857307.
[25] ZHANG Q,DENG L F.An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network[J]. Journal of Failure Analysis and Prevention,2023,23(2):795-811.
[26] TANG S N,ZHU Y,YUAN S Q.An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal[J]. Engineering Failure Analysis,2022,138:106300.