Diagnosis of incipient faults in wind turbine bearings based on ICEEMDAN–IMCKD

Abstract

To address the difficulty in extracting early fault feature signals of rolling bearings, this paper proposes a novel weak fault diagnosis method for rolling bearings. This method combines the Improved Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and the Improved Maximum Correlated Kurtosis Deconvolution (IMCKD). Utilizing the kurtosis criterion, the intrinsic mode functions obtained through ICEEMDAN are reconstructed and denoised using IMCKD, which significantly reduces noise in the measured signal. This approach maximizes the energy amplitude at the fault characteristic frequency, facilitating fault feature identification. Experimental studies on two test benches demonstrate that this method effectively reduces noise interference and highlights the fault frequency components. Compared with traditional methods, it significantly improves the signal-to-noise ratio and more accurately identifies fault features, meeting the requirements for discriminating rolling bearing faults. The method proposed in this study was applied to the measured vibration signals of the gearbox bearings in the new high-speed wire department of a Long Products Mill. It successfully extracted weak characteristic information of early bearing faults, achieving the expected diagnostic results. This further validates the effectiveness of the ICEEMDAN–IMCKD method in practical engineering applications, demonstrating significant engineering value for detecting and extracting weak impact characteristics in rolling bearings.

Keywords

rolling bearings / early fault / intrinsic mode functions / Improved Complementary Ensemble Empirical Mode Decomposition / Improved Maximum Correlated Kurtosis Deconvolution

References

[1] Li J, Peng J, Zhang S, Zhang J, Meng Z. Weak fault feature extraction of rolling bearing based on multi-system coupled cascaded stochastic resonance system. Meas Sci Technol. 2024;35(3):035108.

[2] Li Z, Ding X, Song Z, Wang L, Qin B, Huang W. Digital twin-assisted dual transfer: a novel information-model adaptation method for rolling bearing fault diagnosis. Inf Fusion. 2024;106:102271.

[3] Chen S, Zheng X. A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection. Meas Sci Technol. 2024;35(4):046111.

[4] Liu T, Jin Y, Wang S, Zheng Q, Yang G. Denoising method of weak fault acoustic emission signal under strong background noise of engine based on autoencoder and wavelet packet decomposition. Struct Health Monit. 2023;22(5):3206-3224.

[5] Dong J, Jiang H, Su D, Gao Y, Chen T, Sheng K. Transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment. Meas Sci Technol. 2024;35(4):046006.

[6] Dong J, Su D, Jiang H, Gao Y, Chen T. A novel algorithm for complex transfer conditions in bearing fault diagnosis. Meas Sci Technol. 2024;35(5):056118.

[7] Li F, Zhao X. A novel approach for bearings multiclass fault diagnosis fusing multiscale deep convolution and hybrid attention networks. Meas Sci Technol. 2024;35(4):045017.

[8] Wang H, Zhang W, Han C, Fu Z, Song L. A bearing fault diagnosis method with an improved residual Unet diffusion model under extreme data imbalance. Meas Sci Technol. 2024;35(4):046113.

[9] McDonald GL, Zhao Q, Zuo MJ. Maximum correlated kurtosis deconvolution and application on gear tooth chip fault detection. Mech Syst Signal Process. 2012;33:237-255.

[10] Wan S, Zhang X, Dou L. Compound fault diagnosis of bearings using an improved spectral kurtosis by MCDK. Math Probl Eng. 2018;2018:1-12.

[11] Jia F, Lei Y, Shan H, Lin J. Early fault diagnosis of bearings using an improved spectral kurtosis by maximum correlated kurtosis deconvolution. Sensors. 2015;15(11):29363-29377.

[12] Dai W, Liu J, Wang L. Cloud ensemble learning for fault diagnosis of rolling bearings with stochastic configuration networks. Inf Sci. 2024;658:119991.

[13] Zheng B, Huang J, Ma X, et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis. Mech Syst Signal Process. 2024;208:111047.

[14] Deng M, Deng A, Shi Y, Liu Y, Xu M. Intelligent fault diagnosis based on sample weighted joint adversarial network. Neurocomputing. 2022;488:168-182.

[15] Guan B, Bao X, Qiu H, Yang D. Enhancing bearing fault diagnosis using motor current signals: a novel approach combining time shifting and CausalConvNets. Measurement. 2024;226:114049.

[16] Li X, Hu Y, Zheng J, Li M, Ma W. Central moment discrepancy based domain adaptation for intelligent bearing fault diagnosis. Neurocomputing. 2021;429:12-24.

[17] Niu G, Wang X, Golda M, Mastro S, Zhang B. An optimized adaptive PReLU-DBN for rolling element bearing fault diagnosis. Neurocomputing. 2021;445:26-34.

[18] Zhong H, Lv Y, Yuan R, Yang D. Bearing fault diagnosis using transfer learning and self-attention ensemble lightweight convolutional neural network. Neurocomputing. 2022;501:765-777.

[19] Chao Z, Han T. A novel convolutional neural network with multiscale cascade midpoint residual for fault diagnosis of rolling bearings. Neurocomputing. 2022;506:213-227.

[20] Ghorvei M, Kavianpour M, Beheshti MTH, Ramezani A. Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis. Neurocomputing. 2023;517:44-61.

[21] Wang S, Lian G, Cheng C, Chen H. A novel method of rolling bearings fault diagnosis based on singular spectrum decomposition and optimized stochastic configuration network. Neurocomputing. 2024;574:127278.

[22] Song B, Liu Y, Fang J, Liu W, Zhong M, Liu X. An optimized CNN-BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples. Neurocomputing. 2024;574:127284.

[23] Wen C, Xue Y, Liu W, Chen G, Liu X. Bearing fault diagnosis via fusing small samples and training multi-state Siamese neural networks. Neurocomputing. 2024;576:127355.

[24] Wang Z, Xu Z, Cai C, et al. Rolling bearing fault diagnosis method using time-frequency information integration and multi-scale TransFusion network. Knowl-Based Syst. 2024;284:111344.

[25] Li X, Wang Y, Yao J, Li M, Gao Z. Multi-sensor fusion fault diagnosis method of wind turbine bearing based on adaptive convergent viewable neural networks. Reliab Eng Syst Saf. 2024;245:109980.

[26] Wang Q, Liu N, Wang J, Yin L, Yang S, Huang N. A zero-sample intelligent fault diagnosis method for bearings based on category relationship model. Eng Appl Artif Intell. 2024;130:107739.

[27] Zheng X, Yang P, Yan K, He Y, Yu Q, Li M. Rolling bearing fault diagnosis based on multiple wavelet coefficient dimensionality reduction and improved residual network. Eng Appl Artif Intell. 2024;133(PA):108087.

[28] Shi H, Miao Y, Li C, Gu X. A novel bearing intelligent fault diagnosis method based on spectrum sparse deep deconvolution. Eng Appl Artif Intell. 2024;133(PA):108102.

[29] Cui L, Jiang Z, Liu D, Wang H. A novel adaptive generalized domain data fusion-driven kernel sparse representation classification method for intelligent bearing fault diagnosis. Expert Syst Appl. 2024;247:123225.

[30] Kulevome DKB, Wang H, Cobbinah BM, Mawuli ES, Kumar R. Effective time-series data augmentation with analytic wavelets for bearing fault diagnosis. Expert Syst Appl. 2024;249(PA):123536.

[31] Cui L, Dong Z, Xu H, et al. Triplet attention-enhanced residual tree-inspired decision network: a hierarchical fault diagnosis model for unbalanced bearing datasets. Adv Eng Inf. 2024;59:102322.

[32] Bin GF, Gao JJ, Li XJ, Dhillon BS. Early fault diagnosis of rotating machinery based on wavelet packets-empirical mode decomposition feature extraction and neural network. Mech Syst Signal Process. 2012;27:696-711.

[33] Qiao Z, Shu X. Coupled neurons with multi-objective optimization benefit incipient fault identification of machinery. Chaos Solitons Fractals. 2021;145:110775.

[34] Qiao Z, Chen S, Lai Z, Zhou S, Sanjuán MAF. Harmonic-Gaussian double-well potential stochastic resonance with its application to enhance weak fault characteristics of machinery. Nonlinear Dyn. 2023;111(8):7293-7307.

[35] Mei Y, Chen L, Xu W, Liu C, Qiao Z, Lai Z. Fractional order derivative and time-delay feedback enabled stochastic resonance for bearing fault diagnosis. Shock Vib. 2023;2023:1-12.

[36] Ke Z, Liu H, Shi J, et al. Fault diagnosis method of weak vibration signal based on improved VMD and MCKD. Meas Sci Technol. 2024;35(2):9-10.

[37] Cui B, Guo P, Zhang W. Research on fault diagnosis of rolling bearing based on the MCKD-SSD-TEO with optimal parameters. J Mech Sci Technol. 2022;37(1):31-42.

[38] Zhou J, Wu SS, Liu T, et al. Application of IPSO-MCKD-IVMD-CAF in the compound fault diagnosis of rolling bearing. Meas Sci Technol. 2023;34(3):5-8.

[39] Jiezhong T. Fault diagnosis method of internal combustion engine bearing based on genetic algorithm optimization of BP neural network. Intern Combust Engine Accessories. 2024;(3):19-21.

[40] Tang W, Jia Z, Lai D. Fault diagnosis of railway freight car rolling bearings based on ACMD and improved MCKD. Adv Eng Innovation. 2024;9:74-86.

[41] Li D, Li M, Yang L, et al. Rolling bearing fault diagnosis in strong noise background based on vibration signals. Signal Image Video Process. 2023;18(2):1295-1303.

[42] Liu Y, Wang J, Feng D, et al. Bearing fault diagnosis method based on maximum noise ratio kurtosis product deconvolution with noise conditions. Measurement. 2023;221:113542.

RIGHTS & PERMISSIONS

2024 The Author(s). International Journal of Mechanical System Dynamics published by John Wiley & Sons Australia, Ltd on behalf of Nanjing University of Science and Technology.