A vibration-based fault diagnosis method for rolling bearings via optimized wavelet-SVM fusion

Zhang, A. Haitao; Guan, B. Li; Chang, C. Long

doi:10.22061/jcarme.2025.10582.2401

تعداد نشریات	11
تعداد شماره‌ها	237
تعداد مقالات	2,398
تعداد مشاهده مقاله	3,830,613
تعداد دریافت فایل اصل مقاله	2,775,225

	A vibration-based fault diagnosis method for rolling bearings via optimized wavelet-SVM fusion
Journal of Computational & Applied Research in Mechanical Engineering (JCARME)
مقاله 5، دوره 15، شماره 1 - شماره پیاپی 29، مهر 2025، صفحه 63-74 اصل مقاله (880.92 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22061/jcarme.2025.10582.2401
نویسندگان
A. Haitao Zhang^* ¹؛ B. Li Guan¹؛ C. Long Chang²
¹College of Mechanical Engineering, Nanjing Vocational University of Industry Technology, Nanjing , China.
²Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China.
تاریخ دریافت: 20 دی 1402، تاریخ بازنگری: 27 شهریور 1404، تاریخ پذیرش: 06 مهر 1404
چکیده
Rolling bearings are critical components of rotating machinery, and their health status directly affects the operational reliability of equipment. This paper proposes an optimized wavelet-SVM fault diagnosis method based on multi-source vibration signal fusion: Three-channel inputs are constructed by synchronously collecting vibration signals from the drive end and fan end, along with their differential signals; Wavelet packet decomposition is utilized to extract frequency-domain features such as unit node energy entropy and wavelet coefficient standard deviation, while dimensionless indicators independent of rotational speed (kurtosis factor/waveform factor/impulse factor) are introduced to enhance time-domain characterization; The fused features are input into an RBF-SVM classifier after dimensionality reduction via PCA (retaining 99% variance, reducing dimensions from 102 to 4). Experiments indicate that on the CWRU dataset, this method achieves 97.0% precision, 96.9% recall, and an F1-score of 96.9% (representing a 2.9% improvement over single-source input methods); Although there is a 2.4% absolute accuracy gap compared to deep learning solutions, it possesses significant edge advantages—memory usage is only 12KB and inference latency is 0.6ms—providing a high-precision, low-cost embedded solution for rotating machinery fault diagnosis
کلیدواژه‌ها
Statistical features؛ Wavelet packet decomposition؛ Gaussian kernel function؛ Principal component analysis؛ Prediction accuracy

مراجع
[1] A. Rai and S. H. Upadhyay, "A review on signal processing techniques utilized in the fault diagNosis of rolling element bearings," Tribol. Int., Vol. 96, pp. 289-306, (2016). [2] B. Wang, Y. Lei, N. Li, and N. Li, "A Hybrid ProgNostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings," Ieee. T. Reliab., Vol. 69, No. 1, pp. 401-412, (2020). [3] S. Qiu et al., "Multi-sensor information fusion based on machine learning for real applications in human activity recognition: State-of-the-art and research challenges," Inform. Fusion., Vol. 80, pp. 241-265, (2022). [4] L. H. Wang, X. P. Zhao, J. X. Wu, Y. Y. Xie, and Y. H. Zhang, "Motor Fault DiagNosis Based on Short-time Fourier Transform and ConVolutional Neural Network," Chin. J. Mech. Eng-En., Vol. 30, No. 6, pp. 1357-1368, (2017). [5] O. Abdeljaber, S. Sassi, O. Avci, S. Kiranyaz, A. A. Ibrahim, and M. Gabbouj, "Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring," Ieee. T. Ind. Electron., Vol. 66, No. 10, pp. 8136-8147, (2019). [6] A. A. Ballakur and A. Arya, "Empirical Evaluation of Gated Recurrent Neural Network Architectures in Aviation Delay Prediction," ICCCS, pp. 1-7, (2020). [7] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural. Comput., Vol. 9, No. 8, pp. 1735-1780, (1997). [8] A. Vaswani et al., "Attention is All you Need," Neural. IPS., (2017) . [9] C. Chen, Y. Yuan, and F. Zhao, "Intelligent Compound Fault DiagNosis of Roller Bearings Based on Deep Graph ConVolutional Network," Sensors, Vol. 23, No. 20, pp. 8489, (2023). [10] Z. Wang, Y. Dong, W. Liu, and Z. Ma, "A Novel Fault DiagNosis Approach for Chillers Based on 1-D ConVolutional Neural Network and Gated Recurrent Unit," Sensors, Vol. 20, No. 9, pp. 2458, (2020). [11] X. Li, Y. Yang, H. Y. Pan, J. Cheng, and J. S. Cheng, "A Novel deep stacking least squares support vector machine for rolling bearing fault diagNosis," Comput. Ind., Vol. 110, pp. 36-47, (2019). [12] Y. Shao, X. F. Yuan, C. J. Zhang, C. Z. Liu, and Ieee, "Rolling Bearing Fault DiagNosis Based on Wavelet Package Transform and IPSO Optimized SVM," CCDC, pp. 2758-2763, (2020) [13] G. Li, C. Deng, J. Wu, Z. Chen, and X. Xu, "Rolling Bearing Fault DiagNosis Based on Wavelet Packet Transform and ConVolutional Neural Network," Appl. Sci-Basel., Vol. 10, No. 3, pp. 770, (2020). [14] Y. K. Sun, Y. Cao, G. Xie, and T. Wen, "Sound Based Fault DiagNosis for RPMs Based on Multi-Scale Fractional Permutation Entropy and Two-Scale Algorithm," Ieee. T. Veh. Technol., Vol. 70, No. 11, pp. 11184-11192, (2021). [15] Y. Q. Wu et al., "The Fault DiagNosis of Rolling Bearings Based on FFT-SE-TCN-SVM," Actuators, Vol. 14, No. 3, (2025). [16] J. L. Song, Z. Y. Shi, B. H. Du, L. Y. Han, H. G. Wang, and Z. W. Wang, "MEMS gyroscope wavelet de-Noising method based on redundancy and sparse representation," Microelectron. Eng., Vol. 217, (2019). [17] S. Ehrich, "On the estimation of wavelet coefficients," Adv. Comput. Math., Vol. 13, No. 2, pp. 105-129, (2000). [18] J. Roffers-Agarwal, K. J. Hutt, and L. S. Gammill, "Paladin is an antiphosphatase that regulates neural crest cell formation and migration," Dev. Biol., Vol. 371, No. 2, pp. 180-190, (2012). [19] L. Ouahid, H. Nebdi, and L. Dalil-Essakali, "Kurtosis factor of truncated and Non-truncated simplified general-type beams," Opt. Quant. Electron., Vol. 49, No. 3, (2017). [20] L. S. Kwon and L. E. E. Jaemin, "A Study on the Structural Causal Relationship of Marketing Stimulating Factors on Online Impulse Purchase through Consumer Value : Focusing on the Mediating Effect of Consumer Value," J. Wellbeing Manag. Appl. Psychol., Vol. 5, No. 3, pp. 7-17, (2022). [21] C. Casari, P. J. Lenting, N. Wohner, O. D. Christophe, and C. V. Denis, "Clearance of von Willebrand factor," J. Thromb. Haemost., Vol. 11, pp. 202-211, (2013). [22] W. A. Smith and R. B. Randall, "Rolling element bearing diagNostics using the Case Western Reserve University data: A benchmark study," Mech. Syst. Signal. Pr., Vol. 64-65, pp. 100-131, (2015).
آمار تعداد مشاهده مقاله: 159 تعداد دریافت فایل اصل مقاله: 107

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

آمار

A vibration-based fault diagnosis method for rolling bearings via optimized wavelet-SVM fusion