Intelligent fault detection of zero-sample rolling bearings driven by combined time-frequency analysis and multimodal knowledge

Haifeng Wei; Huijian  Que; Rongxiang Zheng; Jianbin  Liao; Guoqiang Li; Jin  Yan

doi:10.59400/sv3658

Intelligent fault detection of zero-sample rolling bearings driven by combined time-frequency analysis and multimodal knowledge

Haifeng Wei
Longyan Tobacco Industrial Co., Ltd., Longyan 364021, China
Huijian Que
Longyan Tobacco Industrial Co., Ltd., Longyan 364021, China
Rongxiang Zheng
Longyan Tobacco Industrial Co., Ltd., Longyan 364021, China
Jianbin Liao
School of Marine Engineering, Jimei University, Xiamen 361021, China
Guoqiang Li
School of Marine Engineering, Jimei University, Xiamen 361021, China
Jin Yan
School of Marine Engineering, Jimei University, Xiamen 361021, China

Article ID: 3658

DOI: https://doi.org/10.59400/sv3658

Keywords: gearboxes; zero fault sample; prior knowledge; compound fault; contrastive loss function

Abstract

To meet the demand for intelligent monitoring of rolling bearings and overcome the limitation of scarce fault samples in the real world, this paper proposes a zero-fault sample-based condition detection method that integrates the time-frequency analysis of rolling bearings with modal knowledge, which mainly includes: 1) The HHT envelope analysis and high-frequency filtering is introduced to reduce the interference of the base-frequency information of rolling bearings and to enhance the frequency of the fault information. 2) A novel zero-fault sample-based loss function is designed by combining the strong temporal sequence of rolling bearing monitoring data with the a priori knowledge of information mutualism to realize the effective training of the data-driven model. 3) An intelligent fault detection algorithm for rolling bearings is established based on a trained data-driven model. The proposed method is validated using a constructed rolling bearing experimental platform. The validation results show that the proposed method is able to build an effective intelligent fault detection model with zero fault samples of rolling bearings, which shows better fault detection performance than other supervised and unsupervised learning-based methods. The proposed anomaly detection method based on zero-fault samples can quickly establish its state detection model for important rolling bearings applied in engineering practice, providing a new perspective for data-driven fault diagnosis methods for rolling bearings.

Published

2025-09-30

How to Cite

Wei, H., Que, H., Zheng, R., Liao, J., Li, G., & Yan, J. (2025). Intelligent fault detection of zero-sample rolling bearings driven by combined time-frequency analysis and multimodal knowledge. Sound & Vibration, 59(5). https://doi.org/10.59400/sv3658

Download Citation

Issue

Vol. 59 No. 5 (2025)

Section

Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Zhang M, Jiang Z, Feng K. Research on variational mode decomposition in rolling bearings fault diagnosis of the multistage centrifugal pump. Mechanical Systems and Signal Processing. 2017; 93: 460–493. doi: 10.1016/j.ymssp.2017.02.013

[2]Li C, De Oliveira JV, Cerrada M, et al. A Systematic Review of Fuzzy Formalisms for Bearing Fault Diagnosis. IEEE Transactions on Fuzzy Systems. 2019; 27(7): 1362–1382. doi: 10.1109/TFUZZ.2018.2878200

[3]Chen X, Yang R, Xue Y, et al. Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016. IEEE Transactions on Instrumentation and Measurement. 2023; 72: 1–21. doi: 10.1109/TIM.2023.3244237

[4]Wang D, Miao Q, Fan X, et al. Rolling element bearing fault detection using an improved combination of Hilbert and wavelet transforms. Journal of Mechanical Science and Technology. 2009; 23(12): 3292–3301. doi: 10.1007/s12206-009-0807-4

[5]Wang D, Zhao X, Kou L-L, et al. A simple and fast guideline for generating enhanced/squared envelope spectra from spectral coherence for bearing fault diagnosis. Mechanical Systems and Signal Processing. 2019; 122: 754–768. doi: 10.1016/j.ymssp.2018.12.055

[6]Meng D, Nie P, Yang S, et al. Reliability analysis of wind turbine gearboxes: past, progress and future prospects. International Journal of Structural Integrity. 2025; 16(1): 4–38. doi: 10.1108/IJSI-08-2024-0129

[7]Dalian Y, Junjun Z, Hui L. Capsule networks for intelligent fault diagnosis: a roadmap of recent advancements and challenges. Expert Systems with Applications. 2026; 296: 128814. doi: 10.1016/j.eswa.2025.128814

[8]Rehman AU, Jiao W, Jiang Y, et al. Deep learning in industrial machinery: A critical review of bearing fault classification methods. Applied Soft Computing. 2025; 171: 112785. doi: 10.1016/j.asoc.2025.112785

[9]Tang J, Hu Y, Zhou X, et al. Self-powered sensor for online monitoring of eccentricity faults in rotating machinery and its application in spindle eccentricity monitoring of machine tools. Nano Energy. 2024; 130: 110084. doi: 10.1016/j.nanoen.2024.110084

[10]Liu K, Li Y, Cui Z, et al. Adaptive frequency attention-based interpretable Transformer network for few-shot fault diagnosis of rolling bearings. Reliability Engineering & System Safety. 2025; 263: 111271. doi: 10.1016/j.ress.2025.111271

[11]Hakim M, Omran AAB, Ahmed AN, et al. A systematic review of rolling bearing fault diagnoses based on deep learning and transfer learning: Taxonomy, overview, application, open challenges, weaknesses and recommendations. Ain Shams Engineering Journal. 2023; 14(4): 101945. doi: 10.1016/j.asej.2022.101945

[12]Xu Y, Fan Y, Bao Y, et al. Few-shot learning for structural health diagnosis of civil infrastructure. Advanced Engineering Informatics. 2024; 62: 102650. doi: 10.1016/j.aei.2024.102650

[13]Pan H, Xu H, Cheng J, et al. A Multiclass Graph Embedding Matrix Classification Method for Roller Bearing State Identification Under Limited Sample. IEEE Transactions on Reliability. 2025; 74(3): 3824–3832. doi: 10.1109/TR.2025.3530441

[14]Siavash-Abkenari N, Rahmani-Sane G, Torkaman H, et al. Exploring a Cutting-Edge Framework for Bearing Fault Detection: A Synergistic Approach Integrating Statistical Analysis and Deep Learning Methods. IEEE Journal of Emerging and Selected Topics in Industrial Electronics. 2024; 5(3): 1226–1233. doi: 10.1109/JESTIE.2024.3373313

[15]Choudhary A, Mian T, Fatima S, et al. Passive Thermography Based Bearing Fault Diagnosis Using Transfer Learning With Varying Working Conditions. IEEE Sensors Journal. 2023; 23(5): 4628–4637. doi: 10.1109/JSEN.2022.3164430

[16]Liu X, Liu S, Xiang J, et al. A transfer learning strategy based on numerical simulation driving 1D Cycle-GAN for bearing fault diagnosis. Information Sciences. 2023; 642: 119175. doi: 10.1016/j.ins.2023.119175

[17]Wang Y, Li D, Li L, et al. A novel deep learning framework for rolling bearing fault diagnosis enhancement using VAE-augmented CNN model. Heliyon. 2024; 10(15): e35407. doi: 10.1016/j.heliyon.2024.e35407

[18]Ren Z, Lin T, Feng K, et al. A Systematic Review on Imbalanced Learning Methods in Intelligent Fault Diagnosis. IEEE Transactions on Instrumentation and Measurement. 2023; 72: 1–35. doi: 10.1109/TIM.2023.3246470

[19]Sun Y, Song H, Guo L, et al. A transfer learning method: Universal domain adaptation with noisy samples for bearing fault diagnosis. Advanced Engineering Informatics. 2025; 65: 103243. doi: 10.1016/j.aei.2025.103243

[20]Zhong J, Zheng Y, Ruan C, et al. M-IPISincNet: An explainable multi-source physics-informed neural network based on improved SincNet for rolling bearings fault diagnosis. Information Fusion. 2025; 115: 102761. doi: 10.1016/j.inffus.2024.102761

[21]Qin Y, Liu H, Wang Y, et al. Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samples. Knowledge-Based Systems. 2024; 292: 111641. doi: 10.1016/j.knosys.2024.111641

[22]Herwig N, Borghesani P, Smith W, et al. Signal processing- and physics-informed neural network for explainable bearing condition monitoring. Mechanical Systems and Signal Processing. 2025; 235: 112925. doi: 10.1016/j.ymssp.2025.112925

[23]Peng C, Sheng Y, Gui W, et al. A Rolling Bearing Fault Diagnosis Method Based on Multimodal Knowledge Graph. IEEE Transactions on Industrial Informatics. 2024; 20(11): 13047–13057. doi: 10.1109/TII.2024.3431074

[24]Berredjem T, Benidir M. Bearing faults diagnosis using fuzzy expert system relying on an Improved Range Overlaps and Similarity method. Expert Systems with Applications. 2018; 108: 134–142. doi: 10.1016/j.eswa.2018.04.025

[25]Wang Z, Yu X, Guo Y, et al. A noise-enhanced feature extraction method combined with tunable Q-factor wavelet transform and its application to planet-bearing fault diagnosis. Applied Acoustics. 2025; 239: 110845. doi: 10.1016/j.apacoust.2025.110845

[26]Ying W, Li Y, Noman K, et al. Stockwell transform spectral amplitude modulation method for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing. 2025; 223: 111884. doi: 10.1016/j.ymssp.2024.111884

[27]Zhao D, Wang H, Cui L. Frequency-chirprate synchrosqueezing-based scaling chirplet transform for wind turbine nonstationary fault feature time–frequency representation. Mechanical Systems and Signal Processing. 2024; 209: 111112. doi: 10.1016/j.ymssp.2024.111112

[28]Lv Y, Hao J, Tang M, et al. Multimodal data fusion-based intelligent fault diagnosis for ship rotating machinery: Status quo and perspectives. Engineering Applications of Artificial Intelligence. 2025; 160: 111767. doi: 10.1016/j.engappai.2025.111767

[29]Han K, Wang Y, Chen H, et al. A Survey on Vision Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023; 45(1): 87–110. doi: 10.1109/TPAMI.2022.3152247

[30]Hosseini NK, Toshani H, Abdi Jalebi S, et al. Enhanced Bearing Fault Detection in Induction Motors Using Projection-Based SVM. IEEE Transactions on Industry Applications. 2025; 61(3): 3623–3636. doi: 10.1109/TIA.2025.3536425

[31]Wang Z, Liu T, Wu X, et al. Application of an Oversampling Method Based on GMM and Boundary Optimization in Imbalance-Bearing Fault Diagnosis. IEEE Transactions on Industrial Informatics. 2024; 20(2): 1931–1940. doi: 10.1109/TII.2023.3282236

[32]Kim HH, Choi JY. Hierarchical multi-class LAD based on OvA-binary tree using genetic algorithm. Expert Systems with Applications. 2015; 42(21): 8134–8145. doi: 10.1016/j.eswa.2015.06.037

[33]Muralidharan V, Sugumaran V. A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing. 2012; 12(8): 2023–2029. doi: 10.1016/j.asoc.2012.03.021

[34]Li G, Wu J, Deng C, et al. Convolutional Neural Network-Based Bayesian Gaussian Mixture for Intelligent Fault Diagnosis of Rotating Machinery. IEEE Transactions on Instrumentation and Measurement. 2021; 70: 1–10. doi: 10.1109/TIM.2021.3080402

[35]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. Advanced Engineering Informatics. 2024; 59: 102322. doi: 10.1016/j.aei.2023.102322

[36]Trizoglou P, Liu X, Lin Z. Fault detection by an ensemble framework of Extreme Gradient Boosting (XGBoost) in the operation of offshore wind turbines. Renewable Energy. 2021; 179: 945–962. doi: 10.1016/j.renene.2021.07.085

This paper introduces a universal framework for understanding the vibration responses of systems subjected to harmonic excitation. By examining a simplified cylinder-spring-damper model, the study refurbishes traditional scaling methods for the excitation frequency ratio and critical damping ratio. The findings indicate that in damped systems, the maximum amplitude of vibration does not align with the natural frequency. This observation leads to the introduction of a new scaling method for reduced frequency. This new approach aligns resonance peaks at the new reduced velocity of 1.0 across different damping ratios, providing a consistent characterization of vibration behavior. A new critical damping ratio of 0.707 is identified for an excited system as opposed to the traditional damping ratio of 1.0 for an unexcited system. Key properties such as maximum amplitude, phase lag, bandwidth, and quality factor are analyzed, demonstrating that the proposed reduced frequency and critical damping ratio effectively capture the dynamics of both damped and undamped excited systems. The findings offer significant insights for practical applications in engineering and various scientific fields.

This study makes significant contributions to the field of ultrasonic testing (UT) by offering a novel approach to the identification of artificially introduced defects within Japanese cedar wood (Cryptomeria japonica). The findings are of particular relevance for the heritage conservation and construction sectors, where non-invasive defect detection is paramount. The study establishes a robust framework for assessing the structural integrity of timber by correlating ultrasonic wave velocity reductions with defect size and distribution. Big-sized defects led to more substantial decreases in wave velocity. The study establishes a robust framework for assessing the structural integrity of historical timber by correlating ultrasonic wave velocity reductions with defect size and distribution. This framework has the potential to be applicable to diverse wood species and defect types.

The control of vehicle interior noise has become a critical metric for assessing noise, vibration, and harshness (NVH) in vehicles. During the initial phases of vehicle development, accurately predicting the impact of road noise on interior noise is essential for reducing noise levels and expediting the product development cycle. In recent years, data-driven methods based on machine learning have gained significant attention due to their robust capability in navigating complex data mapping relationships. Notably, surrogate models have demonstrated exceptional performance in this domain. Numerous researchers have integrated diverse intelligent algorithms into the study of vehicle noise, leveraging advantages such as the elimination of precise modeling requirements, extensive solution space exploration, continuous learning from data, and robust algorithmic versatility. However, in NVH engineering applications, data-driven models face inherent limitations, particularly in interpretability and stability. To address these issues, this paper introduces an improved Long Short-Term Memory (LSTM) network that combines knowledge and data. Inspired by the physical information neural network concept, this approach incorporates values calculated through empirical formulas into the neural network as constraints. Comparative assessments with traditional LSTM networks highlight the advantages of this deep learning model. By integrating empirical formulas constraints, the model not only enhances interpretability but also achieves robust generalization with fewer data samples. The proposed method is validated on a specific vehicle model, showing significant improvements in prediction accuracy and efficiency.