Weak fault feature extraction and system fault analysis under strong noise

Tiejun Cui
School of Environmental and Chemical Engineering, Shenyang Ligong University, Shenyang 110159, China; Liaoning Safety Engineering Industry School, Shenyang Ligong University, Shenyang 110159, China
Zijian Cui
School of Environmental and Chemical Engineering, Shenyang Ligong University, Shenyang 110159, China
Shasha Li
School of Environmental and Chemical Engineering, Shenyang Ligong University, Shenyang 110159, China; Liaoning Safety Engineering Industry School, Shenyang Ligong University, Shenyang 110159, China

Article ID: 4224

(This article belongs to the Special Issue Vibration and System Fault Analysis)

Keywords: strong noise; weak fault; feature extraction; uncertainty quantification; fault analysis

Abstract

To tackle the intractable problems including weak fault feature extraction and evolution uncertainty quantification for complex systems in strong noise environments, a novel method for weak fault diagnosis and evolution analysis is proposed. This method integrates the fuzzy structured element (FSE), cloud model (CM), and Space Fault Network (SFN). The method centers on adaptive wavelet denoising, fault feature cloudification, and SFN probability propagation. The fault signal under strong noise is reconstructed by optimizing the wavelet threshold with the FSE. The uncertainty encapsulation of the peak factor of fault features is realized based on the CM to establish the feature CM. The fault event topology is constructed relying on the SFN. The quantitative transfer of uncertainty in the fault evolution is achieved combined with cloud algebra. Verified by the inner ring pitting fault of axle box bearings, the results demonstrate that the proposed method can extract the fault characteristic frequency of 250.5 Hz. The derived fault probability CM (0.680, 0.059, 0.023) accurately quantifies the system risk level. This result is consistent with the actual fault evolution law in engineering practice. This method provides technical support for early fault warning and maintenance of complex industrial system. Furthermore, comparative experiments confirm its superiority over traditional methods in noise suppression and feature retention. Parameter analysis is also discussed to improve engineering generalization.

Published

2026-07-23

How to Cite

Cui, T., Cui, Z., & Li, S. (2026). Weak fault feature extraction and system fault analysis under strong noise . Sound & Vibration, 60(5). https://doi.org/10.59400/sv4224

Download Citation

Issue

Vol. 60 No. 5 (2026): In Progress

Section

Article

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

References

[1]Zou M, Zhou B, Dai M, et al. An adaptive signal processing framework for fault diagnosis: Intelligent spectral optimization for robust weak periodic feature extraction from vibration signals. Digital Signal Processing. 2026; 176: 106055. doi: 10.1016/j.dsp.2026.106055

[2]Zhang K, Li M, Jin F, et al. Variational filtering differential strategy with amplitude modulation for fault feature extraction. Measurement Science and Technology. 2026; 37(10): 106105. doi: 10.1088/1361-6501/ae4cbb

[3]Wang Z, Yu X, Guo Y, et al. Research on a novel weak fault detection method based on vibrational resonance in high-dimensional chaotic system, and variational mode decomposition. Chaos, Solitons & Fractals. 2026; 208: 118084. doi: 10.1016/j.chaos.2026.118084

[4]Liu L, Xu H, Guo P, et al. GE-HOFMD fusion-based early fault feature extraction and diagnosis for rolling bearings. Engineering Research Express. 2026; 8(4): 045513. doi: 10.1088/2631-8695/ae42ec

[5]Shi G, Qin C, Xia P, et al. Generalized envelope nonlinear Gini index-gram guided two-stage chirp mode decomposition for shield machine main bearing fault diagnosis. Advanced Engineering Informatics. 2026; 71: 104354. doi: 10.1016/j.aei.2026.104354

[6]Liu Y, Zhou Y, Hu T, et al. A weak-fault diagnosis method for bearings based on quadratic Manhattan entropy. Measurement. 2026; 264: 120242. doi: 10.1016/j.measurement.2025.120242

[7]Guo D, Chen J, Liu X, et al. Research on Rolling Bearing Fault Diagnosis Based on IRBMO-CYCBD. Mathematics. 2026; 14(1): 201. doi: 10.3390/math14010201

[8]Zou Y, Zhang Y, Li CF, et al. A multi-scale dilated convolutional neural network-based bearing fault diagnosis method with dense connections under strong noise conditions. Measurement Science and Technology. 2026; 37(7): 076110. doi: 10.1088/1361-6501/ae44bd

[9]Chen Y, Zhang W, Cao Z, et al. Multi-scale adaptive quadratic convolutional network: reliable gearbox fault identification under severe noise. Measurement Science and Technology. 2026; 37(6): 066101. doi: 10.1088/1361-6501/ae412d

[10]Wang H, Fang G, Cui X, et al. Parallel Axial Attention and ResNet-Based Bearing Fault Diagnosis Method. Electronics. 2026; 15(4): 899. doi: 10.3390/electronics15040899

[11]Xu Z, Chen Z, Li X, et al. EPA-RepViT: A lightweight model for fault diagnosis of planetary gearbox under strong noise. Engineering Research Express. 2026; 8(1): 015207. doi: 10.1088/2631-8695/ae29bd

[12]Li Z, Li P, Yang J, et al. Auditory perception–based acoustic fault diagnosis for railway wheelset bearings under strong noise: a comparison with short-time Fourier transform, Mel spectrogram, and continuous wavelet transform. Engineering Research Express. 2026; 8(2): 025508. doi: 10.1088/2631-8695/ae35d7

[13]Dong H, Zhang Y, Zhang B, et al. A noise-robust xLSTM-based method for fault diagnosis in gas-insulated Switchgear using acoustic signals under strong noise interference. Expert Systems with Applications. 2026; 304: 130827. doi: 10.1016/j.eswa.2025.130827

[14]Li M, Huang J, Zhang F, et al. MSIF-Convformer: A novel end-to-end fault diagnosis framework with multi-source sensors under strong noise. Information Fusion. 2026; 129: 104000. doi: 10.1016/j.inffus.2025.104000

[15]Zhao L, Liu Y, Zhang Z, et al. Nonlinear convolutional sparse filtering with Gaussian fitting for rolling bearings compound fault diagnosis. Structural Health Monitoring. 2026; 25(1): 516–536. doi: 10.1177/14759217241286087

[16]Li S, Wang T, Xu X, et al. An Improved DQN Framework with Dual Residual Horizontal Feature Pyramid for Autonomous Fault Diagnosis in Strong-Noise Scenarios. Sensors. 2025; 25(24): 7639. doi: 10.3390/s25247639

[17]Cui T, Wei P, Li S. Partial differential analytical expression for the failure rate change of electrical components under multi-fault coupling. Advances in Differential Equations and Control Processes. 2025; 32(3). doi: 10.59400/adecp3444

[18]Guo S, Song T. Operations and Measurement of Interval-valued Fuzzy Numbers Based on the Method of Structured Element. Fuzzy Information and Engineering. 2011; 3(1): 101–110. doi: 10.1007/s12543-011-0069-6

[19]Li D, Liu C, Gan W. A new cognitive model: Cloud model. International Journal of Intelligent Systems. 2009; 24(3): 357–375. doi: 10.1002/int.20340

[20]Si Y, Zhang Z, Kong L, et al. Aging condition identification of viscoelastic sandwich structure based on empirical wavelet transform and Hilbert envelope demodulation. Composite Structures. 2019; 215: 13–22. doi: 10.1016/j.compstruct.2019.02.039

[21]Cui TJ, Li S. Deep learning of system reliability under multi-factor influence based on space fault tree. Neural Computing and Applications. 2019; 31(9): 4761–4776. doi: 10.1007/s00521-018-3416-2

[22]Jang J, Lee H. Resilient fault diagnosis and recovery framework for driving modules of electric vehicles using continuous wavelet transform-based fault-aware deep learning. Applied Soft Computing. 2026; 198: 115289. doi: 10.1016/j.asoc.2026.115289

[23]Fang C, Liang Y, Zhou W, et al. Dynamic and contact characteristics of axle-box bearing for a high-speed train under wheel polygonization. Mechanism and Machine Theory. 2026; 224: 106437. doi: 10.1016/j.mechmachtheory.2026.106437

[24]Cui TJ, Li SS. Study on the construction and application of discrete space fault tree modified by fuzzy structured element. Cluster Computing. 2019; 22(S3): 6563–6577. doi: 10.1007/s10586-018-2342-5

[25]Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1989; 11(7): 674–693. doi: 10.1109/34.192463

[26]Zheng FL, Pan HY, Zheng JD, et al. Fuzzy projection twin broad learning and its application to rolling bearing fault diagnosis. 2025; 44(08): 192–198. doi: 10.13465/j.cnki.jvs.2025.08.021 (in Chinese)

[27]Chen J, Cao Z, Liu YB, et al. Multi-degree-of-freedom dynamic modeling of ball bearing with rolling element spalling defect. Journal of Machine Design. 2026; 43(01): 53–61. doi: 10.13841/j.cnki.jxsj.2026.01.009 (in Chinese)

[28]Huang K, Li A, Zhu G, et al. A comprehensive review of fractal theory in gear transmission: From microscopic contact to fault diagnosis. Engineering Research Express. 2025; 7(4): 042505. doi: 10.1088/2631-8695/ae2239

[29]Zhao GC, Liu CD, Song YN, et al. Bearing fault diagnosis method based on fusion of time-frequency features by cross-attention mechanism. Journal of Vibration and Shock. 2025; 44 (12): 228–237. doi: 10.13465/j.cnki.jvs.2025.12.024 (in Chinese)

[30]Liu SY, Dong YL, Qiao YM, et al. Research on Dynamic Fault Injection of Bearing Digital Twin Model Based on Improved Dung Beetle Optimization Algorithm. Journal of Mechanical Engineering. 2026; 62(03): 446–457. Available online: http://www.cjmenet.com.cn/CN/10.3901/JME.260097 (in Chinese)

[31]Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing. 2020; 138: 106587. doi: 10.1016/j.ymssp.2019.106587

Editor-in-Chief

Prof. Jun Yang

Institute of Acoustics, Chinese Academy of Sciences, China

ISSN

1541-0161 (Print)

2693-1443 (Online)

Publication Frequency

Bi-monthly

Indexing

Web of Science Coverage

Emerging Sources Citation Index (IF 4.2, Q1)

Elsevier Solutions

Scopus (2025 CiteScore 2.0);

Portico, etc.

About the Publisher

Academic Publishing insists on taking academic exchange and publication as the main line, carrying out comprehensive management based on science and technology, and fully exploring excellent international publishing resources. Within 5 years, it will form a strategic framework and scale with science (S), technology (T), medicine (M), education (E), and humanities and arts (H) as the main publishing fields. Academic Publishing is headquartered in Singapore and based in Malaysia, with the United States and China providing the main scientific and academic resources. At the same time, it has established long-term good cooperative relations with other publishing companies, scientific research communities, and academic organizations in more than a dozen countries and regions. Academic Publishing uses English and Chinese as its main publishing languages, mainly publishing books, journals, and conference papers in print and online. The vast majority of publications follow the international open access policy, providing stable and long-term quality and professional publications. With the joint efforts of the expert team and our professional editorial team, our publications will gradually be indexed by international databases in stages to provide convenient and professional retrieval for various scholars. At the same time, manuscripts we accept will be subject to the peer review principle, and cutting-edge and innovative research articles will be preferentially accepted for peer reference and discussion. All kinds of our publications are welcome for peer to contribute, access, and download.

more

Member of ASC

Volume Arrangement

Featured Articles

New scaling of critical damping and reduced frequency for mechanically excited systems

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.

Ultrasonic wave velocity as a universal metric for defect detection in timber structures: A case study on Japanese cedar wood (Cryptomeria japonica)

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.

Vehicle structural road noise prediction based on an improved Long Short-Term Memory method

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.

Weak fault feature extraction and system fault analysis under strong noise

Abstract

References

Most read articles by the same author(s)