A Hybrid Fuzzy–Probabilistic Methodology for Machinery Reliability Assessment via Vibration Testing

Yogeesh N; Asokan  Vasudevan; Mohammed  Almakki; Puspanathan  Doraisingam; Khan  Sarfaraz Ali

doi:10.59400/sv3949

A Hybrid Fuzzy–Probabilistic Methodology for Machinery Reliability Assessment via Vibration Testing

Yogeesh N
Research Fellow, INTI International University, Nilai 71800, Malaysia; Department of Mathematics, Government First Grade College, Tumakuru 572102, India
Asokan Vasudevan
Faculty of Business and Communications, INTI International University, Nilai 71800, Malaysia
Mohammed Almakki
School of Engineering, Architecture and Interior Design, Amity University Dubai, Dubai 345019, United Arab Emirates
Puspanathan Doraisingam
Faculty of Business and Communications, INTI International University, Nilai 71800, Malaysia
Khan Sarfaraz Ali
Faculty of Business and Communications, INTI International University, Nilai 71800, Malaysia

Article ID: 3949

Keywords: Machinery reliability; Vibration testing; Hybrid uncertainty; Fuzzy Bayesian inference; Proportional hazards; Weibull model; α-cut propagation; Failure probability interval; Prognostics and health management; Process Innovation.

Abstract

Vibration testing is central to condition monitoring and fault prognosis in rotating and structural machinery, yet reliability conclusions drawn from vibration data often suffer from two competing uncertainty sources: stochastic variability in measured dynamic responses and epistemic imprecision in model parameters, thresholds, and degradation definitions. This paper proposes a hybrid fuzz probabilistic methodology for machinery reliability assessment that integrates vibration-derived health indicators with probabilistic hazard modeling under fuzzy parameter uncertainty. The approach begins with frequency-response and time-domain vibration features obtained from controlled excitation or operational monitoring, followed by normalization and fusion into a monotonic health indicator representing degradation progression. Reliability is then quantified using a probabilistic time-to-failure model (e.g., Weibull or proportional hazards), while uncertain parameters such as failure thresholds, feature-to-damage mappings, and prior hyperparameters are represented by fuzzy numbers. Using -cut decomposition, the fuzzy parameter set is propagated through the probabilistic model to produce interval-valued reliability and failure probability estimates over time. To ensure decision consistency, the resulting reliability bounds are evaluated with calibration and discrimination diagnostics adapted for time-to-event prediction, and maintenance decisions are supported through net-benefit based utility analysis. The proposed framework therefore provides both mathematical rigor and engineering practicality: it preserves probabilistic interpretation where randomness dominates, retains transparency under imprecise assumptions, and yields reliability intervals that explicitly reflect uncertainty in vibration-based inference. The methodology is suitable for machinery reliability assessment in laboratory vibration qualification and in-field monitoring, offering a structured route to robust maintenance planning under uncertainty.

Published

2026-04-22

How to Cite

N, Y., Vasudevan, A., Almakki, M., Doraisingam, P., & Sarfaraz Ali, K. (2026). A Hybrid Fuzzy–Probabilistic Methodology for Machinery Reliability Assessment via Vibration Testing. Sound & Vibration, 60(2). https://doi.org/10.59400/sv3949

Download Citation

Issue

Vol. 60 No. 2 (2026)

Section

Article

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

References

[1]Cox DR. Regression Models and Life-Tables. Journal of the Royal Statistical Society Series B: Statistical Methodology. 1972; 34(2): 187–202. doi: 10.1111/j.2517-6161.1972.tb00899.x

[2]Breslow N. Covariance Analysis of Censored Survival Data. Biometrics. 1974; 30(1): 89. doi: 10.2307/2529620

[3]Efron B. The Efficiency of Cox’s Likelihood Function for Censored Data. Journal of the American Statistical Association. 1977; 72(359): 557–565. doi: 10.1080/01621459.1977.10480613

[4]Weibull W. A Statistical Distribution Function of Wide Applicability. Journal of Applied Mechanics. 1951, 18(3): 293–297. Available online: https://hal.science/hal-03112318/document

[5]Vlok PJ, Coetzee JL, Banjevic D, et al. Optimal component replacement decisions using vibration monitoring and the proportional-hazards model. Journal of the Operational Research Society. 2002; 53(2): 193–202. doi: 10.1057/palgrave.jors.2601261

[6]Lin D, Banjevic D, Jardine AKS. Using principal components in a proportional hazards model with applications in condition-based maintenance. Journal of the Operational Research Society. 2006; 57(8): 910–919. doi: 10.1057/palgrave.jors.2602058

[7]Heng A, Zhang S, Tan ACC, et al. Rotating machinery prognostics: State of the art, challenges and opportunities. Mechanical Systems and Signal Processing. 2009; 23(3): 724–739. doi: 10.1016/j.ymssp.2008.06.009

[8]Zheng R, Najafi S, Zhang Y. A recursive method for the health assessment of systems using the proportional hazards model. Reliability Engineering & System Safety. 2022; 221: 108379. doi: 10.1016/j.ress.2022.108379

[9]Jardine AKS, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing. 2006; 20(7): 1483–1510. doi: 10.1016/j.ymssp.2005.09.012

[10]Martarelli M, Ewins DJ. Continuous scanning laser Doppler vibrometry and speckle noise occurrence. Mechanical Systems and Signal Processing. 2006; 20(8): 2277–2289. doi: 10.1016/j.ymssp.2005.06.003

[11]Zhu Y, Du Q, Li J. Vibration Pollution Assessment Method Based on Fuzzy Logic. Measurement. 2024: 226, 114609

[12]Chu T, Nguyen T, Yoo H, et al. A review of vibration analysis and its applications. Heliyon. 2024; 10(5): e26282. doi: 10.1016/j.heliyon.2024.e26282

[13]Devriendt C, De Sitter G, Vanlanduit S, et al. Operational modal analysis in the presence of harmonic excitations by the use of transmissibility measurements. Mechanical Systems and Signal Processing. 2009; 23(3): 621–635. doi: 10.1016/j.ymssp.2008.07.009

[14]Zhao J, Wang W, Huang J, et al. A comprehensive review of deep learning-based fault diagnosis approaches for rolling bearings: Advancements and challenges. AIP Advances. 2025; 15(2): 020702. doi: 10.1063/5.0255451

[15]Khalid S, Jo SH, Shah SY, et al. Artificial Intelligence-Driven Prognostics and Health Management for Centrifugal Pumps: A Comprehensive Review. Actuators. 2024; 13(12): 514. doi: 10.3390/act13120514

[16]Lu W, Liu J, Lin F. The Fault Diagnosis of Rolling Bearings Is Conducted by Employing a Dual-Branch Convolutional Capsule Neural Network. Sensors. 2024; 24(11): 3384. doi: 10.3390/s24113384

[17]Pandiyan M, Babu TN. Systematic Review on Fault Diagnosis on Rolling-Element Bearing. Journal of Vibration Engineering & Technologies. 2024; 12(7): 8249–8283. doi: 10.1007/s42417-024-01358-4

[18]Samaila B, Sekar C. Quantum Power Flow: Revolutionizing Power Systems Analysis. SciWaveBulletin. 2023; 1(2): 1–9. doi: 10.61925/SWB.2023.1201

[19]Machaila VF, Waliu T. Unveiling Data’s Tapestry: Challenges, Opportunities, and Netflix’s Analytical Triumph. SciWaveBulletin. 2023; 1(4): 16–23. doi: 10.61925/SWB.2023.1403

[20]Abdullahi Saleh I, Srivastava A. Exploring the Intersection of Fuzzy Logic and Quantum Logic: A New Frontier in Non-Classical Logics. SciWaveBulletin. 2023; 1(2): 27–34. doi: 10.61925/SWB.2023.1204

[21]Vickers AJ, Elkin EB. Decision Curve Analysis: A Novel Method for Evaluating Prediction Models. Medical Decision Making. 2006; 26(6): 565–574. doi: 10.1177/0272989X06295361

[22]Vickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. BMJ. 2016; i6. doi: 10.1136/bmj.i6

[23]Van Calster B, McLernon DJ, van Smeden M, et al. Calibration: the Achilles heel of predictive analytics. BMC Medicine. 2019; 17(1): 230. doi: 10.1186/s12916-019-1466-7

[24]Mendel JM, John RIB. Type-2 fuzzy sets made simple. IEEE Transactions on Fuzzy Systems. 2002; 10(2): 117–127. doi: 10.1109/91.995115

[25]Takagi T, Sugeno M. Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics. 1985; SMC-15(1): 116–132. doi: 10.1109/TSMC.1985.6313399

[26]Jang JSR. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics. 1993; 23(3): 665–685. doi: 10.1109/21.256541

[27]Li DF, Shan F, Cheng CT. On properties of four IFS operators. Fuzzy Sets and Systems. 2005; 154(1): 151–155. doi: 10.1016/j.fss.2005.03.004

[28]Yogeesh N, Raja N, Vasudevan A, et al. Type-2 fuzzy logic framework for adaptive noise control in vibrating structures. Sound & Vibration. 2025; 59(3): 3478. doi: 10.59400/sv3478

[29]Yogeesh N, Karthik M, Raja N, et al. Fuzzy-grey relational optimization for active vibration control in smart composite beams: a multi-objective framework with experimental validation. Sound & Vibration. 2025; 59(4). doi: 10.59400/sv3496

[30]Yogeesh N. Fuzzy Logic-Based Beat Tracking in Music Signals. Musik In Bayern. 2023; 88(9): 145–157.

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.

A Hybrid Fuzzy–Probabilistic Methodology for Machinery Reliability Assessment via Vibration Testing

Abstract

References

Most read articles by the same author(s)