Predictive analysis of industrial safety based on noise, vibrations and machinery reliability

Henry Nelson  Aguilera Vidal; Ruth Isabel  Torres Torres; Irene Teresa  Bustillos Molina; Eudes  Martínez Porro

doi:10.59400/sv3995

Predictive analysis of industrial safety based on noise, vibrations and machinery reliability

Henry Nelson Aguilera Vidal
Faculty of Industrial and Production Sciences, Quevedo State Technical University, Quevedo EC120550, Ecuador
Ruth Isabel Torres Torres
Faculty of Industrial and Production Sciences, Quevedo State Technical University, Quevedo EC120550, Ecuador
Irene Teresa Bustillos Molina
Faculty of Industrial and Production Sciences, Quevedo State Technical University, Quevedo EC120550, Ecuador
Eudes Martínez Porro
Faculty of Industrial and Production Sciences, Quevedo State Technical University, Quevedo EC120550, Ecuador

Article ID: 3995

Keywords: industrial safety; noise exposure; vibration analysis; machinery reliability; predictive modeling; risk assessment; condition monitoring; logistic regression

Abstract

This study develops a predictive approach for assessing industrial safety risk through the integrated analysis of physical indicators associated with machinery operation, specifically noise, vibration, and mechanical reliability. The research was conducted in industrial environments characterized by the continuous operation of rotating equipment, including motors, pumps, compressors, and transmission systems. A dataset of approximately 18,000 operational records collected over a 12-month period was analyzed, incorporating acoustic measurements, vibration parameters, machinery condition, and records of potentially unsafe operating states. Equivalent sound pressure level (Leq), Root Mean Square (RMS) acceleration, and crest factor were calculated as the main dynamic indicators, and these variables were normalized and integrated into an Industrial Risk Index (IRI) designed to represent the operational safety state of the equipment. Subsequently, a logistic regression model was developed to classify operating conditions into safe or risk states. The results showed that the combined use of acoustic and vibration indicators improves the identification of hazardous conditions compared with isolated metrics. The predictive model achieved strong classification performance, with an accuracy of 0.88, sensitivity of 0.86, specificity of 0.84, and an AUC-ROC of 0.90, demonstrating a high capacity to distinguish safe operation from risk scenarios. Sustained increases in noise and vibration, particularly when associated with signs of mechanical degradation, were found to precede unsafe states. The findings confirm that integrating dynamic condition monitoring with predictive analytics strengthens failure anticipation and supports preventive decision-making, providing a technically interpretable basis for more proactive industrial safety management systems.

Published

2026-04-02

How to Cite

Aguilera Vidal, H. N., Torres Torres, R. I., Bustillos Molina, I. T., & Martínez Porro, E. (2026). Predictive analysis of industrial safety based on noise, vibrations and machinery reliability. Sound & Vibration, 60(2). https://doi.org/10.59400/sv3995

Download Citation

Issue

Vol. 60 No. 2 (2026): in progress

Section

Article

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

References

[1]Hämäläinen P, Takala J, Saarela KL. Global estimates of occupational accidents. Safety Science. 2006; 44(2): 137–156.

[2]Griffin MJ. Handbook of Human Vibration. Academic Press; 2012. pp. 1–1005.

[3]Singh I, Nigam SP, Saran VH. Modal analysis of human body vibration model for Indian subjects under sitting posture. 2015; 58(7): 1117–1132. doi: 10.1080/00140139.2014.961567

[4]Themann CL, Masterson EA. Occupational noise exposure: A review of its effects, epidemiology, and impact with recommendations for reducing its burden. The Journal of the Acoustical Society of America. 2019; 146(5): 3879–3905.

[5]Basner M, Babisch W, Davis A, et al. Auditory and Non-Auditory Effects of Noise on Health. The Lancet. 2014; 383(9925): 1325–1332. doi: 10.1016/S0140-6736(13)61613-X

[6]Randall A. Risk and Precaution. Cambridge University Press; 2011.

[7]Luque-Mohedano R. Dynamic Modeling and Analysis of the Olive Tree Subjected to Mechanical Vibration [PhD thesis]. University of Córdoba; 2024. Available online: https://produccioncientifica.ugr.es/documentos/68505d194e31682f4064766c (in Spanish)

[8]Contreras IT. Diagnosis of Mechanical Failures in Rotating Machines Considering Nonlinear Dynamic Behavior Using Recurrence Diagrams [PhD thesis]. Universidad Autónoma de Querétaro; 2023.

[9]Mobley RK. An Introduction to Predictive Maintenance. Elsevier; 2002. pp. 1–451.

[10]Jia F, Lei Y, Lu N, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mechanical Systems and Signal Processing. 2018; 110: 349–367.

[11]Ordysiński S. Prediction of the Injury Severity of Accidents at Work: A New Approach to Analysis of Already Existing Statistical Data. Applied Sciences. 2025; 15(19): 10666. doi: 10.3390/app151910666

[12]Obasi IC, Cheng P, Varianou-Mikellidou C, et al. Machine learning for occupational accident analysis: Applications, challenges, and future directions. Journal of Safety Science and Resilience. 2026; 7(1): 100–250.

[13]Xia X, Xiang P, Khanmohammadi S, et al. Predicting Safety Accident Costs in Construction Projects Using Ensemble Data-Driven Models. Journal of Construction Engineering and Management. 2024; 150(7). doi: 10.1061/JCEMD4.COENG-14397

[14]Xu X, Qiao Z, Lei Y. Repetitive transient extraction for machinery fault diagnosis using multiscale fractional order entropy infogram. Mechanical Systems and Signal Processing. 2018; 103: 312–326.

[15]Harris CM, Piersol AG. Shock and Vibration Handbook, 5th ed. McGraw-Hill; 2002. pp. 1–1050.

[16]Jacobs N, Roberts B, Reamer H, et al. Noise exposures in different community settings measured by traditional dosimeter and smartphone app. Applied Acoustics. 2020; 167: 107408. doi: 10.1016/j.apacoust.2020.107408

[17]Jiang W, Zhou R, Jia H. Research on Mechanical Equipment Fault Diagnosis and Prediction Technology Based on Vibration Signal Analysis. In: Proceedings of the 2024 International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC); 14–16 August 2024; Athens, Greece. pp. 494–498.

[18]Li Z, Zhao Y, Zhang Y, et al. A novel transformer-enhanced and acoustic-based approach for wind turbine blade fault detection with integrated system implementation. Journal of Engineering Design. 2025; 36(5–6): 642–671. doi: 10.1080/09544828.2024.2332122

[19]Lee J, Lee U, Oh J. Development of Algorithm for Vibration Analysis Automation of Rotating Equipments Based on ISO 20816. Journal of the Korean Institute of Gas. 2024; 28(2): 93–104.

[20]Cerrada M, Macancela JC, Cabrera D, et al. Reciprocating Compressor Multi-Fault Classification Using Symbolic Dynamics and Complex Correlation Measure. Applied Sciences. 2020; 10(7): 2512. doi: 10.3390/app10072512

[21]Macias ÁAT, González EDPT. Vibration Analysis in Rotating Machinery: Fault Diagnosis and Predictive Maintenance Strategies. Revista Sociedad Fronteriza. 2024; 4(4): e44365–e44365. (in Spanish)

[22]Ali M, Lee YS, Chowdhury M, et al. Analysis of Driving Stability and Vibration of a 20-kW Self-Propelled 1-Row Chinese Cabbage Harvester. Journal of Biosystems Engineering. 2021; 46(1): 48–59. doi: 10.1007/s42853-021-00087-w

[23]Solé AC. Reliability and Safety of Industrial Processes (Vol. 49). Marcombo; 1991. Available online: https://www.amazon.com/-/es/Fiabilidad-Seguridad-Procesos-Industriales-Prod%C3%BActica/dp/8426708153 (in Spanish)

[24]Bakdash RS, Younis MN, Chanbasha B, et al. Analytical detection methods for measuring residual corrosion inhibitors in oil and gas and other industrial facilities. Results in Engineering. 2026; 29: 108547. doi: 10.1016/j.rineng.2025.108547

[25]Pandey S, Singh AK, Parhi S, et al. Transforming workplace safety through leveraging predictive analytics and explainable AI in steel industries. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability. 2025; 239(6): 1332–1345. doi: 10.1177/1748006X251331681

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.