Machinery Faults Detection Based on Mechanical Vibrations with Machine Learning Techniques
DOI:
https://doi.org/10.70567/mc.v41i20.106Keywords:
Machine learning, failure detection, vibrations, industrial machineryAbstract
The analysis of mechanical vibrations is a widely used technique for failure detection in industrial machinery. The traditional approach requires a wide expertise to interpret the results and tune the procedure according to each application. However, new machine learning technologies that incorporate neuronal-network-based systems have reduced the participation of analysts in damage detection. In this work, three neural network architectures designed to detect faults from vibration signals are presented: i) a feed-forward network; ii) a 1D convolutional network; and, iii) a 2D convolutional network. The three architectures are trained with sets of synthetic and experimental signals representing systems in normal and abnormal operation conditions, and their ability to detect these conditions is comparatively evaluated. The results show the potential of these systems to efficiently achieve their objective.
References
Atmaja B.T., Ihsannur H., Suyanto, y Arifianto D. Lab-scale vibration analysis dataset and baseline methods for machinery fault diagnosis with machine learning. Journal of Vibration Engineering & Technologies, 12(2):1991-2001, 2024. https://doi.org/10.1007/s42417-023-00959-9
Belfiore N.P. y Rudas I.J. Applications of computational intelligence to mechanical engineering. páginas 351-368, 2014. https://doi.org/10.1109/CINTI.2014.7028702
Islam M.M. y Kim J.M. Motor bearing fault diagnosis using deep convolutional neural networks with 2d analysis of vibration signal. En Advances in Artificial Intelligence: 31st Canadian Conference on Artificial Intelligence, Canadian AI 2018, Toronto, ON, Canada, May 8-11, 2018, Proceedings 31, páginas 144-155. Springer, 2018. https://doi.org/10.1007/978-3-319-89656-4_12
Kumar S., Kumar V., Sarangi S., y Singh O.P. Gearbox fault diagnosis: A higher order moments approach. Measurement, 210:112489, 2023. ISSN 0263-2241. https://doi.org/10.1016/j.measurement.2023.112489
Liu R., Yang B., Zio E., y Chen X. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108:33-47, 2018. https://doi.org/10.1016/j.ymssp.2018.02.016
Mourtzis D., Angelopoulos J., y Panopoulos N. A literature review of the challenges and opportunities of the transition from industry 4.0 to society 5.0. Energies, 15(17), 2022. ISSN 1996-1073. https://doi.org/10.3390/en15176276
Ribeiro F. Machinery fault database (mafaulda)-multivariate time-series acquired by sensors on a spectraquest's machinery fault simulator (mfs) alignment-balance-vibration (abvt). 2022.
Sepulveda N.E. y Sinha J. Parameter optimisation in the vibration-based machine learning model for accurate and reliable faults diagnosis in rotating machines. Machines, 8(4):66, 2020. https://doi.org/10.3390/machines8040066
Taylor J. The Vibration Analysis Handbook: A Practical Guide for Solving Rotating Machinery Problems. VCI, 2003. ISBN 9780964051720.
Vrba J., Cejnek M., Steinbach J., y Krbcova Z. A machine learning approach for gearbox system fault diagnosis. Entropy, 23(9), 2021. ISSN 1099-4300. https://doi.org/10.3390/e23091130
Zhang J., Yi S., Liang G., Hongli G., Xin H., y Hongliang S. A new bearing fault diagnosis method based on modified convolutional neural networks. Chinese Journal of Aeronautics, 33(2):439-447, 2020. https://doi.org/10.1016/j.cja.2019.07.011
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Argentine Association for Computational Mechanics
This work is licensed under a Creative Commons Attribution 4.0 International License.
This publication is open access diamond, with no cost to authors or readers.
Only those papers that have been accepted for publication and have been presented at the AMCA congress will be published.
