Machine Learning based Fault Prediction Method for Mechanical Vibration Signals

DOI

10.2991/978-94-6463-823-3_39How to use a DOI?

Keywords

Fault Prediction; Machine Learning; Mechanical Vibration Signals

Abstract

One crucial piece of technology to guarantee the regular operation of mechanical systems is the prediction of mechanical vibration signal failures. This paper reviews the recent advances in traditional methods for predicting mechanical vibration faults and machine learning-based methods for predicting signals from mechanical vibration. Traditional methods such as spectrum analysis and time-domain averaging, although simple and convenient, play an important role in early detection, but still have limitations when dealing with some complex system problems. With the progressive development of machine learning, it has become a trend to apply it to fault detection. This study offers insights into the use of several deep learning models by methodically examining the combination of conventional wavelet transform (WT), empirical mode decomposition (EMD), and machine learning algorithms. These include models that combine long-short-term memory (LSTM) networks and convolutional neural networks (CNNs); models that combine long-short-term memory (LSTM) and the error of multiple sparse self-encoders (EFMSAE); multi-feature fusion models that combine artificial neural networks and particle swarm optimization algorithms (PSO-ANN) based on the Continuous Hidden Markov Model (CHMM) and the Dempster-Shafer evidence theory. Through comparative analysis, the advantages and limitations of the above types of methods are summarized to provide some theoretical support for the prediction of mechanical vibration signals.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xinyi Gao
PY  - 2025
DA  - 2025/08/31
TI  - Machine Learning based Fault Prediction Method for Mechanical Vibration Signals
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 396
EP  - 404
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_39
DO  - 10.2991/978-94-6463-823-3_39
ID  - Gao2025
ER  -