An overview of deep learning techniques for fault detection using vibration signal

초록

As a specialized sub-domain of machine learning, deep learning has secured enormous implications in various real-world applications, and in noise and vibration engineering field is no exception. Deep learning has shown a promising result with near-to-human-level accuracy. The objective of this paper is to give an overview of the state-of-the-art deep learning techniques and their applications to fault detection methods using vibration signal. Several presently publications published in some outlets were included, providing a big picture of deep learning-based condition monitoring approaches based on vibration analysis. Lastly, some remaining research challenges and opportunities that require further investigation are also reported. © Proceedings of 2020 International Congress on Noise Control Engineering, INTER-NOISE 2020. All rights reserved.