Machine Learning and Audio Signal Processing for Predictive Maintenance: A review | IEEE Conference Publication | IEEE Xplore

Machine Learning and Audio Signal Processing for Predictive Maintenance: A review


Abstract:

This work shows a systematic review of literature of machine learning and audio processing for applications in preventive maintenance. It intends to prove how audio signa...Show More

Abstract:

This work shows a systematic review of literature of machine learning and audio processing for applications in preventive maintenance. It intends to prove how audio signal processing combined with Machine Leanring techniques can produce a powerfool tool to detect anomalies and malfunctions in electromechanical devices. The document describes a review of art state and the algorithms that can be used for preventive maintenance applications. When reviewed, the literature proves that Machine Learning and Deep Learning approaches provide high accuracy results as tools for PdM, and that Support Vector Machines, k-Nearest Neighbors and Convolutional Neural Networks are the most used approaches as they achieve the highest evaluation metrics, and prove sound, vibration and current to be the most popular signals to train ML-PdM oriented models.
Date of Conference: 17-20 October 2023
Date Added to IEEE Xplore: 06 December 2023
ISBN Information:

ISSN Information:

Conference Location: Popayan, Colombia

Funding Agency:


I. Introduction

Throughout modern history humanity has faced transformative events known as "industrial revolutions"; the First Industrial Revolution introduced steam machines and hydraulic energy, allowing the transition from the usage of humans and animals; this revolution is followed by the one that came with fuel and gas, alongside with the invention of telephone, which brought mass production and the origins of automatization, followed by the arrival of Programmable Logical Controllers that introducted to data analysis. Industry is currently going through the Fourth Industrial Revolution, also known as Industry 4.0 (I4.0); the goal is the integration between physical and digital systems, or as Lee [12] defines it: the pursuit of autonomous industrial systems base on Artificial Intelligence, Big Data, Data Analytics, Cloud Computing, Internet of Things, among others, implying the possibility of automatizing data collection from machines and components. Cinar [34] claims Machine learning algorithms can be applied over the collected data and allow fault detection and diagnosis. The techniques often used for this end infuse intelligence within systems so they can learn automatically and adapt to changing environments using historical experience in the training stages.

References

References is not available for this document.