Data fusion techniques for fault diagnosis of industrial machines: a survey

TL;DR

This survey reviews recent data fusion techniques used in predictive maintenance for industrial machine fault diagnosis, highlighting classifications, applications, challenges, and future research directions.

Contribution

It provides a comprehensive classification and analysis of data fusion methods in machinery fault diagnosis, summarizing recent progress and identifying future research trends.

Findings

Classified data fusion strategies for fault diagnosis

Analyzed levels of data fusion in industrial applications

Discussed challenges and future opportunities in the field

Abstract

In the Engineering discipline, predictive maintenance techniques play an essential role in improving system safety and reliability of industrial machines. Due to the adoption of crucial and emerging detection techniques and big data analytics tools, data fusion approaches are gaining popularity. This article thoroughly reviews the recent progress of data fusion techniques in predictive maintenance, focusing on their applications in machinery fault diagnosis. In this review, the primary objective is to classify existing literature and to report the latest research and directions to help researchers and professionals to acquire a clear understanding of the thematic area. This paper first summarizes fundamental data-fusion strategies for fault diagnosis. Then, a comprehensive investigation of the different levels of data fusion was conducted on fault diagnosis of industrial machines. In conclusion, a discussion of data fusion-based fault diagnosis challenges, opportunities, and future trends are presented.