Analysis of key flavors of event-driven predictive maintenance using logs of phenomena described by Weibull distributions

TL;DR

This paper compares classification and regression approaches for event-driven predictive maintenance in Industry 4.0, analyzing various data preprocessing, algorithms, and ensemble methods to identify effective strategies using Weibull-distributed logs.

Contribution

It systematically evaluates different data-driven methods for predictive maintenance, providing insights into their relative strengths and guiding practitioners in method selection.

Findings

Classification and regression approaches have distinct advantages.

Data preprocessing significantly impacts prediction accuracy.

Ensemble and sampling methods improve model robustness.

Abstract

This work explores two approaches to event-driven predictive maintenance in Industry 4.0 that cast the problem at hand as a classification or a regression one, respectively, using as a starting point two state-of-the-art solutions. For each of the two approaches, we examine different data preprocessing techniques, different prediction algorithms and the impact of ensemble and sampling methods. Through systematic experiments regarding the aspectsmentioned above,we aimto understand the strengths of the alternatives, and more importantly, shed light on how to navigate through the vast number of such alternatives in an informed manner. Our work constitutes a key step towards understanding the true potential of this type of data-driven predictive maintenance as of to date, and assist practitioners in focusing on the aspects that have the greatest impact.