A two-level machine learning framework for predictive maintenance: comparison of learning formulations

TL;DR

This paper proposes and compares a two-level machine learning framework for predictive maintenance, integrating failure prediction with decision-making, and evaluates different learning formulations on real industrial data.

Contribution

It introduces a two-level framework combining health indicator construction and decision-making, comparing multiple learning formulations including simple thresholding and supervised learning.

Findings

Simple models perform well in failure detection

Refined models improve prediction accuracy with proper parameter tuning

Support Vector Machine variations enhance predictive maintenance performance

Abstract

Predicting incoming failures and scheduling maintenance based on sensors information in industrial machines is increasingly important to avoid downtime and machine failure. Different machine learning formulations can be used to solve the predictive maintenance problem. However, many of the approaches studied in the literature are not directly applicable to real-life scenarios. Indeed, many of those approaches usually either rely on labelled machine malfunctions in the case of classification and fault detection, or rely on finding a monotonic health indicator on which a prediction can be made in the case of regression and remaining useful life estimation, which is not always feasible. Moreover, the decision-making part of the problem is not always studied in conjunction with the prediction phase. This paper aims to design and compare different formulations for predictive maintenance in a two-level framework and design metrics that quantify both the failure detection performance as well as the timing of the maintenance decision. The first level is responsible for building a health indicator by aggregating features using a learning algorithm. The second level consists of a decision-making system that can trigger an alarm based on this health indicator. Three degrees of refinements are compared in the first level of the framework, from simple threshold-based univariate predictive technique to supervised learning methods based on the remaining time before failure. We choose to use the Support Vector Machine (SVM) and its variations as the common algorithm used in all the formulations. We apply and compare the different strategies on a real-world rotating machine case study and observe that while a simple model can already perform well, more sophisticated refinements enhance the predictions for well-chosen parameters.