Predictive maintenance on event logs: Application on an ATM fleet

TL;DR

This paper explores predictive maintenance using event logs instead of sensor data, introduces a new dataset of ATM machine logs, and proposes an evaluation framework to guide future research in this area.

Contribution

It presents a new public dataset of ATM event logs and an evaluation framework for predictive maintenance systems based on event data.

Findings

Analysis of existing approaches in literature

Introduction of a new ATM event log dataset

Evaluation of solutions under business constraints

Abstract

Predictive maintenance is used in industrial applications to increase machine availability and optimize cost related to unplanned maintenance. In most cases, predictive maintenance applications use output from sensors, recording physical phenomenons such as temperature or vibration which can be directly linked to the degradation process of the machine. However, in some applications, outputs from sensors are not available, and event logs generated by the machine are used instead. We first study the approaches used in the literature to solve predictive maintenance problems and present a new public dataset containing the event logs from 156 machines. After this, we define an evaluation framework for predictive maintenance systems, which takes into account business constraints, and conduct experiments to explore suitable solutions, which can serve as guidelines for future works using this new dataset.