Keywords: Maintenance, Imperfect maintenance, Causal inference, Individual treatment effects, Machine learning
TL;DR: A flexible and general framework for prescribing maintenance by learning individual treatment effects from observational data.
Abstract: The goal in maintenance is to avoid machine failures and overhauls, while simultaneously minimizing the cost of preventive maintenance. Maintenance policies aim to optimally schedule maintenance by modeling the effect of preventive maintenance on machine failures and overhauls. Existing work assumes the effect of preventive maintenance is (1) deterministic or governed by a known probability distribution, and (2) machine-independent. Conversely, this work proposes to relax both assumptions by learning the effect of maintenance conditional on a machine's characteristics from observational data on similar machines using existing methodologies for causal inference. This way, we can estimate the number of overhauls and failures for different levels of maintenance and, consequently, optimize the preventive maintenance frequency. We validate our proposed approach using real-life data on more than 4,000 maintenance contracts from an industrial partner. Empirical results show that our novel, causal approach accurately predicts the maintenance effect and results in individualized maintenance schedules that are more accurate and cost-effective than supervised or non-individualized approaches.