Optimal data pooling for shared learning in maintenance operations

TL;DR

This paper investigates optimal data pooling strategies in maintenance operations, demonstrating that pooling reduces costs and characterizing the structure of optimal policies for condition-based maintenance and spare parts management.

Contribution

It introduces a decomposition method for high-dimensional MDPs in maintenance, enabling analysis of pooled data effects and deriving optimal control policies.

Findings

Pooling data significantly reduces maintenance costs.

Optimal policies are control limit and order-up-to level policies.

Decomposition simplifies complex decision problems.

Abstract

We study optimal data pooling for shared learning in two common maintenance operations: condition-based maintenance and spare parts management. We consider a set of systems subject to Poisson input -- the degradation or demand process -- that are coupled through an a-priori unknown rate. Decision problems involving these systems are high-dimensional Markov decision processes (MDPs) and hence notoriously difficult to solve. We present a decomposition result that reduces such an MDP to two-dimensional MDPs, enabling structural analyses and computations. Leveraging this decomposition, we (i) demonstrate that pooling data can lead to significant cost reductions compared to not pooling, and (ii) show that the optimal policy for the condition-based maintenance problem is a control limit policy, while for the spare parts management problem, it is an order-up-to level policy, both dependent on the pooled data.