Integrated maintenance service and spare parts supply strategy for service-oriented manufacturers with partially unknown information

Original equipment manufacturers (OEMs) are increasingly penetrating the aftersales market by providing maintenance services and OEM parts. Competition from independent maintenance service providers and independent parts suppliers necessitates that OEMs optimize strategies to enhance competitiveness while maintaining cost efficiency. Different from the independent operation of either business, the integration of OEMs’ dual roles creates significant interactions between maintenance service and spare parts supply. Particularly, within the constraints of production and inventory capacities, dynamic spare parts demand from internal maintenance needs and external orders complicates production quantity decisions and inventory allocation. From the perspective of service-oriented manufacturers under dual competition, this paper proposes an optimization model to maximize the expected total profits from maintenance services and spare parts sales. The model captures the interactions among decisions including pricing for service and spare parts, maintenance intervals, production quantities, and inventory allocation for dual-source demand. However, the differing decision timelines and partially unknown market information pose challenges to the collaborative optimization of these strategies. To address this, a two-stage algorithm integrating reinforcement learning is proposed, providing a “predetermination and online adjustment” mechanism. Numerical studies validate the advantages of the proposed methodology in mitigating potential profit loss due to independent optimization and estimation errors.