Hierarchical-clustering-based joint optimization of spare part provision and maintenance scheduling for serial-parallel multi-station manufacturing systems

Both the spare part provision and the maintenance scheduling are important in ensuring the production of the Serial-Parallel Multi-Station System (SPMMS). In the multi-specification and small-batch production, the production plan, which renews batch by batch, leads to variable and uncertain working conditions. The existing Dynamic Opportunistic Maintenance (DOM), which separately optimizes each cycle, ignores the aftereffects of both the spare part provision and the Preventive Maintenance (PM) on the following PM scheduling. This paper studies the dynamic joint optimization of spare part provision and maintenance scheduling for the SPMMS, where the aftereffects of the information are especially investigated. During the failure rate modelling, the aftereffect of the historical working conditions is described with the accelerated failure-time model. In the system-level maintenance modelling, a Hierarchical-Clustering-Based Opportunistic Maintenance (HCBOM) policy, which uses a non-parametrical clustering, is introduced to incorporate the aftereffects of the PM. The case study and the policy comparisons verify the above-mentioned aftereffects. The proposed HCBOM is more cost-effective than the tradition Opportunistic Maintenance (OM) frame, the DOM, the group maintenance and the station-level maintenance. From the perspective of clustering, this work provides an innovative OM policy, which can guide practitioners to formulate cost-effective PM scheme without time-expensive calculations.