LAUSR

Abstract Huge maintenance costs in non-residential buildings weighted it down the overall costs allocated to HVAC (Heating, ventilation and air conditioning) system maintenance. Maintenance Management objective is to reduce or even avoid the corrective maintenance by proper planning and implementation of maintenance tasks at the right time. The aim of this paper is to early plan maintenance interventions for a multi-components system based on stoppages characteristics, system RUL (Remaining Useful Life) and components criticalities. This maintenance plan is made through a dynamic maintenance decision approach (DMDA) to help the maintenance expert in taking decision. Since combining maintenance activities is cheaper than performing maintenance on components separately, maintenance actions groupings are performed in the proposed approach by the mean of odds algorithm. This will allow optimizing system availability, reducing maintenance costs and delaying as late as possible maintenance interventions. Components criticalities are used for prioritizing components in the grouping process. Moreover, DMDA take into account predictive information such as system/components RUL, given by an existing prognostic process. At the end, a numerical example of a HVAC system with five components (Heat exchanger, filter, dampers, valve and fan) demonstrates the use and the advantages of the proposed DMDA.