摘要：AbstractOptimization of failure-prone manufacturing systems with uncertainty in demand and inventory levels are considered. Conventional approach to production optimization of manufacturing systems requires precise knowledge of demand and inventory. In case of unknown demand and imprecise inventory the online estimation is needed in order to implement optimal policies. We propose in this work a novel methodology for monitoring and online assessment of demand and inventory levels based on the state estimators in the case of precisely known inventory and on Kalman filtering in the case of uncertainty in inventory information. The proposed approach allows to continuously monitor the uncertain states of the system and provides converging estimates of demand and inventory levels (when they are not precisely measured). The cases of constant, slow-varying and randomly-varying demand are considered. Obtained estimates are shown not to be affected by the discontinuous changes in production capacity, that are due to random failure-repair processes. The proposed methodology is described in detail for the case one-machine-one-product system and the possible extensions to the case of hybrid manufacturing-remanufacturing systems with uncertain demand and return are outlined.
