Motivated by the challenges encountered in sawmill production planning, we study a multi-product, multi-period planning problem with uncertainty quality of raw materials and consequently processes yields, as well products demands. As demand yield own different uncertain natures, they are modelled separately then integrated. Demand is considered dynamic stochastic data process during horizon, which scenario tree. Each stage tree corresponds to cluster time periods, for has stationary...

This paper integrates preventive maintenance with tactical production planning in multi-state systems. The proposed model coordinates the decisions, so that total expected cost is minimized. We are given a set of products must be produced lots on system during specified finite horizon. Planned maintenance, and unplanned corrective can performed each component system. policy suggests cyclical replacements components, minimal repair failed components. objective to determine an integrated...

This paper considers a multi-period multi-product capacitated lot-sizing problem. It develops an integrated predictive maintenance and production planning framework using deep learning mathematical programming. The objective is to minimise the sum of maintenance, setup, holding, backorder, costs, while satisfying demand for all products over horizon under consideration. Based on rolling approach, model dynamically integrates data-driven planning. used policy includes replacements minimal...

This paper develops a data-driven approach to dynamically integrate tactical production and predictive maintenance planning for multi-state system composed of several series-parallel machines. The objective is determine an integrated lot-sizing preventive strategy that will minimize the sum costs, while satisfying demand all products over entire horizon. A rolling horizon adopted continuously update plans based on new data obtained through sensors. Unlike existing models, we develop hybrid...

In this paper, integrated planning of production, imperfect maintenance and process inspections in a multi-machine system is investigated. This consists parallel machines which deteriorate with time they may shift from primarily in-control state to degraded higher defective rate or failed state. Maintenance scheduling corresponds discrete age-based large number alternatives. Process are considered detect the current system. Detecting deteriorated condition initiates quality check related...