The mixed-model assembly line balancing problem (MMALBP) in multi-demand scenarios is investigated, which addresses demand fluctuations for each product in each scenario. The objective is to minimize the sum of costs associated with tasks allocation, workstation activation, and penalty costs for unbalanced workloads. A mixed integer programming model is developed to consider the constraint of workstation space capacity. A phased heuristic algorithm is designed to solve the problem. The computational results show that considering demand fluctuations in multiple demand scenarios leads to more balanced workstation loads and improved assembly line production efficiency. Finally, sensitivity analysis of important parameters is conducted to summarize the impact of parameter changes on the results and provide practical management insights.

The inventory routing problem (IRP) arises in the joint practices of vendor-managed inventory (VMI) and vehicle routing problem (VRP), aiming to simultaneously optimize the distribution, inventory and vehicle routes. This paper studies the multi-vehicle multi-compartment inventory routing problem with stochastic demands (MCIRPSD) in the context of fuel delivery. The problem with maximum-to-level (ML) replenishment policy is modeled as a two-stage stochastic programming model with the purpose of minimizing the total cost, in which the inventory management and routing decisions are made in the first stage while the corresponding resource actions are implemented in the second stage. An acceleration strategy is incorporated into the exact single-cut Benders decomposition algorithm and its multi-cut version respectively to solve the MCIRPSD on the small instances. Two-phase heuristic approaches based on the single-cut decomposition algorithm and its multi-cut version are developed to deal with the MCIRPSD on the medium and large-scale instances. Comparing the performance of the proposed algorithms with the Gurobi solver within limited time, the average objective value obtained by the proposed algorithm has decreased more than 7.30% for the medium and large instances, which demonstrates the effectiveness of our algorithms. The impacts of the instance features on the results are further analyzed, and some managerial insights are concluded for the manager.