Production Process Optimization Decision Based on Monte Carlo Simulation and Dynamic Programming

This paper introduces a sampling inspection model that updates defect rates with Monte Carlo simulation data, using a five-stage dynamic programming approach. It incorporates specific factors like assembly costs and develops relevant models. Applying Monte Carlo and dynamic programming in reverse order to six scenarios, it proposes a new multi-process decision optimization scheme. By analyzing the impact of decisions at each stage, considering defect rate, inspection cost, and dismantling fees, it determines the maximum profit for each decision and selects the optimal one.