Research on Quality Inspection and Optimal Decision-Making in Production Processes Based on Dynamic Programming Algorithm

This study investigates the quality inspection and optimal decision-making in production processes using a dynamic programming algorithm. The primary objective is to develop a sampling inspection plan for components provided by suppliers, aiming to detect whether the defect rate of components is within the specified nominal value under different confidence levels (95% and 90%) while minimizing inspection costs. We propose a sampling model based on the Binomial Distribution and the approximate Normal Distribution to conduct hypothesis testing for defect rate detection. Additionally, a dynamic programming model is constructed to optimize decision-making in the production process, considering factors such as inspection costs, potential risk costs, and losses from defective products entering the market. The results show that the proposed models effectively balance inspection costs and quality control, leading to optimal decisions that maximize profit and minimize losses. Through Python-based simulations, we visualize the decision outcomes and validate the feasibility of the proposed approach.