Research on Production Process Decision Optimization Based on Nonlinear Programming and Particle Swarm Optimization Genetic Algorithm

This paper investigates the optimization of production process decisions based on nonlinear programming and particle swarm optimization genetic algorithm. Initially, a quality level sampling inspection model and a sequential sampling inspection model are established to determine the appropriate error range, reduce the number of samples, and lower inspection costs. Subsequently, a nonlinear programming model is used to maximize expected profits, considering factors such as the inspection ratio of parts, the inspection ratio of finished products, and the disassembly ratio of non-conforming products. A genetic algorithm based on particle swarm optimization is employed to solve this optimization problem, and case analyses under six different scenarios demonstrate the decision ratios and maximum expected profits. The results indicate that the proposed models and algorithms can effectively support decision-making in the production process, ensuring product quality while reducing costs.