Research on Production Optimization Based on Bayesian Updating and Genetic Algorithm

The purpose of this paper is to explore how to optimize the quality inspection and cost management of enterprises in the production process through the combination of Bayesian updating and genetic algorithm. First, based on sequential sampling theory, the study combines normal approximation and Bayesian updating to design a dynamic inspection scheme to minimize the number of sampling times and effectively determine whether the defective rate of spare parts exceeds the nominal value. Second, a systematic cost-benefit model is constructed for the quality control problem in the multi-stage production process. By simulating the combinations of strategies under different production situations, genetic algorithms are used to select the optimal strategy and realize the effective control of total production cost. Finally, this paper also optimizes the inspection and disassembly strategies in the multi-stage production process to ensure that the quality of products can be improved while controlling the cost.