Research on Sampling Inspection in Electronic Product Manufacturing Process Based on Bayesian Optimization

With the intensification of competition in the electronic products market, enterprises must optimize the sampling inspection strategy to control quality and the defective product rate while balancing quality control and inspection resource consumption. This study constructs the expected total resource consumption model, considers the impact of spare parts' defective product rate and the process on finished products, calculates the defective product rate, models with the Markov decision process, optimizes with the genetic algorithm, and selects the optimal inspection strategy with the Monte Carlo simulation. Considering the uncertainty of the defective product rate's sampling inspection, the Bayesian update method is used to handle the distribution, the resource consumption model is constructed, and the Bayesian algorithm is introduced for optimization. Finally, the reliability constraint interval is used to quantify the range and make production decisions. The estimated defective product rate is 8.00%, and the confidence interval is [2.68%, 13.32%], helping understand the uncertainty and make the optimal decision.