Optimization Design of Multi-Step Electronics Production Decisions Based on Monte Carlo Simulation and 0-1 Planning Model

This paper begins by employing a one-tailed test method, utilizing simple random sampling to determine the minimum sample size required. Normal distribution is chosen as an approximation for the binomial distribution in the case of large sample sizes. Furthermore, the study optimizes the 2-test using Finite Population Correction (FPC) to measure the minimum sample size under limited sample conditions. Additionally, a sampling detection model based on Monte Carlo simulation is established under the premise of limited sample capacity. Sensitivity analysis is conducted to assess the impact of actual defect rates on the minimum sample size and decision accuracy. By adjusting parameters such as the lower limit of sample size and simulation times, the model optimizes the sampling detection scheme, ensuring accuracy and cost-effectiveness while minimizing the required testing frequency. Finally, a 0-1 planning model is developed, treating each decision as a binary variable of “whether to execute.” By constructing a cost function and optimizing these decision combinations, the study aims to minimize production costs, addressing a multi-stage cost minimization problem.