Research on component inspection and profit optimization based on two-stage decision model

In industrial production, the optimization of product quality control and inspection workload at various stages is a critical issue for enhancing corporate competitiveness. Specifically, this study proposes a quality control model for industrial production, integrating hypothesis testing under binomial distribution with normal approximation, to assess if the defect rate of components exceeds supplier-declared standards. By incorporating a random permissible error E and dynamically adjusting the significance level and E, the model optimizes inspection workload while ensuring accuracy. A two-stage decision-making planning model is developed to address inspection and disassembly at each production stage, leading to an optimal strategy. The experimental results indicate that at a 95% confidence level, the minimum sample size required is 139, which reduces to 98 at a 90% confidence level, significantly lowering the sampling needs. In complex chains, per-product outcome shifts from -22.82 to 75.80 yuan, marking a transition from negative to positive results. This highlights the method's effectiveness and practical value.