Intelligent Quality Control in Spare Parts Production: A Dual-Stage Hypothesis Testing Approach

With the continuous development of intelligent manufacturing technologies, quality control issues in production processes have become increasingly complex, especially in large-scale production, where efficiently detecting and controlling defect rates has become a key challenge in ensuring product quality. This study proposes an engineering-oriented quality control optimization framework based on a dual-stage hypothesis test to evaluate whether the defect rate of spare parts meets the technical standards specified by suppliers. The framework first conducts a preliminary screening test on a small sample. If the results are inconclusive, a secondary validation test is performed on a larger sample, with acceptance or rejection thresholds set at specific confidence levels to strike a balance between accuracy and efficiency. Applied across key stages of production—including spare parts screening, product assembly, and returns handling—the framework demonstrates that selective testing of low-defectrate parts and optimized dismantling processes significantly enhance product quality stability. This framework not only provides strong support for quality management and improvement in engineering practice but also illustrates how the integration of statistical analysis and resource management methods can facilitate efficient quality control and risk prevention within the field of intelligent manufacturing, advancing the practical application of artificial intelligence technologies in production quality management.