To address the common issues of low production line efficiency, poor product quality, and inadequate equipment maintenance in current industrial production, this paper investigates the application of smart manufacturing technology in optimizing industrial production processes and controlling product quality. First, industrial data is preprocessed using parallelized K-means clustering combined with the contour coefficient method to determine the optimal production process clusters. Second, the parallelized Apriori algorithm is employed to mine industrial product association chains. Based on this, a flexible neural tree model is introduced for production process optimization modeling. A industrial production execution management system with three core functions—smart scheduling, quality prediction, and equipment health management—has been designed and implemented. The AI industrial production execution management system proposed in this paper significantly improves industrial production efficiency, resource utilization, and equipment reliability. After its implementation, the overall qualified rate of A Company’s main power supply circuit board production increased by 20%, providing a feasible solution for the company to achieve smart manufacturing upgrades.