Optimization of Collaborative Scheduling and Profit Fluctuation Control in Manufacturing Supply Chains Using Artificial Intelligence Algorithms

Manufacturing supply chains for textile and related engineering products are increasingly affected by volatile orders, short delivery cycles, and unstable profit margins. In production scenarios involving electromagnetic materials, wearable antennas, conductive textiles, and shielding components, collaborative scheduling is also related to the timely supply of materials and components used in electromagnetic wave and antenna applications. This study investigates an artificial-intelligence-based method for collaborative scheduling and profit fluctuation control in manufacturing supply chains. The current problems of scheduling coordination and profit instability are first analyzed, followed by a comparison of genetic algorithms, particle swarm optimization, and deep learning methods for supply chain optimization. On this basis, a collaborative scheduling model and a profit fluctuation control model are constructed. Experimental results show that the proposed method reduces total operating costs by 21.2%, decreases order delivery delay time by 75%, and lowers the standard deviation of profit by 57.1% compared with traditional scheduling methods. The results indicate that artificial intelligence algorithms can improve scheduling efficiency and financial stability in complex manufacturing systems. The study provides a practical decision-support approach for supply chain management in engineering-oriented textile production and related electromagnetic manufacturing fields.