The core of intelligent design of clothing materials is to form a collaborative optimization between wear performance, process adaptation and sustainable goals. Aiming at the problems of traditional material development relying on manual screening, long sample cycle, and lagging green index feedback, this paper proposes a reinforcement learning driven intelligent design and sustainability optimization strategy for clothing materials. The strategy integrates material performance state modeling, material combination decision-making, process parameter adjustment and sustainable reward feedback, and integrates fiber proportion, fabric structure, dyeing and finishing parameters, carbon emission, water consumption and recyclable proportion into a unified calculation framework. The experimental results show that the comprehensive performance score of the complete reinforcement learning scheme is improved from 77.1 to 84.6, the design adaptation accuracy is improved to 90.8%, the unit carbon emission is reduced from 4.82 kgCO₂e/kg to 3.91 kgCO₂e/kg, and the sustainability score is improved to 81.5. The results show that the proposed method can improve the efficiency of clothing material design and the level of green optimization, and provide technical support for the intelligent and low-carbon transformation of the clothing industry.
