Double-layer planning model for supply chain service combination of high-end equipment manufacturing industry

In the field of supply chain management and optimization of the high-end equipment manufacturing industry, traditional planning models and optimization algorithms are not flexible and intelligent enough when dealing with modern complex supply chain systems, and the optimization methods are inefficient in solving complex problems, resulting in insufficient supply chain dynamics and collaborative optimization. This article proposed a double-layer programming model for artificial intelligence communication technology and optimized it through Cloud Genetics Algorithm to improve the overall efficiency and intelligence level of the supply chain service portfolio in the high-end equipment manufacturing industry. This article constructed a double-layer planning model, in which the upper level performs supply chain strategic resource allocation and high-level decision-making, involving long-term planning, partner selection, resource scheduling, etc. The lower level optimizes specific tactical issues, such as logistics route optimization, inventory management, supplier selection, etc. In the process of model building, artificial intelligence communication technology was integrated into supply chain management to collect and process supply chain data in real time to enhance the dynamic response capability of the supply chain. Based on Cloud Genetics Algorithm, the parallel processing capability of cloud computing was utilized to accelerate the solution of large-scale, multi-objective optimization problems. Through selection, crossover, and mutation operations, the supply chain service combination scheme was continuously optimized. Experimental results show that the total operating cost of the double-layer model in this article was reduced from US$50,000 to US$23,000 within 12 months, and the service response time was reduced from the initial 18 h to 6 h, which had a good supply chain service efficiency. The convergence speed of Cloud Genetics Algorithm approached 90 s in 35 generations, and the optimization precision was maintained above 95% 21 times, with faster convergence speed and optimization precision. The fitness value in the four cases was stable between 0.92 and 0.97, showing better algorithm stability. Experimental data proves that the model proposed in this article has flexibility and high efficiency in the supply chain optimization of the high-end equipment manufacturing industry.