model comparison (Idle/%).

The multi-objective supply chain needs a full look at enterprise costs, coordinated delivery of different products, and more fluidity and efficiency within the network of the supply chain. However, existing methodologies rarely delve into the intricacies of the industrial supply chain. Therefore, in the emerging industrial supply chain network, a model for the multi-objective problem was made using a meta-heuristic approach, specifically the improved genetic algorithm, which is a type of soft computing. To create the initial population, a hybrid approach that combines topology theory and the random search method was adopted, which resulted in a modification of the conventional single roulette wheel selection procedure. Additionally, the crossover and mutation operations were enhanced, with determining their respective probabilities determined through a fusion of the elite selection approach and the roulette method. The simulation results indicate that the improved genetic algorithm reduced the supply load from 0.678 to 0.535, labor costs from 1832 yuan to 1790 yuan, and operational time by approximately 39.5%, from 48 seconds to 29.5 seconds. Additionally, the variation in node utilization rates significantly decreased from 30.1% to 12.25%, markedly enhancing resource scheduling efficiency and overall balance within the supply chain.多目标供应链需要全面考量企业成本、不同产品的协同配送，以及供应链网络内更高的流动性与运行效率。然而现有研究方法鲜有深入剖析工业供应链的复杂运行机制。因此，针对新兴工业供应链网络，本文采用元启发式（meta-heuristic）方法构建多目标优化模型，具体选用改进型遗传算法（genetic algorithm）——一类软计算（soft computing）技术。在初始种群构建环节，本文融合拓扑理论与随机搜索法形成混合策略，对传统单一轮盘赌选择（roulette wheel selection）流程进行了改进。此外，本文还优化了交叉与变异操作，通过融合精英选择（elite selection）与轮盘赌法确定二者的概率参数。仿真结果表明，所提改进遗传算法将供应链负载从0.678降至0.535，人力成本从1832元降至1790元，运行时间缩短约39.5%（从48秒降至29.5秒）。同时，节点利用率的离散程度从30.1%大幅降至12.25%，显著提升了供应链内的资源调度效率与整体均衡性。