Currently, simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing systems. Simultaneous allocation problems have been solved previously to satisfy economic requirements; however, owing to the progress of green manufacturing, energy conservation and environmental protection have become increasingly crucial. Therefore, an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems, subject to the total buffer capacity, total service rate, and predefined energy efficiency. The energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression tree. The former algorithm searches for Pareto-optimal solutions of sufficient quality. The latter algorithm builds prediction models to rapidly calculate the throughput, energy consumption, and energy efficiency. Numerical examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported approaches. Furthermore, the prediction models can rapidly evaluate manufacturing systems with sufficient accuracy. This study benefits the multi-objective optimization of green manufacturing systems.

目前，同时缓冲和服务速率分配是制造系统优化中的一个令人感兴趣的话题。先前已经解决了同时分配问题以满足经济要求；然而，随着绿色制造的进步，节能环保变得越来越重要。因此，开发了一种节能方法，以最大程度地提高制造系统的吞吐量并最小化制造系统的能耗，具体取决于总缓冲区容量、总服务率和预定义的能源效率。该节能方法将模拟退火-非支配排序遗传算法-II与蜜獾算法-基于直方图的梯度提升回归树相结合。前一种算法搜索足够质量的帕累托最优解。后者算法建立预测模型来快速计算吞吐量、能耗和能源效率。数值例子表明，与之前报道的方法相比，所提出的混合方法可以实现更好的解决方案质量。此外，预测模型可以以足够的精度快速评估制造系统。本研究有利于绿色制造系统的多目标优化。