Based on the analysis of multi-objective flexible job-shop scheduling problem (FJSP), a multi-objective low-carbon job-shop scheduling problem(MLFJSP) with variable processing speed constraint is proposed in this paper. The optimization objectives of MLFJSP include minimizing the makespan, total carbon emission and machine loading. Meanwhile, an improved artificial bee colony algorithm (IABC) is designed to solve the MLFJSP. The improvement of algorithm mainly includes: (1) an effective three-dimensions encoding/decoding mechanism and a mixed initialization strategy are designed to generate a better initial population; (2) special crossover operators and mutation operators were designed to increase the diversity of the population in the employed bee phase; (3)an efficient dynamic neighbor search (DNS) is applied to enhance local search capabilities in the onlooker bee phase; (4) the new food sources generation strategy was proposed to reduce the blindness in the scout bee phase. Finally, this paper carried out a series of comparative experimental studies, including the comparison before and after algorithm improvement, and the comparison between the improved algorithm with MOPSO, MODE and NSGA-II. The results demonstrate that the IABC can achieve a better performance for solving the MLFJSP.

在分析多目标柔性作业车间调度问题（FJSP）的基础上，提出了一种具有可变处理速度约束的多目标低碳作业车间调度问题（MLFJSP）。MLFJSP的优化目标包括最小化制造期，总碳排放量和机器负荷。同时，设计了一种改进的人工蜂群算法（IABC）来求解MLFJSP。算法的改进主要包括：（1）设计有效的三维编解码机制和混合初始化策略，以产生更好的初始种群。（2）设计了特殊的交叉算子和变异算子，以增加受雇蜂阶段种群的多样性；（3）采用有效的动态邻居搜索（DNS）来增强围观蜂阶段的本地搜索能力；（4）提出了新的食物来源生成策略，以减少侦察蜂阶段的失明。最后，本文进行了一系列对比实验研究，包括算法改进前后的比较，以及改进后的算法与MOPSO，MODE和NSGA-II的比较。结果表明，IABC可以更好地解决MLFJSP问题。并对改进后的算法与MOPSO，MODE和NSGA-II进行了比较。结果表明，IABC可以更好地解决MLFJSP问题。并对改进后的算法与MOPSO，MODE和NSGA-II进行了比较。结果表明，IABC可以更好地解决MLFJSP问题。