考虑安全约束的连退生产过程多目标操作优化

针对连退生产过程中经常出现的薄料带钢跑偏问题,建立考虑安全约束的连退生产过程多目标操作优化模型,并针对问题特点提出一种基于分类和多种群竞争协调的多目标进化算法(MOEA-CMCC).在算法中引入具有不同进化策略的多个种群以增强搜索的多样性,并在多种群之间引入竞争机制和信息共享的协调机制以提高算法的鲁棒性;通过对外部档案集中的解进行分类并在类内进行局部搜索,以保证外部档案集的分散性和算法的收敛速度.基于Benchmark问题的实验结果表明,所提出的算法具有较好的收敛性和分散性;对连退操作优化问题的实验结果表明,所提出的算法能够有效求解该问题.

Multi-objective operation optimization of continuous production process with safety constraints

To deal with the running deviation of thin strip in the continuous annealing production process, a multi-objective operation optimization model with the consideration of safety constraints is established, and a multi-objective evolutionary algorithm is proposed, in which the classification and the multi-population with competition and coordination are incorporated. The mechanism of multi-population with different evolution strategies is established to enhance the search diversity, and the competition and cooperation based on information sharing is adopted to improve the robustness of the algorithm. The solutions in the external archive(EXA) are classified into different groups, and then local search is performed within each group, which can help to ensure the diversity of the non-dominated solutions in EXA and improve the convergence speed of the algorithm. Computational results based on benchmark problems show that the proposed algorithm has good convergence and diversity, and further results based on the practical operation optimization of continuous annealing illustrate the effectiveness of the proposed algorithm.