基于鲁棒能力的体系多目标组合优化  

Multi-objective portfolio optimization of system-of-systems based on robust capabilities

作　　者：李瑞阳 王智学 禹明刚 何红悦 LI Ruiyang;WANG Zhixue;YU Minggang;HE Hongyue(College of Command and Control Engineering, Army Engineering University, Nanjing 210000, China)

机构地区：[1]陆军工程大学指挥控制工程学院,江苏南京210000

出　　处：《系统工程与电子技术》2019年第5期1034-1042,共9页Systems Engineering and Electronics

基　　金：国家自然科学基金(61273210);国家自然科学青年基金(61802428)资助课题

摘　　要：针对体系组合优化问题中,不同场景下系统贡献的不确定问题,提出了基于鲁棒能力的体系优化决策方法。首先对体系的鲁棒能力和模糊能力风险进行定量描述;然后以鲁棒能力最大,建设风险和成本最低为目标,考虑军事能力需求等约束,建立多目标体系组合优化模型,采用改进的基于参考点的非支配排序遗传算法求解模型,生成一组符合决策需求的非劣质解;最后通过仿真实验验证了模型和算法的有效性,可以为体系总体建设规划提供决策支持。To solve the problem of uncertain system contribution under different scenarios for the problem of portfolio optimization, an optimization and decision-making method based on robust capabilities is proposed. First, the quantitative description of the robust capabilities and fuzzy capabilities risk is given. Then, a multi-objective portfolio optimization model is established, balancing maximum capabilities, minimum construction risk and cost, within the constraints of military capability requirements. The improved non-dominated sorting genetic algorithm 3 (NSGA3) is adopted to solve the model by generating a set of non-inferior solutions that meet the decision-making requirements. Finally, simulation experiments verify the effectiveness of the model and algorithm, and can provide support for the overall construction plan of the system.

关 键 词：体系 多目标优化 鲁棒能力 基于参考点的非支配排序遗传算法 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]