摘要
有效的行动过程是组织成功完成使命的关键.提出了使用动态影响网对行动过程问题进行建模的方法,通过引入因果强度参数,替代贝叶斯网络中的条件概率表,缓解模型在知识获取方面的瓶颈问题,给出了利用因果强度参数进行概率传播的具体计算方法;并用粒子群优化算法对模型进行优化求解.最后结合一个联合作战的想定,验证了方法可行性和有效性.
An effective course of actions(COA) is the key to accomplish the mission successfully for the organization.A method based on dynamic influence nets(DINs) which to model the COA problem is proposed.In this method,the causal strength parameters are introduced instead of conditional probability tables,so that the bottle-neck problem of knowledge acquisition is mitigated,and the probability propagation algorithm using causal strength parameters is presented.Then particle swarm optimization (PSO) algorithm is adopted to select the best COA.At last,the feasibility and efficiency of this method is illuminated by a case of joint campaign.
出处
《系统工程理论与实践》
EI
CSSCI
CSCD
北大核心
2011年第10期1985-1993,共9页
Systems Engineering-Theory & Practice
基金
国家高技术研究发展计划(863计划)(2010AAJ146)
国家自然科学基金(71071157)
关键词
行动过程
动态影响网
因果强度
粒子群优化
蒙特卡洛
course of actions
dynamic influence nets
causal strength
particle swarm optimization
Monte Carlo