面向分布式作战的智能模型持续演化方法  

Continuous Evolution Method of Intelligent Model Oriented to Distributed Operations

作　　者：朱晓敏[1] 张雄涛 王吉 陈超[1] ZHU Xiao-Min;ZHANG Xiong-Tao;WANG Ji;CHEN Chao(College of Systems Engineering,National University of Defense Technology,Changsha Hunan 410073,China)

机构地区：[1]国防科技大学系统工程学院,湖南长沙410073

出　　处：《指挥与控制学报》2021年第4期374-382,共9页Journal of Command and Control

基　　金：国家自然科学基金(61872378);湖南省杰出青年基金(2018JJ1032);国防科技大学科学研究项目(ZK19-03)资助。

摘　　要：智能化和分布式是未来战争的主要方向,智能模型是实现分布式作战节点智能化的重要手段.战场环境下,敌方通信干扰、电磁压制等反制措施给作战节点智能模型演化带来了巨大挑战.为此,提出了一种面向分布式作战的智能模型持续演化架构,该架构可适应动态通信状况,自主选择有中心的分层联邦学习方法和完全分布式的gossip学习方法,并随战场环境变化进行动态切换.经验证,该架构可以适应不同通信状况,达到较好的智能模型演化效果.Intelligence and distribution are the main directions of future warfare,while intelligent model is an important means to realize them.In the battlefield,enemy operations have brought huge challenges to the evolution of intelligent models.Therefore,an architecture for continuous evolution of intelligent models for distributed operations is proposed.This architecture can adaptively select the centralized hierarchical federated learning and the fully distributed gossip learning according to the communication status.And dynamically switch as the battlefield environment changes.It has been verified that this architecture can adapt to different communication conditions and achieve a better intelligent model evolution effectiveness.

关 键 词：分布式作战 智能模型 持续演化 信息体系 联邦学习 gossip学习 

分 类 号：E91[军事]