| ID | 原文 | 译文 |
| 7614 | 针对传统层次聚类法采用贪婪策略的聚类过程可能无法达到聚类效果最优的情况,提出了一种基于rollout策略下的层次聚类法对所得聚类方案进行优化改进。 | In view of the traditional hierarchical clustering method USES the greedy strategy clustering process may not be able to achieve the optimal clustering effect, this paper proposes a hierarchical clustering method based on rollout strategy is optimized to improve the clustering scheme. |
| 7615 | 分析了聚类过程中决策实体、平台与任务之间的关系以及约束条件,以作战任务的执行时间作为工作负载测度,建立以决策实体工作负载的均方根(root mean square,RMS)为目标函数的问题数学模型。 | Analyzes the decision-making entities in the process of clustering, the relationship between the platform and task as well as the constraint condition, to combat mission execution time as a work load measure, establish a decision-making entities workload of RMS (root mean square, RMS) mathematical model as the objective function of the problem. |
| 7616 | 以任务与平台的分配关系作为输入信息,在基于最小RMS值的平台合并准则下采用rollout策略对层次聚类法的每层聚类进行优化,得到平台与决策实体的优化配置关系。 | With the relations of distribution among the tasks and platform as the input information, based on the minimum RMS value platform adopts the rollout strategy under the merger guidelines for hierarchical clustering method of each layer of clustering optimization, get the platform and the optimal allocation of decision-making entity relationship. |
| 7617 | 最后通过联合作战仿真算例和一般算例进行仿真分析,验证了该方法的可行性和优越性。 | Finally through joint operations simulation case and general example simulation analysis, verified the feasibility and superiority of this method. |
| 7618 | 随着雷达技术的进步,雷达发展趋于多功能与智能化,抗干扰能力增强,应用于常规雷达的对抗方法作战效能下降,针对多功能雷达,尤其是工作模式未知的智能对抗成为雷达对抗领域的热点与难点。 | With the development of radar technology, radar development tend to be multi-functional and intelligent, and enhance anti-jamming capability and the application of the conventional radar against a method of operational effectiveness drops, for multi-function radar, especially the working mode of the unknown intelligence against become a hotspot in the field of radar against difficulties. |
| 7619 | 基于此,该文阐述了智能雷达对抗(intelligent radar countermeasure,IRC)方法,对比了智能雷达对抗与传统雷达对抗(traditional radar countermeasure,TRC)的区别。 | Based on this, this paper expounds the intelligent radar countermeasures (intelligent radar countermeasure, IRC) method, compared the intelligent radar against with the traditional radar against (traditional radar countermeasure, TRC) difference. |
| 7620 | 介绍了强化学习(reinforcement learning,RL)基本原理,针对雷达工作模式及数目未知情况,提出了基于Q-学习的智能雷达对抗方法,给出了算法步骤,分析了Q矩阵收敛时间、收敛值与循环次数的关系。 | Introduces the reinforcement learning, reinforcement learning, RL) basic principle, in view of the radar working mode and the number of unknown situation, put forward the intelligent radar countermeasures based on the Q - learning method and algorithm steps are given, analyzes the convergence time and convergence value Q matrix and the relationship between cycles. |
| 7621 | 仿真实验表明:给定仿真实验条件下,智能化雷达对抗Q矩阵收敛时间仅为秒量级,能根据干扰效果自主学习并智能决策,提高了雷达对抗系统的实时性与自适应性,且能同时对抗多工作模式的雷达。 | Simulation experiments show that the given simulation conditions, the intelligent radar against Q matrix convergence time was only seconds, can according to the interference effect of autonomous learning and intelligent decision-making, improve the real-time and adaptive radar countermeasures system, and able to work at the same time fight more model of radar. |
| 7622 | 作战资源虚拟化是网络化作战组织云协同的关键问题之一,是云服务组合、搜索和执行的前提。 | Combat resource virtualization is one of the key problems of collaborative networked organization cloud, is the precondition of cloud services portfolio, search and execution. |
| 7623 | 提出了一种基于接口和事件驱动架构的资源虚拟化方法,该方法包含两个步骤: | Put forward a kind of resource virtualization method based on interfaces and event driven architecture, the method includes two steps: |