WO2021057329A1 - 一种作战体系架构建模与最优搜索方法 - Google Patents

一种作战体系架构建模与最优搜索方法 Download PDF

Info

Publication number
WO2021057329A1
WO2021057329A1 PCT/CN2020/109335 CN2020109335W WO2021057329A1 WO 2021057329 A1 WO2021057329 A1 WO 2021057329A1 CN 2020109335 W CN2020109335 W CN 2020109335W WO 2021057329 A1 WO2021057329 A1 WO 2021057329A1
Authority
WO
WIPO (PCT)
Prior art keywords
network
task
command
nodes
ososa
Prior art date
Application number
PCT/CN2020/109335
Other languages
English (en)
French (fr)
Inventor
王维平
周鑫
王涛
朱一凡
李小波
井田
李童心
段婷
王彦锋
黄美根
Original Assignee
中国人民解放军国防科技大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国人民解放军国防科技大学 filed Critical 中国人民解放军国防科技大学
Publication of WO2021057329A1 publication Critical patent/WO2021057329A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation

Definitions

  • the invention relates to the technical field of combat systems, in particular to a method for modeling and optimal searching of combat system architecture.
  • the purpose of the present invention is to solve the shortcomings in the prior art, and propose a method for modeling and optimal searching of combat system architecture.
  • a combat system architecture modeling and optimal search method including a hyper-network-based OSoSA formal definition and OSoSA search.
  • the OSoSA formal definition is composed of three heterogeneous networks: mission network, system network, and command network.
  • the mission network includes mission nodes
  • the system network includes system nodes
  • the command network includes command nodes
  • the operational capabilities formally defined by OSoSA are obtained by OSoS
  • the mission network, system network, and command network jointly constitute a combat system.
  • the task node of the task network is a combat activity that can be executed by the equipment system, denoted as T.
  • the system node of the task network refers to equipment that has a specific function and can complete a specific task, denoted as S.
  • the accusation node of the accusation network is used as a logical node for processing information, management organization, decision planning, control feedback, etc., denoted as C.
  • the method of combat system architecture modeling and optimal search proposed by the present invention has the beneficial effect that: in the process of application of this solution, the average return value of this solution can be in a higher state than that of the traditional method. In turn, this scheme becomes conducive to popularization and application.
  • Figure 1 is an example diagram of the task network of the present invention
  • Figure 2 is an example diagram of the system network of the present invention.
  • Figure 3 is a bipartite diagram of the corresponding relationship between the task network and the system network of the present invention.
  • Figure 4 is an example diagram of the command network of the present invention.
  • Fig. 5 is a bipartite diagram of the corresponding relationship between the system network and the command network of the present invention.
  • a combat system architecture modeling and optimal search method including the formal definition of OSoSA and OSoSA search based on the hypernetwork.
  • the formal definition of OSoSA consists of three heterogeneous networks: mission network, system network, and command network
  • the mission network contains mission nodes
  • the system network contains system nodes
  • the command network contains command nodes.
  • the operational capabilities formally defined by OSoSA are obtained by OSoS.
  • the mission network, system network, and command network jointly constitute the combat system.
  • the task node of the task network is the combat activity that can be executed by the equipment system, denoted as T.
  • the mission should be decomposed into a series of executable tasks, namely the task link; the task link can be abstracted as a directed graph, a
  • the system mission can be decomposed into different task links.
  • Each task link has a start task node and an end task node.
  • Different task links may have different efficiencies.
  • There are two main types of logical relationships in the task links, namely sequence Execution and parallel execution, multiple tasks correspond to multiple task links constituting the task network, denoted as G T (V T , E T ), as shown in Figure 1.
  • the system node of the mission network refers to the equipment that has specific functions and can complete specific tasks, denoted as S.
  • the equipment system with specific functions is used to complete specific tasks, so system nodes (such as drones, tanks, etc.)
  • system nodes such as drones, tanks, etc.
  • the relationship between the task node and the ship) is affected by the task node, as shown in Figure 2:
  • the accusation node of the accusation network is used to process information, management organization, decision planning, control feedback, etc.
  • OSoS Since OSoSA's formal definition of combat capabilities is obtained by OSoS, OSoS may be affected by factors other than OSoSA, which may lead to emergence. Therefore, OSoS capabilities based on OSoSA may not be unique, and therefore each OSoSA solution has an uncertain potential return value.
  • the commander needs to choose an architectural solution (scheme for short) in the architectural solution space to develop the combat system.
  • OSoS capability is measured by the return value.
  • the return value of each architecture is uncertain in advance, but it can be obtained by developing OSoS or consulting other agents.
  • the agent continuously explores the schemes in the undeveloped scheme space, and finally selects a scheme in all the developed scheme spaces as the final option.
  • the goal of the agent is to choose an architecture with the highest expected return value and the least cumulative search cost.
  • the unknown state indicates that the program has not been developed, and its reward value is unknown; the known state indicates that the program has been developed, and its reward value is known.
  • the search status indicates that the return value of the program is being queried. Before exploring a program, the program has potential rewards. After OSoS is developed, the return value of the solution is known. Agent's actions include: self-development, development by other agents, and consulting related agents. Specifically, based on having a cost of After the solution k is developed, the unknown state is converted to the known state. In addition, the agent can request other agents to The cost of developing OSoS. In addition, the agent can consult related agents, such as institutions or departments that may have completed similar tasks. The cost of the consultation process is recorded as
  • Embodiment 1 The present invention is introduced by taking scheme k as an example.
  • OSoSASP OSoSA search problem
  • Constraint (a) ensures that any solution is either already developed or undeveloped.
  • Constraint (b) means that if a solution is finally selected, the solution must have been developed.
  • Constraint (c) means that only one solution is selected in the end.
  • Constraint (d) represents the value space of the four decision variables.
  • Constraint (e) represents the number of times that the agent requests the relevant agent.
  • Constraint (f) refers to the discount rate, which represents the impact of development time on the return value.
  • Constraint (g) represents the cost of each action.
  • Each plan k defines execution actions with , Where the indicators are respectively denoted as with
  • the state And indicator collection Design a simple but optimal search rule, divided into judgment rule and selection rule.
  • the judgment rule means that if the agent wants to further explore the structure with unknown effect, then it must choose an unknown structure with the largest index. At the same time, choose the action according to the largest index, that is, research and development by yourself, company development, or ask for help from relevant agencies.
  • the stop rule means that when the maximum sample return value collected is greater than the R&D indicators, development indicators, and consulting indicators of all location architectures, the search is stopped and the architecture with the largest return value is selected as the solution.
  • each indicator is independent and is not affected by the probability distribution of the return value of other programs.
  • GSDP is composed of index calculation program, sequence search program and structure development program.
  • the Agent first calculates the decision-making indicators of all schemes according to the formula. Secondly, the indicators are sorted according to the sorting method, such as the heap sorting method, and the sorting result is stored in the vector ⁇ . Third, execute the SequenceSearching program to get the best solution.
  • the optimal architecture solution can be calculated after K iterations at most.
  • the current maximum sampling value y is compared with the maximum index ⁇ (0) in each iteration. If the maximum sampling value is not less than the maximum index, the search is stopped, and the architecture m with the current maximum sampling return value is used as the selected architecture. Otherwise, according to the structure index i and action a corresponding to ⁇ (0), execute the Executing program to continue the search. If the sample return value of architecture i is obtained, then the variable D is updated, ⁇ ,y,m, where Means to remove the collection Architecture in i.
  • Example 1 is applied to 100 scenarios in the solution space, and its average return value exceeds at least 17.6% of the average return value of the optimal algorithm; in the scenario space where the number of solutions is 10,000, the average return value exceeds at least the average return value of the optimal algorithm 15.2% of the return value; in the scenario of a solution space where the number of solutions is 1,000,000, the average return value exceeds at least 21.9% of the average return value of the optimal algorithm.
  • the average return in the present invention The value can be in a higher state, which in turn makes the present invention beneficial for popularization and application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种作战体系架构建模与最优搜索方法，包括基于超网络的OSoSA形式化定义和OSoSA搜索，所述OSoSA由任务网络、系统网络和指控网络三种异构网络组成，所述任务网络包含任务节点，所述系统网络包含系统节点，所述指控网络包含指控节点，所述OSoSA形式化定义的作战能力由OSoS得到，所述任务网络、系统网络和指控网络共同构成作战体系。所述方法在运用的过程中，使得平均回报值相较于传统的方法能够处于较高的状态，进而有利于进行推广运用。

Description

一种作战体系架构建模与最优搜索方法 技术领域
本发明涉及作战系统技术领域，尤其涉及一种作战体系架构建模与最优搜索方法。
背景技术
不少学者将作战体系架构建模为超网络模型，有研究人员提出了一个以网络为中心的军事通信超网络结构。该网络由五个异构节点组成：传感器节点、信息节点、决策节点、通信节点和效应节点。有研究人员提出了一种指挥控制系统的超网络模型，包括观测节点、指控节点、效应节点，以及三种类型节点之间的关系。此外，还有研究人员建立了基于网络中心模式的武器装备系统超网络模型，并提出了一种基于商空间理论降低武器系统生成方案复杂度的粒度分析方法。也有研究人员提出了一种基于属性协同优先级和超图理论的多层指挥控制超网络模型。这些研究从装备系统、功能和命令与控制结构的角度分别进行了研究，没有从体系能力生成要素出发考虑问题，因而，这些研究方法、模型在实际的实验过曾在的平均回报值较低。为此，我们提出了一种作战体系架构建模与最优搜索方法。
发明内容
本发明的目的是为了解决现有技术中存在的缺点，而提出的一种作战体系架构建模与最优搜索方法。
为了实现上述目的，本发明采用了如下技术方案：
一种作战体系架构建模与最优搜索方法，包括基于超网络的 OSoSA形式化定义和OSoSA搜索，所述OSoSA形式化定义由任务网络、系统网络和指控网络三种异构网络组成，所述任务网络包含任务节点，所述系统网络包含系统节点，所述指控网络包含指控节点，所述OSoSA形式化定义的作战能力由OSoS得到，所述任务网络、系统网络和指控网络共同构成作战体系。
优选的，所述任务网络的任务节点是可由装备系统执行的作战活动，记为T。
优选的，所述任务网络的系统节点是指具有特定功能并能够完成特定任务的装备，记为S。
优选的，所述指控网络的指控节点用于处理信息、管理组织、决策规划、控制反馈等的逻辑节点，表示为C。
本发明提出的一种作战体系架构建模与最优搜索方法，有益效果在于：本方案在运用的过程中，使得通过本方案的平均回报值相较于传统的方法能够处于较高的状态，进而使得本方案变得有利于进行推广运用。
附图说明
图1为本发明的任务网络的示例图；
图2为本发明的系统网络的示例图；
图3为本发明的任务网络与系统网络的对应关系的二分图；
图4为本发明的指控网络的示例图；
图5为本发明的系统网络与指控网络的对应关系的二分图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。
在本发明的描述中，需要理解的是，术语“上”、“下”、“前”、“后”、“左”、“右”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。
参照图1-5，一种作战体系架构建模与最优搜索方法，包括基于超网络的OSoSA形式化定义和OSoSA搜索，OSoSA形式化定义由任务网络、系统网络和指控网络三种异构网络组成，任务网络包含任务节点，系统网络包含系统节点，指控网络包含指控节点，OSoSA形式化定义的作战能力由OSoS得到，任务网络、系统网络和指控网络共同构成作战体系。
任务网络的任务节点是可由装备系统执行的作战活动，记为T，为了完成体系使命，使命应当分解为一系列可执行的任务，即任务链路；任务链路可以抽象为有向图，一个体系使命可以分解为不同的任务链路，每个任务链路具有起始任务节点和结束任务节点，不同的任务链路可能有不同的效能，任务链路中主要有两类逻辑关系，即顺序执行和并行执行，多个使命对应于构成任务网络的多个任务链路，记为G T＝(V T,E T)，并如图1所示。
任务网络的系统节点是指具有特定功能并能够完成特定任务的 装备，记为S，在任务规划法中，具有特定功能的装备系统用于完成特定任务，因而系统节点(例如无人机、坦克和舰艇)之间的关系受任务节点的影响，如图2：系统网络记为G S＝(V S,E S)；任务节点和系统节点之间的对应关系可以被定义为二分图，如图3：记为G TS＝(V TS,E TS)。
指控网络的指控节点用于处理信息、管理组织、决策规划、控制反馈等的逻辑节点，表示为C，指控节点处理上级和下级的指令信息，并保持与同级指控节之间的信息交互，因此指控网络是所有指控节点由指令关系构成组织结构，记为G C＝(V C,E C)，如图4；且多数组织结构都被建模为但不限于树状图，另外，系统节点和指控节点之间的对应关系被定义为二分图，记为G SC＝(V SC,E SC)，如图5。
由于OSoSA形式化定义的作战能力由OSoS得到，因此OSoS可能会受到OSoSA之外的因素的影响，这些因素可能导致涌现。因此，基于OSoSA的OSoS能力可能并不是唯一的，因而每个OSoSA方案具有不确定的潜在回报值。
指挥官需要在架构方案空间中选择一种架构方案(简称方案)来开发作战体系。为简单起见，本本将指挥官、决策机构和咨询机构建模为Agent。OSoS能力由回报值度量。每个方案的回报值x k服从概率分布Fk(xk)，不同方案的回报值相互独立。其中，k∈K,K＝{1,2,…,|K|}，K为方案空间中的方案数量。每个架构的回报值事先是不确定的，但可以通过开发OSoS或咨询其他Agent获得。Agent不断探索未开发方案空间中的方案，最后在所有已开发的方案空间中 选择一个方案作为最终选项。Agent的目标是选择一个具有最高预期回报值和最少累积搜索成本的架构。
其中，未知状态表明该方案尚未开发，其回报值是未知的；已知状态表明该方案已经被开发，并且其回报值是已知的。搜索状态表示正在查询该方案的回报值。在探索一个方案前，该方案有潜在的回报值。在开发OSoS之后，方案的回报值是已知的。Agent的行动包括：自行开发，由其他Agent开发，以及咨询相关Agent。具体地，在基于具有成本为
Figure PCTCN2020109335-appb-000001
的方案k被开发之后，未知状态转换到已知状态。此外，Agent可以请求其他Agent以
Figure PCTCN2020109335-appb-000002
的成本开发OSoS。此外，Agent可以咨询相关Agent，例如可能已经完成类似工作的机构或部门。咨询过程的成本记为
Figure PCTCN2020109335-appb-000003
实施例1本发明以方案k为例进行介绍，四个二元决策变量定义如下：如果方案是由Agent本身开发，那么
Figure PCTCN2020109335-appb-000004
否则
Figure PCTCN2020109335-appb-000005
如果该方案是由其他Agent开发的，那么
Figure PCTCN2020109335-appb-000006
否则
Figure PCTCN2020109335-appb-000007
如果Agent选择咨询相关Agent，那么
Figure PCTCN2020109335-appb-000008
否则
Figure PCTCN2020109335-appb-000009
如果选择方案k作为最终方案，那么s k＝1，否则s k＝0。OSoSA搜索问题(OSoSASP)框架如下：
CSoSAS:
Figure PCTCN2020109335-appb-000010
S.t.
Figure PCTCN2020109335-appb-000011
Figure PCTCN2020109335-appb-000012
Figure PCTCN2020109335-appb-000013
Figure PCTCN2020109335-appb-000014
Figure PCTCN2020109335-appb-000015
Figure PCTCN2020109335-appb-000016
Figure PCTCN2020109335-appb-000017
目标函数为最大化已开发架构的回报值与最小化累积搜索成本的加和。具体而言，约束(a)确保任一方案要么已经开发，要么未开发。约束(b)表示如果最终选择了一个方案，那么必须已经开发了该方案。约束(c)表示最终只选择一个方案。约束(d)表示四个决策变量的值空间。约束(e)表示Agent请求相关Agent的次数。约束(f)是指折扣率，表示开发时间对回报值的影响。约束(g)表示每个动作的成本。
进一步的解决OSoSA动态规划问题。
(1)决策指标
每个方案k定义执行行动
Figure PCTCN2020109335-appb-000018
和
Figure PCTCN2020109335-appb-000019
的指标，其中指标分别记为
Figure PCTCN2020109335-appb-000020
和
Figure PCTCN2020109335-appb-000021
Figure PCTCN2020109335-appb-000022
Figure PCTCN2020109335-appb-000023
Figure PCTCN2020109335-appb-000024
进一步，
Figure PCTCN2020109335-appb-000025
Figure PCTCN2020109335-appb-000026
Figure PCTCN2020109335-appb-000027
根据状态
Figure PCTCN2020109335-appb-000028
和指标集合
Figure PCTCN2020109335-appb-000029
设计一种简单但最优的搜索规则，分为判断规则和选择规则。判断规则指的是，如果Agent要进一步探索效果未知的架构，那么要选择一个具有最大指标的未知架构。同时根据最大指标选择动作，即自己研发，公司开发，还是向相关机构求助。停止规则指的是，当收集的最大采样回报值大于所有位置架构的研发指标、开发指标和咨询指标时，停止搜索并选择具有最大回报值的架构作为方案。
(2)搜索算法
每个指标的计算是独立的，不受其他方案的回报值概率分布的影响。GSDP由指标计算程序、顺序搜索程序和架构开发程序组成。具体而言，Agent首先根据公式计算所有方案的决策指标。其次，根据排序方法对指标进行排序，例如堆排序方法，排序结果保存到向量π中。第三，执行SequenceSearching程序以获得最佳方案。
Figure PCTCN2020109335-appb-000030
在SequenceSearching程序中，最多经过K次迭代就可以计算得到最优架构方案。根据设定的规则，每轮迭代中将当前最大采样值y与最大指标π(0)进行对比。如果最大采样值不小于最大指标，则停止搜索，并将具有当前最大采样回报值的架构m作为选择的架构。反之，则根据π(0)对应的架构索引i和动作a，执行Executing程序继续搜索。如果获得了架构i的采样回报值，则更新变量D,
Figure PCTCN2020109335-appb-000031
π,y,m，其中
Figure PCTCN2020109335-appb-000032
表示去除集合
Figure PCTCN2020109335-appb-000033
中的架构i。
Figure PCTCN2020109335-appb-000034
在Executing程序中，如果采取的动作是咨询，则判断是否能够通过相关机构获得架构i的回报值，即判断Available是否为true。其中“～”表示采样，y i～F i(x i)表示对概率分布F i(x i)进行采样。
Figure PCTCN2020109335-appb-000035
实施例1应用在100例的方案空间场景中，其平均回报值至少超出最优算法平均回报值的17.6％；在方案数为10000的方案空间场景中，其平均回报值至少超出最优算法平均回报值的15.2％；在方案数为1000000的方案空间场景中，其平均回报值至少超出最优算法平均回报值的21.9％，结合最优算法平均回报值的数据，使得本发明中的平均回报值能够处于较高的状态，进而使得本发明有利于进行推广运用。
以上所述，仅为本发明较佳的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，根据本发明的技术方案及其发明构思加以等同替换或改变，都应涵盖在本发明的保护范围之内。

Claims (4)

  1. 一种作战体系架构建模与最优搜索方法，其特征在于，包括基于超网络的OSoSA形式化定义和OSoSA搜索，所述OSoSA由任务网络、系统网络和指控网络三种异构网络组成，所述任务网络包含任务节点，所述系统网络包含系统节点，所述指控网络包含指控节点，所述OSoSA形式化定义的作战能力由OSoS得到，所述任务网络、系统网络和指控网络共同构成作战体系。
  2. 根据权利要求1所述的一种作战体系架构建模与最优搜索方法，其特征在于，所述任务网络的任务节点是可由装备系统执行的作战活动，记为T。
  3. 根据权利要求1所述的一种作战体系架构建模与最优搜索方法，其特征在于，所述任务网络的系统节点是指具有特定功能并能够完成特定任务的装备，记为S。
  4. 根据权利要求1所述的一种作战体系架构建模与最优搜索方法，其特征在于，所述指控网络的指控节点用于处理信息、管理组织、决策规划、控制反馈等的逻辑节点，表示为C。
PCT/CN2020/109335 2019-09-25 2020-08-14 一种作战体系架构建模与最优搜索方法 WO2021057329A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910912549.0 2019-09-25
CN201910912549.0A CN110688754B (zh) 2019-09-25 2019-09-25 一种作战体系架构建模与最优搜索方法

Publications (1)

Publication Number Publication Date
WO2021057329A1 true WO2021057329A1 (zh) 2021-04-01

Family

ID=69110265

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/109335 WO2021057329A1 (zh) 2019-09-25 2020-08-14 一种作战体系架构建模与最优搜索方法

Country Status (2)

Country Link
CN (1) CN110688754B (zh)
WO (1) WO2021057329A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114021319A (zh) * 2021-10-26 2022-02-08 岭南师范学院 一种基于改进桥接系数的指挥控制网络关键边识别方法

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110688754B (zh) * 2019-09-25 2024-07-26 中国人民解放军国防科技大学 一种作战体系架构建模与最优搜索方法
CN111967741B (zh) * 2020-08-04 2022-11-18 中国人民解放军国防科技大学 一种基于ec2的无人化作战体系云流化指控架构设计方法
GB2618302A (en) * 2020-11-13 2023-11-08 National Univ Of Defense Technology Hypernetwork model-based organization architecture modeling method and space exploration algorithm
CN112632744B (zh) * 2020-11-13 2023-05-16 中国人民解放军国防科技大学 基于超网络模型的作战体系架构建模方法及空间探索方法
CN112422353B (zh) * 2021-01-25 2021-04-09 中国人民解放军国防科技大学 一种基于效用性的兵力配系网络生成方法
CN112801539A (zh) * 2021-02-23 2021-05-14 中国人民解放军国防科技大学 无人机集群任务的柔变网络架构动态调度模型
CN114154322A (zh) * 2021-11-29 2022-03-08 上海烜翊科技有限公司 一种由体系架构模型输出的系统总体设计方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150082399A1 (en) * 2013-09-17 2015-03-19 Auburn University Space-time separated and jointly evolving relationship-based network access and data protection system
CN106603309A (zh) * 2017-01-04 2017-04-26 大连大学 一种基于超网络的指控网络分层演化方法
CN110688754A (zh) * 2019-09-25 2020-01-14 中国人民解放军国防科技大学 一种作战体系架构建模与最优搜索方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937486A (zh) * 2010-05-06 2011-01-05 中国人民解放军理工大学 复杂系统的信息支持能力评估分析方法
FR3020889A1 (fr) * 2014-05-07 2015-11-13 Malbert Michel Decways- systeme de conduite de projet assurant la supervision de la conduite, la coordination et l'aide aux decisions de l'equipe operationnelle
CN107707412A (zh) * 2017-11-08 2018-02-16 大连大学 基于多属性加权的指挥控制网络建模方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150082399A1 (en) * 2013-09-17 2015-03-19 Auburn University Space-time separated and jointly evolving relationship-based network access and data protection system
CN106603309A (zh) * 2017-01-04 2017-04-26 大连大学 一种基于超网络的指控网络分层演化方法
CN110688754A (zh) * 2019-09-25 2020-01-14 中国人民解放军国防科技大学 一种作战体系架构建模与最优搜索方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WANG TAO, ZHOU XIN , WANG WEIPING , ZHU YIFAN , JING TIAN: "An Optimal Approach for Combat System-of-Systems Architecture Search Under Uncertainty", IEEE ACCESS, vol. 7, 26 August 2019 (2019-08-26), pages 119140 - 119150, XP011744017, DOI: 10.1109/ACCESS.2019.2937321 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114021319A (zh) * 2021-10-26 2022-02-08 岭南师范学院 一种基于改进桥接系数的指挥控制网络关键边识别方法

Also Published As

Publication number Publication date
CN110688754B (zh) 2024-07-26
CN110688754A (zh) 2020-01-14

Similar Documents

Publication Publication Date Title
WO2021057329A1 (zh) 一种作战体系架构建模与最优搜索方法
CN112632744B (zh) 基于超网络模型的作战体系架构建模方法及空间探索方法
Zhang et al. Multi-level decision making
US8694561B2 (en) System and method of optimizing performance of schema matching
CN101083019A (zh) 基于空间态势感知的快速评估系统
CN112700099A (zh) 基于强化学习和运筹学的资源调度规划方法
US8219607B2 (en) Collaborative planning actions and recipes
Sun et al. An artificial bee colony algorithm with random location updating
Le et al. ER-DCOPs: A framework for distributed constraint optimization with uncertainty in constraint utilities
CN116663416A (zh) 一种基于行为树的cgf决策行为仿真方法
CN113566831B (zh) 基于人机交互的无人机集群导航方法、装置和设备
de Rosa et al. Opytimizer: A nature-inspired python optimizer
Tian et al. Decision models to find a promising start-up firm with QUALIFLEX under probabilistic linguistic circumstance
Pereira et al. Multi‐objective sunflower optimization: A new hypercubic meta‐heuristic for constrained engineering problems
CN111190711B (zh) Bdd结合启发式a*搜索的多机器人任务分配方法
Wang et al. An optimal approach for combat system-of-systems architecture search under uncertainty
Nguyen et al. Review, analysis and design of a comprehensive deep reinforcement learning framework
CN114611990A (zh) 一种网络信息体系要素体系贡献率评估方法和装置
CN111354427A (zh) 用于大规模电子健康档案知识协同约简的最近邻多粒度利润方法
Wu et al. Learning to Transfer for Evolutionary Multitasking
CN117592385B (zh) 基于影响因子的体系设计优化方法、服务器及存储介质
Tamouk et al. A multimetric and multideme multiagent system for multiobjective optimization
CN114638031B (zh) 复杂工程体系构建过程改进系统及终端
Jiao et al. City-LEO: Toward Transparent City Management Using LLM with End-to-End Optimization
CN117669710B (zh) 面向博弈对抗任务的多行为树决策方案聚合方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20869576

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20869576

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20869576

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25.05.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20869576

Country of ref document: EP

Kind code of ref document: A1