CN112287521A - Decision-making platform of intelligent combat equipment - Google Patents
Decision-making platform of intelligent combat equipment Download PDFInfo
- Publication number
- CN112287521A CN112287521A CN202011080003.2A CN202011080003A CN112287521A CN 112287521 A CN112287521 A CN 112287521A CN 202011080003 A CN202011080003 A CN 202011080003A CN 112287521 A CN112287521 A CN 112287521A
- Authority
- CN
- China
- Prior art keywords
- combat
- decision
- model
- intelligent
- action
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 76
- 230000009471 action Effects 0.000 claims abstract description 53
- 230000008569 process Effects 0.000 claims abstract description 44
- 230000019771 cognition Effects 0.000 claims abstract description 26
- 238000013461 design Methods 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000002787 reinforcement Effects 0.000 claims abstract description 11
- 238000010924 continuous production Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 13
- 238000011160 research Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000007704 transition Effects 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000007123 defense Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 239000010931 gold Substances 0.000 description 3
- 229910052737 gold Inorganic materials 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent combat equipment decision platform, which adopts an improved hybrid random time delay Petri network model with a three-layer structure of a decision layer, an event layer and a physical layer to model an intelligent combat equipment cognition and decision system, and can carry out modeling simulation on 5 types of hybrid characteristics of discrete events, continuous processes, time delay characteristics, random phenomena and decision problems in the combat system; optimizing an action rule model, a battle decision model and a command decision model by designing an interface between HSTPNSim software and a Python end and using a deep learning and reinforcement learning method; and designing a visual deduction interface to display the battlefield situation in real time. The invention provides an intelligent combat equipment cognition and decision system design method based on an M-HSTPN model, which realizes the self-adaptive learning and evolution of situation cognition and opportunistic decision by means of a reinforcement learning and deep learning method, intuitively demonstrates the combat process and results by adopting a visual deduction interface and is beneficial to better research and analysis of a combat system.
Description
Technical Field
The invention relates to the field of cognition and decision making of intelligent combat equipment, in particular to modeling and simulation of a combat system with a complex cognition and decision making process in a modern battlefield environment.
Background
The modern combat process is high-tech wars, and two parties or one party of the combat uses high-tech weaponry and a combat method adapted to the high-tech weaponry to carry out non-contact and high-precision attack on military targets, so that military teams of all countries in the world are exploring and researching on strengthening modern military training. Because of peaceful period, people are difficult to learn war from war like the past, and meanwhile, large-scale military exercises not only consume a large amount of material resources and financial resources, but also are limited by international political environment. With the acceleration of the informatization construction pace, computer simulation has gradually become an effective way for researching a war system, namely, the war is researched by constructing an intelligent combat equipment cognition and decision system.
The intelligent combat equipment cognition and decision platform is constructed, command strategy can be carried out on commanders or officers involved in the combat, the formulated combat schemes or combat methods are evaluated and optimized, and the combat effectiveness of the existing/future weaponry equipment is evaluated. The simulation method has the advantages of controllable, safe, economic, nondestructive and repeatable process, is not limited by conditions such as climate, space, time and the like, and can reflect and count conditions such as the loss of the maneuvering, fighting and weapon performance of the army timely and dynamically, so that the analysis and evaluation of the fighting process and the result are more scientific.
Modern combat systems can be viewed as a class of large promiscuous systems that include discrete processes, continuous processes, time delay characteristics, stochastic characteristics, and decision characteristics. The M-HSTPN is an effective tool for modeling a hybrid system, and can simultaneously describe discrete events, continuous processes, time delay characteristics, random phenomena and decision processes. The HSTPNSim software can realize the visual modeling and solving of the M-HSTPN model, and creates conditions for the modeling and simulation of the M-HSTPN. Python is a scripting language combining interpretability, compilability, interactivity and object-oriented, has a very strong readability in design, has a more distinctive syntactic structure than other high-level languages, supports object-oriented style or code encapsulation in object programming technologies, and can be applied to system programming, image processing, scientific computing, text processing, database programming, network programming and multimedia applications.
Therefore, the patent provides an intelligent combat equipment cognition and decision system based on a three-layer structure of 'decision layer-event layer-physical layer' of M-HSTPN, the cognition and decision system comprises a visual deduction interface and model optimization based on a Python end, and modeling and simulation of the combat system are achieved.
Disclosure of Invention
The invention provides an intelligent combat equipment decision platform which can effectively describe discrete events, a continuous process, time delay characteristics, random phenomena and a decision process in a modern combat process, and optimizes an action rule model, a combat decision model and a command decision model by using methods such as deep learning, reinforcement learning and the like at a Python end through a data interface, wherein the specific scheme is as follows:
an intelligent combat equipment decision platform adopts an M-HSTPN model with a three-layer structure of a decision layer, an event layer and a physical layer to model an intelligent combat equipment cognition and decision system, and comprises the following steps:
the action rule model is mainly a program and a method for various specific combat actions of a combat unit, and consists of six elements, namely an action subject, an action event, an action object, an action condition, action time and an action result.
The battle decision model is mainly used for evaluating battlefield situations, and can give out the result of the success or the failure of battle and judge the income of each stage in the battle process.
The command decision model is mainly a comprehensive balancing process aiming at the battle tasks, the battle ordinances, the command theory and the battle experience.
And the data interface is used for optimizing the action rule model, the fighting decision model and the command decision model by designing HSTPNSim software and a Python end communication interface through reinforcement learning and deep learning of the fighting system.
And the visual interface realizes a visual deduction interface through a DirectX technology, displays the change of the battlefield situation in real time, and visually displays the operation flow and the operation result.
Preferably, the intelligent combat equipment cognition and decision platform adopts a design method and a design rule of an M-HSTPN model, designs a combat system design method based on the M-HSTPN model by analyzing discrete events, a continuous process, time delay characteristics, random phenomena and a decision process in a combat system, and builds an intelligent combat equipment cognition and decision system by utilizing HSTPNSim software;
preferably, the action rule model is clustered at a Python end by adopting a clustering method, the action rule model of the battle system is optimized by adopting a deep learning method, and the optimized result is transmitted to a model built in HSTPNSim software through a data interface;
preferably, the engagement decision model is optimized by adopting a deep learning method at a Python end, so that an engagement result can be quickly obtained after a given engagement action is achieved, the engagement result is input into the current state, namely the current battlefield situation and the action to be executed, the situation evaluation value is output as the battlefield situation after engagement is finished, and then the situation evaluation value is transmitted into a model established by HSTPNSim software through a data interface;
preferably, the command decision model is optimized by reinforcement learning on the basis of the action rule optimization model and the engagement decision optimization model, and the optimized result is transmitted to a model built by HSTPNSim software through a data interface, so that the engagement command and cooperation capability is improved;
preferably, DirectX is used to combine with Microsoft basic MFC development, the operation control is taken charge of by the combat simulation program in the system, and the operation of the combat visual deduction program and the stop of the operation of the combat simulation program are uniformly scheduled by instructions.
Preferably, the design method and the design criteria of the M-HSTPN model comprise seven steps of combat process analysis, combat model abstraction, hybrid characteristic analysis, event layer modeling, physical layer modeling, decision layer modeling and link integration, wherein the combat process starts with a library and ends with the library, and the method improves the rationality and the accuracy of the M-HSTPN modeling.
Preferably, the communication mode is synchronous communication, that is, the client sends a service request to the server, and the client blocks and waits for the server to return a processing result
The intelligent combat equipment cognition and decision platform based on the M-HSTPN model adopts a three-layer architecture of a decision layer, an event layer and a physical layer, and comprises a command decision model based on reinforcement learning, an action rule model based on deep learning, a combat decision model based on deep learning and a visual deduction interface. The system can perform modeling simulation on 5 types of discrete, continuous, time-delay, random and decision mixed characteristics in the intelligent combat equipment cognition and decision system based on the M-HSTPN model. And providing a combat system design method and design criteria based on an M-HSTPN model to realize modular modeling. By designing interfaces of HSTPNSim software and a Python end, a synchronous communication mode is adopted, and situation cognition and opportunistic decision-making adaptive learning and evolution are achieved by means of strong scientific calculation and modeling capacity.
The cognitive and decision-making platform of the intelligent combat equipment can be applied to multiple aspects of military training, military exercises, national defense planning, military operational research, weapon development and the like, and can save a large amount of manpower, material resources, funds and time resources for related work. The intelligent combat equipment cognition and decision system modeling method based on a three-layer structure of a decision layer, an event layer and a physical layer can be used for guiding the modeling of various combat systems.
Drawings
FIG. 1 is a block diagram of an intelligent combat simulation system based on M-HSTPN model according to the present invention;
FIG. 2 is a schematic diagram of various libraries in M-HSTPN provided by the present invention: wherein FIG. 2a represents a discrete library site, FIG. 2b is a continuous library site, FIG. 2c is a time delay library site, FIG. 2d is a random library site, and FIG. 2e is a decision library site;
fig. 3 is a schematic diagram of a three-layer architecture of a decision layer-event layer-physical layer of the M-HSTPN model provided in the present invention;
FIG. 4 is a modeling step of the intelligent combat equipment cognition and decision-making system based on the M-HSTPN model provided by the invention.
FIG. 5 is a model of "gold canyon" action links based on an intelligent combat equipment cognition and decision platform provided by an embodiment of the invention;
FIG. 6 is a schematic diagram of data interaction between a combat simulation program and a visualization deduction program based on an M-HSTPN model provided by the present invention;
Detailed Description
The invention provides an intelligent combat equipment cognition and decision platform based on an M-HSTPN model, which can effectively describe discrete events, continuous processes, time delay characteristics, random phenomena and decision processes in a combat system, realize cognition and decision problems in a complex battlefield environment through reinforcement learning and deep learning, and visually display combat processes and results through a visual deduction interface.
The M-HSTPN-based intelligent combat equipment cognition and decision platform comprises a decision layer, an event layer, a physical layer and a visual deduction interface, wherein the decision layer is composed of a combat decision model and a command decision model, the event layer represents the state of each combat unit, the physical layer is composed of an action rule model, the data interface a realizes data interaction between the decision layer and the event layer, the data interface b realizes data interaction between the event layer and the physical layer, and the data interface c realizes interaction between a simulation system and the deduction system. The design refines the functions of each layer, reduces the coupling degree of the system and improves the expandability of the platform.
The action rule model of the M-HSTPN-based intelligent combat equipment cognition and decision platform shown in FIG. 1 takes action subjects, action events, action objects, action conditions and action time of the action rule model as input, and takes action result historical data as a label to train an action rule deep learning network. The battle decision neural network model is trained by using historical battle data, and is applied to a battlefield environment to generate a final battle result and update an evaluation value based on a situation evaluation value given by the battle decision network model and in combination with an action rule model. On the basis of an action rule optimization model of combat equipment and a combat decision optimization model, the action rule model acts on a strategy given by a command decision model and acts on a battlefield environment, the combat decision model gives a situation evaluation value, and the obtained situation evaluation value is used for correcting a reinforced learning network parameter of the command decision model.
The M-HSTPN model is an improved Hybrid random time delay Petri network model (M-HSTPN), and is defined as a quintuple:
M-HSTPN＝(SG,T,F,Q0,TH)
wherein SG ═ SD,SC,ST,SS,SJ) Denotes a finite set of libraries, SDRepresents a collection of discrete libraries, SCRepresenting a set of contiguous bins, STRepresenting a time delay library set, SSRepresenting a random pool, SJRepresenting a set of decision libraries;
t represents a finite set of transitions; f represents a directed arc set connecting the library and the transition; q0Representing an initial set of promiscuous states; TH denotes a library enabled threshold or set of parameters. The symbols of the libraries and transitions in M-HSTPN are shown in FIG. 2.
The M-HSTPN model is a three-layer architecture including a "decision layer-event layer-physical layer", as shown in fig. 3, wherein the decision layer encapsulates a model for cognition and decision of a complex combat system, including a deep learning-based combat decision model and a reinforcement learning-based command decision model, and the decision layer receives description information of the event layer on battlefield situation, triggers behaviors such as task planning, action decision reasoning of combat units and the like, and transmits a task scheme or an action strategy to the event layer. The event layer describes the state of each fighting unit in the system and events possibly occurring in the system based on the M-HSTPN model, further represents the state topological space of the fighting system, receives a task scheme or an action strategy of the decision layer and triggers the occurrence of the events, and when the fighting units described in the layer are in an activated state, the state evolution of corresponding entity models of the fighting units in the physical layer is triggered. The physical layer encapsulates the entity models of the operation units related to the operation system, including description equations of radar scanning process, aircraft track and the like. When the description equation of the entity model of a certain combat unit in the layer evolves to a certain state threshold value, certain events in the event layer can be caused to occur, and the deduction of the system is driven.
The operation system has the problems of complex operation process, staggered links, strong coupling degree and the like, and a modular modeling method from top to bottom is necessary to be adopted from the system level, wherein the modeling method mainly comprises seven steps:
the method comprises the following steps: combat process analysis
The operation process analysis is to analyze the composition units and the operation process of the whole operation system, divide the operation process of the operation system into a plurality of links according to specific granularity, and divide each link into smaller granularity according to the requirement.
Step two: operational model abstraction
The operation model abstraction mainly models elements in an operation system and the mixed characteristics of the system, eliminates influence factors which have small influence on the operation process analysis and irrelevant operation processes, further simplifies the system and forms an abstract model which can be analyzed and synthesized.
Step three: confounding characteristic profiling
According to the result of the operational process analysis and the operational model abstraction, taking each link as a unit, discrete events, continuous processes, random phenomena, time delay characteristics and decision characteristics in the operational process are extracted.
(1) The continuous process comprises the following steps: the continuity of the state is represented as a process that the running track or the state of the battle equipment continuously changes along with time before action or event occurs, such as continuous dynamic processes of information acquisition, fighter plane flight, missile flight and the like;
(2) discrete event: under different battlefield situations, different events usually occur to the combat equipment, and the occurrence of the events usually causes the change of the battlefield situations such as damage of fighters, missile launching and the like relative to the continuous change of the state of the combat equipment;
(3) time delay characteristic: the time delay characteristic is obvious in the processes of action opportunity, information transmission, shooting preparation and the like of the combat equipment in the system;
(4) random phenomenon: randomness refers to some unstable and uncertain factors existing in a battlefield environment, such as weather environment, detection results and other factors;
(5) decision characteristics: and (4) decision reasoning process in the battle process, such as selection of a battle strategy.
Step four: event layer modeling
And (4) considering the characteristics of dispersion, continuity, time delay, randomness and decision mixing in each link in the step three, and designing an internal subnet of each link by combining an M-M-HSTPN typical structure, wherein the process determines the topological details of each link. And (4) establishing a logical topological relation in each link by combining the analysis of the hybrid characteristics of the combat system.
Step five: physical layer modeling
Modeling a physical evolution process of the hybrid characteristics in the fighting process, wherein the modeling comprises the steps of program design of a continuous process and a probability calculation process, the determination of threshold values of all libraries, the data interface design of a Python end, the input and output variable setting and the compiling of an optimization program of the Python end.
Step five: decision layer modeling
And modeling decision characteristics in the mixed characteristics contained in the fighting process, wherein the decision characteristics comprise program design of the processes of judgment, planning, reasoning and the like, data interface design of a Python end, input and output variable setting and programming of an optimization program of the Python end.
Step six: link integration
Each link begins with a transition and ends with a transition, and the end of the old state and the start of the new state are represented by the discrete library in the middle. The calling relation of the variables between the ring nodes is designed, and the variables are usually set as global variables. And respectively adding transitions before and after each link, and connecting each link through a discrete library to obtain the Petri network model.
By utilizing the cognitive and decision modeling method for the combat equipment, modeling simulation is carried out by taking a 'gold canyon' action initiated by America Pair-Bibia as an example, and an event layer model of an intelligent combat equipment simulation system based on the 'gold canyon' action of M-HSTPN is shown in FIG. 4 and comprises a army attack part and an army defense part, wherein the army attack part comprises a detection model 1, a command control model 2, attack models 3 and 4 and a combat decision model 8; the army defense comprises a detection model 5, a command control model 6 and a defense model 7. The meaning of each symbol in the event layer model of the M-HSTPN-based intelligent combat simulation system is shown in figure 3. The ctrl _1 of the decision library can communicate with the Python terminal through a data interface, the command decision model of the army is optimized by using a reinforcement learning method, the ctrl _9 of the decision library can communicate with the Python terminal through a data interface, the engagement decision model is optimized by using a deep learning method, the continuum libraries such as the radar _1, the radar _2, the radar _3, the track _1 and the track _2 can communicate with the Python terminal through a data interface, and the action rule model of each engagement unit is optimized by using the deep learning method.
As shown in fig. 6, data interaction between the simulation program of the combat equipment based on the M-HSTPN model and the visual deduction program enters a periodic cycle mode of the calculation of the combat simulation model through a start instruction, meanwhile, battlefield situation data in the combat process is issued to the visual deduction program in the calculation process, and after the model calculation is finished, a stop instruction is sent to the visual deduction program to finish the combat simulation program; after the simulation deduction visualization program is started and initialized, waiting for receiving a starting instruction sent by the combat simulation program, receiving the instruction, circularly receiving data issued by the combat simulation program, performing combat deduction display, displaying battlefield situation data in real time, and ending the program when receiving a stopping instruction sent by the combat simulation program.
Claims (8)
1. An intelligent combat equipment decision platform is characterized in that an M-HSTPN model of a three-layer structure of a decision layer-event layer-physical layer is adopted to model an intelligent combat equipment cognition and decision system, and the platform comprises:
the action rule model is mainly a program and a method for various specific combat actions of a combat unit, and consists of six elements, namely an action subject, an action event, an action object, an action condition, action time and an action result.
The battle decision model is mainly used for evaluating battlefield situations, and can give out the result of the success or the failure of battle and judge the income of each stage in the battle process.
The command decision model is mainly a comprehensive balancing process aiming at the battle tasks, the battle ordinances, the command theory and the battle experience.
And the data interface is used for optimizing the action rule model, the fighting decision model and the command decision model by designing HSTPNSim software and a Python end communication interface through reinforcement learning and deep learning of the fighting system.
And the visual interface realizes a visual deduction interface through a DirectX technology, displays the change of the battlefield situation in real time, and visually displays the operation flow and the operation result.
2. The intelligent combat equipment decision platform as claimed in claim 1, wherein the intelligent combat equipment cognition and decision platform adopts a design method and design criteria of an M-HSTPN model, designs a combat system design method based on the M-HSTPN model by analyzing discrete events, continuous processes, time delay characteristics, random phenomena and decision processes in a combat system, and builds the intelligent combat equipment cognition and decision system by using HSTPNSim software.
3. The intelligent combat equipment decision platform according to claim 1, wherein the action rule model is clustered at a Python end by using a clustering method, the action rule model of the combat system is optimized by using a deep learning method, and the optimized result is transmitted to a model built in HSTPNSim software through a data interface.
4. The intelligent combat equipment decision platform as claimed in claim 1, wherein the combat decision model is optimized by a deep learning method at a Python end, so that a combat result can be obtained quickly after a given combat action, the combat result is input into a current state, namely a current battlefield situation and an action to be executed, a situation evaluation value of the battlefield situation after the combat is finished is output, and the situation evaluation value is transmitted to a model built by using HSTPNSim software through a data interface.
5. The intelligent combat equipment decision platform as claimed in claim 1, wherein the command decision model is optimized by reinforcement learning based on an action rule optimization model and a combat decision optimization model, and the optimized result is transmitted to a model built by using HSTPNSim software through a data interface, so as to improve the combat command and coordination ability.
6. The intelligent combat equipment decision platform according to claim 1, wherein the system is developed by combining DirectX with microsoft basic MFC, the operation control is performed by a combat simulation program, and the operation and the stop of the operation of the combat visual deduction program are performed by the combat simulation program in a unified instruction scheduling mode.
7. The intelligent combat equipment decision platform according to claim 2, wherein the M-HSTPN model design method and design criteria comprise seven steps of combat process analysis, combat model abstraction, confounding characteristic analysis, event layer modeling, physical layer modeling, decision layer modeling and link integration, wherein the combat process starts with a library and ends with the library, and the method improves the rationality and accuracy of M-HSTPN modeling.
8. The intelligent combat equipment decision platform as claimed in any one of claims 3 to 5, wherein the communication mode is synchronous communication, that is, the client sends a service request to the server, and the client blocks and waits for the server to return a processing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011080003.2A CN112287521A (en) | 2020-10-10 | 2020-10-10 | Decision-making platform of intelligent combat equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011080003.2A CN112287521A (en) | 2020-10-10 | 2020-10-10 | Decision-making platform of intelligent combat equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287521A true CN112287521A (en) | 2021-01-29 |
Family
ID=74422465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011080003.2A Pending CN112287521A (en) | 2020-10-10 | 2020-10-10 | Decision-making platform of intelligent combat equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287521A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158430A (en) * | 2021-03-25 | 2021-07-23 | 中国电子科技集团公司第二十九研究所 | Efficient online behavior modeling combat simulation method |
| CN114792072A (en) * | 2022-05-18 | 2022-07-26 | 中国人民解放军国防科技大学 | Function-based equipment decision behavior simulation modeling method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100015579A1 (en) * | 2008-07-16 | 2010-01-21 | Jerry Schlabach | Cognitive amplification for contextual game-theoretic analysis of courses of action addressing physical engagements |
| CN106446427A (en) * | 2016-09-29 | 2017-02-22 | 北京华如科技股份有限公司 | Combined type battling entity modelwith control module as core and establishment method thereof |
| CN107229789A (en) * | 2017-05-25 | 2017-10-03 | 东北大学 | Hybrid system Modeling and simulation platform and emulation mode based on HSTPN models |
| CN107967134A (en) * | 2017-11-20 | 2018-04-27 | 中国人民解放军国防科技大学 | Novel combat effectiveness simulation modeling method |
| CN108873737A (en) * | 2018-07-18 | 2018-11-23 | 东北大学 | A kind of automatic sorting control and decision system based on M-HSTPN model |
| CN109636699A (en) * | 2018-11-06 | 2019-04-16 | 中国电子科技集团公司第五十二研究所 | A kind of unsupervised intellectualized battle deduction system based on deeply study |
| CN110619131A (en) * | 2018-06-20 | 2019-12-27 | 陕西师范大学 | UUV agent behavior planning method based on weighted fuzzy Petri net |
-
2020
- 2020-10-10 CN CN202011080003.2A patent/CN112287521A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100015579A1 (en) * | 2008-07-16 | 2010-01-21 | Jerry Schlabach | Cognitive amplification for contextual game-theoretic analysis of courses of action addressing physical engagements |
| CN106446427A (en) * | 2016-09-29 | 2017-02-22 | 北京华如科技股份有限公司 | Combined type battling entity modelwith control module as core and establishment method thereof |
| CN107229789A (en) * | 2017-05-25 | 2017-10-03 | 东北大学 | Hybrid system Modeling and simulation platform and emulation mode based on HSTPN models |
| CN107967134A (en) * | 2017-11-20 | 2018-04-27 | 中国人民解放军国防科技大学 | Novel combat effectiveness simulation modeling method |
| CN110619131A (en) * | 2018-06-20 | 2019-12-27 | 陕西师范大学 | UUV agent behavior planning method based on weighted fuzzy Petri net |
| CN108873737A (en) * | 2018-07-18 | 2018-11-23 | 东北大学 | A kind of automatic sorting control and decision system based on M-HSTPN model |
| CN109636699A (en) * | 2018-11-06 | 2019-04-16 | 中国电子科技集团公司第五十二研究所 | A kind of unsupervised intellectualized battle deduction system based on deeply study |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158430A (en) * | 2021-03-25 | 2021-07-23 | 中国电子科技集团公司第二十九研究所 | Efficient online behavior modeling combat simulation method |
| CN113158430B (en) * | 2021-03-25 | 2022-08-02 | 中国电子科技集团公司第二十九研究所 | Efficient online behavior modeling combat simulation method |
| CN114792072A (en) * | 2022-05-18 | 2022-07-26 | 中国人民解放军国防科技大学 | Function-based equipment decision behavior simulation modeling method and system |
| CN114792072B (en) * | 2022-05-18 | 2024-01-16 | 中国人民解放军国防科技大学 | Function-based equipment decision behavior simulation modeling method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | UAV air combat autonomous maneuver decision based on DDPG algorithm | |
| CN113255916A (en) | Using method of combat knowledge system and combat decision auxiliary method | |
| CN113705102B (en) | Deduction simulation system, deduction simulation method, deduction simulation equipment and deduction simulation storage medium for sea-air cluster countermeasure | |
| CN113392521B (en) | Method and system for constructing resource marshalling model for air-sea joint combat mission | |
| CN112820164A (en) | Layered behavior model-based VR virtual confrontation training system | |
| CN112287521A (en) | Decision-making platform of intelligent combat equipment | |
| CN113919068B (en) | Task-based aviation equipment support system simulation evaluation method | |
| CN113298260B (en) | Confrontation simulation deduction method based on deep reinforcement learning | |
| CN114282833A (en) | Rules-based hierarchical task planning method for air-sea combined combat action | |
| CN105678030A (en) | Air-combat tactic team simulating method based on expert system and tactic-military-strategy fractalization | |
| Mour et al. | Agent‐Based modeling for systems of systems | |
| CN114169142A (en) | Task meta-model construction method, database and device for general combat process | |
| Zacharias et al. | SAMPLE: Situation awareness model for pilot in-the-loop evaluation | |
| CN110109653A (en) | A kind of land battle war game intelligent engine and its operation method | |
| Liu et al. | Task assignment in ground-to-air confrontation based on multiagent deep reinforcement learning | |
| CN114240169A (en) | Intelligent tactical decision method based on killer chain | |
| CN111881622A (en) | Method for deductive evaluation of combat plan by person in loop | |
| CN116663416A (en) | CGF decision behavior simulation method based on behavior tree | |
| KR101345645B1 (en) | Simulation System And Method for War Game | |
| CN114968193A (en) | Operation scenario verification method based on coloring net | |
| Tang et al. | Dynamic scheduling for multi-level air defense with contingency situations based on Human-Intelligence collaboration | |
| CN113505538B (en) | Unmanned aerial vehicle autonomous combat system based on computer generated force | |
| CN114329928B (en) | Modularized assembly and overall parameter rapid generation method of equipment model | |
| Gimiga | THE IMPACT OF TECHNOLOGY ON THE PROCESS OF PLANNING AND DECISION MAKING | |
| Hua et al. | CB-MLC2A—A command and control architecture for unmanned combat SoS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |