27 results about "Combat unit" patented technology

The invention provides a real-time command and control strategy optimization method and device based on multi-agent reinforcement learning, equipment and a storage medium, and the method comprises the steps: deploying a pre-trained cooperative intention network on edge equipment of each combat unit, and coding local observation data and a historical sequence thereof into a low-dimensional local cooperative intention vector; replacing original high-dimensional data as inter-unit communication content; whether broadcasting is carried out or not is dynamically determined according to observation uncertainty and a channel state by combining a self-adaptive intention broadcasting mechanism, and communication resources are distributed according to needs; after each unit receives an adjacent collaborative intention vector, a lightweight space-time attention module in a pre-trained local strategy execution network carries out space weighting on adjacent intentions and fuses time features of own historical intentions, and a collaborative and consistent real-time command and control instruction is generated under the condition that global information convergence is not needed.

The invention relates to the field of combat command and dispatch, in particular to a multistage linkage combat unit command and dispatch system. According to the invention, a basic-level minimum emergency unit element information base is constructed through a data acquisition module; generating an electronic map supporting 2D and 3D switching; an intelligent analysis early warning module identifies abnormal conditions and generates early warning information; a plurality of multi-level linkage combat unit topology networks are generated through the multi-level linkage command architecture module; generating a command data large screen for dynamically aggregating public security indexes and a global situation visualization electronic map through a global situation visualization module; an early warning area is circled and selected through the intelligent scheduling module; and associating the corresponding multi-stage linkage combat unit to generate a deployment instruction. According to the multi-level linkage combat unit command and dispatch system provided by the invention, the multi-level linkage combat unit is effectively combined with a dynamic visual geographical environment from data acquisition, analysis and early warning to command and dispatch through cooperation of multiple modules, so that the command and dispatch efficiency is remarkably improved.

The invention discloses a tactical simulation confrontation training system based on digital twinning and VR. The tactical simulation confrontation training system comprises a digital twinning construction and synchronization module, a virtual reality interaction and presentation module, a tactical confrontation simulation and deduction module, a training process monitoring and data acquisition module and a training effect evaluation and intelligent redisk module. According to the invention, the digital twinborn body synchronously mapped with the real combat unit and the environment is constructed, and is deeply integrated with the immersive VR interaction environment, so that a highly vivid and panoramic immersive tactical training scene is provided for trainees, the system supports red and blue parties or multiple parties to carry out intelligent confrontation in a virtual-real combined dynamic environment, and the training efficiency is improved. The multi-dimensional training data is acquired in real time, and based on the data, the system can perform refined and quantitative objective evaluation and intelligent redisk on the tactical actions, decision-making processes and collaborative effects of individuals and teams, so that the authenticity of training, the intelligence of confrontation and the scientificity of evaluation are remarkably improved.

The invention discloses an end-to-end unmanned aerial vehicle target behavior detection system and method based on large kernel convolution. The system comprises a visual acquisition module, an embedded edge calculation module, a flight platform, an end-to-end decision link and a time sequence feature fusion module. According to the invention, the behavior detection task can be executed accurately and efficiently. Aiming at hidden dynamic behaviors (including reconnaissance, attack and escape) of an enemy combat unit in a complex battlefield environment, visible light-infrared multi-source data collaborative acquisition, multi-stage expansion convolution feature extraction, time sequence attention feature fusion and end-to-end decision link construction are carried out, so that the hidden dynamic behaviors of the enemy combat unit in the complex battlefield environment are obtained. Millisecond-level real-time detection, high-precision behavior recognition and threat evaluation of military targets are realized.

The invention provides a virtual collusion tactical intention analysis method and device, equipment and a storage medium, and the method comprises the steps: obtaining multi-modal battlefield intelligence, carrying out the feature alignment and fusion of information data of different modals through employing a cross-modal attention mechanism, mapping heterogeneous data to a unified semantic space, obtaining a unified feature vector of each combat entity, and carrying out the analysis of the virtual collusion tactical intention. Therefore, the problem of multi-source heterogeneous data splitting is solved. A dynamic battlefield map is constructed based on unified feature vectors, combat units and key facilities serve as nodes, tactical interaction relations serve as edges, the weights of the edges are dynamically calculated by a map attention mechanism according to node features, and self-adaptive modeling of the tactical cooperation relations between combat entities is achieved. And finally, inputting the dynamic battlefield map into a multilayer map attention network for message passing and feature aggregation to obtain node high-order representation fused with global associated information, performing classification prediction on enemy tactical intentions based on the high-order representation, generating tactical intention probability distribution, and realizing adaptive intention reasoning.

The utility model relates to an unmanned aerial vehicle double-launch throwing device which comprises a main body, the top of the main body is fixedly connected with a fixing ribbon, the fixing ribbon is used for fixing the throwing device and an unmanned aerial vehicle body, and two mounting mechanisms are symmetrically arranged at the bottom of the main body; a power module, a light sensation receiver and a mechanical lock catch are arranged in the main body, the light sensation receiver is used for receiving a light source signal sent by the unmanned aerial vehicle, and the light sensation receiver is electrically connected with the mechanical lock catch; one end of the mounting mechanism is movably connected with the side wall of the main body, the other end of the mounting mechanism is fixedly connected with a bolt, the bolt is inserted into the main body, and the bolt is detachably fixed with the mechanical lock catch. According to the invention, two grenades or self-made warheads can be continuously put in the air.

The present application relates to a kind of unfragmented fire extinguishing bomb, comprising: warhead, fire extinguishing combat unit, propelling device, window breaking device and control unit;Warhead and propelling device are located at the opposite ends of fire extinguishing combat unit, and propelling device is set apart from fire extinguishing combat unit;Window breaking device is installed at the end of warhead away from fire extinguishing combat unit;Control unit is arranged in warhead;Fire extinguishing combat unit includes: outer shell, inner shell arranged in outer shell, fire extinguishing agent release device arranged in inner shell;Outer shell is hollow regular cylinder, including: two symmetrically arranged outer shell parts, hinged structure and switch structure;Two outer shell parts are respectively connected with hinged structure, so that two outer shell parts are rotated with hinged structure;Two outer shell parts are respectively connected with switch structure, for controlling the opening and closing of two outer shell parts;Inner shell is hollow cylinder, and a plurality of through holes are arranged on the side wall of inner shell;Fire extinguishing agent release device uses compressed gas explosion type fire extinguishing device.

The application discloses a protection device for inhibiting explosion incidental damage of an active interception combat unit, which comprises a barrier layer for bearing a detonation wave of the active interception combat unit, an H-shaped arc muscle structure arranged at the rear end of the barrier layer, a plurality of ceramic round-taip-shaped protection blocks connected between the barrier layer and a honeycomb plate and having a front end area greater than a rear end area, the height of the ceramic round-taip-shaped protection blocks being greater than the height of the H-shaped arc muscle structure, and the height and density of the ceramic round-taip-shaped protection blocks at the central position being greater than those at the peripheral position, so that ceramic cones can be formed under the action of pressure, the honeycomb plate for dispersing and absorbing impact force, a back plate for supporting the honeycomb plate and connecting an eight-shaped reinforced front end, a plurality of eight-shaped reinforced structures arranged in a central symmetry, the rear end of the eight-shaped reinforced structures being used for being connected with a vehicle body and being inclined outward, so that the front ends of the plurality of eight-shaped reinforced structures are broken laterally under the action of pressure. The application can reduce the tactical index of incidental damage to the loaded vehicle body.

The application provides a multi-target switching device, which comprises a target frame, a target plate, a driving mechanism and a base, the target frame comprises two power edges and two fixed edges; the target plate comprises an upper target plate and a lower target plate; one end of the first fixed edge is hinged to the base, and the other end is hinged to one end of the first power edge; the first fixed edge is arranged in a vertical state, can be tilted backward and fixed back; the second power edge is located in front of the first fixed edge, one end of the second power edge is connected to the driving mechanism and can rotate around the driving mechanism; the two ends of the second fixed edge are respectively hinged to the other ends of the two power edges; the upper target plate is fixedly connected to the second fixed edge, and the lower target plate is fixedly connected to the second power edge; when the two power edges are in a vertical state, the upper target plate and the lower target plate are located in the same plane; a shifting block is arranged on the second power edge. The application can independently realize random switching of the tactical posture of a combat unit and more realistically simulate the tactical action of the combat unit in actual combat.

The application provides a simplified particle swarm weapon target distribution method with priority, and belongs to the field of resource distribution. First, weapon and target information of a combat unit is acquired, and priority of the combat unit to a strike target is calculated. Then, a distribution method is selected according to the priority, if the priority is less than a threshold value, a simplified particle swarm method is adopted, if the priority is greater than the threshold value, weapon distribution is directly performed according to threat degrees of the strike targets in sequence. The application determines the priority of the strike target, so that the strike target with higher threat is preferentially distributed with the weapon, and the threat degree of the combat unit is reduced. The application adopts the simplified particle swarm algorithm, and the convergence time of the algorithm can be shortened, which is of great significance for efficient strike of targets in cooperative air combat.

The invention discloses a multi-anti-ship missile cooperative route planning method based on a particle swarm optimization algorithm, and the method comprises the steps: summarizing a multi-anti-ship missile cooperative route planning problem into a series of 1: 1 combat units, and carrying out the initialization definition of environment parameters; four-point constraints are provided for a series of 1: 1 combat units; aiming at the route planning of the multi-anti-ship missile, constructing a problem model of multi-anti-ship missile collaborative route planning by utilizing four-point constraint in combination with geometric knowledge and rules of the route planning of the anti-ship missile; based on the problem model and in combination with a particle swarm optimization algorithm, the multi-antiship missile collaborative route planning problem with a 1: 1 combat unit as a combat mode is solved; and outputting the collaborative route planning results of all the anti-ship missile 1: 1 combat units to a single standard coordinate system to obtain a complex multi-anti-ship missile collaborative route planning scheme. According to the technical scheme, the problem of complex multi-antiship missile collaborative route planning can be solved.

The application belongs to the field of military unmanned aerial vehicle, and particularly relates to a hand-throwing unmanned aerial vehicle and application thereof, which comprises an unmanned aerial vehicle main body and a combat device, the combat device is detachably arranged at the head end of the unmanned aerial vehicle main body, the combat device comprises a seeker and a combat unit which are electrically connected with each other, the seeker is arranged towards the front of the unmanned aerial vehicle main body, and the seeker is in communication connection with the flight control unit of the unmanned aerial vehicle main body, the unmanned aerial vehicle main body and the combat device are detachably connected with each other, different types of combat units can be replaced to adapt to different combat requirements, the head of the unmanned aerial vehicle main body serves as both a mounting part and a firewall to isolate the combat device, the normal work of the combat device can be ensured, and interference with the unmanned aerial vehicle main body can be avoided.

This application belongs to the field of computer technology and discloses a method, device, equipment, and storage medium for combat control of virtual characters. The method includes: in response to an automatic combat command, acquiring map data and combat units of the game combat scene; the combat units include multiple friendly characters and multiple enemy characters; constructing a quadtree based on the map data and combat units; when any friendly character's target enemy character dies, detecting whether the friendly character has a skill to be released; if so, acquiring the friendly character's current coordinates in the game combat scene and the attack range of the skill to be released; constructing a query region based on the current coordinates and attack range; traversing the quadtree based on the query region to obtain at least one target enemy character; and controlling the friendly character to use the skill to be released on the target enemy character. This application can reduce the computational complexity of target enemy character selection and support smooth combat with hundreds of units on the same screen.

The invention provides a heterogeneous unmanned combat unit cooperative control method and device based on improved multi-agent near-end strategy optimization, and the method comprises the steps: enabling agents with similar functions to share the parameters of a perception coding layer and a situation planning layer through constructing a hierarchical parameter sharing strategy network, so as to achieve the knowledge migration; meanwhile, each agent fuses historical actions of teammates through an independently held communication attention layer to generate a communication context vector so as to understand a collaborative intention, and differentiated actions are output through a role decision head; inputting the global state, the action and the communication context vector into a triple value network system to respectively calculate a joint action advantage and a role inherent advantage; identifying a current task stage through a stage classifier, dynamically generating an advantage fusion coefficient and a strategy cutting parameter, carrying out weighted fusion on two types of advantages, calculating a total loss function, training, and adaptively adjusting each weight along with a training stage, a task stage and role characteristics; therefore, the efficient collaborative decision-making of the heterogeneous intelligent agent in the dynamic task is realized.

The invention discloses an intelligent cooperative game simulation modeling method for a heterogeneous combat unit, and relates to the technical field of military simulation modeling and computer simulation, and the method comprises the following units: an environment construction layer, an intelligent agent decision-making layer, a cooperative game layer and a performance evaluation layer. The problem that a traditional collaborative decision-making method is poor in adaptability is effectively solved, the environment construction layer simulates real-time changes of geography, weather, electromagnetic and enemy environments through a dynamic random process, and the intelligent agent decision-making layer constructs a differentiated deep reinforcement learning model for functional differences of heterogeneous combat units. A priority experience playback mechanism and a TD3 strategy are introduced into an improved DDPG algorithm, so that the utilization efficiency of important experience samples is improved, the problem of over-estimation of a critic network is relieved, the system gets rid of limitation of a traditional preset rule, the dynamic nature and uncertainty of a battlefield can be dynamically responded, and the self-adaptive decision-making capability of a heterogeneous combat unit in complex enemies and environments is enhanced.

The application discloses a ground-air integrated multifunctional fire extinguishing system and belongs to the technical field of fire-fighting equipment. The system comprises a ground vehicle combat unit, an aerial bomb-throwing unit and a high-rise building fixed water spraying unit. The ground vehicle is composed of an ice cannon launching vehicle and a water supply supply vehicle, the ice cannon vehicle adopts a six-legged walking mechanism and a multi-tube launching device, can launch high-density ice bombs or other fire extinguishing media, and is provided with an independent generator and a quick power supply interface, and the two vehicles are backup for each other; the aerial unmanned aerial vehicle or fixed-wing aircraft is hung with a throwable ice bomb cabin to realize high-altitude accurate attack; and the high-rise building is internally provided with a multi-section relay type independent water spraying system. The application effectively solves the fire extinguishing problems of complex fire scenes such as mountains, high-rise buildings and oil and chemical plants through ground-air three-dimensional cooperation, double effects of ice bomb cooling and suffocation, safe redundant power supply and all-terrain adaptability, and has the advantages of high fire extinguishing efficiency, strong reliability and wide application range.

The application discloses a kind of wargame strategy determination method and related products.The scheme, obtain the tactical target corresponding to current battlefield situation information;Based on the tactical target, the action space of multiple combat units is designed respectively, the action set corresponding to each combat unit is obtained, and based on the action set corresponding to each combat unit, the target action of each combat unit is determined;The target action of each combat unit indicates the action in the action set corresponding to each combat unit, corresponding to current battlefield situation information;Based on the target action of each combat unit, wargame strategy is obtained.Compared with the precision of wargame strategy generated by intelligent decision method in prior art is low, the application has obvious advantages.

This invention discloses a tactical simulation and extrapolation method based on heterogeneous computing power collaboration, belonging to the field of tactical simulation and extrapolation technology. The method includes the following steps: First, by constructing a simulation index structure to distinguish between initialized and uninitialized units, newly added combat units are identified during simulation operation, and based on the identification results, these newly added combat units are marked as temporarily added combat units. Second, based on the marked temporarily added combat units, state change data and behavioral command sequences are collected within multiple consecutive simulation frames to construct a behavioral event sequence matrix. Third, a sliding window weighted summation algorithm is used to calculate the behavioral change amount between each frame, and a short-term behavioral change rate index is established on the behavioral event sequence matrix. This invention solves the problem of inaccurate computing power adaptation for temporarily added combat units, realizes dynamic adjustment of heterogeneous computing power resources based on behavioral change rate, and improves simulation response efficiency and timing accuracy.

The application discloses a kind of based on key event detection's wargaming process key battle method mining method and device, comprising: the multi-resolution situation feature abstraction of the wargaming data collected, obtain the battlefield situation feature set of combat unit under uniform dimension;Known key event in wargaming data is extracted based on battlefield situation feature set using weak supervision self-training method, and specific key event set is obtained;Based on battlefield situation feature set and specific key event set, new key event in wargaming data is extracted using new key event identification method based on deep hidden layer feature, and new key event set is obtained by labeling new key event;Each key event in specific key event set and new key event set is combined according to time sequence relationship, forms multiple battle method set, completes key battle method mining.The present application improves the timeliness and accuracy of key battle method mining.

The invention relates to the technical field of tactical decision support, in particular to a dynamic construction method and system for a killing chain based on an action sequence, equipment and a medium, and the method mainly comprises the steps of defining a combat unit model and a killing chain module, defining the action of a combat unit, and constructing the killing chain module. Searching a target action sequence converted from an initial state to a target state; and obtaining the sum of the action cost of the target sequence, and selecting the killing chain with the lowest cost from all the searched feasible action sequences and the corresponding killing chains as a final output result. Through the method, the flexibility and the practicability are high, the action is realized by attaching to the combat unit, different actions can be realized for the heterogeneous combat unit, and the action selection which can be executed by the combat unit can be adjusted when the environment is changed.

The application discloses an air-based intercepting aircraft with a seeker installed at the rear of the flight direction, comprising four cabin sections of a leading-war cabin, a control cabin, a rudder cabin and a guiding cabin; the seeker, a guidance controller, a navigation device, a thermal battery, a rudder, a combat unit and a proximity fuze are installed in the cabin sections; the leading-war cabin, the control cabin, the rudder cabin and the guiding cabin are sequentially connected to form the cabin body structure of the air-based intercepting aircraft; the combat unit and the proximity fuze are installed in the leading-war cabin and are independent cabins; the guidance controller, the navigation device and the thermal battery are installed in the control cabin; the rudder is installed in the rudder cabin and is an independent cabin; and the seeker is installed in the guiding cabin and is an independent cabin. The air-based intercepting aircraft has the active killing capacity, can be used for intercepting the rear attacking target of an airplane, realizes the active protection of the airplane platform and effectively protects the airplane.

The invention provides a simulation battlefield situation awareness method and system, and belongs to the technical field of combat simulation, the method comprises the following steps: loading a basic model of simulation battlefield situation awareness, the basic model comprising a situation map, a combat unit and a target; a task area is created in the situation map, the task area is divided into a plurality of sensing areas, and each combat unit corresponds to one sensing area; monitoring and judging whether the target exists in a sensing area or not according to the position data of the target and the position data of the sensing area corresponding to the combat unit; and if the target is in the sensing area, determining a speed vector and an acceleration vector of target movement by using the position data of the target, determining a predicted trajectory of the target according to the speed vector and the acceleration vector of target movement, and performing intention speculation on the target based on the predicted trajectory of the target, and performing simulation battlefield situation sensing. According to the invention, trajectory prediction and intention speculation of the target are realized, and the comprehensiveness and accuracy of simulation battlefield situation awareness are improved.

The application provides a real-time command control strategy optimization method and device based on multi-agent reinforcement learning, an equipment and a storage medium. A pre-trained cooperative graph network is deployed on the edge equipment of each combat unit, local observation data and its historical sequence are encoded into a low-dimensional local cooperative graph vector, and the original high-dimensional data is replaced as the communication content between units. Combined with an adaptive intention broadcast mechanism, whether to broadcast is dynamically determined according to observation uncertainty and channel state, and on-demand allocation of communication resources is realized. After each unit receives the adjacent cooperative graph vector, the adjacent intention is spatially weighted by a lightweight space-time attention module in the pre-trained local strategy execution network, and the time characteristics of the historical intention of the unit are fused, so that a cooperative and consistent real-time command control instruction is generated without global information convergence.

The invention discloses an energy gathering type front prefabricated fragment warhead structure. The charging top end is designed to be the spherical segment cavity, the fragment box protruding outwards in a certain shape is filled with the prefabricated fragments, the lining is arranged at the spherical segment cavity, and through the material and structure matching design, the fragments cannot converge and collide in the radial direction in the driving process, deformation is small, and a better flight trajectory is achieved; and the two layers of gas closing structures restrain detonation products, so that leakage of the detonation products in gaps of the prefabricated fragments is greatly reduced, the energy utilization rate is increased, and the fragment power is increased.

The invention relates to the technical field of computer simulation, in particular to a CMO-based simulation engine rapid construction method, which comprises the following steps of S1, establishing a high-level combat conceptual model library, wherein a standardized combat conceptual model formed by abstracting and packaging basic combat units and combat actions in the CMO is stored; s2, a battle description interface is provided, a user is allowed to call models in the high-level combat conceptual model library, and a high-level battle scenario is constructed in a declarative or graphical mode. The high-level scenario of the user is automatically converted into a CMO native file package through an automatic scene generator; compared with the prior art, the method has the advantages that the tedious and error-prone manual unit placement and script writing process needing to consume several days and even several weeks in the prior art is replaced, the construction period of the simulation engine is greatly shortened, human errors are reduced due to the standardized process, and the wanted quality and consistency are improved.

The invention relates to the technical field of combat simulation training evaluation, and discloses a hierarchical aggregation combat simulation training evaluation method based on multiple dimensions. The method comprises the following steps: receiving original behavior data streams of combat units in real time by establishing a data connection channel, and extracting space coordinates, time sequences, equipment interaction and tactical action features of the original behavior data streams to construct a feature vector set; and performing multi-round iterative computation on the feature vectors by using a dynamic clustering engine, adaptively terminating iteration by monitoring a grouping stability index, and outputting a hierarchical aggregation unit of a final group. After the feature data of the aggregation units are stored in an assessment data warehouse, the feature data are analyzed and processed by a multi-stage assessment model to generate assessment index data for each aggregation unit, and finally a visual assessment report is formed and pushed to a command terminal. According to the method, automatic, multi-dimensional and systematic efficiency evaluation on the tactical unit dynamically formed in the simulation training is realized.