CN113642237A - Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network - Google Patents
Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network Download PDFInfo
- Publication number
- CN113642237A CN113642237A CN202110916510.3A CN202110916510A CN113642237A CN 113642237 A CN113642237 A CN 113642237A CN 202110916510 A CN202110916510 A CN 202110916510A CN 113642237 A CN113642237 A CN 113642237A
- Authority
- CN
- China
- Prior art keywords
- threat
- battlefield
- unit
- underwater
- data
- 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.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000000007 visual effect Effects 0.000 title claims abstract description 17
- 238000012800 visualization Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 6
- 230000001364 causal effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005094 computer simulation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 241000209094 Oryza Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001960 triggered effect Effects 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an underwater battlefield threat assessment and visual simulation system and method based on a Bayesian network, belonging to the field of underwater threat assessment. The underwater threat assessment module is based on a Bayesian network and carries out structural design and algorithm improvement aiming at the characteristics of an underwater battlefield; the threat assessment visualization simulation module displays a simulation three-dimensional model of a battlefield environment and a combat unit, and displays threat degree information obtained by the threat assessment module in a specific threat information display interface. The threat assessment module performs corresponding preprocessing and characteristic analysis operation on the underwater battlefield data by acquiring the underwater battlefield data, and obtains threat degree information of a combat unit by utilizing an assessment algorithm. And the visual simulation module displays the threat information. The invention provides threat situation analysis and visual display for underwater battlefields for underwater operation units and related personnel.
Description
Technical Field
The invention relates to the field of underwater threat assessment, in particular to an underwater battlefield threat assessment and visual simulation system and method based on a Bayesian network. The method is mainly suitable for information fusion and threat assessment of underwater combat targets and corresponding visual display.
Background
In the world today, underwater operations have become an extremely important part of the marine battlefield. The underwater battlefield environment is complex and changeable, the underwater communication condition is harsh, the concealment of the underwater operation unit is strong, the underwater operation unit is difficult to detect, and the underwater operation weapons are various, so that the underwater operation attack and defense are very difficult, and the threat from the underwater battlefield is more huge compared with the threat from the water surface battlefield. In order to deal with threats from an underwater battlefield, it is necessary to develop a corresponding underwater battlefield threat assessment technology, identify potential underwater enemy targets, judge the fighting intentions of enemies and assess the threat levels of the targets, and provide the basis of early warning and decision planning for the fighting units of our parties. The existing underwater threat assessment technology is mainly divided into a numerical model-based calculation method and an artificial intelligence technology-based analysis method. The calculation method based on the numerical model mainly depends on establishing a specific mathematical model, utilizes the mathematical model to perform matrix calculation on relevant information values of a target, and ranks threat levels. The analysis method based on the artificial intelligence technology mainly obtains approximate simulation of a real model by establishing an artificial neural network and training the neural network by utilizing a large amount of combat data, and the method usually depends on a large amount of training data, and the obtained evaluation result is difficult to mathematically explain, and has other problems of difficult training, overfitting and the like.
In addition, for the evaluation result of the underwater battlefield threat evaluation, the prior art lacks a visual display mode, which is not beneficial to the mastering of the battlefield threat situation, the threat distribution and the movement of the operation unit by technical users.
Therefore, the prior art has the following problems:
(1) the numerical model-based calculation method lacks subjective judgment and is difficult to generalize to other scenes.
(2) The evaluation result obtained by the analysis method based on the artificial intelligence technology is difficult to be mathematically explained, and other problems such as difficult training, overfitting and the like exist.
(3) And the visual display mode of the threat in the underwater battlefield is lacked.
Disclosure of Invention
In order to solve the problems, the invention provides an underwater battlefield threat assessment and visual simulation system and method based on a Bayesian network, which generate required combat unit instance data through a three-dimensional battlefield simulation program, or receive combat unit data from the real world, evaluate the threat degree of a combat unit by using an underwater threat assessment model in software, and display the evaluation result of the threat degree on a visual interface to form a set of software for simulating the threat in underwater combat.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the invention provides an underwater battlefield threat assessment and visualization system based on a Bayesian network, which comprises an underwater battlefield threat assessment module and a threat assessment visualization simulation module; the underwater battlefield threat assessment module acquires battlefield data, preprocesses the acquired battlefield data, extracts threat elements and then assesses the extracted threat elements; the threat assessment visual simulation module is used for displaying the three-dimensional models of the battlefield environment and the battlefield operation units and visually displaying the assessment results from the threat assessment module.
Preferably, the underwater battlefield threat assessment module specifically comprises:
a data acquisition unit for acquiring battlefield data from the real world;
the data preprocessing unit is used for performing feature screening, redundant data elimination and format conversion operation on the acquired battlefield data;
the element extraction unit is used for converting the preprocessed data into underwater battlefield related threat element information;
and the underwater battlefield threat model unit based on the Bayesian network is used for evaluating and deducing the threat degree of the obtained battlefield data source combat unit according to the battlefield threat element information and outputting an evaluation result.
Preferably, the threat assessment visualization simulation module specifically includes:
the three-dimensional model display unit is used for displaying the simulated battlefield environment and the three-dimensional model of the battlefield combat unit on the display interface;
the threat information display unit is used for displaying the threat degree evaluation result of the battlefield target in an information panel of a display interface, and the evaluation result is from the threat degree evaluation result output by the underwater battlefield threat evaluation module;
and the battlefield combat unit generating unit is used for simulating and generating battlefield combat unit examples required in simulation operation.
Preferably, the threat elements are divided into three parts, including environmental threats, target space threats and target combat threats.
Preferably, the evaluation result of the underwater battlefield threat evaluation module is a target overall threat, and the target overall threat is obtained by jointly evaluating the results of the comprehensive environment threat, the target space threat and the target battle threat.
Preferably, the environmental threats in the threat elements include information related to sea state environment and underwater acoustic communication environment; the target space threat comprises the related information of the three-dimensional coordinate, the movement speed and the movement direction of the target; the target combat threat comprises the physical attributes of the targets, the types and the number of carried weapons and the related information of the target combat state.
Preferably, the data acquisition unit comprises a battlefield data acquisition interface and a battlefield combat unit sample generation unit. A battlefield data acquisition interface acquires information such as weather, sea conditions, unit coordinates of enemies and the like captured by a battlefield front-end sensor through a network; the battlefield combat unit sample generating unit generates battlefield combat unit sample data through preset parameters and templates, and the generated combat sample has the same functions and structures as the related data captured by the front end.
Preferably, the data preprocessing unit converts battlefield data captured from the front end into data with a specific format and a specific structure through specific screening and modification rules, so as to facilitate reading and processing of a subsequent threat assessment module. The pre-processing rules adopted by the method include but are not limited to removing repeated data, removing deviated data, adjusting data precision, converting data formats and the like.
Preferably, the element extraction unit extracts the preprocessed battlefield data into battlefield element information for obtaining high-level battlefield information. The element extraction method includes but is not limited to: obtaining group attributes of the target by using a clustering algorithm, such as a combat center, group movement speed and direction lamps; the combat capability of the target in a specific state is obtained by using an empirical formula, for example, firepower threat and combat capability of the target are calculated according to the empirical formula by carrying weapons and quantity by the target.
Preferably, the basic structure of the Bayesian network-based underwater battlefield threat assessment unit takes the form of a Bayesian network. Firstly, establishing a topological graph of a threat model, obtaining various battlefield elements participating in threat assessment through pre-analysis, converting the battlefield elements into random variables, and establishing a corresponding Bayesian network topological graph according to the correlation and causal relationship among the elements; secondly, establishing a computer model of the threat model, using a computer program to realize the concrete realization of the Bayesian network model through a Bayesian estimation algorithm, exposing the input and output of the model, and providing data reading and result presenting functions; and finally, inputting the extracted real-time battlefield element information into a Bayesian network model, respectively calculating the threat degree of the target from three levels of environmental threat, target space threat and target combat threat by using a Bayesian evaluation algorithm, and finally calculating the total threat degree of the target through the three partial threat degrees.
Preferably, the Bayesian estimation algorithm is used by the Bayesian network-based underwater battlefield threat estimation unit, each Bayesian network node X is regarded as an information propagator and an information receiver, and each node continuously transmits the information to the node (parent node P) related to the node itselfXAnd child node CX) And propagating information, receiving information from nodes related to the nodes, and updating belief values BEL (X) of the nodes to the current network state by using the received information, wherein BEL (X) is the approximation of marginal condition probability P (X | E) of the nodes X in the network, and E represents the known node information in the current Bayesian network, namely threat element information input into the Bayesian network model. And continuously exchanging information among the nodes until the respective beliefs of the nodes converge to the respective marginal conditional probabilities, and keeping the stability unchanged. In addition, the Bayesian evaluation algorithm is used for correcting and adjusting the calculation of the belief value at the current moment by introducing the related information of the belief value at the past moment, so that the continuity of judgment of the threat model is maintained on the time level.
Preferably, the three-dimensional model display unit is designed and developed based on a Unity3D engine, and includes a plurality of groups of terrain three-dimensional models, ocean three-dimensional models and combat unit three-dimensional models.
Preferably, the threat information display unit includes an information display part for the battlefield environment, an information display part for the specific attributes of the combat units, and an information display part for the evaluation results obtained by the threat evaluation model.
The invention also provides an underwater battlefield threat assessment and visual simulation method based on the Bayesian network for the system, which comprises the following steps:
the method comprises the following steps: generating a preset three-dimensional battlefield environment by a threat assessment visualization simulation module, and rendering a three-dimensional model of the battlefield environment on a display interface;
step two: selecting a combat example generated by simulation or a combat example generated by underwater battlefield data in the real world according to a use scene; if the battle instance generated by simulation is selected, a battle field battle unit sample generating unit of the data acquisition unit randomly extracts data of a plurality of battle unit samples from preset parameters and templates; if a combat instance generated by the real world underwater battlefield data is selected, reading the real world underwater battlefield data by using the data acquisition interface;
the method comprises the following steps of utilizing a data preprocessing unit to carry out feature screening, redundant data elimination and format conversion on underwater battlefield data, creating a corresponding battle unit example by a battle field battle unit generating unit, giving a corresponding attribute value to the battle unit example, and rendering a corresponding three-dimensional model on a display interface;
step three: the method comprises the steps of loading a structure file and a parameter data file for an underwater battlefield threat model unit based on a Bayesian network, setting a Bayesian network structure of the underwater battlefield threat model based on the Bayesian network, and setting node parameters in the Bayesian network.
Step four: the underwater battlefield threat assessment module periodically scans all the combat unit examples to acquire the data of the combat unit examples and simultaneously acquire the relevant data of the battlefield environment; the underwater battlefield threat assessment module analyzes and extracts threat elements from the scanned and acquired data, sets state values of corresponding nodes in the Bayesian network according to the obtained threat element information, and meanwhile, arranges and deduces the threat element information to obtain threat degree values of each combat unit instance in the current state;
step five: the threat assessment visualization simulation module respectively displays threat degree assessment results obtained by the underwater battlefield threat assessment module in the threat information display panels of the corresponding combat unit examples, so that a user can visually know the threat degree of the combat unit examples.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method analyzes the threat elements of the underwater battle scene, utilizes the Bayesian network to model the threat model, effectively expresses and combines the correlation among the threat elements, and simulates the threat degree of an approximate target in a probability form; on the basis of basic mathematical analysis, empirical knowledge is introduced for reasoning, and the evaluation capability of the cognitive reasoning angle is improved.
(2) The method uses the node probability value output by the Bayesian network model as the threat level value of a target, solves the node probability value, firstly inputs battlefield data and combat unit data into the Bayesian network, and then evaluates the battlefield data and the combat unit data by a Bayesian network derivation algorithm. The probability value reflects the threat degree of the target, and the evaluation result is an accurate probability value which can be mathematically interpreted. The building of the Bayesian network can be automatically carried out by codes, and the derivation operation speed of the Bayesian network is fast enough, so that the threat assessment can be carried out on the target in real time.
(3) According to the invention, a specific Bayesian network algorithm is used for building and reasoning operation on the Bayesian network model, so that the steps of building the model are greatly simplified, and the realization of automatically adjusting the network structure by modifying the json structure file is realized, so that the model is easy to modify and transplant; the time required by model reasoning is reduced, threat assessment can be carried out on a single combat unit within 20ms, and a corresponding threat degree value is returned, so that the timeliness and the rapidity of the threat assessment are ensured.
(4) The method and the system utilize the threat assessment visual simulation software to display the result of the underwater battlefield threat assessment, increase the intuition of the assessment result and facilitate the fighter to rapidly master the battlefield threat situation from visual information.
Drawings
FIG. 1 is a block diagram of an underwater threat assessment model module in the present invention.
Fig. 2 is a block diagram of a bayesian network in the underwater threat assessment model unit based on the bayesian network according to the present invention.
Fig. 3 and 4 are real-time operation interfaces of the threat assessment visualization simulation software in the invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention provides an underwater battlefield threat assessment and visualization system based on a Bayesian network, which comprises an underwater battlefield threat assessment module and a threat assessment visualization simulation module; the underwater battlefield threat assessment module acquires battlefield data, preprocesses the acquired battlefield data, extracts threat elements and then assesses the extracted threat elements; the threat assessment visual simulation module is used for displaying the three-dimensional models of the battlefield environment and the battlefield operation units and visually displaying the assessment results from the threat assessment module. The underwater battlefield threat assessment module specifically comprises: the system comprises a data acquisition unit, a data preprocessing unit, an element extraction unit and an underwater battlefield threat model unit based on a Bayesian network.
In fig. 1, the data acquisition unit provides the system with raw battlefield data; in an embodiment of the invention, the data acquisition unit includes a battlefield data acquisition interface and a battlefield combat unit sample generation unit. A battlefield data acquisition interface acquires information such as weather, sea conditions, unit coordinates of enemies and the like captured by a battlefield front-end sensor through a network; the battlefield combat unit sample generating unit generates battlefield combat unit sample data through preset parameters and templates, and the generated combat sample has the same functions and structures as the related data captured by the front end. In one embodiment of the present invention, the data acquisition unit reads real world battlefield data or battlefield data generated by customizing a data object format defined inside a program through a specific API interface.
The data preprocessing unit performs operations such as screening, redundant data elimination, format conversion and the like on the original data. In an embodiment of the present invention, the data preprocessing unit converts battlefield data captured from the front end into data having a specific format and a specific structure through specific screening and modification rules, so as to facilitate reading and processing of a subsequent threat assessment model module. The pre-processing rules adopted by the method include but are not limited to removing repeated data, removing deviated data, adjusting data precision, converting data formats and the like.
The element extraction unit converts the preprocessed data into underwater battlefield related threat element information by using experience knowledge; specifically, the element extraction unit extracts the preprocessed battlefield data into battlefield element information for obtaining high-level battlefield information. The element extraction method includes but is not limited to: obtaining group attributes of the target by using a clustering algorithm, such as a combat center, group movement speed and direction lamps; the combat capability of the target in a specific state is obtained by using an empirical formula, for example, firepower threat and combat capability of the target are calculated according to the empirical formula by carrying weapons and quantity by the target.
The underwater battlefield threat assessment model unit based on the Bayesian network calculates the threat element information, so as to obtain the threat degree information of the battlefield combat unit corresponding to the data source. The Bayesian network based underwater battlefield threat assessment model unit adopts a Bayesian network structure, and the structure diagram of the Bayesian network structure is shown in FIG. 2. Firstly, establishing a topological graph of a threat model, obtaining various battlefield elements participating in threat assessment through pre-analysis, converting the battlefield elements into random variables, and establishing a corresponding Bayesian network topological graph according to the correlation and causal relationship among the elements; secondly, establishing a computer model of the threat model, using a computer program to realize the concrete realization of the Bayesian network model through a Bayesian estimation algorithm, exposing the input and output of the model, and providing data reading and result presenting functions; and finally, inputting the extracted real-time battlefield element information into a Bayesian network model, respectively calculating the threat degree of the target from three levels of environmental threat, target space threat and target combat threat by using a Bayesian evaluation algorithm, and finally calculating the total threat degree of the target through the three partial threat degrees.
Preferably, the Bayesian estimation algorithm is used by the Bayesian network-based underwater battlefield threat estimation unit, each Bayesian network node X is regarded as an information propagator and an information receiver, and each node does not pass through the Bayesian network node XTo a node associated with itself (parent node P)XAnd child node Cx) And propagating information, receiving information from nodes related to the nodes, and updating belief values BEL (X) of the nodes to the current network state by using the received information, wherein BEL (X) is the approximation of marginal condition probability P (X | E) of the nodes X in the network, and E represents the known node information in the current Bayesian network, namely threat element information input into the Bayesian network model. And continuously exchanging information among the nodes until the respective beliefs of the nodes converge to the respective marginal conditional probabilities, and keeping the stability unchanged. In addition, the Bayesian evaluation algorithm is used for correcting and adjusting the calculation of the belief value at the current moment by introducing the related information of the belief value at the past moment, so that the continuity of judgment of the threat model is maintained on the time level.
The threat assessment visualization simulation software module specifically comprises: the system comprises a three-dimensional model display unit, a threat information display unit and a battlefield combat unit generation unit.
In the threat assessment visualization simulation software module shown in fig. 3 and 4, the three-dimensional model display unit is used for displaying the simulated three-dimensional models of the battlefield environment and the battlefield combat unit on the system display interface; the threat information display unit is used for displaying the threat degree evaluation result of the battlefield target in an information panel of the display interface, and the evaluation result is from the threat degree evaluation result output by the underwater battlefield threat evaluation module; and the battlefield combat unit generating unit is used for simulating and generating battlefield combat unit examples required in simulation operation.
In an embodiment of the present invention, the three-dimensional model used in the three-dimensional model display unit includes: a submarine three-dimensional model, an ocean three-dimensional model and an island three-dimensional model; the information displayed by the threat information display unit comprises: the name, coordinates, depth, distance, course, underwater displacement, ship length, ship width, draught, voyage, maximum navigational speed, threat degree presented by the operational unit and the like of the operational unit; the preset combat unit data utilized by the battlefield combat unit generating unit comes from related military encyclopedia guidelines, and the basic data of the preset combat unit data comprises information of underwater displacement, ship length, ship width, draught, range, maximum speed, carried weapons, electronic support systems, radars, sonars and the like of the combat unit.
As shown in fig. 3 and 4, the underwater battlefield threat assessment and visualization simulation method based on the bayesian network of the invention comprises the following steps:
the method comprises the following steps: generating a preset three-dimensional battlefield environment by a threat assessment visualization simulation module, and rendering a three-dimensional model of the battlefield environment on a display interface; wherein the three-dimensional model comprises the sea, the island and the like.
Step two: selecting a combat example generated by simulation or a combat example generated by underwater battlefield data in the real world according to a use scene; if the battle instance generated by simulation is selected, a battle field battle unit sample generating unit of the data acquisition unit randomly extracts data of a plurality of battle unit samples from preset parameters and templates; if a combat instance generated by the real world underwater battlefield data is selected, reading the real world underwater battlefield data by using the data acquisition interface; if a combat instance generated by the real world underwater battlefield data is selected, reading the real world underwater battlefield data by using the data acquisition interface;
the method comprises the following steps of utilizing a data preprocessing unit to carry out feature screening, redundant data elimination and format conversion on underwater battlefield data, creating a corresponding battle unit example by a battle field battle unit generating unit, giving a corresponding attribute value to the battle unit example, and rendering a corresponding three-dimensional model on a display interface;
step three: and establishing a corresponding Bayesian network-based underwater threat assessment model according to the Bayesian network structure shown in FIG. 2. Loading a structure file and a parameter data file by an underwater battlefield threat model unit based on a Bayesian network, setting a Bayesian network structure of the underwater battlefield threat model based on the Bayesian network, and setting node parameters in the Bayesian network;
step four: the underwater battlefield threat assessment module periodically scans all the combat unit examples to acquire the data of the combat unit examples and simultaneously acquire the relevant data of the battlefield environment; the underwater battlefield threat assessment module analyzes and extracts threat elements from the scanned and acquired data, sets state values of corresponding nodes in the Bayesian network according to the obtained threat element information, and meanwhile, arranges and deduces the threat element information to obtain threat degree values of each combat unit instance in the current state;
step five: the threat assessment visualization simulation module respectively displays threat degree assessment results obtained by the underwater battlefield threat assessment module in the threat information display panels of the corresponding combat unit examples, so that a user can visually know the threat degree of the combat unit examples.
In all the steps, the threat assessment visualization simulation module also adopts a Unity3D engine to load the three-dimensional model and manage the display of the combat unit.
In the second step described above, in the data generation unit, the generation format of the fighting unit is represented by json key-value pairs shown in table 1 below.
TABLE 1 combat Unit samples
| Key with a key body | Value of |
| Name of unit of war | Stage "209 |
| Type of unit of war | Submarine |
| Underwater displacement (ton) | 1185 |
| Warship length (rice) | 55.9 |
| Warship width (rice) | 6.3 |
| Draft (Rice) | 5.5 |
| Maximum navigational speed (festival) | 21.5 |
| Voyage (mile) | 7500 |
| Missile (missile) | 'harpoon' anti-ship missile |
| Torpedo | 533-millimeter-caliber proud torpedo |
| Mine | Torpedo launching tube |
| Bait for angling | C303 type noise jamming/bait system |
| Radar | Thomson-CSF (particle swarm optimization-CSF) 'Carlipsol' II/III water surface search radar |
| Sonar | CSU 83-90(DBQS-21) sonar system |
| Support system | Argo electronic support system |
In the third step, the structure of the established bayesian network is defined by two files, namely nodes. The node names and the value spaces of the nodes in the Bayesian network are defined in node. In addition, parameters of the bayesian network include prior probabilities and conditional probabilities of the nodes, wherein the prior probabilities are stored in a prior _ prob.json file, the prior probabilities of the values of each node are set, the conditional probabilities are stored in a { node name }. csv file under a BN _ tables/folder, and the conditional probabilities corresponding to value combinations of parent nodes and child nodes are set.
In the fourth step, the threat assessment model scans all the combat units on the battlefield in the program, wherein the scanning period T is 1s, and during the scanning process,
step 4.1: firstly, preprocessing the data of a combat unit through a data preprocessing unit, screening out relevant data required by a model, and converting the relevant data into a data format which can be read by the model, such as correcting the speed of the model according to the coordinate change of a target, or updating the combat state of the target and the like;
step 4.2: and then, converting the preprocessed data into specific threat assessment reference elements by using empirical knowledge, wherein the step is mainly to analyze and summarize some battlefield data according to specific combat rules and expert knowledge. For example, according to the coordinates of the target, other enemy combat units within a certain range are analyzed, the number of surrounding enemy units is counted, and according to the distribution and motion rules of the units, the overall characteristics of the combat group, such as formation form, combat trends and other factors, are further extracted.
Step 4.3: after the threat assessment reference elements are extracted, the Bayesian network model assigns the values of the corresponding elements to the corresponding element nodes, and then the threat assessment operation is carried out on the operation unit by utilizing a Bayesian network assessment algorithm. The input data is recorded as evidence E, the obtained THREAT assessment result is recorded as THREAT, and the calculation process of the THREAT assessment is the process of obtaining the conditional probability P (THREAT | E). In the calculation process, three THREAT values of an environment THREAT, a target space THREAT and a target combat THREAT are calculated respectively through corresponding battlefield THREAT elements, and then the three THREATs are subjected to further THREAT assessment operation through a Bayesian network model to obtain a target overall THREAT, namely the THREAT. The obtained target overall threat is a threat assessment result which is a conditional probability value of three threat assessment levels (high, medium and low) under the condition of the known evidence E, and finally, the threat assessment result with the larger probability value is taken as a final threat assessment result of a warfare unit.
In the fifth step, the threat assessment model based on the bayesian network stores the threat degree of the operation unit obtained by assessment in the data of the operation unit instance, and the threat assessment visualization simulation module displays the threat degree of the operation unit in the threat information panel in real time. This process updates the display of threat levels in an event-triggered manner. When the threat degree value is changed, a change event signal is sent out, the threat information display unit captures the signal, and when the signal is received, the updated threat degree is read, and the updated information is displayed.
To further illustrate the feasibility of the present invention, the present embodiment performs a simulation experiment of the threat assessment of an underwater battlefield, first, a data generating unit is used to generate a plurality of specific submarine unit instances, and related data of the submarine is set, so that the submarine moves on the battlefield shown in the program. And then constructing an underwater threat assessment model based on the Bayesian network, periodically scanning submarine units on a battlefield, performing threat assessment on the obtained submarine real-time data, and returning the corresponding threat degree. After receiving the signal of changing the threat degree, the threat information display unit updates the real-time threat degree information on a program interface, and can look up more specific related information by clicking the corresponding submarine unit.
The foregoing lists merely illustrate specific embodiments of the invention. It is obvious that the invention is not limited to the above embodiments, but that many variations are possible. All modifications which can be derived or suggested by a person skilled in the art from the disclosure of the present invention are to be considered within the scope of the invention.
Claims (8)
1. An underwater battlefield threat assessment and visualization system based on a Bayesian network is characterized by comprising an underwater battlefield threat assessment module and a threat assessment visualization simulation module; the underwater battlefield threat assessment module acquires battlefield data, preprocesses the acquired battlefield data, extracts threat elements and then assesses the extracted threat elements; the threat assessment visual simulation module is used for displaying the three-dimensional models of the battlefield environment and the battlefield operation units and visually displaying the assessment results from the threat assessment module.
2. The bayesian network-based underwater battlefield threat assessment and visualization system as claimed in claim 1, wherein said underwater battlefield threat assessment module specifically comprises:
a data acquisition unit for acquiring battlefield data from the real world;
the data preprocessing unit is used for performing feature screening, redundant data elimination and format conversion operation on the acquired battlefield data;
the element extraction unit is used for converting the preprocessed data into underwater battlefield related threat element information;
and the underwater battlefield threat model unit based on the Bayesian network is used for evaluating and deducing the threat degree of the obtained battlefield data source combat unit according to the battlefield threat element information and outputting an evaluation result.
3. The Bayesian network-based underwater battlefield threat assessment and visualization system as recited in claim 2, wherein the data acquisition unit comprises a battlefield data acquisition interface and a battlefield combat unit sample generation unit; a battlefield data acquisition interface acquires weather, sea conditions and unit coordinate information of an enemy captured by a battlefield front-end sensor through a network; the battlefield combat unit sample generating unit generates battlefield combat unit sample data through preset parameters and templates, and the generated combat sample has the same functions and structures as the related data captured by the front end.
4. The bayesian-network-based underwater battlefield threat assessment and visualization system according to claim 2, wherein the basic structure of said bayesian-network-based underwater battlefield threat assessment unit takes the form of a bayesian network; firstly, establishing a topological graph of a threat model, obtaining various battlefield elements participating in threat assessment through pre-analysis, converting the battlefield elements into random variables, and establishing a corresponding Bayesian network topological graph according to the correlation and causal relationship among the elements; secondly, establishing a computer model of the threat model, using a computer program to realize the concrete realization of the Bayesian network model through a Bayesian estimation algorithm, exposing the input and output of the model, and providing data reading and result presenting functions; and finally, inputting the extracted real-time battlefield element information into a Bayesian network model, respectively calculating the threat degree of the target from three levels of environmental threat, target space threat and target combat threat by using a Bayesian evaluation algorithm, and finally calculating the total threat degree of the target through the three partial threat degrees.
5. The Bayesian network-based underwater battlefield threat assessment and visualization system as recited in claim 4, wherein a Bayesian assessment algorithm used by the Bayesian network-based underwater battlefield threat assessment unit is specifically: each Bayesian network node X is regarded as an information propagator and an information receiver, and each node is communicated with a parent node P continuouslyxAnd child node CxPropagating the information and from the parent node PxAnd child node CxReceiving information, and updating a belief value BEL (X) of the node X to the current network state by using the received information, wherein the BEL (X) is the marginal of the node X in the networkAn approximation of the conditional probability P (X | E), where E represents known node information in the current bayesian network, i.e. threat element information input into the bayesian network model; continuously exchanging information among the nodes until the respective beliefs of the nodes converge to the respective marginal conditional probabilities, and keeping the stability unchanged; in addition, the Bayesian evaluation algorithm is used for correcting and adjusting the calculation of the belief value at the current moment by introducing the related information of the belief value at the past moment, so that the continuity of judgment of the threat model is maintained on the time level.
6. The Bayesian network-based underwater battlefield threat assessment and visualization system according to claim 4, wherein the threat degrees of the targets are respectively calculated from three levels of environmental threats, target space threats and target combat threats, and the total threat degree of the targets is finally calculated through three partial threat degrees, specifically:
after THREAT assessment reference elements are extracted, the Bayesian network model assigns values of the corresponding elements to corresponding element nodes, then THREAT assessment operation is carried out on the combat unit by using a Bayesian network assessment algorithm, the input data is recorded as evidence E, the obtained THREAT assessment result is recorded as THREAT, and the calculation process of THREAT assessment is the process of obtaining a conditional probability P (THREAT | E); in the calculation process, three THREAT values of an environment THREAT, a target space THREAT and a target combat THREAT are respectively calculated through corresponding battlefield THREAT elements, then THREAT assessment operation is carried out on the three THREATs through a Bayesian network model to obtain a target overall THREAT, the obtained target overall THREAT is a THREAT assessment result THREAT which is a conditional probability value of the assessment levels of the three THREATs under the condition of known evidence E, and finally, one with a larger probability value is taken as a final combat unit THREAT assessment result.
7. The Bayesian network-based underwater battlefield threat assessment and visualization system according to any one of claims 1-6, wherein the threat assessment visualization simulation module specifically comprises:
the three-dimensional model display unit is used for displaying the simulated battlefield environment and the three-dimensional model of the battlefield combat unit on the display interface;
the threat information display unit is used for displaying the threat degree evaluation result of the battlefield target in an information panel of a display interface, and the evaluation result is from the threat degree evaluation result output by the underwater battlefield threat evaluation module;
and the battlefield combat unit generating unit is used for simulating and generating battlefield combat unit examples required in simulation operation.
8. An underwater battlefield threat assessment and visualization simulation method based on the Bayesian network based on the system of claim 7 is characterized by comprising the following steps:
the method comprises the following steps: generating a preset three-dimensional battlefield environment by a threat assessment visualization simulation module, and rendering a three-dimensional model of the battlefield environment on a display interface;
step two: selecting a combat example generated by simulation or a combat example generated by underwater battlefield data in the real world according to a use scene; if the battle instance generated by simulation is selected, a battle field battle unit sample generating unit of the data acquisition unit randomly extracts data of a plurality of battle unit samples from preset parameters and templates; if a combat instance generated by the real world underwater battlefield data is selected, reading the real world underwater battlefield data by using the data acquisition interface;
the method comprises the following steps of utilizing a data preprocessing unit to carry out feature screening, redundant data elimination and format conversion on underwater battlefield data, creating a corresponding battle unit example by a battle field battle unit generating unit, giving a corresponding attribute value to the battle unit example, and rendering a corresponding three-dimensional model on a display interface;
step three: the method comprises the steps of loading a structure file and a parameter data file for an underwater battlefield threat model unit based on a Bayesian network, setting a Bayesian network structure of the underwater battlefield threat model based on the Bayesian network, and setting node parameters in the Bayesian network.
Step four: the underwater battlefield threat assessment module periodically scans all the combat unit examples to acquire the data of the combat unit examples and simultaneously acquire the relevant data of the battlefield environment; the underwater battlefield threat assessment module analyzes and extracts threat elements from the scanned and acquired data, sets state values of corresponding nodes in the Bayesian network according to the obtained threat element information, and meanwhile, arranges and deduces the threat element information to obtain threat degree values of each combat unit instance in the current state;
step five: the threat assessment visualization simulation module respectively displays threat degree assessment results obtained by the underwater battlefield threat assessment module in the threat information display panels of the corresponding combat unit examples, so that a user can visually know the threat degree of the combat unit examples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110916510.3A CN113642237B (en) | 2021-08-11 | 2021-08-11 | Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110916510.3A CN113642237B (en) | 2021-08-11 | 2021-08-11 | Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642237A true CN113642237A (en) | 2021-11-12 |
| CN113642237B CN113642237B (en) | 2024-03-26 |
Family
ID=78420646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110916510.3A Active CN113642237B (en) | 2021-08-11 | 2021-08-11 | Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642237B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035225A (en) * | 2022-06-05 | 2022-09-09 | 西北工业大学 | Battlefield threat assessment warning method based on OSG |
| CN117521424A (en) * | 2024-01-05 | 2024-02-06 | 中国电子科技集团公司第十五研究所 | Simulation training scene generation method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN109711087A (en) * | 2019-01-14 | 2019-05-03 | 哈尔滨工程大学 | A kind of UUV dynamic threats method for situation assessment |
-
2021
- 2021-08-11 CN CN202110916510.3A patent/CN113642237B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN109711087A (en) * | 2019-01-14 | 2019-05-03 | 哈尔滨工程大学 | A kind of UUV dynamic threats method for situation assessment |
Non-Patent Citations (1)
| Title |
|---|
| JUDEA PEARL: "probabilistic reasoning in Intelligent systems", MORGAN KAUFMANN , pages: 4 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035225A (en) * | 2022-06-05 | 2022-09-09 | 西北工业大学 | Battlefield threat assessment warning method based on OSG |
| CN115035225B (en) * | 2022-06-05 | 2024-02-23 | 西北工业大学 | Battlefield threat assessment warning method based on OSG |
| CN117521424A (en) * | 2024-01-05 | 2024-02-06 | 中国电子科技集团公司第十五研究所 | Simulation training scene generation method and device |
| CN117521424B (en) * | 2024-01-05 | 2024-04-09 | 中国电子科技集团公司第十五研究所 | Simulation training scene generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642237B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112668175B (en) | Military simulation method and system based on dynamic situation driving | |
| CN113642237B (en) | Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network | |
| CN109711087B (en) | UUV dynamic threat situation assessment method | |
| Seo et al. | Measurement of effectiveness for an anti-torpedo combat system using a discrete event systems specification-based underwater warfare simulator | |
| CN109960148B (en) | Autonomy evaluation method and system for intelligent unmanned system | |
| CN112749761A (en) | Enemy combat intention identification method and system based on attention mechanism and recurrent neural network | |
| Liang | An approximate reasoning model for situation and threat assessment | |
| CN117214904A (en) | Intelligent fish identification monitoring method and system based on multi-sensor data | |
| Wang et al. | Learning embedding features based on multisense-scaled attention architecture to improve the predictive performance of air combat intention recognition | |
| CN116486244A (en) | Underwater target detection method based on detail enhancement | |
| CN115456090A (en) | Knowledge inference engine-based multi-level composite intent prediction method for fighter | |
| CN114818113A (en) | Underwater target detection and identification simulation system and method | |
| RU2689813C1 (en) | Simulation method of multi-stage process of development and application of weapon system | |
| Li et al. | Situation assessment approach based on a hierarchic multi-timescale Bayesian network | |
| Smith et al. | A fuzzy logic resource manager and underlying data mining techniques | |
| CN115374392B (en) | Method for acquiring object parameters of target event, electronic equipment and storage medium | |
| Couture et al. | Sensor data fusion of radar, ESM, IFF, and data LINK of the Canadian patrol frigate and the data alignment issues | |
| CN112257627B (en) | Overwater image data set expansion method | |
| Smith et al. | Optimal Allocation of Distributed Resources Using Fuzzy Logic and a Genetic Algorithm | |
| Wang et al. | Research on Modeling and Application of Anti-Submarine Decision-Aided System Based on Neural Network | |
| Wilson | Analysis of tracking and identification characteristics of diverse systems and data sources for sensor fusion | |
| CN113222797A (en) | Combat method and system | |
| CN115563861A (en) | Comprehensive performance evaluation and optimization method for radar seeker intelligent tracking algorithm | |
| Chang et al. | Application of Bayes nets in sensor fusion | |
| CN117993173A (en) | Marine combat distribution interactive simulation system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |