CN116187207B - Land battle equipment system simulation evaluation method, device and storage medium - Google Patents
Land battle equipment system simulation evaluation method, device and storage medium Download PDFInfo
- Publication number
- CN116187207B CN116187207B CN202310451360.2A CN202310451360A CN116187207B CN 116187207 B CN116187207 B CN 116187207B CN 202310451360 A CN202310451360 A CN 202310451360A CN 116187207 B CN116187207 B CN 116187207B
- Authority
- CN
- China
- Prior art keywords
- data
- prediction model
- index
- land
- model
- 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.)
- Active
Links
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
A land battle equipment system simulation evaluation method, a device and a storage medium, wherein the method comprises the following steps: determining indexes related to a land warfare equipment system according to fight thinking, acquiring simulation data according to efficiency values to be calculated according to thinking, and constructing an efficiency prediction model by using the simulation data; training the efficiency prediction model by using the simulation data to obtain an optimal efficiency prediction model; and performing performance evaluation on the land combat equipment system within the index range by using the trained performance prediction model. According to the invention, the machine learning model is used for replacing the original complex simulation evaluation process, and the mechanism in the simulation evaluation process is learned by the machine learning model, so that the quick evaluation by the machine learning model is realized, the evaluation time is shortened, and the design efficiency is improved; and on the basis of the existing efficiency evaluation model, a plurality of feasible solutions are heuristically and rapidly generated, the efficiency evaluation model is utilized to evaluate the feasible solutions, and the optimal feasible solution is selected, so that the land warfare equipment system is rapidly optimized.
Description
Technical Field
The invention relates to the technical field of combat equipment evaluation, in particular to a land combat equipment system simulation evaluation method, a land combat equipment system simulation evaluation device and a storage medium.
Background
The land battle equipment system efficiency of the land battle team air-ground integrated unmanned battle system refers to the degree that the battle system completes specified mission tasks in a typical battle scene, and the equipment system efficiency can be regarded as the specific expression of the system capacity in a specific scene.
The evaluation of the system efficiency mainly has two research meanings: firstly, the combat capability of the current system is evaluated, and a basis is provided for improvement and optimization of the current system; and secondly, the method can guide the design and development planning of future equipment systems, and provide guidance for the development and design of new equipment. The efficiency evaluation method can be divided into analytic evaluation and simulation evaluation according to the evaluation process, wherein the common analytic evaluation methods comprise a analytic hierarchy process, an ADC efficiency analysis method, a principal component analysis method and the like; the simulation evaluation is mainly performed through computer simulation, can evaluate the operational capability of the system from the aspects of the integrity and the emergence of the system, and can evaluate the weapon equipment system from the aspects of shooting efficiency, cost effectiveness, value exchange ratio and the like.
The existing evaluation method solves the traditional efficiency evaluation problem to a certain extent, but as the styles of equipment systems are increased, interaction relations become more complex due to system design factors. Therefore, how to accurately and rapidly evaluate the performance of the equipment system is a difficult problem to be solved in the prior art.
Disclosure of Invention
The invention aims to provide a land battle equipment system simulation evaluation method and device, which can accurately and rapidly evaluate the effectiveness of a land battle equipment system and improve the quality and efficiency of evaluation.
To achieve the purpose, the invention adopts the following technical scheme:
a land battle equipment system simulation evaluation method comprises the following steps:
simulation model construction step S110:
determining indexes related to a land warfare equipment system according to fight thinking, acquiring simulation data according to efficiency values to be calculated according to thinking, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model;
simulation efficacy model training step S120:
training the efficiency prediction model by using the simulation data to obtain an optimal efficiency prediction model;
land arming system evaluation step S130:
and performing performance evaluation on the land combat equipment system within the index range by using the trained performance prediction model.
Optionally, in the simulation model construction step S110:
specifically, according to the fight design, determining indexes related to a land fight equipment system, constructing an index historical database by using related index parameters, preprocessing data of the historical database, performing correlation analysis by using multidimensional parameters of the preprocessed index historical data, performing feature selection, and constructing a multidimensional parameter prediction model by using the selected features.
Optionally, in the simulation model construction step S110:
performing correlation analysis by using the preprocessed multidimensional parameters of the index historical data, and performing feature selection, wherein the method specifically comprises the following steps:
the multidimensional parameters of the standard index data are arranged, and different index data parameters are extracted; and performing dimension reduction processing on the different index data parameters by adopting a weighted kernel principal component analysis method to obtain index features, wherein the index features comprise shooting indexes, interception indexes and system contribution rate indexes.
Optionally, in the simulation model construction step S110:
the constructed multidimensional parameter prediction model is a multidimensional parameter prediction model based on generating a mixture of an countermeasure network DD-GAN and a selective kernel convolutional neural network SK-CNN, wherein the selective kernel convolutional neural network SK-CNN comprises an implicit layer and an output layer, the implicit layer comprises the countermeasure network DD-GAN model, and the countermeasure network DD-GAN model is parallel to the selective kernel convolutional neural network SK-CNN.
Optionally, the step S120 of training the simulated efficacy model specifically includes:
a preprocessing sub-step S121, wherein preprocessing is carried out on the data of the historical database, the preprocessing comprises data cleaning, and the influence of the original dimension of the data on the result is eliminated to obtain standard index data;
step S122, dividing the preprocessed data into a model training set and a model test set according to the proportion of 8:2, and then training a performance prediction model, namely a multi-dimensional parameter prediction model by using training samples; and debugging relevant parameters of the multidimensional parameter prediction model, and judging the quality of the trained multidimensional parameter prediction model according to model evaluation indexes until the optimal multidimensional parameter prediction model is obtained.
Optionally, in the preprocessing substep S121, the performing data cleaning on the historical database data to obtain standard index data includes:
screening out disorder code data and offside data from the data of the historical database to obtain screening index data;
vectorizing the screening index data to obtain a screening index vector set, and adding space-time vectors to each screening index vector in the screening index vector set to obtain a space-time vector set;
performing feature clustering on the space-time vector set to obtain a clustering center data set;
and filling each null value data in the screening index data according to the clustering center data set to obtain standard index data.
Optionally, the land battle equipment system assessment step S130 specifically includes:
adopting an optimization algorithm, taking the trained effectiveness prediction model as an fitness function, and calculating to obtain an effectiveness value in an index range so as to evaluate the performance of the land and warfare equipment system; the efficiency value is shooting efficiency, interception efficiency and system contribution rate.
Optionally, in a simulated performance model training step S120,
evaluating training and testing results of the model by adopting a resolvable coefficient R2 and a mean square error MSE to obtain an optimal multidimensional parameter prediction model;
in the land arming system evaluation step S130,
the optimization algorithm is a cuckoo optimization algorithm (CSO), i.e., the trained efficacy prediction model is utilized as a fitness function of the cuckoo optimization algorithm (CSO).
The invention further discloses a land battle equipment system simulation evaluation device, which comprises:
the simulation module is used for determining indexes related to a land warfare equipment system according to the fight conception, acquiring simulation data according to efficiency values required to be calculated, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model;
the training module is used for training the efficiency prediction model by utilizing the simulation data to obtain an optimal efficiency prediction model;
and the evaluation module is used for evaluating the effectiveness of the land combat equipment system in the index range by utilizing the trained effectiveness prediction model.
The invention also discloses a computer readable storage medium which stores instructions which when executed by a processor perform the land warfare equipment system simulation evaluation method.
The invention has the following effects:
1) The machine learning model is used for replacing the original complex simulation evaluation process, and the mechanism in the simulation evaluation process is learned by the machine learning model, so that the quick evaluation by the machine learning model is realized, the evaluation time is greatly shortened, and the design efficiency is improved.
2) On the basis of the existing efficiency evaluation model, a plurality of feasible solutions are heuristically and rapidly generated, the feasible solutions are evaluated by utilizing the efficiency evaluation model, and the feasible solution with the optimal efficiency result is selected, so that the rapid optimization of the land fight equipment system is realized.
Drawings
FIG. 1 is a flow chart of a land warfare equipment architecture simulation evaluation method in accordance with a specific embodiment of the present invention;
fig. 2 is a block diagram of a land warfare equipment architecture simulation evaluation device according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
The invention mainly comprises the following steps: the machine learning model is adopted to replace the original complex simulation evaluation process, and the mechanism in the simulation evaluation process is learned by the machine learning model, so that the quick evaluation by the machine learning model is realized, the evaluation time is shortened, and the design efficiency of the land battle equipment system is improved.
Referring to fig. 1, a land combat equipment architecture simulation assessment method according to a specific embodiment of the present invention is shown, comprising the steps of:
simulation model construction step S110:
according to the fight design, determining indexes related to a land fight equipment system, acquiring simulation data according to the design to be calculated efficiency value, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model.
Specifically, the efficacy prediction model is a multidimensional parameter prediction model, indexes related to a land warfare equipment system are determined according to a warfare design, an index historical database is constructed by using related index parameters, data preprocessing is carried out on historical database data, correlation analysis is carried out by using multidimensional parameters of the preprocessed index historical data, feature selection is carried out, and the multidimensional parameter prediction model is constructed by using the selected features.
Further, the correlation analysis is performed by using the preprocessed multidimensional parameters of the index history data, and the feature selection is performed, which specifically comprises:
the multidimensional parameters of the standard index data are arranged, and different index data parameters are extracted; and performing dimension reduction processing on the different index data parameters by adopting a weighted kernel principal component analysis method to obtain index features, wherein the index features comprise shooting indexes, interception indexes and system contribution rate indexes.
Still further, the constructed multidimensional parameter prediction model of the present invention is a multidimensional parameter prediction model based on generating a mixture of an countermeasure network DD-GAN and a selective kernel convolutional neural network SK-CNN, the selective kernel convolutional neural network SK-CNN comprising an implicit layer and an output layer, the implicit layer comprising the countermeasure network DD-GAN model, the countermeasure network DD-GAN model being concurrent with the selective kernel convolutional neural network SK-CNN.
The land battle equipment system is suitable for an air-ground integrated unmanned battle system of a land battle team, and aims to construct a lightweight C4 ISRK battle equipment system.
The novel unmanned combat system is not used for directly replacing the existing team-level system equipment, but is used for quickly constructing a relatively independent team-level/unmanned cooperative combat system in the area/direction by configuring a team-level on/off cooperative combat control system (hereinafter referred to as a team-level team control system) to remodel the battlefield function configuration of a person and a machine; through the mode of communication cluster networking, fighter units such as personnel (with individual soldier information terminals), aerial unmanned platform, ground unmanned platform and the like are deeply crosslinked with nodes, unmanned equipment platform carries task loads such as firepower, communication, reconnaissance and reactance, the fighter is equipped with the individual soldier information terminals, the fighter capacity of the teams is comprehensively expanded from the aspects such as time, space, information type/means, firepower density/strength, attack distance/direction and the like through an intelligent command control system, the fighter capacity of the teams is realized, the urgent demands of air-ground cooperation and fighter capacity aggregation of an active/unmanned cooperative system are effectively solved, the short-distance air information, quick firepower support and autonomous communication guarantee of land battle field ground level fighters are effectively solved, the reaction time is shortened, the real-time situation is mastered, the quick command decision is formed, the fighter capacity is multiplied, and the casualties risk of fighter is furthest reduced.
Simulation efficacy model training step S120:
and training the efficiency prediction model by using the simulation data to obtain an optimal efficiency prediction model.
Specifically, the method comprises the following steps:
a preprocessing sub-step S121, wherein preprocessing is carried out on the data of the historical database, the preprocessing comprises data cleaning, and the influence of the original dimension of the data on the result is eliminated to obtain standard index data;
in the embodiment of the present invention, the step of performing data cleaning on the historical database data to obtain standard index data includes:
screening out disorder code data and offside data from the data of the historical database to obtain screening index data;
vectorizing the screening index data to obtain a screening index vector set, and adding space-time vectors to each screening index vector in the screening index vector set to obtain a space-time vector set;
performing feature clustering on the space-time vector set to obtain a clustering center data set;
and filling each null value data in the screening index data according to the clustering center data set to obtain standard index data.
Step S122, dividing the preprocessed data into a model training set and a model test set according to the proportion of 8:2, and then training a performance prediction model, namely a multi-dimensional parameter prediction model by using training samples; and debugging relevant parameters of the multidimensional parameter prediction model, and judging the quality of the trained multidimensional parameter prediction model according to model evaluation indexes until the optimal multidimensional parameter prediction model is obtained.
The invention can further adopt the determinable coefficient R2 and the mean square error MSE (mean squarederror) to evaluate the training and testing results of the model, and obtain the optimal multidimensional parameter prediction model.
Land arming system evaluation step S130:
and performing performance evaluation on the land combat equipment system within the index range by using the trained performance prediction model.
The method specifically comprises the following steps: adopting an optimization algorithm, taking the trained effectiveness prediction model as an fitness function, and calculating to obtain an effectiveness value in an index range so as to evaluate the performance of the land and warfare equipment system; the efficiency value is shooting efficiency, interception efficiency and system contribution rate.
Specifically, the optimization algorithm is a cuckoo optimization algorithm (CSO), that is, the trained performance prediction model is used as a fitness function of the cuckoo optimization algorithm (CSO).
In the step, an optimization algorithm is adopted, a trained effectiveness prediction model is taken as an fitness function, and an effectiveness value is calculated in an index range to evaluate the performance of land and warfare equipment systems, which specifically comprises the following steps: initializing the position of a cuvettes of the cuvettes, wherein each cuvettes position is an index value solution; and (3) performing quick evaluation on the effectiveness of the land fight equipment system under the index value by using the effectiveness prediction model to obtain the effectiveness value of the land fight equipment system.
Further, see fig. 2: the invention also discloses a land battle equipment system simulation evaluation device, which comprises:
the simulation module is used for determining indexes related to a land warfare equipment system according to the fight conception, acquiring simulation data according to efficiency values required to be calculated, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model;
the training module is used for training the efficiency prediction model by utilizing the simulation data to obtain an optimal efficiency prediction model;
and the evaluation module is used for evaluating the effectiveness of the land combat equipment system in the index range by utilizing the trained effectiveness prediction model.
Specifically, in the simulation module, indexes related to a land warfare equipment system are determined according to a warfare theory, an index history database is constructed by using related index parameters, data preprocessing is carried out on the history database data, correlation analysis is carried out by using multidimensional parameters of the preprocessed index history data, feature selection is carried out, and a multidimensional parameter prediction model is constructed by using the selected features.
Further, the correlation analysis is performed by using the preprocessed multidimensional parameters of the index history data, and the feature selection is performed, which specifically comprises:
the multidimensional parameters of the standard index data are arranged, and different index data parameters are extracted; and performing dimension reduction processing on the different index data parameters by adopting a weighted kernel principal component analysis method to obtain index features, wherein the index features comprise shooting indexes, interception indexes and system contribution rate indexes.
Still further, the constructed multidimensional parameter prediction model of the present invention is a multidimensional parameter prediction model based on generating a mixture of an countermeasure network DD-GAN and a selective kernel convolutional neural network SK-CNN, the selective kernel convolutional neural network SK-CNN comprising an implicit layer and an output layer, the implicit layer comprising the countermeasure network DD-GAN model, the countermeasure network DD-GAN model being concurrent with the selective kernel convolutional neural network SK-CNN.
In the training module, preprocessing the data of the historical database, including data cleaning and normalization, and eliminating the influence of the original dimension of the data on the result to obtain standard index data; dividing a model training set and a model testing set according to the ratio of 8:2 for the preprocessed data, and then training a performance prediction model, namely a multidimensional parameter prediction model, by using training samples; and debugging relevant parameters of the multidimensional parameter prediction model, and judging the quality of the trained multidimensional parameter prediction model according to model evaluation indexes until the optimal multidimensional parameter prediction model is obtained.
In the embodiment of the present invention, the step of performing data cleaning on the historical database data to obtain standard index data includes:
screening out disorder code data and offside data from the data of the historical database to obtain screening index data;
vectorizing the screening index data to obtain a screening index vector set, and adding space-time vectors to each screening index vector in the screening index vector set to obtain a space-time vector set;
performing feature clustering on the space-time vector set to obtain a clustering center data set;
and filling each null value data in the screening index data according to the clustering center data set to obtain standard index data.
The invention can further evaluate the training and testing results of the model by adopting the determinable coefficient R2 and the mean square error MSE (mean squarederror) to obtain the optimal multidimensional parameter prediction model
In the evaluation module, an optimization algorithm is adopted, a trained efficiency prediction model is taken as an adaptability function, and an efficiency value is calculated in an index range so as to evaluate the performance of the land and warfare equipment system; the efficiency value is shooting efficiency, interception efficiency and system contribution rate.
Specifically, the optimization algorithm is a cuckoo optimization algorithm (CSO), that is, the trained performance prediction model is used as a fitness function of the cuckoo optimization algorithm (CSO).
The method for evaluating the performance of the land battle equipment system by using the performance prediction model after training as an fitness function through an optimization algorithm comprises the following steps of: initializing the position of a cuvettes of the cuvettes, wherein each cuvettes position is an index value solution; and (3) performing quick evaluation on the effectiveness of the land fight equipment system under the index value by using the effectiveness prediction model to obtain the effectiveness value of the land fight equipment system.
The invention also discloses a computer readable storage medium storing instructions, wherein the instructions, when executed by a processor, perform the land warfare equipment system simulation evaluation method described in the embodiment.
The invention has the following effects:
1) The machine learning model is used for replacing the original complex simulation evaluation process, and the mechanism in the simulation evaluation process is learned by the machine learning model, so that the quick evaluation by the machine learning model is realized, the evaluation time is greatly shortened, and the design efficiency is improved.
2) On the basis of the existing efficiency evaluation model, a plurality of feasible solutions are heuristically and rapidly generated, the feasible solutions are evaluated by utilizing the efficiency evaluation model, and the feasible solution with the optimal efficiency result is selected, so that the rapid optimization of the land fight equipment system is realized.
It will be apparent to those skilled in the art that the elements or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or they may alternatively be implemented in program code executable by a computer device, such that they may be stored in a storage device for execution by the computing device, or they may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps in them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
While the invention has been described in detail in connection with specific preferred embodiments thereof, it is not to be construed as limited thereto, but rather as a result of a simple deduction or substitution by a person having ordinary skill in the art without departing from the spirit of the invention, which is to be construed as falling within the scope of the invention defined by the appended claims.
Claims (4)
1. A land battle equipment system simulation evaluation method is characterized by comprising the following steps:
simulation model construction step S110:
determining indexes related to a land warfare equipment system according to fight thinking, acquiring simulation data according to efficiency values to be calculated according to thinking, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model;
simulation efficacy model training step S120:
training the efficiency prediction model by using the simulation data to obtain an optimal efficiency prediction model;
land arming system evaluation step S130:
performing performance evaluation on the land combat equipment system within the index range by using the trained performance prediction model;
in the simulation model construction step S110:
specifically, according to the fight design, determining indexes related to a land fight equipment system, constructing an index historical database by using related index parameters, preprocessing data of the historical database, performing correlation analysis by using multidimensional parameters of the preprocessed index historical data, performing feature selection, and constructing a multidimensional parameter prediction model by using the selected features;
performing correlation analysis by using the preprocessed multidimensional parameters of the index historical data, and performing feature selection, wherein the method specifically comprises the following steps:
the multidimensional parameters of the standard index data are arranged, and different index data parameters are extracted; performing dimension reduction processing on the different index data parameters by adopting a weighted kernel principal component analysis method to obtain index features, wherein the index features comprise shooting indexes, interception indexes and system contribution rate indexes;
the constructed multidimensional parameter prediction model is a multidimensional parameter prediction model based on the generation of a mixture of an countermeasure network DD-GAN and a selective kernel convolutional neural network SK-CNN, wherein the selective kernel convolutional neural network SK-CNN comprises an implicit layer and an output layer, the implicit layer comprises the countermeasure network DD-GAN model, and the countermeasure network DD-GAN model is parallel to the selective kernel convolutional neural network SK-CNN;
the step S120 of training the simulation efficacy model specifically includes:
a preprocessing sub-step S121, wherein preprocessing is carried out on the data of the historical database, the preprocessing comprises data cleaning, and the influence of the original dimension of the data on the result is eliminated to obtain standard index data;
step S122, dividing the preprocessed data into a model training set and a model test set according to the proportion of 8:2, and then training a performance prediction model, namely a multi-dimensional parameter prediction model by using training samples; debugging relevant parameters of the multidimensional parameter prediction model, and judging the quality of the trained multidimensional parameter prediction model according to model evaluation indexes until an optimal multidimensional parameter prediction model is obtained;
in the preprocessing substep S121, the step of performing data cleaning on the historical database data to eliminate the influence of the original dimension of the data on the result, and obtain standard index data includes:
screening out disorder code data and offside data from the data of the historical database to obtain screening index data;
vectorizing the screening index data to obtain a screening index vector set, and adding space-time vectors to each screening index vector in the screening index vector set to obtain a space-time vector set;
performing feature clustering on the space-time vector set to obtain a clustering center data set;
filling each null value data in the screening index data according to the clustering center data set to obtain standard index data;
in the land arming system evaluation step S130,
the optimization algorithm is a particle swarm algorithm (PSO), namely, a trained efficiency prediction model is used as an adaptability function of the particle swarm algorithm (PSO);
the method comprises the following steps:
adopting an optimization algorithm, taking the trained effectiveness prediction model as an fitness function, and calculating to obtain an effectiveness value in an index range so as to evaluate the performance of the land and warfare equipment system; wherein the efficacy value is shooting efficacy, interception efficacy and system contribution rate;
the method for evaluating the performance of the land battle equipment system by using the performance prediction model after training as an fitness function through an optimization algorithm comprises the following steps of: initializing the states of 'particles', wherein each 'particle' is an index value solution; and (3) performing quick evaluation on the effectiveness of the land fight equipment system under the index value by using the effectiveness prediction model to obtain the effectiveness value of the land fight equipment system.
2. The land warfare equipment system simulation evaluation method of claim 1, wherein,
in the simulated performance model training step S120,
by using a determinable coefficient R 2 And evaluating the training and testing results of the model by using the MSE to obtain the optimal multidimensional parameter prediction model.
3. A land battle equipment system simulation evaluation device, comprising:
the simulation module is used for determining indexes related to a land warfare equipment system according to the fight conception, acquiring simulation data according to efficiency values required to be calculated, and constructing an efficiency prediction model by utilizing the simulation data, wherein the efficiency prediction model is a multidimensional parameter prediction model;
the training module is used for training the efficiency prediction model by utilizing the simulation data to obtain an optimal efficiency prediction model;
the evaluation module is used for evaluating the effectiveness of the land combat equipment system in the index range by utilizing the trained effectiveness prediction model;
specifically, in the simulation module, indexes related to a land warfare equipment system are determined according to a warfare theory, an index historical database is constructed by utilizing related index parameters, data preprocessing is carried out on historical database data, correlation analysis is carried out by utilizing multidimensional parameters of the preprocessed index historical data, feature selection is carried out, and a multidimensional parameter prediction model is constructed by utilizing the selected features;
performing correlation analysis by using the preprocessed multidimensional parameters of the index historical data, and performing feature selection, wherein the method specifically comprises the following steps:
the multidimensional parameters of the standard index data are arranged, and different index data parameters are extracted; performing dimension reduction processing on the different index data parameters by adopting a weighted kernel principal component analysis method to obtain index features, wherein the index features comprise shooting indexes, interception indexes and system contribution rate indexes;
the constructed multidimensional parameter prediction model is a multidimensional parameter prediction model based on the mixture of an countermeasure network DD-GAN and a selective kernel convolution neural network SK-CNN, wherein the selective kernel convolution neural network SK-CNN comprises an implicit layer and an output layer, the implicit layer comprises the countermeasure network DD-GAN model, and the countermeasure network DD-GAN model is parallel to the selective kernel convolution neural network SK-CNN;
the training module is used for preprocessing the data of the historical database, including data cleaning and normalization, and eliminating the influence of the original dimension of the data on the result to obtain standard index data; dividing a model training set and a model testing set according to the ratio of 8:2 for the preprocessed data, and then training a performance prediction model, namely a multidimensional parameter prediction model, by using training samples; debugging relevant parameters of the multidimensional parameter prediction model, and judging the quality of the trained multidimensional parameter prediction model according to model evaluation indexes until an optimal multidimensional parameter prediction model is obtained;
the step of cleaning the data of the historical database to obtain standard index data comprises the following steps:
screening out disorder code data and offside data from the data of the historical database to obtain screening index data;
vectorizing the screening index data to obtain a screening index vector set, and adding space-time vectors to each screening index vector in the screening index vector set to obtain a space-time vector set;
performing feature clustering on the space-time vector set to obtain a clustering center data set;
filling each null value data in the screening index data according to the clustering center data set to obtain standard index data;
in the evaluation module, an optimization algorithm is adopted, a trained efficiency prediction model is taken as an adaptability function, and an efficiency value is calculated in an index range so as to evaluate the performance of the land and warfare equipment system; the efficiency value is shooting efficiency, interception efficiency and system contribution rate;
specifically, the optimization algorithm is a Particle Swarm Optimization (PSO), namely, a trained efficiency prediction model is used as an adaptability function of the PSO;
the method for evaluating the performance of the land battle equipment system by using the performance prediction model after training as an fitness function through an optimization algorithm comprises the following steps of: initializing the states of 'particles', wherein each 'particle' is an index value solution; and (3) performing quick evaluation on the effectiveness of the land fight equipment system under the index value by using the effectiveness prediction model to obtain the effectiveness value of the land fight equipment system.
4. A computer-readable storage medium having instructions stored thereon, characterized in that,
the instructions, when executed by a processor, perform the land warfare equipment architecture simulation assessment method of claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310451360.2A CN116187207B (en) | 2023-04-25 | 2023-04-25 | Land battle equipment system simulation evaluation method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310451360.2A CN116187207B (en) | 2023-04-25 | 2023-04-25 | Land battle equipment system simulation evaluation method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116187207A CN116187207A (en) | 2023-05-30 |
| CN116187207B true CN116187207B (en) | 2023-07-25 |
Family
ID=86452493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310451360.2A Active CN116187207B (en) | 2023-04-25 | 2023-04-25 | Land battle equipment system simulation evaluation method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187207B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196240A (en) * | 2023-09-21 | 2023-12-08 | 广东省核工业地质局测绘院 | House-ground integrated project-based household registration information acquisition method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10757132B1 (en) * | 2017-09-08 | 2020-08-25 | Architecture Technology Corporation | System and method for evaluating and optimizing training effectiveness |
| CN110763929A (en) * | 2019-08-08 | 2020-02-07 | 浙江大学 | Intelligent monitoring and early warning system and method for convertor station equipment |
| CN113095481B (en) * | 2021-04-03 | 2024-02-02 | 西北工业大学 | Air combat maneuver method based on parallel self-game |
| CN114298414A (en) * | 2021-12-28 | 2022-04-08 | 江南机电设计研究所 | Equipment system efficiency prediction and index optimization method |
| CN114943245A (en) * | 2022-04-07 | 2022-08-26 | 中国人民解放军海军航空大学航空作战勤务学院 | Automatic modulation recognition method and device based on data enhancement and feature embedding |
-
2023
- 2023-04-25 CN CN202310451360.2A patent/CN116187207B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116187207A (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647414A (en) | Operation plan adaptability analysis method based on emulation experiment and storage medium | |
| CN116187207B (en) | Land battle equipment system simulation evaluation method, device and storage medium | |
| CN110929394A (en) | Combined combat system modeling method based on super network theory and storage medium | |
| CN106776796B (en) | Unmanned aerial vehicle task planning system and method based on cloud computing and big data | |
| CN112182977A (en) | Control method and system for cooperative game confrontation of unmanned cluster | |
| CN105678030B (en) | Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics | |
| CN110175773A (en) | Drones for surveillance's Combat Efficiency Evaluation method based on Bayesian network | |
| CN109960863B (en) | Complex simulation system credibility evaluation method based on network topology path | |
| CN112801540B (en) | Intelligent collaborative architecture design method based on unmanned clusters | |
| CN109541960B (en) | System and method for aircraft digital battlefield confrontation | |
| CN109597839B (en) | Data mining method based on avionic combat situation | |
| CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
| CN115047907B (en) | Air isomorphic formation command method based on multi-agent PPO algorithm | |
| CN114895710A (en) | Control method and system for autonomous behavior of unmanned aerial vehicle cluster | |
| Hao et al. | Flight Trajectory Prediction Using an Enhanced CNN-LSTM Network | |
| Jiang et al. | Modeling and Resilience Analysis of Combat Systems-of-Systems Based on Kill Web | |
| CN110930054A (en) | Data-driven battle system key parameter rapid optimization method | |
| Zhang et al. | Solving “limited” task allocation problem for UAVs based on optimization algorithms | |
| CN117669710B (en) | Multi-behavior tree decision scheme aggregation method and device for game countermeasure task | |
| Sui et al. | Research on mission capability testing and evaluation system of UAV swarm | |
| CN108199868A (en) | A kind of group system distributed control method based on tactics cloud | |
| CN114491879B (en) | Weapon equipment system simulation evaluation method considering dynamic reconstruction | |
| Wang et al. | Review of the Multi-perspective Evaluation Methods of Information Systems Equipment Facing the System Contribution Rate | |
| CN116151492B (en) | Auxiliary decision analysis system of combined combat system | |
| CN114397907B (en) | Cluster self-adaptive reconstruction behavior modeling method based on multiple agents |
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 |