Ultra-wideband antenna design method, system and medium based on deep learning

Abstract

The present invention discloses a method, system, and medium for designing ultra-wideband antennas based on deep learning, including: obtaining a design target for a target ultra-wideband antenna, extracting structural parameters related to antenna performance based on antenna design example data; preparing sample data based on the structural parameters and performing preprocessing; constructing a proxy model based on a NAR dynamic network combined with a multi-layer perceptron; training the proxy model using the sample data; and configuring proxy model parameters; obtaining the optimal structural parameters of the target ultra-wideband antenna using the trained proxy model; performing simulation verification on the outputted optimal structural parameters; and configuring a design solution for the target ultra-wideband antenna. The present invention utilizes a NAR dynamic network combined with a multi-layer perceptron to establish a proxy model that can adapt to optimization tasks for different structural parameters, improving efficiency while ensuring performance, and enhancing the design speed and accuracy of ultra-wideband antennas.

Description

Technical Field

[0001] The present invention relates to the field of antenna design technology, and more specifically, to a method, system, and medium for designing an ultra-wideband antenna based on deep learning. Background Art

[0002] Antennas, devices that convert electromagnetic waves into electric currents and vice versa, are an integral part of wireless communication systems. In the era of booming wireless communications, antennas are shouldering increasingly heavy responsibilities, and the demands placed on them by the system are constantly increasing. Rapidly designing antennas that meet these requirements has become a worthy pursuit. As the system demands increasingly stringent performance from antennas, antenna design requires comprehensive consideration of multiple performance aspects and multi-objective optimization. With the advancement of artificial intelligence, the use of surrogate models and deep learning algorithms for antenna optimization has become a key research area in the antenna field.

[0003] Traditional antenna design methods use mathematical equations to calculate electromagnetic fields based on the complexity of the structure. For simple designs such as square patches, circular patches, and wire antennas, mathematical equations already exist, derived from Maxwell's equations, and can be used to determine the antenna's performance at the desired frequency. However, for the optimization design of complex, multi-parameter antennas, deriving these equations is extremely difficult and complex. Furthermore, high-fidelity electromagnetic simulation software such as HFSS, CST, and FEKO is used to analyze antenna performance (S11 parameters, bandwidth, gain, etc.) and optimize antenna parameters. However, this method involves full-wave simulation of the antenna, requiring extensive computational effort for each simulation, which is time-consuming and memory-intensive. Therefore, the question is how to leverage deep learning methods to build proxy models to improve efficiency while designing antennas that meet target requirements. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes a deep learning-based ultra-wideband antenna design method, system and medium. The purpose is to propose a deep learning-based proxy model to optimize the time-consuming problem in the antenna design process, while ensuring performance and achieving higher accuracy.

[0005] A first aspect of the present invention provides an ultra-wideband antenna design method based on deep learning, comprising:

[0006] Obtaining a design goal for a target ultra-wideband antenna, extracting antenna design example data based on the design goal, and extracting structural parameters related to antenna performance based on the antenna design example data;

[0007] Prepare sample data and perform preprocessing according to the structural parameters, build a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, use the sample data to train the proxy model, and configure the proxy model parameters;

[0008] The trained proxy model is used to obtain the optimal structural parameters of the target ultra-wideband antenna, and the optimal structural parameters are simulated and verified to obtain a design solution for the target ultra-wideband antenna.

[0009] In this solution, antenna design example data is extracted based on the design goal, and structural parameters related to antenna performance are extracted based on the antenna design example data, specifically:

[0010] The design goal is segmented and the word vector is processed by pre-training the antenna design keyword library. Keywords are extracted based on similarity calculation, different keywords and their corresponding values ​​are determined, and the design goal keywords and corresponding values ​​are used to construct a retrieval task:

[0011] Based on the retrieval task, antenna design example data that meets the preset requirements is extracted from historical ultra-wideband antenna design data. The retrieved antenna design example data is structured and a heterogeneous graph of different design target keywords is constructed based on semantic association and data association.

[0012] Extracting a meta-path starting from the design target keyword in the heterogeneous graph, constructing an adjacency matrix under two relationships based on semantic association and data association in the meta-path, and performing node feature aggregation based on the adjacency matrix under the two relationships using a graph attention network;

[0013] The weights of the two relationships are obtained through relationship-level attention. Based on the weights of the two relationships and the total weight of the keyword nodes in the meta-path, the keyword nodes that meet the preset weight threshold are screened and further screened based on the type labels of the keyword nodes.

[0014] Structural parameter categories related to antenna performance are obtained according to the screening results, and data integration is performed in antenna design example data using the structural parameter categories.

[0015] In this solution, an agent model is constructed based on the NAR dynamic network combined with a multi-layer perceptron. Specifically:

[0016] Obtaining data samples after integration of data of various structural parameter categories, performing data fusion on the data samples using a Copula function to obtain a data sample set based on Copula tail correlation fusion, and dividing the data sample set into training samples and test samples;

[0017] Initialize the network parameters of the NAR dynamic network, optimize the delay order and the number of hidden layer neurons based on the improved genetic algorithm, use the BP algorithm to train the NAR dynamic network, adjust the connection weights of the NAR dynamic network according to the error data, and obtain the optimized NAR dynamic network through iterative training;

[0018] The output data of the optimized NAR dynamic network is obtained and imported into the multi-layer perceptron for training. The model parameters of the NAR dynamic network and the multi-layer perceptron are fine-tuned according to the training results. After stopping the training, the test error is obtained based on the test sample. When the test error is less than the preset error threshold, the proxy model with the configured parameters is output.

[0019] In this scheme, the network parameters of the NAR dynamic network are initialized, and the delay order and the number of hidden layer neurons are optimized based on the improved genetic algorithm. Specifically:

[0020] Initializing the network parameters of the NAR dynamic network, mapping the network parameters using a Circle chaotic sequence to generate a chaotic population, and mapping the obtained chaotic population to genetic population individuals to generate a chaotic initialization population;

[0021] Generating reverse positions of individuals in the chaotic initialization population, constructing a reverse population, merging the chaotic initialization population and the reverse population, and selecting dominant individuals through evaluation to generate a final population;

[0022] An improved genetic algorithm is used to optimize individuals in the population. The fitness of individuals in the population is calculated based on the average accuracy of the test samples as the fitness function. In the iterative process, adaptive mutations and dynamic weights that change with the number of iterations are introduced to enhance the ability to search for excellent individuals.

[0023] The fitness of individuals is continuously calculated through iteration, and individuals are selected, crossed, and adaptively mutated to generate the next generation population. After completing the set number of iterations, the optimal delay order and the optimal number of hidden layer neurons of the NAR dynamic network are obtained.

[0024] In this solution, the output data of the optimized NAR dynamic network is obtained and imported into the multi-layer perceptron for training. The model parameters of the NAR dynamic network and the multi-layer perceptron are fine-tuned according to the training results. Specifically:

[0025] Obtaining output data of the NAR dynamic model during the training process, using the output data as input to a multilayer perceptron, initializing a network structure of the multilayer perceptron, and determining network parameters through iterative training;

[0026] Using multiple fully connected layers in a multi-layer perceptron to perform feature dimensionality reduction on the output data, using a self-attention mechanism to assign weights to the reduced output data, and compressing the weighted features through a fully connected layer to obtain deep features;

[0027] The NAR dynamic model is combined with the multi-layer perceptron to build an overall model. The root mean square error between the test data and the predicted output of the overall model is calculated as the test error. The model parameters of the overall model are adjusted using back propagation based on the test error.

[0028] The goal is to minimize the test error. When it is less than the preset threshold, the proxy model with configured parameters is output.

[0029] In this solution, the optimal structural parameters of the target ultra-wideband antenna are obtained, specifically:

[0030] Importing structural parameters corresponding to the design objectives of the target ultra-wideband antenna into the optimized proxy model to obtain predicted optimal structural parameters, and obtaining simulation data based on the optimal structural parameters;

[0031] Performing simulation calculations based on sample data corresponding to the structural parameters, obtaining simulation results of the sample data, calculating the degree of deviation between the simulation data of the optimal structural parameters and the simulation results of the sample data, and normalizing the degree of deviation;

[0032] When the normalized deviation degree is less than a preset threshold, a design scheme of the target ultra-wideband antenna is generated according to the optimal structural parameters.

[0033] A second aspect of the present invention provides an ultra-wideband antenna design system based on deep learning, the system comprising a design target acquisition unit, a structural parameter confirmation unit, a proxy model unit, a proxy model training unit, and a simulation verification unit;

[0034] The design target acquisition unit is responsible for acquiring the design target of the target ultra-wideband antenna;

[0035] The structural parameter confirmation unit is responsible for extracting structural parameters related to antenna performance from antenna design example data according to design goals;

[0036] The proxy model unit is responsible for constructing a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, configuring the proxy model parameters through training, and using the proxy model to obtain the optimal structural parameters of the target ultra-wideband antenna;

[0037] The agent model training unit is responsible for training the agent model using the improved genetic algorithm to obtain the optimal model parameters;

[0038] The simulation verification unit is responsible for performing simulation verification on the optimal structural parameters, and obtaining the design scheme of the target ultra-wideband antenna after verification.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention utilizes the NAR dynamic network in combination with a multi-layer perceptron to establish a proxy model that can adapt to optimization tasks with different structural parameters. By optimizing the training process of the proxy model through an improved genetic algorithm, the problem of difficulty in training samples for antennas with multi-dimensional structural parameters is solved. While ensuring performance, efficiency is improved, the design speed and accuracy of ultra-wideband antennas are enhanced, and the labor cost of ultra-wideband antenna design is further reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or exemplary descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to these drawings without paying any creative work.

[0042] Figure 1 A flow chart of a method for designing ultra-wideband antennas based on deep learning is shown;

[0043] Figure 2 A flowchart of an embodiment for constructing an agent model is shown;

[0044] Figure 3 A flow chart of an embodiment for obtaining optimal structural parameters of a target ultra-wideband antenna is shown;

[0045] Figure 4 A block diagram of a deep learning-based ultra-wideband antenna design system is shown. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0048] Figure 1 A flowchart of an ultra-wideband antenna design method based on deep learning is shown.

[0049] like Figure 1 As shown, this embodiment provides an ultra-wideband antenna design method based on deep learning, including:

[0050] S102, obtaining a design goal of a target ultra-wideband antenna, extracting antenna design example data based on the design goal, and extracting structural parameters related to antenna performance based on the antenna design example data;

[0051] S104, preparing sample data according to the structural parameters and performing preprocessing, building a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, training the proxy model using the sample data, and configuring proxy model parameters;

[0052] S106 , using the trained proxy model to obtain optimal structural parameters of the target ultra-wideband antenna, performing simulation verification on the optimal structural parameters, and obtaining a design solution for the target ultra-wideband antenna.

[0053] It should be noted that ultra-wideband antennas are capable of matching characteristics within a specific operating frequency band and operating stably and continuously within the operating bandwidth. Ultra-wideband antennas coexist and operate stably with other devices operating in narrowband systems. Ultra-wideband antennas are improved to include stopband notching or other filtering features to remove interference from narrowband signals. Basic parameters of ultra-wideband antennas include operating bandwidth, input impedance, return loss and voltage standing wave ratio (VSWR), radiation pattern, and antenna efficiency and gain.

[0054] The design objectives of the target ultra-wideband antenna are obtained, such as fractal structure, size and position information, and the design objectives are segmented and the word vectors are processed by pre-training the antenna design keyword library. The antenna design keyword library is obtained by accessing the antenna design related database and the related field knowledge graph for pre-training. Keywords are extracted based on the similarity calculation through the pre-trained antenna design keyword library. If the similarity between the word vector corresponding to the design objective and the keyword vector in the keyword library meets the standard, it is marked as a keyword. Through traversal calculation, different keywords and their corresponding values ​​are determined, and the design objective keywords and corresponding values ​​are used to construct a retrieval task: based on the retrieval task, antenna design instance data that meets the preset requirements is extracted from the historical ultra-wideband antenna design data.

[0055] The retrieved antenna design instance data is structured, and the semantic association and data association are obtained by calculating the Pearson correlation coefficient and the mRMR algorithm using the structured instance data. A heterogeneous graph of different design target keywords is constructed based on the semantic association and data association. In the heterogeneous graph, the design target keywords extracted from the structured instance data are used as nodes, and the edge structure between the target keyword nodes is designed through the semantic association and data association.

[0056] A meta-path starting from the design target keyword is extracted in the heterogeneous graph using random walks. Adjacency matrices under two relationships are constructed in the meta-path based on semantic association and data association. Node features are aggregated based on the adjacency matrices under the two relationships using a graph attention network. Aggregate features of the k-th layer of neighboring nodes are obtained by aggregating the embeddings of the k-th layer of neighboring nodes using a mean aggregation method. The aggregated features are embedded and spliced ​​with the risk features of the k-th layer of the design target keyword node to obtain an embedded representation of the design target keyword node in the relationship graph. A nonlinear transformation is performed using a graph attention mechanism. After multiplication by an activation function and a learnable parameter, the average is taken to obtain the weight under the relationship. The weights under the two relationships are obtained through relationship-level attention. The total weight of the keyword nodes in the meta-path is obtained based on the sum of the weights of the two relationships. Keyword nodes that meet a preset weight threshold are screened and further screened based on the type labels of the keyword nodes. Structural parameter categories related to antenna performance are obtained based on the screening results. Instance data are extracted from antenna design instance data using the structural parameter categories to achieve sample data integration.

[0057] Figure 2 A flowchart of an embodiment for constructing an agent model is shown.

[0058] According to an embodiment of the present invention, an agent model is constructed based on a NAR dynamic network combined with a multi-layer perceptron, specifically:

[0059] S202, obtaining data samples after integration of data of various structural parameter categories, performing data fusion on the data samples using a Copula function to obtain a data sample set based on Copula tail correlation fusion, and dividing the data sample set into training samples and test samples;

[0060] S204, initializing the network parameters of the NAR dynamic network, optimizing the delay order and the number of hidden layer neurons based on the improved genetic algorithm, training the NAR dynamic network using the BP algorithm, adjusting the connection weights of the NAR dynamic network based on the error data, and obtaining the optimized NAR dynamic network through iterative training;

[0061] S206, obtaining the output data of the optimized NAR dynamic network, importing it into the multi-layer perceptron for training, fine-tuning the model parameters of the NAR dynamic network and the multi-layer perceptron according to the training results, and obtaining the test error based on the test sample after stopping the training. When the test error is less than the preset error threshold, the proxy model with the configured parameters is output.

[0062] It should be noted that using the Copula function to establish a data dependency model between data samples and characterize the tail correlation between data samples can further optimize the multivariate analysis in antenna design. The delay order of the NAR dynamic network gives the network a memory function. A reasonable delay order can improve network performance. The network parameters of the NAR dynamic network, including the delay order and the number of hidden layer neurons, are initialized. The network parameters are mapped using the Circle chaotic sequence to generate a chaotic population. The obtained chaotic population is mapped to the genetic population individuals to generate a chaotic initialization population. The calculation formula for the chaotic individual X after mapping is: X = X L +(X L -X U )×α, where X U 、X L are the upper and lower limits of the individual dimension, and α is the chaotic variable.

[0063] Generate the reverse position of individuals in the chaotic initialization population to construct a reverse population. The individuals in the reverse population are represented by X f =X L +X U -X, merge the chaotic initialization population and the reverse population, and generate the final population by evaluating and selecting dominant individuals; optimize the individuals in the population through the improved genetic algorithm, calculate the fitness of individuals in the population based on the average accuracy of the test samples as the fitness function, and introduce adaptive mutation and dynamic weight that change with the number of iterations in the iterative process to increase the search ability of excellent individuals; the adaptive mutation expands the individual selection range, and performs comparative calculation of fitness in a larger range, which is conducive to individual search for better solutions. In addition, the dynamic weight changes with the number of iterations, and optimizes the individual fitness search calculation. The dynamic weight λ(i) calculation formula is: λ(i)=λ c -i(λ c -λ z ) / T max ,λ c is the initial dynamic weight, λ z is the final dynamic weight, i is the number of iterations, T max is the maximum number of iterations; the fitness of individuals is continuously calculated through iteration, and individuals are selected, crossed, and adaptively mutated to generate the next generation population. After completing the set number of iterations, the optimal delay order and the optimal number of hidden layer neurons of the NAR dynamic network are obtained.

[0064] Preferably, an elite strategy is introduced into the mutation operation of the genetic algorithm. The direction of individual mutation is clarified based on the elite individual combined with differential update, and the optimal fitness individual is selected in combination with the reverse learning strategy. A random factor is introduced on the basis of the two strategies, and a random factor threshold is preset. When the random factor is greater than or equal to the preset random factor threshold, the elite strategy is used to mutate the optimal fitness individual. When the random factor is less than the preset random factor threshold, the reverse learning strategy is used to update the optimal fitness individual. The individual X after the elite strategy mutation is g Expressed as: in They represent the individual with the highest fitness, the individual with the second highest fitness, and the individual with the third highest fitness, respectively. β1β2 represents a random constant. The optimal fitness individual is updated using the reverse learning strategy, which is expressed as: where X U 、X L are the upper and lower limits of the individual dimension, and θ1θ2 represent random constants.

[0065] The BP algorithm is used to train the NAR dynamic network. The BP algorithm adjusts the network weights through error data. First, the error vector between the true value and the predicted value is calculated, and the connection weights of the network are adjusted according to the error vector. The network is trained iteratively, and the termination conditions of the iteration are that the global error of the network meets the error requirements and the number of training times reaches the maximum, ensuring that the NAR dynamic network meets the stability requirements.

[0066] It should be noted that the multilayer perceptron is a feedforward neural network composed of multiple fully connected neural networks. The output data of the NAR dynamic model during the training process is obtained and used as the input of the multilayer perceptron. The network structure of the multilayer perceptron is initialized, the network parameters are determined through iterative training, and the network parameters are updated through the backpropagation algorithm until the network converges. The output data is reduced in dimension using multiple fully connected layers in the multilayer perceptron. The self-attention mechanism is used to assign weights to the reduced output data, and the weighted features are compressed through the fully connected layer to obtain deep features. The deep features are then imported into the last fully connected layer to obtain the predicted output. The NAR dynamic model is combined with the multilayer perceptron to construct an overall model. The root mean square error between the test data and the predicted output of the overall model is calculated as the test error. The model parameters of the overall model are adjusted using backpropagation according to the test error. With the goal of minimizing the test error, when it is less than a preset threshold, the parameter-configured proxy model is output.

[0067] Figure 3 A flow chart of an embodiment for obtaining optimal structural parameters of a target ultra-wideband antenna is shown.

[0068] According to an embodiment of the present invention, the optimal structural parameters of the target ultra-wideband antenna are obtained, specifically:

[0069] S302, importing structural parameters corresponding to the design objectives of the target ultra-wideband antenna into the optimized proxy model, obtaining predicted optimal structural parameters, and obtaining simulation data based on the optimal structural parameters;

[0070] S304, performing simulation calculations based on the sample data corresponding to the structural parameters, obtaining simulation results of the sample data, calculating the degree of deviation between the simulation data of the optimal structural parameters and the simulation results of the sample data, and normalizing the degree of deviation;

[0071] S306: When the normalized deviation degree is less than a preset threshold, a design scheme of the target ultra-wideband antenna is generated according to the optimal structural parameters.

[0072] It should be noted that HFSS is called to implement the design and simulation of ultra-wideband antennas. A VB script is generated using sample data to control the HFSS software, and a three-dimensional model is generated in HFSS. The simulation is then solved and the data is output to obtain the corresponding simulation results. The degree of deviation between the simulation data of the optimal structural parameters and the simulation results of the sample data is calculated using one or more metric functions. For example, the distance vectors between the simulation data are generated using Euclidean distance, Chebyshev distance, Canberra distance, and Mahalanobis distance. All distance vector representations are concatenated and aggregated, and the concatenated and aggregated distance vectors are averaged and pooled to obtain the final degree of deviation.

[0073] Figure 4 A block diagram of a deep learning-based ultra-wideband antenna design system is shown.

[0074] The second embodiment of the present invention provides an ultra-wideband antenna design system 4 based on deep learning, which includes a design target acquisition unit 401, a structural parameter confirmation unit 402, a proxy model unit 403, a proxy model training unit 404 and a simulation verification unit 405;

[0075] The design target acquisition unit is responsible for acquiring the design target of the target ultra-wideband antenna;

[0076] The structural parameter confirmation unit is responsible for extracting structural parameters related to antenna performance from antenna design example data according to design goals;

[0077] The proxy model unit is responsible for constructing a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, configuring the proxy model parameters through training, and using the proxy model to obtain the optimal structural parameters of the target ultra-wideband antenna;

[0078] The agent model training unit is responsible for training the agent model using the improved genetic algorithm to obtain the optimal model parameters;

[0079] The simulation verification unit is responsible for performing simulation verification on the optimal structural parameters, and obtaining the design scheme of the target ultra-wideband antenna after verification.

[0080] A third embodiment of the present invention provides a computer-readable storage medium, which includes an ultra-wideband antenna design method program based on deep learning. When the ultra-wideband antenna design method program based on deep learning is executed by a processor, it implements the steps of the ultra-wideband antenna design method based on deep learning.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0082] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0083] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0084] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0085] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for designing ultra-wideband antennas based on deep learning, characterized in that: The following steps are involved: Obtaining a design goal for a target ultra-wideband antenna, extracting antenna design example data based on the design goal, and extracting structural parameters related to antenna performance based on the antenna design example data; Prepare sample data and perform preprocessing according to the structural parameters, build a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, use the sample data to train the proxy model, and configure the proxy model parameters; The trained proxy model is used to obtain the optimal structural parameters of the target ultra-wideband antenna, and the optimal structural parameters are simulated and verified to obtain a design scheme of the target ultra-wideband antenna; The agent model is constructed based on the NAR dynamic network combined with the multi-layer perceptron. Specifically: Obtaining data samples after integration of data of various structural parameter categories, performing data fusion on the data samples using a Copula function to obtain a data sample set based on Copula tail correlation fusion, and dividing the data sample set into training samples and test samples; Initialize the network parameters of the NAR dynamic network, optimize the delay order and the number of hidden layer neurons based on the improved genetic algorithm, use the BP algorithm to train the NAR dynamic network, adjust the connection weights of the NAR dynamic network according to the error data, and obtain the optimized NAR dynamic network through iterative training; Obtain the output data of the optimized NAR dynamic network, import it into the multi-layer perceptron for training, fine-tune the model parameters of the NAR dynamic network and the multi-layer perceptron based on the training results, stop training, obtain the test error based on the test sample, and output the proxy model with the configured parameters when the test error is less than the preset error threshold; Initialize the network parameters of the NAR dynamic network and optimize the delay order and the number of hidden layer neurons based on the improved genetic algorithm. Specifically: Initializing the network parameters of the NAR dynamic network, mapping the network parameters using a Circle chaotic sequence to generate a chaotic population, and mapping the obtained chaotic population to genetic population individuals to generate a chaotic initialization population; Generating reverse positions of individuals in the chaotic initialization population, constructing a reverse population, merging the chaotic initialization population and the reverse population, and selecting dominant individuals through evaluation to generate a final population; An improved genetic algorithm is used to optimize individuals in the population. The fitness of individuals in the population is calculated based on the average accuracy of the test samples as the fitness function. In the iterative process, adaptive mutations and dynamic weights that change with the number of iterations are introduced to enhance the ability to search for excellent individuals. The fitness of individuals is continuously calculated through iteration, and individuals are selected, crossed, and adaptively mutated to generate the next generation population. After completing the set number of iterations, the optimal delay order and the optimal number of hidden layer neurons of the NAR dynamic network are obtained.

2. The ultra-wideband antenna design method based on deep learning according to claim 1, characterized in that: Extracting antenna design example data based on the design goal, and extracting structural parameters related to antenna performance based on the antenna design example data, specifically: The design goal is segmented and the word vector is processed by pre-training the antenna design keyword library. Keywords are extracted based on similarity calculation, different keywords and their corresponding values ​​are determined, and the design goal keywords and corresponding values ​​are used to construct a retrieval task: Based on the retrieval task, antenna design example data that meets the preset requirements is extracted from historical ultra-wideband antenna design data. The retrieved antenna design example data is structured and a heterogeneous graph of different design target keywords is constructed based on semantic association and data association. Extracting a meta-path starting from the design target keyword in the heterogeneous graph, constructing an adjacency matrix under two relationships based on semantic association and data association in the meta-path, and performing node feature aggregation based on the adjacency matrix under the two relationships using a graph attention network; The weights of the two relationships are obtained through relationship-level attention. Based on the weights of the two relationships and the total weight of the keyword nodes in the meta-path, the keyword nodes that meet the preset weight threshold are screened and further screened based on the type labels of the keyword nodes. Structural parameter categories related to antenna performance are obtained according to the screening results, and data integration is performed in antenna design example data using the structural parameter categories.

3. The ultra-wideband antenna design method based on deep learning according to claim 1, characterized in that: Obtain the output data of the optimized NAR dynamic network, import it into the multi-layer perceptron for training, and fine-tune the model parameters of the NAR dynamic network and the multi-layer perceptron based on the training results. Specifically: Obtaining output data of the NAR dynamic model during the training process, using the output data as input to a multilayer perceptron, initializing a network structure of the multilayer perceptron, and determining network parameters through iterative training; Using multiple fully connected layers in a multi-layer perceptron to perform feature dimensionality reduction on the output data, using a self-attention mechanism to assign weights to the reduced output data, and compressing the weighted features through a fully connected layer to obtain deep features; The NAR dynamic model is combined with the multi-layer perceptron to build an overall model. The root mean square error between the test data and the predicted output of the overall model is calculated as the test error. The model parameters of the overall model are adjusted using back propagation based on the test error. The goal is to minimize the test error. When it is less than the preset threshold, the proxy model with configured parameters is output.

4. The ultra-wideband antenna design method based on deep learning according to claim 1, characterized in that: Obtain the optimal structural parameters of the target ultra-wideband antenna, specifically: Importing structural parameters corresponding to the design objectives of the target ultra-wideband antenna into the optimized proxy model to obtain predicted optimal structural parameters, and obtaining simulation data based on the optimal structural parameters; Performing simulation calculations based on sample data corresponding to the structural parameters, obtaining simulation results of the sample data, calculating the degree of deviation between the simulation data of the optimal structural parameters and the simulation results of the sample data, and normalizing the degree of deviation; When the normalized deviation degree is less than a preset threshold, a design scheme of the target ultra-wideband antenna is generated according to the optimal structural parameters.

5. A deep learning-based ultra-wideband antenna design system, characterized in that: Implementing the ultra-wideband antenna design method based on deep learning as described in any one of claims 1 to 4, the system includes a design target acquisition unit, a structural parameter confirmation unit, a proxy model unit, a proxy model training unit and a simulation verification unit; The design target acquisition unit is responsible for acquiring the design target of the target ultra-wideband antenna; The structural parameter confirmation unit is responsible for extracting structural parameters related to antenna performance from antenna design example data according to design goals; The proxy model unit is responsible for constructing a proxy model based on the NAR dynamic network combined with a multi-layer perceptron, configuring the proxy model parameters through training, and using the proxy model to obtain the optimal structural parameters of the target ultra-wideband antenna; The agent model training unit is responsible for training the agent model using the improved genetic algorithm to obtain the optimal model parameters; The simulation verification unit is responsible for performing simulation verification on the optimal structural parameters, and obtaining the design scheme of the target ultra-wideband antenna after verification.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an ultra-wideband antenna design method program based on deep learning. When the ultra-wideband antenna design method program based on deep learning is executed by a processor, the steps of the ultra-wideband antenna design method based on deep learning as described in any one of claims 1 to 4 are implemented.

Images