Generative adversarial network-based truss structure power transmission tower generation method and related device

Abstract

The invention relates to the technical field of graph generation, and discloses a truss structure power transmission tower generation method based on a generative adversarial network and a related device, and the method comprises the steps: carrying out the power transmission tower graph structure generation operation based on the tower section vertical height, bottleneck width and root opening width of a power transmission tower, and obtaining a power transmission tower graph structure data set; the power transmission tower graph structure data set is adopted to carry out truss structure power transmission tower generative adversarial training on the initial TGN model to obtain a target TGN model, and the initial TGN model is constrained by conditional control vectors and comprises a GVAE generator and a GCN discriminator; and generating a truss structure power transmission tower in the target scene by adopting the target TGN model to obtain a generated power transmission tower. The technical problem that the design effect of the power transmission tower is poor due to the defects that an existing truss structure power transmission tower generation technology is complex in model operation, large in training difficulty, low in efficiency and the like can be solved.

Description

Technical Field

[0001] The present application relates to the field of graph generation technology, and in particular to a method and related device for generating a truss structure transmission tower based on a generative adversarial network. Background Art

[0002] The structural design of transmission towers requires comprehensive considerations from the aspects of safety, environmental protection, convenience, and economy. The traditional structural design method of transmission towers often adopts a digital design form assisted by SolidWorks and CAD as hardware. The digital model is manually built, the model is verified by mechanical calculation, and the structure is optimized. This method requires a lot of manual operation, and the designer must also have many years of experience in tower design. With the development of AI generative algorithms, tower design has begun to extend to the field of automation. Computers can automatically help realize structural modeling, mechanical calculations, system optimization and other operations, but this method requires designers to set constraints and specify optimization directions in advance. The computer itself does not have the ability to learn autonomously. At the same time, it is also necessary to consider the priority of each constraint to alleviate its potential conflicts.

[0003] The existing intelligent tower structure design generally refers to topology generation and subsequent tower material configuration using data-driven neural networks as the computing core. In the field of concrete layout of building structures, unlike the current preliminary exploration of the layout of shear walls in house-type buildings and the beam-rod structure layout problem using generative adversarial networks as the computing core, truss structure design requires training under non-given node sets, which is a graph structure generation problem. The current truss structure graph generation technology based on neural networks has limitations such as complex model operation, high training difficulty, and low efficiency, resulting in poor efficiency and effect of actual transmission tower design, making it difficult to adapt to actual application needs. Summary of the invention

[0004] The present application provides a truss structure transmission tower generation method and related devices based on a generative adversarial network, which are used to solve the technical problems that the existing truss structure transmission tower generation technology has defects such as complex model operation, high training difficulty and low efficiency, resulting in poor transmission tower design effects.

[0005] In view of this, the first aspect of the present application provides a method for generating a truss structure transmission tower based on a generative adversarial network, comprising:

[0006] Based on the vertical height, bottle mouth width and root opening width of the transmission tower, a transmission tower graph structure generation operation is performed to obtain a transmission tower graph structure dataset;

[0007] Using the transmission tower graph structure dataset to perform adversarial training on the initial TGN model for truss structure transmission tower generation, to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator;

[0008] The target TGN model is used to generate a truss structure transmission tower in a target scenario to obtain a generated transmission tower.

[0009] Preferably, the transmission tower graph structure generation operation is performed based on the vertical height of the tower section, the bottle mouth width and the root opening width of the transmission tower to obtain the transmission tower graph structure data set, including:

[0010] The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated;

[0011] Performing a graph structure splicing operation according to the transmission tower basic structure element to obtain graph structure data;

[0012] The graph structure data is converted into a node feature file and an adjacency relationship file to obtain a transmission tower graph structure data set.

[0013] Preferably, the transmission tower graph structure dataset is used to perform adversarial training on the initial TGN model for truss structure transmission tower generation to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator, and also includes:

[0014] By introducing latent variables, combining the GCN encoder and the FNN decoder to construct an initial generator, and configuring generation constraints of the conditional control vector for the initial generator, a GVAE generator is obtained;

[0015] Construct a GCN discriminator through the GCN network and FNN network framework;

[0016] The initial TGN model is obtained by combining the GVAE generator and the GCN discriminator according to the comprehensive loss function.

[0017] Preferably, the comprehensive loss function of the initial TGN model is expressed as:

[0018]

[0019] in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

[0020] The second aspect of the present application provides a truss structure transmission tower generation device based on a generative adversarial network, comprising:

[0021] A data generation unit is used to perform a transmission tower diagram structure generation operation based on a tower section vertical height, a bottle mouth width, and a root opening width of the transmission tower to obtain a transmission tower diagram structure data set;

[0022] A model training unit, used to perform adversarial training of truss structure transmission tower generation on an initial TGN model using the transmission tower graph structure data set to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator;

[0023] The target generation unit is used to generate a truss structure transmission tower under a target scenario by using the target TGN model to obtain a generated transmission tower.

[0024] Preferably, the data generating unit is specifically used for:

[0025] The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated;

[0026] Performing a graph structure splicing operation according to the transmission tower basic structure element to obtain graph structure data;

[0027] The graph structure data is converted into a node feature file and an adjacency relationship file to obtain a transmission tower graph structure data set.

[0028] Preferably, it also includes:

[0029] A generator construction unit is used to construct an initial generator by combining the introduced latent variables with the GCN encoder and the FNN decoder, and configure generation constraints of the conditional control vector for the initial generator to obtain a GVAE generator;

[0030] The discriminator building unit is used to build a GCN discriminator through the GCN network and FNN network framework;

[0031] The model generation unit is used to obtain an initial TGN model by combining the GVAE generator and the GCN discriminator according to a comprehensive loss function.

[0032] Preferably, the comprehensive loss function of the initial TGN model is expressed as:

[0033]

[0034] in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

[0035] A third aspect of the present application provides a truss structure transmission tower generation device based on a generative adversarial network, the device comprising a processor and a memory;

[0036] The memory is used to store program code and transmit the program code to the processor;

[0037] The processor is used to execute the method for generating a truss structure transmission tower based on a generative adversarial network described in the first aspect according to the instructions in the program code.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing program code, wherein the program code is used to execute the method for generating a truss structure transmission tower based on a generative adversarial network as described in the first aspect.

[0039] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0040] In the present application, a method for generating a truss structure transmission tower based on a generative adversarial network is provided, including: performing a transmission tower graph structure generation operation based on the vertical height of a tower section, a bottle mouth width, and a root opening width of the transmission tower to obtain a transmission tower graph structure data set; using the transmission tower graph structure data set to perform truss structure transmission tower generation adversarial training on an initial TGN model to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator; using the target TGN model to generate a truss structure transmission tower in a target scenario to obtain a generated transmission tower.

[0041] The truss structure transmission tower generation method based on generative adversarial network provided by the present application generates a transmission tower graph structure data set based on the transmission tower structure feature data, and generates adversarial training on the constructed initial TGN model based on this data set, which can optimize the truss structure transmission tower graph generation performance of the model, thereby obtaining the target TGN model, and the generative adversarial model can quickly generate a truss structure transmission tower graph with good effect; this process constructs a targeted training data set for model training, making the model training more feasible, and the constructed generative adversarial model structure is relatively simple, the data processing is not complicated, and the graph structure generation efficiency of the model can be improved to a certain extent. Therefore, the present application can solve the technical problem that the existing truss structure transmission tower generation technology has defects such as complex model operation, high training difficulty and low efficiency, resulting in poor transmission tower design effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a flow chart of a method for generating a truss structure transmission tower based on a generative adversarial network provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a truss structure transmission tower generation device based on a generative adversarial network provided in an embodiment of the present application;

[0044] Figure 3 Schematic diagrams of 8 typical transmission tower truss structural elements provided in the embodiments of the present application;

[0045] Figure 4 An example diagram of a transmission tower structure generated based on a transmission tower truss structure element provided in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of the initial TGN model network structure provided in the embodiment of the present application;

[0047] Figure 6 A schematic diagram comparing the discrimination values ​​of different samples from different batches provided for the experimental case of this application;

[0048] Figure 7 Schematic diagram of the changes in the comprehensive loss function of the TGN model provided for the experimental case of this application;

[0049] Figure 8 Schematic diagram of the changes in the prior loss and reconstruction loss functions provided for the experimental cases of this application;

[0050] Fig. 9 An example diagram of the transmission tower section structure generated under different training batches provided for the experimental case of this application. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] For easier understanding, see Figure 1 , an embodiment of a truss structure transmission tower generation method based on a generative adversarial network provided in the present application includes:

[0053] Step 101: Perform a transmission tower graph structure generation operation based on the vertical height of the tower section, the bottle mouth width and the root opening width of the transmission tower to obtain a transmission tower graph structure data set.

[0054] Furthermore, step 101 includes:

[0055] The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated;

[0056] Perform graph structure splicing operations according to the basic structural elements of the transmission tower to obtain graph structure data;

[0057] The graph structure data is converted into node feature files and adjacency relationship files to obtain the transmission tower graph structure dataset.

[0058] It should be noted that in order to achieve network training, the application of creating graph structure datasets based on the determined generator scheme in the field of truss structure design is not mature, so there is currently a lack of transmission tower truss graph structure datasets available for training. Therefore, this embodiment generates a variety of transmission tower basic structure elements based on the vertical height of the tower section, the bottle mouth width and the root opening width according to the number of occurrences; please refer to Figure 3 , 8 typical transmission tower truss structural elements are given in the figure. Then these 8 structures are used as the basic structural elements of the transmission tower. The data set is randomly spliced ​​by 8 structures according to the upper and lower root opening ranges. Please refer to Table 1. Among them, taking structure 1 as the height unit, it is deduced that structure 2 is 2 sections, structures 3~4 are 3 sections, and structures 5~8 are 4 sections. The total number of spliced ​​sections is mainly 5~10 sections. Each spliced ​​structure case contains 2~3 structural elements. A total of 200 graph structure data are produced and converted into node feature and adjacency relationship files for graph generation network training.

[0059] Table 1 Boundary condition range of transmission tower foundation structure element

[0060]

[0061] According to the above transmission tower basic structure elements, we can get the following Figure 4 In the tower segment shown in the figure, when the bottle mouth width and the root opening width meet the splicing conditions, multiple structural elements are randomly spliced. Among them, the node feature is the node coordinate [X n ,Y n ], which is embedded and fused with the adjacency matrix as node embedding features, and the tower section contour features are used as conditions to control the generated graph structure at the graph level. In the graph dataset, the node adjacency matrix is ​​in the form of paired vector groups, the maximum number of graph edges is 60, the number of nodes is 32, and all graphs are symmetrical structures. Based on this, a transmission tower graph structure dataset for network training can be constructed, which contains node feature files and adjacency relationship files. The node feature file contains the positional relationship of the nodes, and the adjacency relationship file contains the topological features of the graph. The training set and test set of the entire dataset are divided into a ratio of 8:2.

[0062] Step 102: Use the transmission tower graph structure dataset to perform adversarial training on the initial TGN model for truss structure transmission tower generation to obtain a target TGN model. The initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator.

[0063] Furthermore, step 102, before that, also includes:

[0064] By introducing latent variables, combining GCN encoder and FNN decoder to build the initial generator, and configuring the generation constraints of the conditional control vector for the initial generator, we get the GVAE generator.

[0065] Construct a GCN discriminator through the GCN network and FNN network framework;

[0066] The initial TGN model is obtained by combining the GVAE generator and the GCN discriminator based on the comprehensive loss function.

[0067] Furthermore, the comprehensive loss function of the initial TGN model is expressed as:

[0068]

[0069] in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

[0070] See also Figure 5The TGN (Truss Generation Network, the network structure constructed in this embodiment) model for truss structure transmission tower generation in this embodiment includes a GVAE generator in the upper part and a GCN discriminator in the lower part; the GVAE (Generation Variational Auto Encoder) generator in the upper part can use the latent space conjugation to convert node embedding into an envelope-invariant graph-level encoding, while allowing learning and generating graphs of variable size on any number of graphs; the GCN discriminator in the lower part can realize discriminant analysis of images. Specifically, the network is mainly divided into two parts, namely the generator and the discriminator. The generator is actually a variational autoencoder, which uses the latent vector distribution encoded by the data set and the SAMPLE label (i.e. vertical height, bottle mouth width, root opening width) as network input, and the network output is the reconstructed graph structure and the generated graph structure. The reconstructed graph structure is input to discriminator 1 and the previous latent distribution to calculate the reconstruction loss, which is used to measure the training status inside the variational autoencoder. The generated graph structure means a new structure generated by the label and decoder part. The generation loss is obtained through discriminator 1 and discriminator 2, which is used to measure the training status of the overall network architecture. When the node order changes, the model can ensure the one-to-one mapping relationship between the graph and the selected structure without retraining; the model can explore graphs of different sizes and arbitrary node orders; it can also strengthen the mapping relationship between the boundary condition control vector space and the node structure space to ensure the efficiency and robustness of the model.

[0071] It can be found that the GVAE generator of this embodiment is constructed based on the GCN (Graph Convolutional Network) encoder and the FNN (Feedforward Neural Network) decoder, and is configured with a conditional control vector for image generation constraints; while the GCN discriminator is constructed based on the GCN network and the double-layer FNN network. In addition, the conditional control vector mainly considers three factors, namely the vertical height of the tower section, the bottle mouth width and the root opening width; in order to facilitate the propagation of network parameters, this embodiment performs a small-scale staged merging, in which the merged tower section vertical height is divided into 6 categories, namely 5 to 10 basic tower section structures, the bottle mouth width is divided into 8 categories, each 1000mm is a category, namely 0 to 8000mm; the root opening width is 10 categories, each 1000mm is a category, namely 0 to 10000mm, and the three are composed of the conditional control vector of the graph structure in the form of a unique hot vector. ; Based on the classification, it can be seen that the dimension of the conditional control vector is 6+8+10=24.

[0072] In the GVAE generator, the graph generation structure adjacency matrix is ​​feature embedded through the Encoder graph convolutional network encoder, that is, given a graph structure G={V, E}, the node feature X=X(A) is generated according to the graph structure adjacency matrix A, and embedded with the standard k-dim spectrum. Gaussian random vectors can also be used instead of spectral embedding, and the specific details are not limited.

[0073] It should be noted that this embodiment introduces latent variables in the encoding stage of the GVAE generator , which is calculated by the node feature X and the structural adjacency matrix A, can be expressed as:

[0074]

[0075] Where n represents the number of nodes, Indicates that under the given observation data X and graph structure A, the i-th hidden variable The posterior distribution of Can be viewed as a graph structure node Node embedding features, where Representing a set of graph-structured nodes by using a single latent space vector distribution For all Modeling, specifically expressed as:

[0076]

[0077] in, , , Respectively represent the mean of the latent space vector, represented by the function The calculated mean value is obtained by the function The calculated standard deviation is represents a diagonal matrix of squared standard deviations, Indicates is the Gaussian distribution with the covariance matrix of the mean; It is a two-layer GCN network, where is the symmetric normalized adjacency matrix of the graph structure G, expressed as , is its degree matrix, expressed as , , All are network parameters; , Represent the mean and standard deviation matrices respectively, and share the first layer network parameters ; yes The mean or standard deviation of the i-th row.

[0078] This embodiment introduces latent variables in the encoding stage of the generator This not only enables the model to perform network training on different sets of node graph structures, but also allows for graph-level variational coding, while also considering the impact of conditional control vectors on network parameters, and ensuring the permutation invariance of the model. Specifically, the graph structure generator used in this embodiment can be obtained by extracting latent space vectors from the latent space vectors. Based on this, a graph of any size m can be generated. Moreover, the conditional control vector can be synchronously embedded during the training of the generator, thereby realizing the training control of the network parameters.

[0079] For the ideal number After sampling, in order to improve the decoding performance of the GCN decoder in the GVAE generator, several layers of fully connected feedforward neural networks f are attached to the GCN decoder before the sigmoid function operation. The specific expression is:

[0080]

[0081] in, Indicates that given the hidden variable Under the condition of, the probability of graph structure A is, Indicates that given the hidden variable and Under the condition of , the probability that there is an edge between node i and node j is, Represents the sigmoid function, which is used to map the input to the (0,1) interval. Represents hidden variables The result after the fully connected feedforward neural network transformation can be expressed as:

[0082]

[0083]

[0084]

[0085] in, is the overall loss of the variational autoencoder, i.e., the loss of the GVAE generator; The loss function is essentially the reconstruction term of the variational autoencoder loss function, which means that its decoder reconstructs the expected log-likelihood of the input data Z based on the latent variable Z; The loss function is essentially the KL divergence term of the variational autoencoder loss function, which is used to describe the potential posterior distribution of the generated graph structure. With Gaussian prior distribution The difference between them; at the same time, the KL divergence term plays a role in restricting the balance of the reconstruction term to avoid overfitting of the model; Indicates that under the given observation data X and graph structure A, the hidden variable The posterior distribution of represents the Kullback-Leibler divergence, represents the Gaussian prior distribution, which can be expressed as:

[0086]

[0087] in, represents the identity matrix; is the mean of the latent space vector; Represents n independent vectors with a mean of 0 and a covariance matrix that is the identity matrix The joint probability distribution model of multivariate Gaussian distribution. is the Gaussian prior distribution based on the Kullback-Leibler divergence The prior loss of is the link reconstruction loss. The above is the encoding and decoding calculation process in the GVAE generator of the TGN model in this embodiment.

[0088] Since the graph structure data generation process of the GVAE generator is still not permutation-invariant, this embodiment constructs a permutation-invariant graph structure discriminator based on the GCN network and the two-layer FNN network, namely the GCN discriminator; the discriminator can learn based on the link reconstruction loss The generated adjacency matrix With the original adjacency matrix Specifically, a two-layer GCN network is constructed, and then connected to a two-layer FNN network; from the overall model, it is trained together with the encoder and decoder of the GVAE generator mentioned above; the network training of the graph structure is completed by optimizing the GAN generation loss of the minimax game, and the GAN generation loss is expressed as:

[0089]

[0090] in, , , Represents spectral embedding, through After the operation, the encoding , is permutation invariant, that is ,in, Represents a matrix rearrangement operation.

[0091] The comprehensive loss function of the initial TGN model The variable weighting parameters in , The weight of different losses can be adjusted; in the process of using the transmission tower graph structure dataset to perform adversarial training on the initial TGN model for truss structure transmission tower generation, the combination function is not used to update all model parameters. The following update rules are used in each training batch to update the model parameters:

[0092]

[0093] in, , , Represent the weight matrices of the encoder, decoder / generator, and discriminator respectively, , , Represent the back propagation gradients of the three respectively; Represents the update operation of the model parameters, that is, updating the corresponding model weight matrix based on the current gradient calculation.

[0094] Combined with comprehensive loss function , the transmission tower graph structure dataset and the above update rule formula can be used to perform generative adversarial training on the initial TGN model for truss structure transmission towers to obtain the target TGN model.

[0095] Step 103: Use the target TGN model to generate a truss structure transmission tower in the target scenario to obtain a generated transmission tower.

[0096] The target TGN model can be directly applied in the actual target scene. By inputting the actual vertical height, bottle mouth width, root opening width and other data requirements in the target scene, the target TGN model can generate a truss structure transmission tower. The specific generation process is similar to the data processing of the training process, which will not be repeated here. The model is simple to operate and highly efficient, which can meet the application requirements of actual scenes. In addition, given that its training process is supported by a reliable loss function and a large number of transmission tower graph structure data sets prepared in advance, the overall training process is not difficult; overall, the model has great engineering significance.

[0097] For ease of understanding, this application provides an experimental case of a truss structure transmission tower generation method based on a generative adversarial network. This process uses NVIDIA GeForce RTX3090GPU for training. The data set is a typical truss transmission tower graph structure data set that has been constructed. The data includes conditional control vector files, node feature files, and adjacency relationship files. The network loss calculation uses a cross entropy loss function, the learning rate is 0.003, the maximum training round is 200, and the discrimination values ​​of different batches and different samples can be found in Figure 6The three curves represent the discriminant values ​​after pre-training sampling, which are used to measure the discriminant performance of the variational autoencoder during pre-training. Figure 6 It can be seen that during the pre-training process of the discriminator D, through the cross entropy loss calculation of the downsampled value and the target value, and the gradient back propagation, it can be seen that the discriminator's discrimination value for real samples gradually increases, and the discrimination value for the variational autoencoder reconstruction and the noise sample gradually decreases, indicating that the discriminator's ability to distinguish between real and false samples continues to improve with the progress of training. At 200 epochs, it already has a strong judgment ability, and the discrimination value K after downsampling of true and false samples is Dis It has reached 0.9 and 0.1. As the discriminator's capabilities improve, during the formal training period, the discriminator and the generator are trained alternately. The generator gradually has the ability to generate graph structures that the discriminator cannot distinguish between true and false, reaching a Nash equilibrium state.

[0098] After the discriminator pre-training is completed, the decoder Decoder / G generator is added to the joint training process. The total loss of the generator G and the discriminator D can be found in Figure 7 , the two loss curves represent the overall loss of the generator and the discriminator respectively. It can be seen that with the increase of the number of epochs, the generator loss and the discriminator loss gradually approach the intermediate value of 0 (after regularization), that is, the generator and the discriminator have reached the Nash equilibrium, indicating that the truss scheme generated by the generative adversarial network is indistinguishable from the real sample in the discriminator.

[0099] See also Figure 8 , the prior loss L during the overall training process prior and the reconstruction loss L rec It approaches zero and maintains a low level for a long time. It can be seen that the Encoder-Decoder structure has a good effect on the reconstruction of the truss structure. The model converges very quickly. During the reconstruction process, the generated truss model embedding matrix has a high similarity with the original real sample.

[0100] After 200 epochs of training, the truss transmission tower structure generated based on the model can be obtained according to different boundary condition control vectors. For details, please refer to Fig. 9 After 200 epochs of training, the generator has the ability to conditionally generate specific truss structures, and can be judged from the number of basic tower segment units. The generation results of the network are controlled by the conditional control vector. As the label value increases, the vertical height, bottle mouth width and root opening width of the generated tower segment are constantly increasing, and the complexity of the truss is also increasing. It can be seen that the constructed graph generation adversarial network framework can be used for the overall intelligent design of the truss structure inside the transmission tower, and can also be connected with the material selection and tower segment merging work in the subsequent design links.

[0101] The truss structure transmission tower generation method based on generative adversarial network provided in the embodiment of the present application generates a transmission tower graph structure data set based on the transmission tower structure feature data, and performs generative adversarial training on the constructed initial TGN model based on this data set, which can optimize the truss structure transmission tower graph generation performance of the model, thereby obtaining the target TGN model, and the generative adversarial model can quickly generate a truss structure transmission tower graph with good effect; this process constructs a targeted training data set for model training, making the model training more feasible, and the constructed generative adversarial model structure is relatively simple, the data processing is not complicated, and the graph structure generation efficiency of the model can be improved to a certain extent. Therefore, the embodiment of the present application can solve the technical problem that the existing truss structure transmission tower generation technology has defects such as complex model operation, high training difficulty and low efficiency, resulting in poor transmission tower design effect.

[0102] For easier understanding, see Figure 2 The present application provides an embodiment of a truss structure transmission tower generation device based on a generative adversarial network, including:

[0103] The data generating unit 201 is used to generate a transmission tower graph structure based on the vertical height of the tower section, the bottle mouth width and the root opening width of the transmission tower to obtain a transmission tower graph structure data set;

[0104] A model training unit 202 is used to perform adversarial training of truss structure transmission tower generation on an initial TGN model using a transmission tower graph structure dataset to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator;

[0105] The target generation unit 203 is used to generate a truss structure transmission tower in a target scenario by using a target TGN model to obtain a generated transmission tower.

[0106] Furthermore, the data generating unit 201 is specifically configured to:

[0107] The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated;

[0108] Perform graph structure splicing operations according to the basic structural elements of the transmission tower to obtain graph structure data;

[0109] The graph structure data is converted into node feature files and adjacency relationship files to obtain the transmission tower graph structure dataset.

[0110] Furthermore, it also includes:

[0111] A generator construction unit 204 is used to construct an initial generator by combining the introduced latent variables with the GCN encoder and the FNN decoder, and configure generation constraints of the conditional control vector for the initial generator to obtain a GVAE generator;

[0112] A discriminator construction unit 205 is used to construct a GCN discriminator through a GCN network and a FNN network framework;

[0113] The model generation unit 206 is used to obtain an initial TGN model by combining the GVAE generator and the GCN discriminator according to the comprehensive loss function.

[0114] Furthermore, the comprehensive loss function of the initial TGN model is expressed as:

[0115]

[0116] in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

[0117] The present application also provides a truss structure transmission tower generation device based on a generative adversarial network, the device comprising a processor and a memory;

[0118] The memory is used to store the program code and transmit the program code to the processor;

[0119] The processor is used to execute the truss structure transmission tower generation method based on the generative adversarial network in the above method embodiment according to the instructions in the program code.

[0120] The present application also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the truss structure transmission tower generation method based on the generative adversarial network in the above method embodiment.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0125] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A truss structure transmission tower generation method based on a generative adversarial network, characterized in that: include: Based on the vertical height, bottle mouth width and root opening width of the transmission tower, a transmission tower graph structure generation operation is performed to obtain a transmission tower graph structure dataset; Using the transmission tower graph structure dataset to perform adversarial training on the initial TGN model for truss structure transmission tower generation, to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator; The target TGN model is used to generate a truss structure transmission tower in a target scenario to obtain a generated transmission tower.

2. The method for generating a truss structure transmission tower based on a generative adversarial network according to claim 1, characterized in that: The transmission tower graph structure generation operation is performed based on the vertical height of the tower section, the bottle mouth width and the root opening width of the transmission tower to obtain a transmission tower graph structure data set, including: The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated; Performing a graph structure splicing operation according to the transmission tower basic structure element to obtain graph structure data; The graph structure data is converted into a node feature file and an adjacency relationship file to obtain a transmission tower graph structure data set.

3. The method for generating a truss structure transmission tower based on a generative adversarial network according to claim 1, characterized in that: The transmission tower graph structure dataset is used to perform adversarial training on the initial TGN model for truss structure transmission tower generation to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator, and also includes: By introducing latent variables, combining the GCN encoder and the FNN decoder to construct an initial generator, and configuring generation constraints of the conditional control vector for the initial generator, a GVAE generator is obtained; Construct a GCN discriminator through the GCN network and FNN network framework; The initial TGN model is obtained by combining the GVAE generator and the GCN discriminator according to the comprehensive loss function.

4. The method for generating a truss structure transmission tower based on a generative adversarial network according to claim 3, characterized in that: The comprehensive loss function of the initial TGN model is expressed as: in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

5. A truss structure transmission tower generation device based on a generative adversarial network, characterized in that: include: A data generation unit is used to perform a transmission tower diagram structure generation operation based on a tower section vertical height, a bottle mouth width, and a root opening width of the transmission tower to obtain a transmission tower diagram structure data set; A model training unit, used to perform adversarial training of truss structure transmission tower generation on an initial TGN model using the transmission tower graph structure data set to obtain a target TGN model, wherein the initial TGN model is constrained by a conditional control vector and includes a GVAE generator and a GCN discriminator; The target generation unit is used to generate a truss structure transmission tower under a target scenario by using the target TGN model to obtain a generated transmission tower.

6. The truss structure transmission tower generation device based on generative adversarial network according to claim 5, characterized in that: The data generating unit is specifically used for: The transmission towers are sorted and screened based on the vertical height, bottle mouth width and root opening width of the transmission towers, and multiple transmission tower foundation structure elements are generated; Performing a graph structure splicing operation according to the transmission tower basic structure element to obtain graph structure data; The graph structure data is converted into a node feature file and an adjacency relationship file to obtain a transmission tower graph structure data set.

7. The truss structure transmission tower generation device based on generative adversarial network according to claim 5, characterized in that: Also includes: A generator construction unit is used to construct an initial generator by combining the introduced latent variables with the GCN encoder and the FNN decoder, and configure generation constraints of the conditional control vector for the initial generator to obtain a GVAE generator; The discriminator building unit is used to build a GCN discriminator through the GCN network and FNN network framework; The model generation unit is used to obtain an initial TGN model by combining the GVAE generator and the GCN discriminator according to a comprehensive loss function.

8. The truss structure transmission tower generation device based on generative adversarial network according to claim 7, characterized in that: The comprehensive loss function of the initial TGN model is expressed as: in, is the prior loss, is the reconstruction loss, To generate the loss, , is a variable weighting parameter.

9. A truss structure transmission tower generation device based on a generative adversarial network, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the method for generating a truss structure transmission tower based on a generative adversarial network as described in any one of claims 1 to 4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the method for generating a truss structure transmission tower based on a generative adversarial network as described in any one of claims 1 to 4.

Images