Traffic engineering structure design scheme recommendation method fusing physical information and neural network

Abstract

The invention relates to the technical field of traffic engineering investigation design scheme recommendation, and discloses a traffic engineering structure design scheme recommendation method fusing physical information and a neural network, and the method comprises the steps: obtaining the feature parameters of a design scheme, and determining an input parameter vector group according to the feature parameters, the input parameter vector group is obtained by vectorization and perturbation according to the characteristic parameters; inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group; physical information and evaluation indexes of the design schemes are obtained, scheme check calculation and index evaluation are conducted on all the design schemes in the design scheme group according to the physical information and the evaluation indexes of the design schemes, and evaluation scores of all the design schemes are obtained; and determining a recommendation scheme according to the evaluation score of each design scheme. According to the method, the traffic engineering investigation design scheme can be accurately evaluated, so that the accuracy of the recommended scheme is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of traffic engineering survey and design scheme recommendation, and in particular to a method for recommending design schemes for traffic engineering structures by integrating physical information and neural networks. Background Art

[0002] With the development of artificial intelligence technology, scientists have proposed various neural networks, including the more classic ones LeNet, AlexNet, VGG, ResNet and GoogLeNet. As artificial intelligence penetrates into various industries, more and more industries have realized the digital transformation of the industry through the empowerment of intelligent technology. The biggest difficulty at present is to solve the actual industry business through intelligent technology. The existing neural network cannot completely solve the actual problems in the process of industry implementation.

[0003] This is because the solutions in the field of business are not the only optimal solutions, and the pros and cons of each solution often need to be judged based on specific scenarios and business goals. Taking the traffic engineering survey and design industry as an example, the specific problems are: (1) Non-unique optimal solution: The problems in the field of traffic engineering survey and design are often diverse and unique, resulting in different solutions for the same project due to factors such as design concepts and engineering requirements. The design solution generated by the artificial intelligence algorithm may be just one of many possible solutions, and it is difficult to guarantee that it is the optimal solution. For example, the artificial intelligence algorithm may generate a design solution with low economic cost in a certain project, but in another project, due to differences in environmental factors and engineering requirements, the same solution may no longer be applicable. (2) Limitations of traditional evaluation indicators: Traditional evaluation indicators such as cost, cycle, quality, etc. can often only evaluate the design solution from one or several dimensions, and it is difficult to fully reflect the pros and cons of the solution. In the traffic engineering survey and design industry, for example, a design solution may perform well in terms of cost and cycle, but may cause quality problems due to ignoring certain special engineering requirements. (3) Dependence on professional knowledge: Traffic engineering survey and design work is highly dependent on professional knowledge and experience, and the solutions generated by artificial intelligence algorithms need to be evaluated by professional engineers. For example, AI algorithms may propose innovative solutions for structural layout, but whether they can meet the structural safety and functional requirements needs to be judged by experienced structural engineers. (4) Complexity of practical application: The actual application scenarios of traffic engineering survey and design work are complex and changeable, and the solutions generated by AI algorithms need to be verified in actual projects. For example, a design solution that performs well in a simulation environment may face unexpected challenges in actual construction, such as construction condition restrictions and material supply problems. (5) The need for innovation in evaluation methods: In view of the characteristics of the traffic engineering survey and design industry, it is necessary to explore new evaluation methods, such as a hybrid evaluation system that combines expert knowledge and AI algorithms. For example, expert systems can be used to assist in the evaluation of AI-generated design solutions. Expert systems can integrate domain knowledge and algorithm-generated data to provide a more comprehensive evaluation. (6) The importance of case libraries: Establishing a case library containing various traffic engineering survey and design cases can help AI algorithms learn and draw on past excellent design solutions. For example, by analyzing successful cases in the case library, AI algorithms can learn which design elements have achieved good results in different projects, and thus draw on these elements when generating new solutions.

[0004] In short, the design schemes in the field of traffic engineering survey and design have the characteristics of complex schemes, non-unique optimal solutions, and strong professional dependence. The current intelligent algorithm evaluation indicators cannot adapt to the quality of traffic engineering survey and design schemes generated by intelligent algorithms, and thus cannot evaluate the advantages and disadvantages of intelligent algorithms, resulting in poor accuracy of recommended schemes.

[0005] Therefore, how to accurately evaluate the design scheme of traffic engineering structures and effectively improve the accuracy of the recommended scheme is a problem that needs to be solved urgently.

[0006] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0007] The main purpose of this application is to provide a method for recommending design schemes for traffic engineering structures that integrates physical information and neural networks, aiming to solve the technical problem of how to accurately evaluate traffic engineering survey and design schemes, thereby effectively improving the accuracy of recommended schemes.

[0008] To achieve the above objectives, the present application proposes a method for recommending design solutions for traffic engineering structures by integrating physical information and neural networks, wherein the method comprises:

[0009] Acquire characteristic parameters of the design scheme, and determine an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters;

[0010] Inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and a plurality of regional fully connected output layers;

[0011] Acquiring physical information and evaluation indicators of the design schemes, and performing scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design schemes, to obtain an evaluation score for each design scheme;

[0012] A recommended solution is determined according to the evaluation scores of the various design solutions.

[0013] In one embodiment, the acquiring characteristic parameters of the design solution and determining the input parameter vector group according to the characteristic parameters includes:

[0014] Acquire characteristic parameters of the design scheme, and vectorize the characteristic parameters to obtain a characteristic parameter vector;

[0015] Several characteristic parameters in the characteristic parameter vector are perturbed to obtain an input parameter vector group.

[0016] In one embodiment, before inputting the input parameter vector group into the solution recommendation model to obtain the design solution group, the method further includes:

[0017] Get the sample library recommended by the solution;

[0018] Pre-training a single-tail neural network using samples in the sample library to obtain an initial recommendation model;

[0019] The initial recommendation model is trained in stages using the data samples in the sample library to obtain a solution recommendation model.

[0020] In one embodiment, the pre-training of a single-tail neural network using samples in the sample library to obtain an initial recommendation model includes:

[0021] Pre-training the single-tail neural network using samples in the sample library to obtain target weights;

[0022] The target weights are transferred to the multi-tail neural network to obtain an initial recommendation model.

[0023] In one embodiment, the acquiring of the physical information and evaluation index of the design scheme, and performing scheme verification and index evaluation on each design scheme in the design scheme group according to the physical information and evaluation index of the design scheme to obtain an evaluation score of each design scheme include:

[0024] Obtain physical information and evaluation indicators of the design solution;

[0025] Constructing a finite element model according to the physical information of the design scheme, and determining a target evaluation function according to the evaluation index of the design scheme;

[0026] According to the finite element model and the target evaluation function, scheme checking and index evaluation are performed on each design scheme in the design scheme group to obtain an evaluation score for each design scheme.

[0027] In one embodiment, performing scheme checking and index evaluation on each design scheme in the design scheme group according to the finite element model and the target evaluation function to obtain an evaluation score for each design scheme includes:

[0028] Performing scheme verification on each design scheme in the design scheme group by using the finite element model to obtain a set of verification results for each design scheme;

[0029] The target evaluation function is used to perform an index evaluation on the check result set of each design solution to obtain an evaluation score for each design solution.

[0030] In one embodiment, determining a recommended solution according to the evaluation scores of the various design solutions includes:

[0031] Sort the design solutions from high to low according to the evaluation scores of the design solutions to obtain a design solution sequence;

[0032] A design scheme with a ranking value of a preset value in the design scheme sequence is used as a recommended scheme.

[0033] In addition, to achieve the above purpose, the present application also proposes a traffic engineering structure design scheme recommendation device that integrates physical information and neural network, and the traffic engineering structure design scheme recommendation device that integrates physical information and neural network includes:

[0034] A determination module, used for acquiring characteristic parameters of the design scheme, and determining an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters;

[0035] An input module, used for inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and a plurality of regional fully connected output layers;

[0036] An evaluation module, used to obtain physical information and evaluation indicators of the design scheme, and perform scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score for each design scheme;

[0037] The determination module is further used to determine a recommended solution according to the evaluation scores of the various design solutions.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for recommending design schemes for traffic engineering structures that integrates physical information and neural networks. The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The computer program is configured to implement the steps of the method for recommending design schemes for traffic engineering structures that integrates physical information and neural networks as described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for recommending a design scheme for a transportation engineering structure that integrates physical information and neural networks as described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for recommending a design scheme for a traffic engineering structure that integrates physical information and a neural network as described above.

[0041] The present application provides a method for recommending design schemes for traffic engineering structures that integrates physical information and neural networks. The present application first obtains characteristic parameters of the design scheme, and determines an input parameter vector group based on the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters; the input parameter vector group is input into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and multiple regional fully connected output layers; the physical information and evaluation indicators of the design scheme are obtained, and scheme verification and indicator evaluation are performed on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score for each design scheme; a recommended scheme is determined based on the evaluation scores of each design scheme, so as to accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme.

[0042] In summary, the present application inputs the input parameter vector group obtained by vectorizing and perturbing the characteristic parameters of the design scheme into the scheme recommendation model, performs scheme verification and index evaluation on the design scheme group output by the model according to the physical information and evaluation indicators of the design scheme, and then determines the recommended scheme according to the evaluation scores of each design scheme. This overcomes the technical defect that the current intelligent algorithm evaluation indicators cannot adapt to the quality of the traffic engineering survey and design scheme generated by the intelligent algorithm, and thus cannot evaluate the advantages and disadvantages of the intelligent algorithm, resulting in poor accuracy of the recommended scheme. This application can accurately evaluate the traffic engineering survey and design scheme, and thus effectively improve the accuracy of the recommended scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 A flow chart of the first embodiment of the method for recommending a design scheme for a traffic engineering structure integrating physical information and a neural network is provided in this application;

[0046] Figure 2 A schematic diagram of the arrangement of pile foundations for a high-speed railway bridge provided in Example 1 of a method for recommending a design scheme for a transportation engineering structure integrating physical information and a neural network in this application;

[0047] Figure 3A double-tail neural network architecture diagram for pile foundation recommendation provided in Example 1 of the traffic engineering structure design scheme recommendation method integrating physical information and neural network in this application;

[0048] Figure 4 A schematic diagram of a comprehensive training method of "pre-training + staged training" provided in Example 1 of a traffic engineering structure design scheme recommendation method integrating physical information and neural network in this application;

[0049] Figure 5 A schematic diagram of the interface relationship between the pile foundation intelligent selection algorithm and the full bridge design subsystem provided in Example 1 of the traffic engineering structure design scheme recommendation method integrating physical information and neural network in this application;

[0050] Figure 6 A technical schematic diagram provided for the first embodiment of the method for recommending a design scheme for a traffic engineering structure integrating physical information and a neural network in this application;

[0051] Figure 7 A flowchart of pile foundation design based on intelligent selection of pile foundations based on a double-tail neural network is provided for the first embodiment of the method for recommending a design scheme for a traffic engineering structure integrating physical information and a neural network in this application;

[0052] Figure 8 A flow chart of Example 2 of a method for recommending a design scheme for a traffic engineering structure by integrating physical information and a neural network is provided in this application;

[0053] Fig. 9 A schematic diagram of the module structure of a traffic engineering structure design scheme recommendation device integrating physical information and neural network in an embodiment of the present application;

[0054] Fig.10 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the method for recommending a design solution for a traffic engineering structure that integrates physical information and a neural network in an embodiment of the present application.

[0055] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] The main solution of the embodiment of the present application is: obtaining characteristic parameters of the design scheme, and determining an input parameter vector group based on the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbation based on the characteristic parameters; inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and multiple regional fully connected output layers; obtaining physical information and evaluation indicators of the design scheme, and performing scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score of each design scheme; and determining a recommended scheme based on the evaluation scores of each design scheme.

[0059] The design schemes in the field of traffic engineering survey and design have the characteristics of complex schemes, non-unique optimal solutions, and strong professional dependence. The current intelligent algorithm evaluation indicators cannot adapt to the quality of traffic engineering survey and design schemes generated by intelligent algorithms, and thus cannot evaluate the pros and cons of intelligent algorithms, resulting in poor accuracy of recommended schemes. Therefore, how to accurately evaluate traffic engineering survey and design schemes and effectively improve the accuracy of recommended schemes is a problem that needs to be solved urgently.

[0060] The present application inputs an input parameter vector based on the characteristic parameters of the design scheme into a scheme recommendation model, evaluates multiple groups of design schemes output by the model according to evaluation indicators, and then determines a recommended scheme according to the evaluation scores of each design scheme. This overcomes the technical defect that the current intelligent algorithm evaluation indicators cannot adapt to the quality of the traffic engineering survey and design scheme generated by the intelligent algorithm, and thus cannot evaluate the advantages and disadvantages of the intelligent algorithm, resulting in poor accuracy of the recommended scheme. This application can accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme.

[0061] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a traffic engineering structure design scheme recommendation device integrating physical information and neural network, etc. The following takes the traffic engineering structure design scheme recommendation device integrating physical information and neural network as an example to illustrate this embodiment and the following embodiments.

[0062] Based on this, the embodiment of the present application provides a method for recommending a design scheme for a traffic engineering structure by integrating physical information and a neural network. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for recommending design solutions for traffic engineering structures that integrates physical information and neural networks in this application.

[0063] In this embodiment, the method for recommending a design scheme for a traffic engineering structure by integrating physical information and a neural network includes steps S10 to S40:

[0064] Step S10, acquiring characteristic parameters of the design scheme, and determining an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters.

[0065] It should be noted that the design scheme may be a design scheme for structures in the field of traffic engineering survey and design, for example, a bridge engineering pile group foundation scheme design, a tunnel engineering support scheme design, etc. This embodiment does not specifically limit this, and this embodiment is described by taking a bridge engineering pile group foundation scheme design as an example.

[0066] It is understandable that the characteristic parameters of a design scheme refer to a data set that can comprehensively describe the characteristics of the design scheme, including but not limited to geological conditions, load requirements, environmental restrictions, material properties, construction conditions and other aspects. In the design of a group pile foundation scheme for a bridge project, the characteristic parameters may be main beam type, main span length, main beam length, pier height, pier location, terrain features, etc., and this embodiment does not impose specific restrictions on this. In the design of a group pile foundation scheme for a bridge project, the design scheme is a pile foundation scheme, which is a combination of pile diameter and pile number to form different types of pile foundation configuration types, such as 8-1.0m and 10-1.25m respectively representing 8 piles. (pile diameter 1m) pile foundation and 10 There are more than 10 commonly used pile diameters, such as 1.0m, 1.25m, 1.5m, 1.8m, 2.0m, 2.2m, 2.5m, 3.0m, etc. The number of piles in each diameter is 8, 9, 10, 11, 12, 15, 16, 18, etc., which are not specifically limited in this embodiment.

[0067] like Figure 2 As shown, Figure 2 It is a schematic diagram of the pile foundation arrangement of a high-speed railway bridge, including pile foundation configuration types of 9-1.0m, 10-1.0m, 11-1.0m, and 12-1.0m. Among them, the pile foundation configuration type of 9-1.0m is a pile foundation configuration type with 9 foundation piles of 1m in diameter arranged in a determinant, the pile foundation configuration type of 10-1.0m is a pile foundation configuration type with 10 foundation piles of 1m in diameter arranged in a quincunx pattern, the pile foundation configuration type of 11-1.0m is a pile foundation configuration type with 11 foundation piles of 1m in diameter arranged in a quincunx pattern, and the pile foundation configuration type of 12-1.0m is a pile foundation configuration type with 12 foundation piles of 1m in diameter arranged in a determinant.

[0068] It is worth noting that the input parameter vector is obtained by organizing the characteristic parameters of the design scheme into a vector in a numerical form and perturbing it, and is used as the input of the scheme recommendation model. In the scenario of the design of the pile group foundation scheme of the bridge engineering, the input parameter vector may include but is not limited to the coded value of the main beam type, the specific value of the main span length, the specific value of the main beam length, the specific value of the pier height, the coordinate value of the pier position, the quantitative index of the terrain characteristics, etc. These numerical characteristic parameters can comprehensively and accurately reflect the characteristics of the design scheme, and provide a basis for the subsequent scheme recommendation and evaluation through the scheme recommendation model.

[0069] In a feasible implementation, step S10 may include: acquiring characteristic parameters of the design solution, and vectorizing the characteristic parameters to obtain a characteristic parameter vector; and perturbing several characteristic parameters in the characteristic parameter vector to obtain an input parameter vector group.

[0070] It should be noted that by vectorizing and perturbing the characteristic parameters, the complex information in the design scheme can be converted into a numerical form that can be recognized by the model, and a certain amount of variation can be introduced to explore the impact of different design parameters on the performance of the overall scheme, thereby obtaining input parameter vector groups for multiple groups of schemes.

[0071] It can be understood that vectorization means expressing characteristic parameters in vector form. In the design of pile group foundation scheme for bridge engineering, characteristic parameter vector = [main beam type, main span length, main beam length, pier height, pier location, terrain characteristics].

[0072] It is worth noting that perturbation refers to the introduction of a small change on the basis of the original characteristic parameter vector to simulate the impact of different design parameters on the performance of the scheme. This change can be randomly generated or based on certain rules. The specific perturbation method can be: select the quantized value of any one or more parameters in the characteristic parameter vector for a certain step increase / decrease, that is, the new parameter value = the original parameter value ±△, then the generated input parameter vector = [main beam type, main span length, main beam length △1, bridge pier height ±△2, bridge pier location, terrain characteristics]. Through the perturbation process, multiple groups of input parameter vectors corresponding to different schemes can be obtained, representing the possible situations of the design scheme under different parameter combinations. These vectors will be used as the input of the scheme recommendation model to evaluate the performance and advantages and disadvantages of different design schemes, thereby providing a scientific basis for decision-making.

[0073] Step S20, inputting the input parameter vector group into a solution recommendation model to obtain a design solution group, wherein the solution recommendation model includes an input layer, a fully connected common hidden layer, and a plurality of regional fully connected output layers.

[0074] It should be noted that the solution recommendation model is an intelligent solution recommendation algorithm based on neural networks or deep learning built according to the business needs of the domain, including an input layer, a fully connected public hidden layer, and multiple regional fully connected output layers. The input layer is used to receive and process the input parameter vector after vectorization and perturbation. The fully connected public hidden layer is responsible for capturing the complex relationships and potential patterns contained in the parameter vector. Through multi-level nonlinear transformations, it extracts feature representations that have a decisive influence on the performance of the design solution. These feature representations not only cover the direct relationship between the design parameters, but also imply their deep information interwoven through multiple factors such as bridge structural mechanics, environmental adaptability, and cost-effectiveness. Multiple regional fully connected output layers correspond to different design parameters. Each output layer is based on the feature representation extracted by the public hidden layer, and outputs the design parameters under the corresponding dimension through a specific weight matrix and activation function.

[0075] It can be understood that in the design of pile group foundation schemes for bridge engineering, the scheme recommendation model is the intelligent selection algorithm of pile foundation based on double-tail neural network. The network model consists of an input layer, a fully connected common hidden layer, and two parallel regional fully connected softmax output layers, namely, the pile foundation diameter decision tail and the pile foundation quantity decision tail. The model input layer consists of characteristic parameters such as main beam type, main span length, main beam length, pier height, pier location, and terrain characteristics. The model output layer consists of two parallel output layers, namely, the pile foundation quantity and pile foundation diameter. Figure 3 As shown, Figure 3 The double-tail neural network architecture diagram is recommended for pile foundation. The sum of the loss functions of the double-tail neural network is used as the total loss function. The specific formula is as follows:

[0076]

[0077] Among them, L conf is the loss value, A and B represent the double-tailed parts, namely the pile diameter label and the pile number label, and the 0 label represents the public hidden layer.

[0078] In the specific implementation, in the design of the pile foundation scheme of the bridge project, in order to evaluate the quality of the pile foundation scheme recommended by the pile foundation intelligent selection algorithm, multiple input parameters are formed by perturbing the characteristic parameters such as the main beam type, main span length, main beam length, pier height, pier position, terrain characteristics, etc., and inputting them into the pile foundation intelligent selection algorithm module, multiple design schemes such as low-level, standard-level and high-level can be generated, that is, the design scheme group. Specifically, the input parameter vector is input into the double-tail neural network pile foundation intelligent selection algorithm in sequence, and multiple recommended schemes such as low-level, standard-level and high-level are recommended. For example, according to physical common sense, the higher the pier, the larger the pile foundation directly needs to be in the pile foundation scheme, and the more piles there are. Then, the parameter values ​​of the pier height dimension in the input parameter vector [{pier height: pier height value - △2}, {pier height: pier height value}, {pier height: pier height value + △2}] correspond to the pier height values ​​input in the low-level, standard-level and high-level pile foundation schemes, respectively.

[0079] In a feasible implementation, before step S20, it also includes: obtaining a sample library for solution recommendation; pre-training a single-tail neural network with samples in the sample library to obtain an initial recommendation model; and training the initial recommendation model in stages with data samples in the sample library to obtain a solution recommendation model.

[0080] It should be noted that the sample library refers to a database consisting of multiple actual design schemes and their corresponding performance evaluation results. In the design of bridge engineering pile group foundation schemes, the sample library for scheme recommendation, namely the intelligent selection sample library for pile foundations, refers to a collection of bridge engineering pile group foundation design schemes and their performance evaluation results collected through actual engineering cases, expert experience, numerical simulation or experimental data. These samples contain rich design parameter information (such as main beam type, main span length, pier height, etc.) and corresponding performance evaluation indicators (such as bearing capacity, stability, economy, etc.), which are the basic data resources for building and training scheme recommendation models.

[0081] As shown in Table 1, Table 1 is an example table of the sample library for intelligent selection of pile foundations, which includes sample numbers and corresponding input data and sample labels, wherein the input data includes main beam type, main span length, main beam length, pier height, pier position, and terrain label, and the sample label includes the pile foundation type. For example, the input data of sample 1 includes that the main beam type is a simply supported beam, the main span length is 24m, the main beam length is 24m, the pier height is 1, the pier position is an edge, the terrain label is A, and the pile foundation type is 8-1.0m.

[0082] Table 1

[0083]

[0084] It can be understood that in this embodiment, the "pre-training + staged" comprehensive training method is used to train the neural network model. The overall technical principle is: first, the common hidden layer is trained according to the conventional fully connected single-tail neural network, and then the weights are transferred to the multi-tail neural network, and then the staged training method is adopted. Pre-training refers to the use of a large amount of sample data in the sample library for preliminary learning within the framework of the single-tail neural network, aiming to enable the network model to capture the basic characteristics and preliminary laws in the input data. Staged training means that on the basis of pre-training, according to specific design requirements and network architecture, the model is expanded to a multi-tail neural network, and refined training is carried out in stages, which can enhance the model's understanding and response capabilities to complex design problems, and ensure that the recommended design scheme not only meets actual needs, but also has high performance and economic benefits.

[0085] In a feasible implementation, the pre-training of a single-tail neural network with samples in the sample library to obtain an initial recommendation model includes: pre-training a single-tail neural network with samples in the sample library to obtain a target weight; and migrating to a multi-tail neural network according to the target weight to obtain an initial recommendation model.

[0086] It should be noted that pre-training is to enable the single-tail neural network to learn the basic mapping relationship between design parameters and pile foundation types through repeated iterative learning. In this process, the single-tail neural network gradually optimizes its internal parameters by continuously adjusting weights and biases to minimize prediction errors. When the single-tail neural network reaches a certain performance index on the sample library, the weight obtained by its training is the target weight.

[0087] It is understandable that migrating the target weights to the two-tailed neural network as the starting point of the initial recommendation model accelerates the training process of the two-tailed neural network and ensures that the model can inherit the basic features and rules learned by the single-tailed neural network, thereby adapting to complex design problems more quickly under the new network architecture.

[0088] In the specific implementation, in the design of the pile group foundation scheme of the bridge project, the phased training process will conduct independent training for each output layer of the double-tail neural network (i.e., the pile diameter decision tail and the pile number decision tail), which helps the model to more accurately capture the specific rules of each design parameter (pile diameter and pile number). Each output layer will gradually optimize its prediction performance based on the common features extracted by the common hidden layer, combined with its own specific weight matrix and activation function. After the independent training stage, joint training will be carried out. The purpose of joint training is to establish a more coordinated relationship between the two output layers and between them and the common hidden layer, to ensure that the entire network model can comprehensively consider all relevant factors when recommending design solutions and achieve the best overall performance. During the joint training process, network parameters such as weights, biases, learning rates, etc. will be continuously adjusted and optimized based on feedback from actual engineering cases to reduce the gap between the predicted values ​​and the actual values.

[0089] It is worth noting that in order to further improve the generalization ability and robustness of the model, regularization, dropout, early stopping and other training methods can be used. Regularization technology limits the complexity of the model by introducing additional penalty terms to prevent overfitting; dropout technology enhances the generalization ability of the model by randomly discarding some neurons during training; early stopping technology monitors the performance of the model on the validation set and terminates training in advance when the performance begins to decline to avoid overfitting. The combination of these technologies can significantly improve the adaptability and accuracy of the model when handling new engineering cases.

[0090] like Figure 4 As shown, Figure 4 Figure 1 is a schematic diagram of the comprehensive training method of "pre-training + staged training". The training process includes (a) pre-training model, (b) weight transfer, (c) freezing common + tail A weights, and (d) freezing common + tail B weights. The pre-training model refers to the process of enabling the single-tail neural network to learn the basic mapping relationship between design parameters and pile foundation types (including pile diameter and pile quantity) through repeated iterative learning, thereby obtaining the target weights. Weight transfer refers to migrating the target weights to the double-tail neural network. Freezing common + tail A weights refers to freezing the weights of the common hidden layer and tail A for pile diameter decision. Freezing common + tail B weights refers to freezing the weights of the common hidden layer and tail B for pile quantity decision.

[0091] Step S30, obtaining physical information and evaluation indicators of the design schemes, and performing scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design schemes to obtain an evaluation score for each design scheme.

[0092] It should be noted that the physical information of the design scheme refers to the various technical parameters specified in the business rules and design specifications of the design scheme, and the evaluation index refers to a series of quantitative standards used to measure the quality of the design scheme. In the design of the pile group foundation scheme of the bridge engineering project, the evaluation index may include pile foundation bearing capacity, stability analysis, settlement control, etc., and this embodiment does not make specific restrictions on this.

[0093] It is understandable that the solutions recommended by the intelligent algorithm need to be optimized through the objective evaluation function in combination with the physical information required by the business rules, that is, the solutions are compared by setting the objective evaluation function and constraints. Taking high-speed railways as an example, the objective optimization functions often set are project cost and construction difficulty, etc. This embodiment does not impose specific restrictions on this.

[0094] Step S40: determining a recommended solution according to the evaluation scores of the various design solutions.

[0095] It should be noted that the design scheme with the highest score can be automatically selected as the final recommended scheme according to the evaluation scores of the various design schemes, or the final recommended scheme can be determined by other methods, which is not specifically limited in this embodiment.

[0096] It is understandable that the process of determining the recommended solution not only depends on the absolute value of the evaluation score, but also needs to comprehensively consider the actual needs of the project, technical feasibility, economic costs, environmental impact, etc. Although the evaluation score provides a basis for quantitative evaluation, it can also be combined with expert opinions, historical case analysis, and the latest engineering technology progress for comprehensive judgment, thereby further improving the accuracy of the recommended solution.

[0097] In a feasible implementation, step S40 may include: sorting the design schemes from high to low according to their evaluation scores to obtain a design scheme sequence; and taking a design scheme with a preset sorting value in the design scheme sequence as a recommended scheme.

[0098] It should be noted that all generated solutions are sorted according to the scores, and the top-K solutions with the highest scores are selected as recommended solutions for detailed solution design.

[0099] It can be understood that in the design of pile foundation schemes for bridge projects, detailed design of the scheme is carried out according to the recommended scheme, that is, the bridge pile foundation design is carried out in the full bridge design subsystem of the bridge intelligent design system based on the double-tail neural network pile foundation intelligent selection algorithm. The specific process includes: (1) defining the sample format, abstracting and refining the sample format according to the bridge scheme elements that affect the pile foundation scheme; (2) constructing a sample set, collecting the parameters required by the sample format and the corresponding pile foundation types from existing bridge engineering projects; (3) designing a network model, using deep learning frameworks such as pytorch and tensorflow to define the neural network model of the pile foundation intelligent line selection algorithm, requiring the number of parameters in the input layer to be consistent with the number of parameters required by the sample format; (4) neural network training, inputting data samples into the neural network to start training, and stopping training when evaluation indicators such as accuracy, recall rate, and F1 value meet the evaluation depth requirements; (5) model migration and deployment, when the neural network model is successfully trained, it is deployed to the server and connected to the business system; (6) model reasoning application, carrying out the scheme in the bridge intelligent design system. Design: According to the bridge methods collected by the system, characteristic parameters such as main beam type, main span length, main beam length, pier height, pier location, and terrain characteristics are extracted, and input into the pile group foundation recommendation algorithm. The neural network model is used to recommend a specific pile foundation design scheme; (7) Expert review of the scheme: Based on the expert experience, the foundation of the bridge scheme is reviewed to determine the pile group scheme that meets the engineering requirements; (8) Scheme optimization and improvement: According to the expert review opinions, the original scheme is modified to a reasonable new scheme; (9) Scheme sample storage: The algorithm input main beam type, main span length, main beam length, pier height, pier location, terrain characteristics and other characteristic parameters, and the new scheme after expert review and optimization are combined into the database to form a new sample record; (10) Network model upgrade: With the design of the new bridge scheme, a large number of new sample data records are added to the sample set, and the new data set is re-called for model training to generate a new neural network model; (11) Repeat (5) to (10) for iterative cycles to achieve neural network upgrade; (12) Algorithm promotion and application: When the accuracy of the algorithm meets the needs of engineering design, it is promoted and applied.

[0100] like Figure 5 As shown, Figure 5The figure is a schematic diagram of the interface relationship between the pile foundation intelligent selection algorithm and the full bridge design subsystem. The bridge intelligent design system includes a pile foundation selection algorithm module, an intelligent span layout module, an intelligent optimization module, a parametric modeling module, a finite element calculation module and a full bridge design subsystem. The pile foundation selection algorithm module is interfaced with the full bridge design subsystem. In the pile foundation selection algorithm module, the foundation selection conditions are obtained from the foundation design in the full bridge design subsystem to determine whether to adopt the pile foundation scheme. If not, other foundation schemes are returned to the geometry engine in the full bridge design subsystem. If adopted, the pile foundation is intelligently selected and the pile foundation configuration library is queried. The pile foundation intelligent selection is achieved by summarizing the rule definition through the experience case library and combining it with the algorithm design, that is, the pile foundation configuration is defined according to the rule definition to form a pile foundation configuration library. The algorithm design calls the pile foundation configuration of the pile foundation configuration library. The pile foundation configuration library returns the configuration to the bridge foundation library in the full bridge design subsystem. The pile foundation sample library is archived according to the information in the bridge foundation library in the full bridge design subsystem, and then the intelligent algorithm training is performed, and then the pile foundation intelligent selection is deployed. In the full bridge design subsystem, the pile foundation scheme is called from the bridge foundation library and the scheme rendering display is realized through the geometry engine call, so as to obtain the foundation design in the bridge span scheme design.

[0101] like Figure 6 As shown, Figure 6 The technical schematic diagram of the method for recommending design schemes for transportation engineering structures that integrates physical information and neural networks is presented. An input parameter vector is generated through multi-condition perturbation, and model reasoning is performed based on the input parameter vector to obtain multi-scheme outputs. Multi-scheme analysis is performed, and multi-scheme evaluation is performed based on the objective function and constraints. The objective function is to minimize the cost, and the constraints are that parameters such as deformation, settlement, stiffness, and load-bearing are less than or equal to the limit values. The optimal scheme is recommended based on the scheme evaluation results, and the optimal scheme is added to the case library. The case library is used for model training and model migration.

[0102] like Figure 7 As shown, Figure 7 The pile foundation design flow chart based on the double-tail neural network pile foundation intelligent selection is as follows: first, the bridge scheme design is carried out, then the bridge foundation design is carried out, and then the pile foundation intelligent selection service is carried out. The design scheme of the pile foundation intelligent selection is reviewed by the scheme experts to determine whether it meets the design requirements. If not, the bridge foundation design is carried out again. If it meets the requirements, new cases are added to the database according to the design scheme, and finally the algorithm is promoted and applied. Among them, the pile foundation intelligent selection service specifically includes: defining the sample format; constructing a sample set; designing a multi-tail neural network; training the neural network model; adding a case sample library; model training and upgrading; and deploying the model to the server to realize the pile foundation intelligent selection service.

[0103] The present embodiment provides a method for recommending design schemes for traffic engineering structures that integrates physical information and neural networks. The present embodiment first obtains characteristic parameters of the design scheme, and determines an input parameter vector group based on the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters; the input parameter vector group is input into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and multiple regional fully connected output layers; the physical information and evaluation indicators of the design scheme are obtained, and scheme verification and indicator evaluation are performed on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score for each design scheme; a recommended scheme is determined based on the evaluation scores of each design scheme, so as to accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme.

[0104] In summary, the present application inputs the input parameter vector group obtained by vectorizing and perturbing the characteristic parameters of the design scheme into the scheme recommendation model, performs scheme verification and index evaluation on the design scheme group output by the model according to the physical information and evaluation indicators of the design scheme, and then determines the recommended scheme according to the evaluation scores of each design scheme. This overcomes the technical defect that the current intelligent algorithm evaluation indicators cannot adapt to the quality of the traffic engineering survey and design scheme generated by the intelligent algorithm, and thus cannot evaluate the advantages and disadvantages of the intelligent algorithm, resulting in poor accuracy of the recommended scheme. This application can accurately evaluate the traffic engineering survey and design scheme, and thus effectively improve the accuracy of the recommended scheme.

[0105] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 8 , the step S30 further includes steps S301-S303:

[0106] Step S301, obtaining physical information and evaluation indicators of the design solution.

[0107] It should be noted that the physical information of the design scheme refers to the various technical parameters specified in the business rules and design specifications of the design scheme, including but not limited to the mechanical properties of materials, geometric dimensions of structures, environmental load conditions, etc. Physical information constitutes the basis of the design scheme. Evaluation indicators are set according to the actual needs of the project and are a series of standards used to measure the pros and cons of the design scheme, such as cost, construction difficulty, safety, durability, environmental impact, etc.

[0108] It is understandable that the use of the analytic hierarchy process to construct an evaluation index system can decompose complex evaluation indicators into multiple levels, each level contains several specific evaluation indicators, thus forming a tree structure. At each level, the weight of each evaluation indicator is determined based on expert experience and historical data to reflect their contribution to the overall quality of the design scheme. In this way, multiple aspects of the design scheme can be evaluated more systematically to ensure the comprehensiveness and accuracy of the evaluation. Determine the evaluation indicators corresponding to the current scheme design based on the evaluation index system.

[0109] It is understandable that in the design of the pile foundation scheme for bridge engineering, a pile foundation scheme evaluation index system is constructed, and the evaluation indexes include pile foundation settlement, pier stiffness, material consumption, construction period, safety risk, engineering cost and other indicators, and this embodiment does not impose specific restrictions on this. Taking high-speed railways as an example, the high-speed railway specification requires that the pile foundation settlement index requirement cannot exceed 20mm. Under the premise of meeting the conditions, the smaller the settlement, the better. Pier stiffness refers to the comprehensive stiffness including pile foundation deformation and pier deformation. The high-speed railway specification requires that the longitudinal stiffness of the pier stiffness cannot be less than 360KN / cm. Under the premise of meeting the stiffness conditions, the smaller the longitudinal stiffness value, the less the pier material consumption, and the better the economy. In the same bridge, the more pile foundation schemes are used, the higher the degree of mechanization, the shorter the construction period, the smaller the safety risk, and the better the economy.

[0110] Step S302: construct a finite element model according to the physical information of the design solution, and determine a target evaluation function according to the evaluation index of the design solution.

[0111] It should be noted that the finite element model is a numerical method that discretizes a continuum into a finite number of units and approximates the overall structural behavior by solving the physical field equations on these units. In the design of pile foundation schemes for bridge engineering, constructing a finite element model can more accurately simulate the interaction between the pile foundation and the soil, as well as the deformation and stress distribution of the pile foundation when it is under load. Finite element analysis can predict key physical parameters such as the settlement and stiffness of the pile foundation, providing a scientific basis for the optimization of the design scheme. Constructing a finite element model based on physical information such as business rules and design specifications can ensure the fit between the model and the actual situation, thereby improving the accuracy of the analysis results.

[0112] It can be understood that the target evaluation function refers to a mathematical model used to comprehensively evaluate the various indicators of the design scheme, which can calculate a value reflecting the overall pros and cons of the design scheme based on the weights of each evaluation indicator and the actual performance of the design scheme. Constructing the target evaluation function based on the evaluation indicators of the design scheme can ensure that the evaluation process has a clear goal orientation and make the evaluation results more accurate. The target evaluation function should include all evaluation indicators and assign reasonable weights to each indicator, so that the physical information of the design scheme can be accurately converted into the quantitative value of the evaluation indicator, thereby achieving a comprehensive evaluation of the design scheme.

[0113] It is worth noting that the objective evaluation function is set as a multi-objective optimization problem, and the weighted sum method can be used to construct the objective evaluation function, in which each evaluation index is assigned different weights according to its importance and the degree of influence on the overall scheme. In the design of the pile foundation scheme of the bridge project, the comprehensive engineering cost of the pile foundation + bridge pier is used as the objective evaluation function.

[0114] Step S303 , performing scheme verification and index evaluation on each design scheme in the design scheme group according to the finite element model and the target evaluation function, and obtaining an evaluation score of each design scheme.

[0115] It should be noted that scheme verification refers to the verification and checking of various technical parameters in the design scheme to ensure that the design scheme meets the requirements of business rules and design specifications. Index evaluation refers to the comprehensive evaluation of each design scheme in the design scheme group according to the evaluation index system to obtain its specific evaluation score, that is, to transform the design scheme from a theoretical concept into a quantifiable evaluation, which directly determines the accuracy and reliability of the recommended scheme.

[0116] It is understandable that through the combined effect of scheme verification and index evaluation, the specific evaluation score of each design scheme in the design scheme group can be obtained. These scores not only reflect the performance of the design scheme in various technical indicators, but also comprehensively consider the economic efficiency, construction difficulty, environmental impact and other aspects of the design scheme. Therefore, determining the recommended scheme based on these evaluation scores can effectively improve the accuracy and reliability of the recommended scheme.

[0117] In a feasible implementation, step S303 may include: performing scheme verification on each design scheme in the design scheme group through the finite element model to obtain a set of verification results for each design scheme; performing indicator evaluation on the set of verification results for each design scheme through the objective evaluation function to obtain an evaluation score for each design scheme.

[0118] It should be noted that the finite element model is the finite element software that integrates physical information such as business rules, that is, the business indicator calculation system, which connects the generated multiple schemes to the existing business indicator calculation system in turn to generate multiple quantitative calculation result sets. The quantitative calculation results are input into the evaluation objective function to calculate the comprehensive score of each scheme.

[0119] It is understandable that in the design of pile foundation schemes for bridge projects, based on the parameters of multiple recommended schemes, the finite element calculation and analysis function in the pile foundation design module is called to perform pile foundation checks on each scheme, and obtain the results of indicators such as pile foundation settlement, pier stiffness, material consumption, construction period, and safety risks for each scheme. The design engineering cost index is used as the total scoring function, and other indicators are used as constraint penalty conditions. The scheme with the lowest engineering cost that meets the design index conditions is selected as the final pile foundation recommendation scheme, and the detailed design of the scheme is carried out.

[0120] In the specific implementation, in the design of the pile foundation scheme for bridge engineering, all the recommended parameters "quantity-diameter" (such as the 8-1.25m scheme) are combined with the pile foundation configuration file to obtain all the parameters, generate a finite element model and input it into the pile foundation verification module for analysis, and obtain the verification results of indicators such as pile foundation settlement, pier stiffness, material consumption, construction period, and safety risk for each scheme. Taking the comprehensive engineering cost of pile foundation + pier as the target evaluation function as an example, combined with engineering economic indicators and material consumption, the engineering cost of all schemes can be calculated, and the schemes can be scored according to their engineering costs.

[0121] In this embodiment, a finite element model and an objective evaluation function are constructed according to the physical information and evaluation indicators of the design scheme, and the design scheme is checked and evaluated by the finite element model and the objective evaluation function, which can effectively improve the accuracy of the design scheme evaluation score.

[0122] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for recommending design solutions for traffic engineering structures that integrate physical information and neural networks in the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0123] This application also provides a traffic engineering structure design scheme recommendation device that integrates physical information and neural networks. Please refer to Fig. 9 The traffic engineering structure design scheme recommendation device integrating physical information and neural network comprises:

[0124] The determination module 10 is used to obtain characteristic parameters of the design scheme and determine an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters.

[0125] The input module 20 is used to input the input parameter vector group into the scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer and multiple regional fully connected output layers.

[0126] The evaluation module 30 is used to obtain physical information and evaluation indicators of the design scheme, and perform scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score for each design scheme.

[0127] The determination module 10 is further configured to determine a recommended solution according to the evaluation scores of the various design solutions.

[0128] The present embodiment provides a traffic engineering structure design scheme recommendation device that integrates physical information and neural networks. The present embodiment first obtains characteristic parameters of the design scheme, and determines an input parameter vector group based on the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters; the input parameter vector group is input into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and multiple regional fully connected output layers; the physical information and evaluation indicators of the design scheme are obtained, and scheme verification and indicator evaluation are performed on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score of each design scheme; the recommended scheme is determined according to the evaluation scores of each design scheme, so as to accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme.

[0129] In summary, the present application inputs the input parameter vector group obtained by vectorizing and perturbing the characteristic parameters of the design scheme into the scheme recommendation model, performs scheme verification and index evaluation on the design scheme group output by the model according to the physical information and evaluation indicators of the design scheme, and then determines the recommended scheme according to the evaluation scores of each design scheme. This overcomes the technical defect that the current intelligent algorithm evaluation indicators cannot adapt to the quality of the traffic engineering survey and design scheme generated by the intelligent algorithm, and thus cannot evaluate the advantages and disadvantages of the intelligent algorithm, resulting in poor accuracy of the recommended scheme. This application can accurately evaluate the traffic engineering survey and design scheme, and thus effectively improve the accuracy of the recommended scheme.

[0130] Optionally, the determination module 10 is further used to obtain characteristic parameters of the design solution, and vectorize the characteristic parameters to obtain a characteristic parameter vector; and perturb several characteristic parameters in the characteristic parameter vector to obtain an input parameter vector group.

[0131] Optionally, the input module 20 is also used to obtain a sample library for solution recommendation; pre-train the single-tail neural network with samples in the sample library to obtain an initial recommendation model; and train the initial recommendation model in stages with data samples in the sample library to obtain a solution recommendation model.

[0132] Optionally, the input module 20 is further used to pre-train the single-tail neural network through samples in the sample library to obtain a target weight; and migrate to the multi-tail neural network according to the target weight to obtain an initial recommendation model.

[0133] Optionally, the evaluation module 30 is also used to obtain physical information and evaluation indicators of the design scheme; construct a finite element model according to the physical information of the design scheme, and determine a target evaluation function according to the evaluation indicators of the design scheme; perform scheme verification and indicator evaluation on each design scheme in the design scheme group according to the finite element model and the target evaluation function to obtain an evaluation score for each design scheme.

[0134] Optionally, the evaluation module 30 is also used to perform scheme verification on each design scheme in the design scheme group through the finite element model to obtain a set of verification results for each design scheme; and perform indicator evaluation on the set of verification results for each design scheme through the objective evaluation function to obtain an evaluation score for each design scheme.

[0135] Optionally, the determination module 10 is further configured to sort the design schemes from high to low according to their evaluation scores to obtain a design scheme sequence; and use a design scheme with a ranking value of a preset value in the design scheme sequence as a recommended scheme.

[0136] The traffic engineering structure design scheme recommendation device that integrates physical information and neural networks provided in the present application adopts the traffic engineering structure design scheme recommendation method that integrates physical information and neural networks in the above-mentioned embodiments, which can solve the technical problem of how to accurately evaluate traffic engineering survey and design schemes, thereby effectively improving the accuracy of recommended schemes. Compared with the prior art, the beneficial effects of the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks provided in the present application are the same as the beneficial effects of the traffic engineering structure design scheme recommendation method that integrates physical information and neural networks provided in the above-mentioned embodiments, and the other technical features of the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks are the same as the features disclosed in the above-mentioned embodiment methods, which will not be repeated here.

[0137] The present application provides a device for recommending design schemes for traffic engineering structures that integrates physical information and neural networks. The device for recommending design schemes for traffic engineering structures that integrates physical information and neural networks includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for recommending design schemes for traffic engineering structures that integrates physical information and neural networks in the above-mentioned embodiment one.

[0138] Reference below Fig.10 , which shows a schematic diagram of the structure of a traffic engineering structure design scheme recommendation device that integrates physical information and neural networks and is suitable for implementing the embodiment of the present application. The traffic engineering structure design scheme recommendation device that integrates physical information and neural networks in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The traffic engineering structure design scheme recommendation device that integrates physical information and neural networks is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0139] like Fig.10As shown, the traffic engineering structure design scheme recommendation device integrating physical information and neural network may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the traffic engineering structure design scheme recommendation device integrating physical information and neural network are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the traffic engineering structure design solution recommendation device integrating physical information and neural networks to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the traffic engineering structure design solution recommendation device integrating physical information and neural networks with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0140] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0141] The traffic engineering structure design scheme recommendation device that integrates physical information and neural networks provided in this application adopts the traffic engineering structure design scheme recommendation method that integrates physical information and neural networks in the above-mentioned embodiment, which can solve the technical problem of how to accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme. Compared with the prior art, the beneficial effects of the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks provided in this application are the same as the beneficial effects of the traffic engineering structure design scheme recommendation method that integrates physical information and neural networks provided in the above-mentioned embodiment, and the other technical features of the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0142] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0144] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for recommending design solutions for traffic engineering structures that integrates physical information and neural networks in the above-mentioned embodiment.

[0145] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0146] The above-mentioned computer-readable storage medium may be included in the traffic engineering structure design solution recommendation device that integrates physical information and neural networks; or it may exist independently without being assembled into the traffic engineering structure design solution recommendation device that integrates physical information and neural networks.

[0147] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks, the traffic engineering structure design scheme recommendation device that integrates physical information and neural networks: obtains characteristic parameters of the design scheme, and determines an input parameter vector group based on the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbating the characteristic parameters; inputs the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and multiple regional fully connected output layers; obtains physical information and evaluation indicators of the design scheme, and performs scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score of each design scheme; and determines a recommended scheme based on the evaluation score of each design scheme.

[0148] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0149] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0150] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0151] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for recommending design solutions for traffic engineering structures by integrating physical information and neural networks, and can solve the technical problem of how to accurately evaluate traffic engineering survey and design solutions, thereby effectively improving the accuracy of recommended solutions. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for recommending design solutions for traffic engineering structures by integrating physical information and neural networks provided by the above-mentioned embodiments, and will not be elaborated here.

[0152] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for recommending design solutions for traffic engineering structures by integrating physical information and neural networks.

[0153] The computer program product provided by this application can solve the technical problem of how to accurately evaluate the traffic engineering survey and design scheme, thereby effectively improving the accuracy of the recommended scheme. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the traffic engineering structure design scheme recommendation method integrating physical information and neural network provided in the above embodiment, and will not be repeated here.

[0154] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for recommending design schemes for traffic engineering structures by integrating physical information and neural networks, characterized in that: The method comprises: Acquire characteristic parameters of the design scheme, and determine an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters; Inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and a plurality of regional fully connected output layers; Acquiring physical information and evaluation indicators of the design schemes, and performing scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design schemes, to obtain an evaluation score for each design scheme; A recommended solution is determined according to the evaluation scores of the various design solutions.

2. The method according to claim 1, characterized in that The step of obtaining characteristic parameters of the design solution and determining an input parameter vector group according to the characteristic parameters includes: Acquire characteristic parameters of the design scheme, and vectorize the characteristic parameters to obtain a characteristic parameter vector; Several characteristic parameters in the characteristic parameter vector are perturbed to obtain an input parameter vector group.

3. The method according to claim 1, characterized in that Before inputting the input parameter vector group into the scheme recommendation model to obtain the design scheme group, the method further includes: Get the sample library recommended by the solution; Pre-training a single-tail neural network using samples in the sample library to obtain an initial recommendation model; The initial recommendation model is trained in stages using the data samples in the sample library to obtain a solution recommendation model.

4. The method according to claim 3, characterized in that The single-tail neural network is pre-trained using samples in the sample library to obtain an initial recommendation model, including: Pre-training the single-tail neural network using samples in the sample library to obtain target weights; The target weights are transferred to the multi-tail neural network to obtain an initial recommendation model.

5. The method according to claim 1, characterized in that The obtaining of the physical information and evaluation index of the design scheme, and performing scheme checking and index evaluation on each design scheme in the design scheme group according to the physical information and evaluation index of the design scheme, to obtain an evaluation score of each design scheme, includes: Obtain physical information and evaluation indicators of the design solution; Constructing a finite element model according to the physical information of the design scheme, and determining a target evaluation function according to the evaluation index of the design scheme; According to the finite element model and the target evaluation function, scheme checking and index evaluation are performed on each design scheme in the design scheme group to obtain an evaluation score for each design scheme.

6. The method according to claim 5, characterized in that The method of performing scheme checking and index evaluation on each design scheme in the design scheme group according to the finite element model and the target evaluation function to obtain an evaluation score for each design scheme includes: Performing scheme verification on each design scheme in the design scheme group by using the finite element model to obtain a set of verification results for each design scheme; The target evaluation function is used to perform an index evaluation on the check result set of each design solution to obtain an evaluation score for each design solution.

7. The method according to claim 1, characterized in that The step of determining a recommended solution according to the evaluation scores of the various design solutions comprises: Sort the design solutions from high to low according to the evaluation scores of the design solutions to obtain a design solution sequence; A design scheme with a ranking value of a preset value in the design scheme sequence is used as a recommended scheme.

8. A traffic engineering structure design scheme recommendation device integrating physical information and neural network, characterized in that: The traffic engineering structure design scheme recommendation device integrating physical information and neural network comprises: A determination module, used for acquiring characteristic parameters of the design scheme, and determining an input parameter vector group according to the characteristic parameters, wherein the input parameter vector group is obtained by vectorizing and perturbing the characteristic parameters; An input module, used for inputting the input parameter vector group into a scheme recommendation model to obtain a design scheme group, wherein the scheme recommendation model includes an input layer, a fully connected common hidden layer, and a plurality of regional fully connected output layers; An evaluation module, used to obtain physical information and evaluation indicators of the design scheme, and perform scheme verification and indicator evaluation on each design scheme in the design scheme group according to the physical information and evaluation indicators of the design scheme to obtain an evaluation score for each design scheme; The determination module is further used to determine a recommended solution according to the evaluation scores of the various design solutions.

9. A traffic engineering structure design scheme recommendation device integrating physical information and neural network, characterized in that: The traffic engineering structure design scheme recommendation device that integrates physical information and neural networks includes: a memory, a processor, and a traffic engineering structure design scheme recommendation program that integrates physical information and neural networks, which is stored in the memory and can be run on the processor. The traffic engineering structure design scheme recommendation program that integrates physical information and neural networks is configured to implement the traffic engineering structure design scheme recommendation method that integrates physical information and neural networks as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a traffic engineering structure design plan recommendation program that integrates physical information and neural networks. When the traffic engineering structure design plan recommendation program that integrates physical information and neural networks is executed by a processor, it implements the traffic engineering structure design plan recommendation method that integrates physical information and neural networks as described in any one of claims 1 to 7.

Images