Earth and rockfill dam generation type intelligent design method, device and equipment and medium

Abstract

The invention discloses an earth and rockfill dam generation type intelligent design method, device and equipment and a medium, and relates to the field of earth and rockfill dam scheme design. The method comprises the steps that a heterogeneous data set used for training is constructed based on design key point requirements of different dam types; inputting the heterogeneous data set into a generator of a generative adversarial network, and constructing a finite element calculation data set according to an earth and rockfill dam design scheme output by the generator based on dam body safety specification requirements of different dam types; inputting the finite element calculation data set into an evaluator of the generative adversarial network, taking the condition that the dam body safety of the earth and rockfill dam design scheme output by the evaluator meets the dam body safety specification requirement as a constraint, and taking the minimum loss value of the workability output by the evaluator and the calculated workability as a target to carry out adversarial training on the generative adversarial network; the trained generator is an earth and rockfill dam generative design model; and the earth and rockfill dam generation type design model is adopted to generate a to-be-designed earth and rockfill dam design scheme, and efficient and high-quality earth and rockfill dam design can be achieved.

Description

Technical Field

[0001] This application relates to the field of earth-rock dam design, and in particular to a generative intelligent design method, device, equipment and medium for earth-rock dams. Background Art

[0002] Dams are the backbone projects of hydropower engineering construction. As one of the important dam types of dams, earth-rock dams have the advantages of safety, economy, energy conservation, environmental protection, etc. Face slab dams and core wall dams are the two major advantageous dam types of earth-rock dams and are widely used in conventional hydropower and pumped storage power stations. In recent years, digital intelligent design and operation and maintenance of earth-rock dams are an inevitable choice to achieve high-quality and efficient engineering design and meet the development needs of intelligent engineering construction.

[0003] The current structural design of earth-rock dams is mainly in the stage of parametric structural design based on high-precision modeling algorithms, and digital intelligent design technology still needs to be further developed. At present, the conventional earth-rock dam scheme design still mainly relies on manual design, and the degree of automation and intelligent design is insufficient. The design mode of earth-rock dams that highly depends on engineers' manual work faces development problems such as difficult inheritance of experience and difficult improvement of efficiency. At present, the design results (drawings, documents, experience, etc.) of the completed face slab dams, as well as a large amount of design knowledge and experience, are always difficult to be effectively utilized, and the excellent experience accumulated in the field is difficult to inherit. At the same time, due to the corresponding upper limit of engineers' productivity, the manual design mode that highly depends on engineers is difficult to further improve the design efficiency. It can be seen that the design mode that overly relies on manual work has gradually faced the dilemmas of difficult improvement of efficiency, difficult inheritance of experience, and difficult reuse of design results, and urgent intelligent transformation is needed. Therefore, developing an artificial intelligence (AI) design theory, method, technology and system platform for earth-rock dams with autonomous learning ability is expected to solve related problems. Summary of the Invention

[0004] The purpose of this application is to provide a generative intelligent design method, device, equipment and medium for earth-rock dams, which can achieve high-efficiency and high-quality design of earth-rock dams.

[0005] To achieve the above purpose, the following solutions are provided in this application.

[0006] In the first aspect, this application provides a generative intelligent design method for earth-rock dams, including the following steps.

[0007] Obtain the design text knowledge of different dam types of earth-rock dams.

[0008] Generate the design key point requirements and dam body safety specification requirements of different dam types according to the design text knowledge.

[0009] Construct a heterogeneous dataset for training based on the design key point requirements of different dam types; the heterogeneous dataset is determined according to text data and image data; the text data includes: dam height, geological exploration data, and physical and mechanical parameters of dam materials; the image data includes: foundation surface image and dam body contour image.

[0010] Input the heterogeneous dataset for training into the generator of the generative adversarial network, and construct a finite element calculation dataset based on the dam body safety specification requirements of different dam types according to the earth-rock dam design scheme output by the generator; the finite element calculation dataset includes: earth-rock dam design scheme and the corresponding working state calculated by the finite element analysis method.

[0011] Input the finite element calculation dataset into the discriminator of the generative adversarial network, and perform adversarial training on the generative adversarial network with the constraint that the dam body safety of the earth-rock dam design scheme output by the discriminator meets the dam body safety specification requirements and with the goal of minimizing the loss value between the working state output by the discriminator and the working state calculated in the finite element calculation dataset, to obtain a trained generative adversarial network; among them, the trained generator is used as an earth-rock dam generative design model, and the trained discriminator is a dam body working state evaluation model.

[0012] Construct a heterogeneous dataset to be designed based on the design key point requirements required for the earth-rock dam to be designed.

[0013] Input the heterogeneous dataset to be designed into the earth-rock dam generative design model to generate a design scheme for the earth-rock dam to be designed.

[0014] In a second aspect, the present application provides an earth-rock dam generative intelligent design device, including the following modules.

[0015] A design text knowledge acquisition module, used to acquire design text knowledge of different dam types of earth-rock dams.

[0016] A requirement generation module, used to generate design key point requirements and dam body safety specification requirements of different dam types according to the design text knowledge.

[0017] A first heterogeneous dataset construction module, used to construct a heterogeneous dataset for training based on the design key point requirements of different dam types; the heterogeneous dataset is determined according to text data and image data; the text data includes: dam height, geological exploration data, and physical and mechanical parameters of dam materials; the image data includes: foundation surface image and dam body contour image.

[0018] A finite element calculation dataset construction module is used to input a heterogeneous dataset for training into the generator of a generative adversarial network, and construct a finite element calculation dataset based on the earth-rock dam design scheme output by the generator according to the dam safety specification requirements for different dam types; the finite element calculation dataset includes: the earth-rock dam design scheme and the corresponding working state calculated by the finite element analysis method.

[0019] An adversarial training module is used to input the finite element calculation dataset into the discriminator of the generative adversarial network, and perform adversarial training on the generative adversarial network with the constraint that the dam safety of the earth-rock dam design scheme output by the discriminator meets the dam safety specification requirements, and with the goal of minimizing the loss value between the working state output by the discriminator and the working state calculated in the finite element calculation dataset, to obtain a trained generative adversarial network; among them, the trained generator serves as an earth-rock dam generative design model, and the trained discriminator is a dam working state evaluation model.

[0020] A second heterogeneous dataset construction module is used to construct a heterogeneous dataset to be designed based on the design key point requirements for the earth-rock dam to be designed.

[0021] An earth-rock dam design scheme generation module is used to input the heterogeneous dataset to be designed into the earth-rock dam generative design model to generate an earth-rock dam design scheme to be designed.

[0022] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the earth-rock dam generative intelligent design method described in any one of the above.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the earth-rock dam generative intelligent design method described in any one of the above.

[0024] According to the specific embodiments provided by the present application, the present application has the following technical effects.

[0025] The present application provides a generative intelligent design method, device, equipment and medium for earth-rock dams. An heterogeneous dataset for training is constructed based on the design key-point requirements of different dam types, and the generator of the generative adversarial network is trained. Based on the dam body safety specification requirements of different dam types, a finite element calculation dataset is constructed according to the earth-rock dam design scheme output by the generator, and the discriminator in the generative adversarial network is trained. During the training process, taking the dam body safety of the earth-rock dam design scheme output by the discriminator meeting the dam body safety specification requirements as a constraint, and aiming at minimizing the loss value between the working state output by the discriminator and the working state calculated in the finite element calculation dataset to achieve adversarial training, a generative design model for earth-rock dams and a dam body working state evaluation model are obtained. The present application considers the working state of the earth-rock dam design scheme, and adversarially trains the generative design model for earth-rock dams. On the basis of the automatic design of the earth-rock dam design scheme, through the intelligent discrimination of the working state of the generated earth-rock dam design scheme, it is ensured that the design generation result meets the requirements of engineering safety and stability, realizing the efficient and high-quality design of earth-rock dams. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1 It is an application environment diagram of a generative intelligent design method for earth-rock dams in an embodiment of the present application.

[0028] Figure 2 It is a flowchart of a generative intelligent design method for earth-rock dams provided in an embodiment of the present application.

[0029] Figure 3 It is a schematic diagram of the adversarial training process provided in an embodiment of the present application.

[0030] Figure 4 It is a schematic diagram of the structure of a generative adversarial network provided in an embodiment of the present application.

[0031] Figure 5 It is a schematic diagram of the functional modules of a generative intelligent design device for earth-rock dams provided in another embodiment of the present application.

[0032] Figure 6 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0034] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0035] The rockfill dam generative intelligent design method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the design text knowledge of different dam types of the earth-rock dam to the server 104. After the server 104 receives the design text knowledge of different dam types of the earth-rock dam, for the design text knowledge of different dam types of the earth-rock dam, the server generates the design key point requirements and dam body safety specification requirements for different dam types according to the design text knowledge; constructs a heterogeneous data set for training based on the design key point requirements of different dam types; inputs the heterogeneous data set for training into the generator of the generative adversarial network, and based on the dam body safety specification requirements of different dam types, constructs a finite element calculation data set according to the rockfill dam design scheme output by the generator; inputs the finite element calculation data set into the evaluator of the generative adversarial network, and performs adversarial training on the generative adversarial network with the condition that the dam body safety of the rockfill dam design scheme output by the evaluator meets the dam body safety specification requirements as a constraint and with the goal of minimizing the loss value between the working state output by the evaluator and the working state calculated in the finite element calculation data set, to obtain a trained generative adversarial network; among them, the trained generator serves as the rockfill dam generative design model, and the trained evaluator is the dam body working state evaluation model; constructs a heterogeneous data set to be designed based on the design key point requirements required for the rockfill dam to be designed; inputs the heterogeneous data set to be designed into the rockfill dam generative design model to generate a design scheme for the rockfill dam to be designed.

[0036] Server 104 can feedback the obtained design scheme of the earth-rock dam to be designed to the terminal 102. In addition, in some embodiments, the earth-rock dam generative intelligent design method can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly process the design text knowledge of different dam types of the earth-rock dam, or the server 104 can obtain the design text knowledge of different dam types of the earth-rock dam from the data storage system and process the design text knowledge of different dam types of the earth-rock dam.

[0037] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0038] In an exemplary embodiment, as Figure 2 shown, an earth-rock dam generative intelligent design method is provided. This method is executed by a computer device, and specifically can be executed separately by a computer device such as a terminal or a server, or can be jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 in as an example for explanation, it includes the following steps 201 to step 207.

[0039] Step 201, obtain the design text knowledge of different dam types of the earth-rock dam.

[0040] Among them, the design text knowledge includes: earth-rock dam design specifications, hydraulic structure design manuals, and typical project design reports, etc.

[0041] Step 202, generate the design key point requirements and dam body safety specification requirements of different dam types according to the design text knowledge.

[0042] Step 203, construct a heterogeneous data set for training based on the design key point requirements of different dam types; the heterogeneous data set is determined according to text data and image data; the text data includes: dam height, geological exploration data, and physical and mechanical parameters of dam materials; the image data includes: foundation surface images and dam body contour images.

[0043] Step 204, input the heterogeneous data set for training into the generator of the generative adversarial network, and based on the dam body safety specification requirements of different dam types, construct a finite element calculation data set according to the earth-rock dam design scheme output by the generator; the finite element calculation data set includes: the earth-rock dam design scheme and the corresponding working state calculated by the finite element analysis method.

[0044] Step 205: Input the finite element calculation dataset into the evaluator of the generative adversarial network. Taking the requirement that the dam body safety of the earth-rock dam design scheme output by the evaluator meets the dam body safety code requirements as a constraint, and aiming at minimizing the loss value between the working state output by the evaluator and the working state calculated in the finite element calculation dataset, conduct adversarial training on the generative adversarial network to obtain a trained generative adversarial network. Among them, the trained generator serves as an earth-rock dam generative design model, and the trained evaluator is a dam body working state evaluation model. The evaluator is an artificial neural network proxy model.

[0045] Among them, for the adversarial training: Input the automatically generated earth-rock dam design scheme into the evaluator, determine the loss function according to the evaluation function, and backpropagate it into the generator to realize the adversarial training of the earth-rock dam generative design model.

[0046] Step 206: Construct a heterogeneous dataset to be designed based on the design key point requirements for the earth-rock dam to be designed.

[0047] Step 207: Input the heterogeneous dataset to be designed into the earth-rock dam generative design model to generate a design scheme for the earth-rock dam to be designed.

[0048] Implementing the above Steps 201 to 207 can achieve efficient and high-quality design of earth-rock dams.

[0049] In another exemplary embodiment of the present application, Step 202 specifically includes the following contents.

[0050] (1) Use natural language processing (NLP) technology to completely digitize, standardize the data format, and unify the data format of the design text knowledge to obtain processed data, with the aim of constructing a knowledge graph in the field of earth-rock dam design.

[0051] (2) Construct a knowledge graph in the field of earth-rock dam design based on the processed data.

[0052] (3) Based on the knowledge graph in the field of earth-rock dam design, use prompt engineering technology to enable the large model to learn domain text knowledge, so that it can accurately and efficiently identify key design text features, and realize the automatic learning of key physical and mechanical parameters and code requirements in the text report. Therefore, generate the design key point requirements and dam body safety code requirements for different dam types according to the learned large model.

[0053] In another exemplary embodiment of the present application, Step 203 specifically includes the following contents.

[0054] (1) Collect the engineering data of the existing earth-rock dam; the engineering data includes: dam height, geological exploration data, foundation surface image, and physical and mechanical parameters of the dam materials.

[0055] (2) Based on the design key point requirements of different dam types, use the engineering data of the existing earth-rock dam to construct a contour image matrix of the foundation surface-dam slope-dam height earth-rock dam and a material parameter vector for training.

[0056] (3) Determine the heterogeneous data set for training according to the contour image matrix of the foundation surface-dam slope-dam height earth-rock dam and the material parameter vector for training.

[0057] Subsequently, based on the heterogeneous data set, using the AI model architecture as the generator, autonomously learn the zoning characteristics of the core wall, face slab, cushion layer, transition layer, filter layer, main rockfill area, secondary rockfill area, drainage area, and additional modeling area of the earth-rock dam, study the AI model architecture for generating the sectional zoning design, and realize the fusion of heterogeneous data to generate the corresponding design image; propose an automatic vectorization extraction method for the design image, and automatically convert the image data that is difficult to use in the design into the sectional zoning design parameters required for parametric modeling and design optimization.

[0058] In another exemplary embodiment of the present application, step 204 specifically includes the following content.

[0059] (1) Based on the dam body safety code requirements of different dam types, perform finite element analysis on the earth-rock dam under the earth-rock dam design scheme and the physical and mechanical parameters of the dam materials output by the generator, and calculate the working state of the corresponding earth-rock dam.

[0060] (2) Establish a finite element calculation data set from the earth-rock dam design scheme output by the generator and the calculated corresponding working state; the finite element calculation data set is used to reflect the seepage stability, deformation stability, seismic safety, and dam slope stability performance of the dam body.

[0061] In another exemplary embodiment of the present application, step 204 and step 205 implement adversarial training. The adversarial training adopts a method of multiple iterations. Refer to Figure 3 For the nth iteration, its process includes the following steps.

[0062] Step 301: Input the heterogeneous data set for training in the nth iteration into the generator in the generative adversarial network, and the generator outputs the earth-rock dam design scheme in the nth iteration.

[0063] Step 302: Construct the finite element calculation data set in the nth iteration according to the earth-rock dam design scheme output by the generator in the nth iteration.

[0064] Step 303: Input the finite element calculation dataset of the nth iteration into the evaluator in the generative adversarial network. The evaluator outputs the dam body safety of the earth-rock dam design scheme of the nth iteration, and calculates the loss value between the working state of the nth iteration output by the evaluator and the working state calculated in the finite element calculation dataset.

[0065] Step 304: Determine whether the dam body safety of the earth-rock dam design scheme of the nth iteration meets the requirements of the dam body safety code, and determine whether the loss value of the nth iteration reaches the set loss value range. If so, execute Step 305: Use the generator trained in the nth iteration as the earth-rock dam generative design model, and use the evaluator trained in the nth iteration as the dam body working state evaluation model. Otherwise, after updating the iteration number, return to Step 301.

[0066] In another exemplary embodiment of the present application, refer to Figure 4 , the generator G includes: a profile generator G1 and a profile partition generator G2. The evaluator EV includes a specification constraint discriminator N and a mechanical property evaluator E.

[0067] The profile generator G1 is used to generate the earth-rock dam profile according to the heterogeneous dataset for training. The profile partition generator G2 is used to generate the earth-rock dam design scheme according to the heterogeneous dataset for training and the earth-rock dam profile. The physical and mechanical parameters of the dam materials adopted when constructing the heterogeneous dataset are determined according to the source information, and the design key points requirements and the dam body safety code requirements are used as design conditions. The earth-rock dam design scheme includes: the earth-rock dam profile design drawing; the earth-rock dam profile partition in the earth-rock dam profile design drawing includes: the earth-rock dam core wall, the facing slab, the cushion layer, the transition layer, the filter layer, the main rockfill area, the secondary rockfill area, the drainage area and the additional model area.

[0068] The specification constraint discriminator N is used to judge the dam body safety of the earth-rock dam design scheme generated by the generator G to realize the constraint of the design specification. The mechanical property evaluator E is used to evaluate the working state of the earth-rock dam design scheme generated by the generator G to realize the optimization of the mechanical properties. The working state includes: stress index and deformation index; the working state is used to reflect the dam body seepage stability, deformation stability, seismic safety and dam slope stability performance.

[0069] In another exemplary embodiment of the present application, in step 206 and step 207, a generated design model of an earth-rock dam is used to generate a design scheme for the earth-rock dam to be designed. Subsequently, the design scheme for the earth-rock dam to be designed is further intelligently evaluated using a working state evaluation model of the dam body. If it does not meet the requirements of the design key points required for the earth-rock dam to be designed and the dam body safety specification requirements required for the earth-rock dam to be designed, it indicates that in the adversarial training process, the dam type of the earth-rock dam to be designed may be missing in the training data. Therefore, it is necessary to add new training data to fine-tune the earth-rock dam generative design model and the working state evaluation model of the dam body to further improve the quality of the earth-rock dam design scheme.

[0070] In practical applications, an implementation process of the above-mentioned intelligent generative design method for earth-rock dams can be specifically described as follows.

[0071] (1) Use prompt engineering technology to learn the text knowledge in the field of earth-rock dam design, and automatically generate the requirements of design key points for different dam types and the specification requirements for dam body safety.

[0072] (2) Construct an earth-rock dam generative design model that trains and fuses multi-modal data.

[0073] Specifically, for the requirements of the design key points of the dam body to be designed, an AI model architecture for generating sectional zoning design of earth-rock dams is proposed by using heterogeneous data that integrates the designed dam height, geological exploration data, foundation surface images, and physical and mechanical parameters of dam materials. The generator is trained on the design instance dataset to obtain the earth-rock dam generative design model.

[0074] (3) Establish a finite element proxy model for evaluating the working state of earth-rock dams based on artificial neural networks.

[0075] Specifically, for the specification requirements of dam body safety, through finite element calculations of earth-rock dams under different sectional forms and physical and mechanical parameters of dam materials, a finite element calculation dataset that can reflect the seepage, deformation, earthquake resistance, and slope stability of the dam body is constructed, and a working state evaluation model of the dam body based on an artificial neural network proxy model (i.e., the evaluator, also known as the finite element calculation proxy model) is established and trained using this dataset.

[0076] In this step, during training, based on finite element analysis, a database of the earth-rock dam structure model and mechanical responses such as stress and deformation is constructed; a deep neural network is constructed, and the evaluator is trained using the earth-rock dam finite element calculation database to achieve the evaluation of the mechanical properties of the earth-rock dam structure. Using this evaluator, stress and deformation index predictions are made for the earth-rock dam design section generated by AI under static and dynamic conditions; feature engineering analysis is performed on the prediction results of the stress and deformation indices, key control indices that can measure the mechanical properties of the earth-rock dam are obtained, and an AI design scheme evaluation model considering the mechanical properties of the earth-rock dam is constructed.

[0077] (4) Consider the safety and stability of the dam body, and conduct adversarial training on the generative design model of the earth-rock dam.

[0078] Construct a loss function for evaluating the multi-dimensional indicators of the working state of the designed dam body to meet the specification requirements, conduct intelligent evaluation on the automatically generated earth-rock dam design scheme, and conduct adversarial training on the generative design model of the earth-rock dam.

[0079] (5) Automatically generate an earth-rock dam design scheme that meets the engineering safety requirements.

[0080] Call the generative design model of the earth-rock dam and the evaluation model of the working state of the dam body, and generate an earth-rock dam design scheme that meets the engineering safety requirements by inputting the key requirements of the design needed and the specification requirements of the dam body safety.

[0081] The method of the above embodiment is a generative intelligent design method of an earth-rock dam with adversarial training on the working state of the dam body. Considering the working state of the section, conduct adversarial training on the generative design model of the earth-rock dam. On the basis of the automatic design of the earth-rock dam section, through the intelligent discrimination of the working state of the generated section, ensure that the design generation result meets the engineering safety and stability requirements, and realize the efficient and high-quality design of the earth-rock dam.

[0082] Based on the same inventive concept, the embodiment of the present application also provides an earth-rock dam generative intelligent design device for implementing the above-mentioned earth-rock dam generative intelligent design method. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the earth-rock dam generative intelligent design device provided below can refer to the limitations on the earth-rock dam generative intelligent design method in the above text, and will not be repeated here.

[0083] In an exemplary embodiment, as Figure 5 shown, an earth-rock dam generative intelligent design device is provided, which includes the following modules.

[0084] The design text knowledge acquisition module 501 is used to acquire the design text knowledge of different dam types of the earth-rock dam.

[0085] The requirement generation module 502 is used to generate the design key point requirements and dam body safety specification requirements of different dam types according to the design text knowledge.

[0086] The first heterogeneous data set construction module 503 is used to construct a heterogeneous data set for training based on the design key point requirements of different dam types; the heterogeneous data set is determined according to text data and image data; the text data includes: dam height, geological exploration data, and physical and mechanical parameters of dam materials; the image data includes: foundation surface image and dam body contour image.

[0087] The finite element calculation dataset construction module 504 is used to input the heterogeneous dataset for training into the generator of the generative adversarial network, and construct a finite element calculation dataset based on the earth-rock dam design scheme output by the generator according to the dam safety specification requirements for different dam types; the finite element calculation dataset includes: the earth-rock dam design scheme and the corresponding working state calculated by the finite element analysis method.

[0088] The adversarial training module 505 is used to input the finite element calculation dataset into the discriminator of the generative adversarial network, and perform adversarial training on the generative adversarial network with the constraint that the dam safety of the earth-rock dam design scheme output by the discriminator meets the dam safety specification requirements, and with the goal of minimizing the loss value between the working state output by the discriminator and the working state calculated in the finite element calculation dataset, to obtain a trained generative adversarial network; wherein, the trained generator serves as an earth-rock dam generative design model, and the trained discriminator is a dam working state evaluation model.

[0089] The second heterogeneous dataset construction module 506 is used to construct a heterogeneous dataset to be designed based on the design key point requirements for the earth-rock dam to be designed.

[0090] The earth-rock dam design scheme generation module 507 is used to input the heterogeneous dataset to be designed into the earth-rock dam generative design model to generate an earth-rock dam design scheme to be designed.

[0091] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the design text knowledge of different dam types of earth-rock dams. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements an earth-rock dam generative intelligent design method.

[0092] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0093] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0094] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0095] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0096] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0097] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, etc., without limitation.

[0098] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0099] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A generative intelligent design method for earth-rock dams, characterized in that The generative intelligent design method for earth-rock dams includes: Obtain the design text knowledge of different types of earth-rock dams; Generate the design key point requirements and dam body safety specification requirements for different types of dams according to the design text knowledge; Construct a heterogeneous dataset for training based on the design key point requirements of different types of dams; the heterogeneous dataset is determined according to text data and image data; the text data includes: dam height, geological exploration data, and physical and mechanical parameters of dam materials; the image data includes: foundation surface image and dam body contour image; Input the heterogeneous dataset for training into the generator of the generative adversarial network, and construct a finite element calculation dataset based on the dam body safety specification requirements of different types of dams according to the earth-rock dam design scheme output by the generator; the finite element calculation dataset includes: earth-rock dam design scheme and the corresponding working state calculated by the finite element analysis method; Input the finite element calculation dataset into the evaluator of the generative adversarial network, and perform adversarial training on the generative adversarial network with the constraint that the dam body safety of the earth-rock dam design scheme output by the evaluator meets the dam body safety specification requirements and with the goal of minimizing the loss value between the working state output by the evaluator and the working state calculated in the finite element calculation dataset, to obtain a trained generative adversarial network; among them, the trained generator is used as the earth-rock dam generative design model, and the trained evaluator is the dam body working state evaluation model; Construct a heterogeneous dataset to be designed based on the design key point requirements required for the earth-rock dam to be designed; Input the heterogeneous dataset to be designed into the earth-rock dam generative design model to generate the design scheme of the earth-rock dam to be designed.

2. The generative intelligent design method for earth-rock dams according to claim 1, wherein Generating the design key point requirements and dam body safety specification requirements for different types of dams according to the design text knowledge specifically includes: Use natural language processing technology to completely digitalize, standardize the data format, and unify the data format of the design text knowledge to obtain processed data; Construct a knowledge graph for earth-rock dam design based on the processed data; Based on the knowledge graph for earth-rock dam design, use prompt engineering technology to perform domain text knowledge learning on the large model, and generate the design key point requirements and dam body safety specification requirements for different types of dams according to the learned large model.

3. The generative intelligent design method for earth-rock dams according to claim 1, wherein Constructing a heterogeneous dataset for training based on the design key point requirements of different types of dams specifically includes: Collect the engineering data of existing earth-rock dams; the engineering data includes: dam height, geological exploration data, foundation surface image, and physical and mechanical parameters of dam materials; Based on the design key point requirements of different types of dams, use the engineering data of existing earth-rock dams to construct a foundation surface-dam slope-dam height earth-rock dam contour image matrix and a material parameter vector for training; Determine the heterogeneous dataset for training according to the foundation surface-dam slope-dam height earth-rock dam contour image matrix and material parameter vector for training.

4. The generative intelligent design method for earth-rock dams according to claim 1, characterized in that, Based on the dam body safety specification requirements of different types of dams, constructing a finite element calculation dataset according to the earth-rock dam design scheme output by the generator specifically includes: Based on the dam body safety code requirements for different dam types, a finite element analysis is carried out on the earth-rock dam under the earth-rock dam design scheme and the physical and mechanical parameters of the dam materials output by the generator, and the working conditions of the corresponding earth-rock dam are calculated. A finite element calculation data set is established from the earth-rock dam design scheme output by the generator and the corresponding calculated working conditions.

5. The generative intelligent design method for earth-rock dams according to claim 1, wherein, The evaluator is an artificial neural network surrogate model.

6. The generative intelligent design method for earth-rock dams according to claim 1, characterized in that The generator includes: a profile generator and a profile zoning generator. The profile generator is used to generate the earth-rock dam profile according to the heterogeneous data set for training; the profile zoning generator is used to generate the earth-rock dam design scheme according to the heterogeneous data set for training and the earth-rock dam profile; the earth-rock dam design scheme includes: the earth-rock dam profile design drawing; the earth-rock dam profile zoning in the earth-rock dam profile design drawing includes: the earth-rock dam core wall, the face slab, the cushion layer, the transition layer, the filter layer, the main rockfill area, the secondary rockfill area, the drainage area and the additional model area. The evaluator includes a code constraint discriminator and a mechanical property evaluator; the code constraint discriminator is used to judge the dam body safety of the earth-rock dam design scheme generated by the generator; the mechanical property evaluator is used to evaluate the working conditions of the earth-rock dam design scheme generated by the generator. The working conditions include: stress index and deformation index; the working conditions are used to reflect the dam body's seepage stability, deformation stability, seismic safety and dam slope stability performance.

7. The generative intelligent design method for earth-rock dams according to claim 1, characterized in that The design text knowledge includes: earth-rock dam design code, hydraulic structure design manual and typical project design report.

8. A generative intelligent design device for an earth-rock dam, characterized in that, The earth-rock dam generative intelligent design device includes: A design text knowledge acquisition module, which is used to acquire the design text knowledge of different dam types of earth-rock dams. A requirement generation module, which is used to generate the design key point requirements and dam body safety code requirements of different dam types according to the design text knowledge. A first heterogeneous data set construction module, which is used to construct a heterogeneous data set for training based on the design key point requirements of different dam types; the heterogeneous data set is determined according to text data and image data; the text data includes: dam height, geological exploration data and physical and mechanical parameters of dam materials; the image data includes: foundation surface image and dam body profile image. A finite element calculation data set construction module, which is used to input the heterogeneous data set for training into the generator of the generative adversarial network, and construct a finite element calculation data set according to the earth-rock dam design scheme output by the generator based on the dam body safety code requirements of different dam types; the finite element calculation data set includes: the earth-rock dam design scheme and the corresponding working conditions calculated by the finite element analysis method. An adversarial training module, configured to input the finite element calculation data set into an evaluator of the generative adversarial network, and perform adversarial training on the generative adversarial network with the satisfaction of the dam body safety of the earth-rock dam design scheme output by the evaluator meeting the requirements of the dam body safety code as a constraint and with the goal of minimizing the loss value between the working state output by the evaluator and the working state calculated in the finite element calculation data set, so as to obtain a trained generative adversarial network; wherein, the trained generator serves as an earth-rock dam generative design model, and the trained evaluator is a dam body working state evaluation model; A second heterogeneous data set construction module, configured to construct a heterogeneous data set to be designed based on the design key point requirements for the earth-rock dam to be designed; An earth-rock dam design scheme generation module, configured to input the heterogeneous data set to be designed into the earth-rock dam generative design model to generate an earth-rock dam design scheme to be designed.

9. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the earth-rock dam generative intelligent design method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the earth-rock dam generative intelligent design method according to any one of claims 1-7.

Images