A method for analyzing bearing performance of power transmission line engineering foundation under extreme rainfall conditions

Abstract

The application relates to the technical field of power transmission line engineering, and discloses a method for analyzing the bearing performance of a power transmission line engineering foundation under extreme rainfall conditions, which comprises collecting data of the water content, pore water pressure and shear strength of the foundation soil, generating a dynamic coupling relationship model by using a long short-term memory network, inputting real-time rainfall parameters to predict the parameter values of the foundation soil, and completing foundation bearing performance simulation through finite element analysis to generate an evaluation report and store the evaluation report in a database. The application can accurately reflect the dynamic change law of the foundation soil parameters with the rainfall process, improve the accuracy and reliability of the foundation bearing performance analysis, and provide scientific basis and technical support for the safety evaluation of the power transmission line engineering under extreme rainfall conditions.

Description

Technical Field

[0001] This invention belongs to the field of power transmission line engineering technology, specifically a method for analyzing the foundation bearing capacity of power transmission line engineering under extreme rainfall conditions. Background Technology

[0002] The safety of power transmission line projects under complex geological conditions has attracted widespread attention. Especially under extreme rainfall conditions, parameters such as soil moisture content, pore water pressure, and shear strength dynamically change with rainfall duration and intensity, and complex coupling relationships exist between these parameters. However, traditional analysis methods typically employ static parameters or simple linear coupling models, which have limitations in reflecting the dynamic evolution of these parameters during rainfall, leading to discrepancies between the foundation bearing capacity analysis results and actual conditions.

[0003] A multimodal data representation learning method and system, published under patent number CN106202281B, integrates feature representations of multimodal data through a graph random walk model and a data reconstruction model to generate low-dimensional discriminant representations and dictionary representations. However, this technical solution focuses more on data heterogeneity and missing data when dealing with dynamically changing foundation soil parameters, exhibiting relatively weak modeling capabilities for nonlinear coupling relationships. Furthermore, its analysis process does not fully utilize the dynamic prediction capabilities of machine learning algorithms, resulting in a lack of analysis of the variation patterns of foundation soil parameters under extreme rainfall conditions, making it difficult to meet the needs of real-time analysis of the bearing capacity of transmission line foundations.

[0004] The aforementioned problems indicate that existing methods for analyzing the bearing capacity of foundations still have room for improvement in areas such as dynamic parameter acquisition, complex coupling modeling, and real-time simulation accuracy. Therefore, this invention provides a method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions. The method aims to establish a dynamic coupling model of moisture content, pore water pressure, and shear strength by combining on-site monitoring with indoor testing. This model is then combined with finite element software to achieve real-time dynamic simulation analysis of the foundation's bearing capacity, thereby improving the accuracy and reliability of the analysis results. Summary of the Invention

[0005] The purpose of this invention is to provide a method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions. This method addresses the problem in existing technologies where traditional analysis methods rely on static parameters or simple linear coupling models, resulting in an inability to accurately reflect the dynamic changes in foundation soil parameters during rainfall. This deficiency leads to significant discrepancies between the foundation bearing capacity analysis results and actual conditions, making it difficult to meet the real-time analysis requirements under complex geological conditions.

[0006] In view of the above problems, the present invention provides a method and system for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions. The method includes the following steps: Collect field monitoring data and indoor test data to obtain the changes in water content, pore water pressure and shear strength of foundation soil under different rainfall intensities and durations; The above data was input into a long short-term memory network for training to generate a dynamic coupling model of water content, pore water pressure and shear strength. Based on this model, real-time rainfall parameters are input, and the current soil parameter values ​​are output. The output foundation soil parameter values ​​are imported into the finite element analysis software, and combined with the preset boundary conditions and material properties, the dynamic simulation analysis of the foundation bearing capacity is completed. A foundation load-bearing capacity assessment report is generated based on the simulation results and stored in the database.

[0007] Preferably, the collection of on-site monitoring data and indoor test data specifically includes: Real-time data on changes in moisture content, pore water pressure, and shear strength are collected through a sensor network deployed in the foundation soil. A complete dataset was formed by combining indoor test data.

[0008] Preferably, the sensor network includes multiple moisture content sensors, pore water pressure sensors, and shear strength sensors, which are arranged at different depths in the foundation soil.

[0009] Preferably, the training process of the Long Short-Term Memory network includes: The dataset is divided into a training set and a validation set; Optimize network parameters using the backpropagation algorithm; The performance of the model was evaluated using cross-validation.

[0010] Preferably, the real-time rainfall parameters include rainfall intensity and rainfall duration.

[0011] Preferably, the dynamic simulation analysis of the foundation bearing capacity adopts a nonlinear analysis method to calculate the foundation bearing capacity, settlement and stability index.

[0012] Preferably, the boundary conditions set in the finite element analysis software include the elastic modulus and Poisson's ratio of the foundation soil, as well as the geometry and load distribution of the foundation structure.

[0013] This invention provides a system for analyzing the foundation bearing capacity of transmission line projects under extreme rainfall conditions. The system includes the following modules: The data acquisition module collects real-time change data of moisture content, pore water pressure and shear strength through a sensor network deployed in the foundation soil, and combines it with indoor test data to form a complete dataset. The model training module uses a long short-term memory network to train the dataset and generate a dynamic coupling relationship model of water content, pore water pressure and shear strength. The parameter prediction module receives real-time rainfall parameters as input and calls the dynamic coupling relationship model to calculate the current soil parameter values. The finite element simulation module combines the foundation soil parameter values ​​with preset boundary conditions and material properties, and completes the dynamic simulation analysis of the foundation bearing capacity through the finite element analysis algorithm. The results storage module generates an evaluation report from the simulation analysis results and stores it in the database.

[0014] Preferably, the sensor network in the data acquisition module transmits the acquired data to the central processing unit via wireless or wired means.

[0015] Preferably, the result storage module supports historical data query and comparative analysis, and users can retrieve relevant reports by inputting specific conditions.

[0016] Compared with the prior art, the beneficial effects of the present invention are: By collecting field monitoring data and indoor test data, a dynamic coupling model of moisture content, pore water pressure, and shear strength is established using a Long Short-Term Memory (LSTM) network. This model reflects the dynamic changes in foundation soil parameters with rainfall. Based on this model, inputting real-time rainfall parameters outputs the current foundation soil parameter values, providing accurate data support for subsequent analysis. The foundation soil parameter values ​​are then imported into finite element analysis software, combined with preset boundary conditions and material properties, to complete a dynamic simulation analysis of the foundation bearing capacity, generating an evaluation report and storing it in a database. These techniques solve the problem of large deviations in foundation bearing capacity analysis results caused by the use of static parameters or simple linear coupling models in traditional analysis methods, improving the accuracy and reliability of the analysis results and providing a scientific basis and technical support for the safety assessment of transmission line projects under extreme rainfall conditions. Attached Figure Description

[0017] Figure 1 A flowchart illustrating the method for analyzing the foundation bearing capacity of transmission line projects under extreme rainfall conditions, provided in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram illustrating the working principle of the data acquisition module in an embodiment of the present invention.

[0019] Figure 3 This is a structural block diagram of the model training module in an embodiment of the present invention.

[0020] Figure 4 This is a functional diagram of the parameter prediction module in an embodiment of the present invention.

[0021] Figure 5 This is a flowchart illustrating the operation of the finite element simulation module in an embodiment of the present invention.

[0022] Figure 6 This is a data processing flowchart of the result storage module in an embodiment of the present invention. Detailed Implementation

[0023] This invention provides a method and system for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions. The specific embodiments of this invention are described in detail below with reference to the accompanying drawings. In this embodiment, the entire analysis process is jointly completed by a data acquisition module, a model training module, a parameter prediction module, a finite element simulation module, and a result storage module. These modules achieve dynamic analysis of the foundation bearing capacity through data transmission and functional collaboration.

[0024] First, the data acquisition module is the data source for the entire system. Its core task is to obtain the changes in moisture content, pore water pressure, and shear strength of the foundation soil under different rainfall intensities and durations. Figure 2 The working principle of the data acquisition module is demonstrated, where a sensor network is deployed at different depths in the foundation soil to monitor changes in moisture content, pore water pressure, and shear strength in real time. These sensors transmit the acquired data to the central processing unit of the data acquisition module via wireless or wired connections. Simultaneously, indoor experimental data is also input as supplementary data to the data acquisition module. This indoor experimental data comes from tests conducted on foundation soil samples under simulated rainfall conditions in the laboratory, including changes in the physical and mechanical properties of the foundation soil under different rainfall intensities and durations. The data acquired through these two methods form a complete dataset, providing fundamental support for the operation of subsequent modules.

[0025] Next, the model training module uses the dataset generated by the data acquisition module to train a Long Short-Term Memory (LSTM) network to generate a dynamic coupling model of water content, pore water pressure, and shear strength. Figure 3The diagram illustrates the structure of the model training module. The input layer of the LSTM network receives the dataset from the data acquisition module. The intermediate layers process the data using a multi-layer neural network to extract the dynamic changes in foundation soil parameters with rainfall. The output layer generates a dynamic coupling model. During training, the module uses backpropagation to continuously optimize the network parameters, ensuring the model accurately reflects the changing trends of actual foundation soil parameters. To improve the model's generalization ability, cross-validation is introduced during training, dividing the dataset into training and validation sets to evaluate the model's performance. The final dynamic coupling model can predict the current foundation soil parameter values ​​based on real-time rainfall parameters.

[0026] The parameter prediction module calculates the current soil parameter values ​​based on the dynamic coupling model generated by the model training module and real-time rainfall parameters. For example... Figure 4 As shown, the parameter prediction module receives real-time rainfall parameters, such as rainfall intensity and duration, from external weather stations or rainfall monitoring equipment and inputs them into the dynamic coupling model. The model internally calculates and outputs predicted values ​​for the current soil moisture content, pore water pressure, and shear strength. These predicted values ​​are then passed to the finite element simulation module, providing data support for subsequent foundation bearing capacity analysis. Notably, the parameter prediction module is designed with real-time performance and accuracy in mind, using optimized algorithms to ensure that prediction results can be generated quickly, meeting the rapid response requirements under extreme rainfall conditions.

[0027] The finite element simulation module is one of the core modules of this invention. Its main task is to combine the foundation soil parameter values ​​output by the parameter prediction module with the preset boundary conditions and material properties to complete the dynamic simulation analysis of the foundation bearing capacity. Figure 5 The operation flow of the finite element simulation module is described. First, the foundation soil parameters are input into the finite element analysis software, and boundary conditions and material properties are set, such as the elastic modulus and Poisson's ratio of the foundation soil, as well as the geometry and load distribution of the foundation structure. Then, the finite element analysis algorithm dynamically simulates the foundation's bearing capacity, calculating key indicators such as bearing capacity, settlement, and stability under the current foundation soil parameters. Nonlinear analysis methods are used during the simulation to fully consider the impact of dynamic changes in foundation soil parameters with rainfall on the foundation's bearing capacity. Finally, the finite element simulation module generates a simulation report containing the foundation's bearing capacity assessment results and transfers the report to the results storage module.

[0028] The results storage module is responsible for processing the simulation reports generated by the finite element simulation module and storing them in the database for subsequent querying and analysis. Figure 6The diagram illustrates the data processing flow of the results storage module. First, the data in the simulation report is formatted to ensure its standardization and readability. Then, the processed data is stored in the database, and a unique identifier is generated for subsequent retrieval. Furthermore, the results storage module supports querying and comparative analysis of historical data. Users can retrieve relevant reports by inputting specific criteria, thereby understanding the changing trends of foundation bearing capacity under different periods or rainfall conditions. This design not only improves the efficiency of data management but also provides technical support for long-term monitoring and evaluation.

[0029] Throughout the system's operation, the connections and collaboration between modules are crucial. The data acquisition module acquires field monitoring data through a sensor network and combines it with indoor experimental data to form a complete dataset, providing input for the model training module. The model training module uses an LSTM network to generate a dynamically coupled model and transmits it to the parameter prediction module. The parameter prediction module calculates foundation soil parameters based on real-time rainfall parameters and transmits the results to the finite element simulation module. The finite element simulation module performs foundation bearing capacity analysis under preset conditions and transmits the simulation report to the results storage module. The results storage module processes and stores the report, forming a closed-loop data flow and functional chain.

[0030] To further illustrate the practical application scenarios of this invention, a detailed description is provided below using a specific case. Assume a power transmission line project is located in a mountainous area, where the foundation soil is mainly composed of cohesive soil and sand, and extreme rainfall events frequently occur in the region. Before construction, technicians deploy a sensor network in the foundation soil, including moisture content sensors, pore water pressure sensors, and shear strength sensors, and set up an indoor testing device to simulate the behavior of the foundation soil under different rainfall conditions. After the data acquisition module collects on-site monitoring data and indoor test data, the model training module uses this data to train an LSTM network and generate a dynamic coupling relationship model. During actual rainfall, the parameter prediction module receives real-time rainfall parameters, such as an hourly rainfall of 50 mm for a duration of 2 hours, and calculates the current foundation soil parameter values ​​using the dynamic coupling relationship model. The finite element simulation module inputs these parameter values ​​into the finite element analysis software, and performs foundation bearing capacity analysis based on preset boundary conditions and material properties, resulting in a 15% decrease in foundation bearing capacity and a 20 mm increase in settlement. The result storage module stores the analysis results in a database and generates an evaluation report for engineers' reference. In this way, engineers can keep abreast of changes in the foundation's load-bearing capacity and take corresponding measures to ensure the safe operation of transmission lines.

[0031] In terms of hardware implementation, the sensor network in the data acquisition module adopts a distributed layout to ensure coverage of key areas of the foundation soil. The sensors connect to the central processing unit via a wireless communication protocol to achieve real-time data transmission. The model training module and parameter prediction module run on a high-performance computing server to meet the computational requirements of LSTM network training and real-time prediction. The finite element simulation module uses commercial finite element analysis software, such as ANSYS or ABAQUS, combined with customized scripts to automate the analysis process. The results storage module relies on cloud storage technology to build a database, supporting efficient storage and rapid retrieval of large-scale data.

[0032] As can be seen from the above specific embodiments, the method and system for analyzing the foundation bearing capacity of transmission line projects under extreme rainfall conditions provided by the present invention can effectively solve the problem of large deviations in the foundation bearing capacity analysis results caused by the use of static parameters or simple linear coupling models in traditional analysis methods.

[0033] All content not described in detail in this specification is prior art known to those skilled in the art, and the model parameters of each electrical appliance are not specifically limited; conventional equipment can be used. Electrical control components not mentioned in this technical solution are not shown in the figures because they are prior art, and will not be described further here.

[0034] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions, characterized in that, The method includes the following steps: Collect field monitoring data and indoor test data to obtain the changes in water content, pore water pressure and shear strength of foundation soil under different rainfall intensities and durations; The above data was input into a long short-term memory network for training to generate a dynamic coupling model of water content, pore water pressure and shear strength. Based on this model, real-time rainfall parameters are input, and the current soil parameter values ​​are output. The output foundation soil parameter values ​​are imported into the finite element analysis software, and combined with the preset boundary conditions and material properties, the dynamic simulation analysis of the foundation bearing capacity is completed. A foundation load-bearing capacity assessment report is generated based on the simulation results and stored in the database.

2. The method for analyzing the foundation bearing capacity of transmission line engineering under extreme rainfall conditions according to claim 1, characterized in that, The collected on-site monitoring data and indoor test data specifically include: Real-time data on changes in moisture content, pore water pressure, and shear strength are collected through a sensor network deployed in the foundation soil. A complete dataset was formed by combining indoor test data.

3. The method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 2, characterized in that, The sensor network includes multiple moisture content sensors, pore water pressure sensors, and shear strength sensors, which are arranged at different depths in the foundation soil.

4. The method for analyzing the foundation bearing capacity of transmission line engineering under extreme rainfall conditions according to claim 1, characterized in that, The training process of the Long Short-Term Memory network includes: The dataset is divided into a training set and a validation set; Optimize network parameters using the backpropagation algorithm; The performance of the model was evaluated using cross-validation.

5. The method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 1, characterized in that, The real-time rainfall parameters include rainfall intensity and rainfall duration.

6. The method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 1, characterized in that, The dynamic simulation analysis of the foundation bearing capacity adopts a nonlinear analysis method to calculate the foundation bearing capacity, settlement and stability index.

7. The method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 1, characterized in that, The boundary conditions set in the finite element analysis software include the elastic modulus and Poisson's ratio of the foundation soil, as well as the geometry and load distribution of the foundation structure.

8. A system for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions, used to execute the method for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions as described in any one of claims 1 to 7, characterized in that, The system includes the following modules: The data acquisition module collects real-time change data of moisture content, pore water pressure and shear strength through a sensor network deployed in the foundation soil, and combines it with indoor test data to form a complete dataset. The model training module uses a long short-term memory network to train the dataset and generate a dynamic coupling relationship model of water content, pore water pressure and shear strength. The parameter prediction module receives real-time rainfall parameters as input and calls the dynamic coupling relationship model to calculate the current soil parameter values. The finite element simulation module combines the foundation soil parameter values ​​with preset boundary conditions and material properties, and completes the dynamic simulation analysis of the foundation bearing capacity through the finite element analysis algorithm. The results storage module generates an evaluation report from the simulation analysis results and stores it in the database.

9. The system for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 8, characterized in that, The sensor network in the data acquisition module transmits the acquired data to the central processing unit via wireless or wired means.

10. The system for analyzing the bearing capacity of transmission line foundations under extreme rainfall conditions according to claim 8, characterized in that, The results storage module supports historical data query and comparative analysis, and users can retrieve relevant reports by inputting specific conditions.

Images