Early diagnosis system and method suitable for large deformation of foundation in high-cold and high-altitude area

Abstract

The invention relates to the technical field of civil engineering, and discloses a foundation large deformation early diagnosis system and method suitable for high-cold and high-altitude areas, and the system specifically comprises a real-time monitoring module and a numerical simulation fusion diagnosis module. The real-time monitoring module is used for acquiring and outputting real-time monitoring data of a foundation site in real time; and the numerical simulation fusion diagnosis module is used for modeling and associating real-time monitoring data with finite element model parameters so as to automatically generate a finite element model of the foundation and carry out analog simulation, and finally a simulation and diagnosis report is generated. The problem that early diagnosis of foundation deformation cannot be accurately carried out in real time in the prior art is solved, and the method has the advantages of being low in power consumption and high in adaptability.

Description

Technical Field

[0001] The present invention relates to the field of civil engineering technology, and more specifically, to an early diagnosis system and method for large deformation of a foundation suitable for high-cold and high-altitude areas. Background Art

[0002] At present, foundation deformation diagnosis technology mainly relies on traditional monitoring methods, such as settlement observation, geological radar, strain gauges and laser scanning. These technologies can provide certain real-time data by regularly measuring the deformation of the foundation to help engineers evaluate the health of the foundation. Especially in some large-scale engineering projects, the combination of multiple monitoring equipment can comprehensively evaluate the foundation status and identify possible deformation trends and hidden dangers.

[0003] Although the existing foundation deformation diagnosis technology can monitor and evaluate the foundation condition to a certain extent, it still has many shortcomings. First, traditional monitoring methods often rely on regular manual inspections, which have a long response time and cannot achieve real-time monitoring and rapid response. Secondly, the deployment and maintenance costs of monitoring equipment are high, especially in cold and high-altitude areas. The harsh climatic conditions and complex geological environment make the long-term stable operation of equipment challenging. In addition, the data analysis and processing capabilities are limited, making it difficult to quickly extract effective information from massive monitoring data, resulting in the identification of potential risks not being timely and accurate enough.

[0004] For example, the prior art has a diagnostic system based on a dam safety assessment strategy library, comprising: a data access module; a data cleaning module; a strategy library management module; a safety diagnosis module; and an exception handling module, wherein the strategy library comprises: monitoring content, including monitoring objects, monitoring locations, monitoring items, and monitoring points; monitoring standards, including monitoring methods, monitoring indicators, monitoring criteria, and fusion rules.

[0005] In summary, although the current foundation deformation diagnosis technology has made some progress in monitoring, its limitations are becoming increasingly prominent in the face of complex challenges in high-cold and high-altitude areas. Therefore, it is urgent to develop a comprehensive intelligent monitoring system that combines advanced sensing technology and data analysis methods to achieve real-time and accurate early diagnosis of foundation deformation. This can not only improve engineering safety, but also provide more reliable technical guarantees for infrastructure construction in high-cold and high-altitude areas, thereby promoting the sustainable development of related projects. Summary of the invention

[0006] In order to solve the problem that the prior art cannot perform early diagnosis of foundation deformation in real time and accurately, the present invention provides a foundation large deformation early diagnosis system and method suitable for high-cold and high-altitude areas, which has the characteristics of low power consumption and strong adaptability.

[0007] In order to achieve the above-mentioned purpose of the present invention, the technical scheme adopted is as follows: An early diagnosis system for large deformation of foundation suitable for high-cold and high-altitude areas, including a real-time monitoring module and a numerical simulation fusion diagnosis module; The real-time monitoring module is used to obtain and output the real-time monitoring data of the foundation site in real time; The numerical simulation fusion diagnosis module is used for modeling and associating real-time monitoring data with finite element model parameters, thereby automatically generating a finite element model of the foundation and performing simulation, and finally generating a simulation and diagnosis report.

[0008] Preferably, the real-time monitoring module includes a real-time acquisition layer, a real-time adjustment layer, and a real-time transmission layer; the real-time acquisition layer is used to select a wireless connection method according to site conditions to obtain multimodal real-time monitoring data including sensor network data, weather service API, and geological database data; the real-time adjustment layer is used to adjust the encoding standard according to the data type; the real-time transmission layer is used to transmit the video stream to the cloud server in real time.

[0009] Furthermore, it also includes a Web application module; the Web application module is used to build a Web application for users to remotely access and retrieve real-time monitoring data from the cloud.

[0010] Furthermore, the overall architecture of the Web application includes a client, a server, and a database layer; the server is provided with an API interface and integrated with a database; the client receives client instructions; the server retrieves and stores real-time monitoring data to the database layer or transmits real-time monitoring data to a monitoring information expansion module according to client instructions.

[0011] Furthermore, it also includes a monitoring information expansion module; the monitoring information expansion module is used to build a real-time data stream processing framework, receive and pre-process real-time monitoring data, identify anomalies, calculate potential foundation instability risks, and obtain monitoring analysis results.

[0012] Furthermore, specifically, the monitoring information expansion module includes a data input layer, a data processing layer, a data analysis layer, a data visualization layer, and a data output layer; The data input layer is used to obtain sensor network data, weather service API, and geological database data from the cloud by designing interfaces and data adapters of different data sources; The data processing layer is used to apply normalization and feature extraction algorithms to clean the acquired raw data, and to perform denoising, fill in missing values ​​and unify data formats; The data analysis layer is used to extract deformation rate and environmental impact factors through statistical and analytical models, and further identify anomalies exceeding safety thresholds based on the deformation rate and environmental impact factors; The data visualization layer is used to predict the trend of the identified anomalies based on historical data and calculate the potential risk of foundation instability through machine learning algorithms; The data output layer is used to output the potential risk of foundation instability as a visualization result.

[0013] Furthermore, the numerical simulation fusion diagnosis module specifically includes a data association layer, a model construction layer, a model simulation layer, and a report generation layer; The data association block is used to dynamically associate the real-time monitoring data with the three-dimensional finite element model parameters through the design interface; The model building layer is used to perform three-dimensional finite element modeling based on the associated three-dimensional finite element model parameters; The model simulation layer is used to perform on-site simulation of the constructed three-dimensional finite element model using a machine learning model to obtain risk areas, key indicators and future forecast data; The report generation layer is used to generate simulation and diagnosis reports based on risk areas, key indicators and future forecast data.

[0014] Furthermore, after constructing the 3D finite element model, a sensitivity analysis was performed on the constructed 3D finite element model through any one or more methods of historical cases or experimental data, so as to identify key variables and understand the variable relationship of the model, and improve the model by reselecting and adjusting the model parameters.

[0015] Furthermore, based on the associated three-dimensional finite element model parameters, three-dimensional finite element model building is performed, specifically: based on the set topography, stress field distribution, environmental parameters, and preset material properties, boundary conditions and loading conditions, the three-dimensional finite element model is constructed.

[0016] An early diagnosis method for large deformation of foundation suitable for high-cold and high-altitude areas includes the following specific steps: Acquire and output real-time monitoring data of the foundation site in real time; The real-time monitoring data is associated with the finite element model parameters to automatically generate a finite element model of the foundation and perform simulation, ultimately generating a simulation and diagnostic report.

[0017] The beneficial effects of the present invention are as follows: The purpose of the present invention is to develop an early diagnosis system for large deformation of foundations suitable for high-cold and high-altitude areas, in order to cope with the challenges brought by the extreme geological conditions and climatic conditions in the region to the safety of infrastructure. By acquiring and outputting real-time monitoring data of the foundation site in real time, the present invention can monitor the deformation of the foundation in real time, and by associating the real-time monitoring data with the finite element model parameters, automatically generate a finite element model of the foundation and perform simulation, so as to identify and warn of potential risks at an early stage. The application of the present invention can significantly improve the safety of infrastructure, reduce the risk of engineering accidents caused by unstable foundations, and ensure the safety of people's lives and property. At the same time, the system design takes into account the characteristics of high-cold and high-altitude environments, has low power consumption and self-diagnosis capabilities, is highly adaptable, and can meet the monitoring needs under extreme conditions, thereby providing a strong guarantee for the reliable operation of infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of an early diagnosis system for large deformation of foundation suitable for high-cold and high-altitude areas.

[0019] Figure 2 This is a schematic diagram of the monitoring information expansion module of the early diagnosis system for large deformation of foundation suitable for high-cold and high-altitude areas.

[0020] Figure 3 It is a flow chart of the early diagnosis method of large deformation of foundation suitable for high-cold and high-altitude areas. DETAILED DESCRIPTION

[0021] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] Example 1 like Figure 1 As shown, a large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas includes a real-time monitoring module and a numerical simulation fusion diagnosis module; The real-time monitoring module is used to obtain and output the real-time monitoring data of the foundation site in real time; The numerical simulation fusion diagnosis module is used for modeling and associating real-time monitoring data with finite element model parameters, thereby automatically generating a finite element model of the foundation and performing simulation, and finally generating a simulation and diagnosis report.

[0023] In this embodiment, the real-time monitoring module is the core component for acquiring and transmitting on-site video data. Its main purpose is to provide visual support for monitoring foundation deformation, so as to make more intuitive analysis and decision-making. The real-time monitoring module realizes real-time monitoring and data transmission of on-site conditions through the deployed video sensors. This system is designed to improve the safety of foundations in high-cold and high-altitude areas, and to achieve early diagnosis and management of foundation pit deformation by integrating different modules.

[0024] In a specific embodiment, the real-time monitoring module includes a real-time acquisition layer, a real-time adjustment layer, and a real-time transmission layer; Among them, the real-time acquisition layer selects wireless communication technologies such as LoRa according to the on-site conditions, adjusts the transmission protocol and path, and uses quality of service (QoS) technology to improve network performance; the real-time adjustment layer selects appropriate encoding standards, such as H.265. Ensure that the compressed video reduces the data volume as much as possible while ensuring the quality. The real-time transmission layer transmits the video stream to the cloud server in real time. Use load balancing technology to ensure network stability when multiple devices transmit simultaneously; and develop and deploy video retrieval tools to enable the real-time transmission layer to support multi-condition fast search. Implement video playback function, support playback by timeline and event markers; and manage large-scale video data by setting the upload frequency and storage duration and using the scalability of cloud storage.

[0025] The numerical simulation fusion diagnosis module is used to integrate numerical simulation technology with actual monitoring data to conduct in-depth analysis and diagnosis of foundation deformation. Its main purpose is to establish a finite element model of the foundation and simulate deformation behavior under different working conditions.

[0026] In a specific embodiment, it also includes a Web application module; the Web application module is used to build a Web application for users to remotely access and retrieve real-time monitoring data in the cloud.

[0027] In a specific embodiment, the overall architecture of the Web application includes a client, a server, and a database layer; the server is provided with an API interface and integrated with a database; the client receives client instructions; the server retrieves and stores real-time monitoring data to the database layer or transmits real-time monitoring data to a monitoring information expansion module according to client instructions.

[0028] In this embodiment, the Web application module selects Vue.js as the front-end framework and Django as the back-end framework. MySQL is selected as the database system and cloud service platform. The Web application module ensures the scalability and maintainability of the system by determining the module division and interface design, integrating the database, ensuring the safe storage and efficient query of real-time monitoring data, integrating the front-end and back-end functions, and ensuring the real-time transmission and synchronization of data.

[0029] In a specific embodiment, it also includes a monitoring information expansion module; the monitoring information expansion module is used to build a real-time data stream processing framework, receive and pre-process real-time monitoring data, identify anomalies, calculate potential foundation instability risks, and obtain monitoring analysis results.

[0030] In a specific embodiment, Figure 2 As shown, specifically, the monitoring information expansion module includes a data input layer, a data processing layer, a data analysis layer, a data visualization layer, and a data output layer; The data input layer is used to obtain sensor network data, weather service API, and geological database data from the cloud by designing interfaces and data adapters of different data sources; The data processing layer is used to apply normalization and feature extraction algorithms to clean the acquired raw data, and to perform denoising, fill in missing values ​​and unify data formats; The data analysis layer is used to extract deformation rate and environmental impact factors through statistical and analytical models, and further identify anomalies exceeding safety thresholds based on the deformation rate and environmental impact factors; The data visualization layer is used to predict the trend of the identified anomalies based on historical data and calculate the potential risk of foundation instability through machine learning algorithms; The data output layer is used to output the potential risk of foundation instability as a visualization result.

[0031] In this embodiment, the data processing layer uses ETL tools to clean the raw data, including denoising, filling missing values ​​and unifying data formats. Normalization and feature extraction algorithms are applied to preprocess the data. The data output layer adds geographic information system (GIS) support to achieve visual map display of monitoring information. Dynamic report generation function is developed to regularly output monitoring and analysis results.

[0032] In a specific embodiment, the numerical simulation fusion diagnosis module specifically includes a data association layer, a model construction layer, a model simulation layer, and a report generation layer; The data association block is used to dynamically associate the real-time monitoring data with the three-dimensional finite element model parameters through the design interface; The model building layer is used to perform three-dimensional finite element modeling based on the associated three-dimensional finite element model parameters; The model simulation layer is used to perform on-site simulation of the constructed three-dimensional finite element model using a machine learning model to obtain risk areas, key indicators and future forecast data; The report generation layer is used to generate simulation and diagnosis reports based on risk areas, key indicators and future forecast data.

[0033] In a specific embodiment, after constructing the three-dimensional finite element model, a sensitivity analysis is performed on the constructed three-dimensional finite element model through any one or more methods of historical cases or experimental data, so as to identify key variables and understand the variable relationship of the model, and improve the model by reselecting and adjusting the model parameters.

[0034] In a specific embodiment, three-dimensional finite element modeling is performed based on the associated three-dimensional finite element model parameters, specifically: based on the set topography, stress field distribution, environmental parameters, and preset material properties, boundary conditions and loading conditions, the three-dimensional finite element model is constructed.

[0035] In this embodiment, the interface design between Flac 3D software and the background simulation calculation module is specifically used to dynamically associate the real-time monitoring data with the Flac 3D model parameters; in this embodiment, before the association, the monitoring data is preprocessed and cleaned using Python's data processing library (such as Pandas, NumPy) to ensure the accuracy and validity of the input data. The interface design between Flac 3D and the background simulation calculation module is further optimized to ensure the dynamic association and seamless integration of data. The association mechanism between the monitoring information and the Flac 3D model parameters is determined to support the dynamic update of real-time data.

[0036] In this embodiment, when constructing a three-dimensional finite element model, the Python interface (Flac3DPython API) provided by Flac3D is used to automatically construct the initial model, and the model geometry, material properties and initial boundary conditions are defined through Python scripts to quickly generate the on-site foundation model. The script can dynamically adjust parameters according to project requirements and support reading geometry and material parameters from external data sources (such as CSV files, databases).

[0037] In this embodiment, before conducting on-site simulation, a script is developed to automatically run the Flac 3D calculation task, transfer data and parameters from the main system to the background, dynamically allocate server resources according to the calculation scale and priority, extract the Flac 3D output displacement field data results, and store them in the database. Then, a machine learning model is used to combine the simulation results with real-time monitoring data for on-site simulation. In this embodiment, when a machine learning model is used to perform on-site simulation of the constructed three-dimensional finite element model, based on the specific amount of data, a regression model (such as random forest regression, support vector regression (SVR)) can be used for parameter regression and prediction, a neural network (such as deep feedforward neural network, convolutional neural network) can be used to capture complex relationships, and XGBoost can be used to process large-scale data. Any machine learning model can be used for simulation and prediction.

[0038] In this embodiment, when generating simulation and diagnosis reports, scientific computing and visualization libraries in Python (such as Matplotlib and PyVista) are used to analyze and visualize the risk areas, key indicators, and future forecast data output by Flac3D. Simulation and diagnosis reports and charts are automatically generated to display key analysis results, risk areas, and risk assessments, and to provide early warnings of potential risks and suggestions for countermeasures.

[0039] In this embodiment, the present invention combines multiple sensor technologies for real-time monitoring to adapt to the impact of high-cold and high-altitude environments on the performance of foundation materials, and constructs an accurate numerical simulation model through numerical simulation software such as Flac 3D. Through real-time simulation calculations in the server background, support is provided for dynamic evaluation of the foundation status and engineering decision-making, while considering the reliability and durability design of the system for long-term operation in extreme environments.

[0040] Example 2 More specifically, in a specific embodiment, the real-time monitoring module is based on 5G network and edge computing, including a real-time acquisition layer, a real-time adjustment layer, and a real-time transmission layer; The real-time acquisition layer uses an embedded GPU video processing chip to pre-process on-site data, and combines it with a distributed file storage system to achieve efficient storage and retrieval of multi-source video streams. The real-time transmission layer optimizes the transmission path through SD-WAN to ensure the stability of large-scale, high-speed data uploads. The real-time adjustment layer uses the H.265+ / AV1 video encoding standard combined with dynamic bit rate adjustment technology to optimize video quality and bandwidth occupancy.

[0041] In a specific embodiment, it also includes a Web application module; the Web application module is used to build a Web application for users to remotely access and retrieve real-time monitoring data in the cloud.

[0042] In a specific embodiment, the overall architecture of the Web application includes a client, a server, and a database layer; the server is provided with an API interface and integrated with a database; the client receives client instructions; the server retrieves and stores real-time monitoring data to the database layer or transmits real-time monitoring data to a monitoring information expansion module according to client instructions.

[0043] In this embodiment, the Web application front end uses Three.js to build an interactive interface, providing real-time data visualization and multi-dimensional data query functions. The back end uses the Django framework to support efficient API calls and asynchronous task scheduling. The database uses MySQL to achieve efficient storage and query of spatiotemporal data. The security mechanism integrates OAuth 2.0 authentication and WebApplication Firewall to provide multi-level access control and protection, and supports modular expansion and dynamic load balancing based on the microservice architecture.

[0044] In a specific embodiment, it also includes a monitoring information expansion module; the monitoring information expansion module is used to build a real-time data stream processing framework, receive and pre-process real-time monitoring data, identify anomalies, calculate potential foundation instability risks, and obtain monitoring analysis results.

[0045] In a specific embodiment, specifically, the monitoring information expansion module includes a data input layer, a data processing layer, a data analysis layer, a data visualization layer, and a data output layer; The data input layer is used to obtain sensor network data, weather service API, and geological database data from the cloud by designing interfaces and data adapters of different data sources; The data processing layer is used to apply normalization and feature extraction algorithms to clean the acquired raw data, and to perform denoising, fill in missing values ​​and unify data formats; The data analysis layer is used to extract deformation rate and environmental impact factors through statistical and analytical models, and further identify anomalies exceeding safety thresholds based on the deformation rate and environmental impact factors; The data visualization layer is used to predict the trend of the identified anomalies based on historical data and calculate the potential risk of foundation instability through machine learning algorithms; The data output layer is used to output the potential risk of foundation instability as a visualization result.

[0046] In this embodiment, the monitoring information expansion module builds a real-time data stream processing framework through Flink to support the dynamic fusion of sensor data, video monitoring and environmental data; the data input layer uses multimodal data integration technology for feature alignment and data completion; the data visualization layer uses a time series prediction algorithm to perform short-term and long-term predictions on deformation trends, and integrates XGBoost and adaptive Boosting models to detect and evaluate anomalies in risk areas; the data output layer uses Cesium.js to develop a three-dimensional geographic information visualization platform to display monitoring results.

[0047] In this embodiment, in the numerical simulation fusion diagnosis module, the Flac 3D software is combined to realize the refined three-dimensional geological model construction and deformation analysis, and the multi-physics field coupling technology is used to simulate the dynamic response of the foundation under complex working conditions. The MPI and OpenMP parallel computing frameworks are integrated to run large-scale simulation tasks in the high-performance computing cluster, and the material parameters and boundary conditions of the simulation model are dynamically adjusted using the parameter inversion algorithm based on Bayesian optimization. The pattern recognition method based on the graph neural network is used to automatically identify potential unstable areas, and an automatic report generation engine is developed to provide a panoramic analysis of risk levels, prediction curves and key influencing factors. In terms of system integration and optimization, the Kubernetes container orchestration technology is used to integrate various modules to ensure the flexible deployment and high reliability of the system. The entire process from data collection to analysis report generation is managed through the ETL workflow based on Apache Airflow, and the target recognition and classification capabilities of video and sensor data are enhanced in combination with deep learning models. In this embodiment, through the application of the above-mentioned advanced technologies, the large deformation early diagnosis system of foundation suitable for high-cold and high-altitude areas realizes the full life cycle monitoring and diagnosis of foundation deformation, providing strong technical support for engineering safety.

[0048] Example 3 like Figure 3 As shown, a method for early diagnosis of large deformation of foundation suitable for high-cold and high-altitude areas includes the following specific steps: Acquire and output real-time monitoring data of the foundation site in real time; The real-time monitoring data is associated with the finite element model parameters to automatically generate a finite element model of the foundation and perform simulation, ultimately generating a simulation and diagnostic report.

[0049] Obviously, the above embodiments of the present invention are only examples for clearly explaining the present invention, and are not intended to limit the implementation methods of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. An early diagnosis system for large deformation of foundation suitable for high-cold and high-altitude areas, characterized by: Including real-time monitoring module and numerical simulation fusion diagnosis module; The real-time monitoring module is used to obtain and output the real-time monitoring data of the foundation site in real time; The numerical simulation fusion diagnosis module is used for modeling and associating real-time monitoring data with finite element model parameters, thereby automatically generating a finite element model of the foundation and performing simulation, and finally generating a simulation and diagnosis report.

2. The large deformation early diagnosis system for foundation suitable for cold and high altitude areas according to claim 1 is characterized by: The real-time monitoring module includes a real-time acquisition layer, a real-time adjustment layer, and a real-time transmission layer; the real-time acquisition layer is used to select a wireless connection method according to on-site conditions to obtain multimodal real-time monitoring data including sensor network data, weather service API, and geological database data; the real-time adjustment layer is used to adjust the encoding standard according to the data type; the real-time transmission layer is used to transmit the video stream to the cloud server in real time.

3. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 1 is characterized by: It also includes a Web application module; the Web application module is used to build a Web application for users to remotely access and retrieve real-time monitoring data from the cloud.

4. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 3 is characterized by: The overall architecture of the Web application includes a client, a server, and a database layer; the server is provided with an API interface and integrated with a database; the client receives customer instructions; the server retrieves and stores real-time monitoring data to the database layer or transmits real-time monitoring data to a monitoring information expansion module according to customer instructions.

5. The large deformation early diagnosis system for foundation suitable for cold and high altitude areas according to claim 1 is characterized by: It also includes a monitoring information expansion module; the monitoring information expansion module is used to build a real-time data stream processing framework, receive and pre-process real-time monitoring data, identify anomalies, calculate potential foundation instability risks, and obtain monitoring analysis results.

6. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 5 is characterized by: Specifically, the monitoring information expansion module includes a data input layer, a data processing layer, a data analysis layer, a data visualization layer, and a data output layer; The data input layer is used to obtain sensor network data, weather service API, and geological database data from the cloud by designing interfaces and data adapters of different data sources; The data processing layer is used to apply normalization and feature extraction algorithms to clean the acquired raw data, and to perform denoising, fill in missing values ​​and unify data formats; The data analysis layer is used to extract deformation rate and environmental impact factors through statistical and analytical models, and further identify anomalies exceeding safety thresholds based on the deformation rate and environmental impact factors; The data visualization layer is used to predict the trend of the identified anomalies based on historical data and calculate the potential risk of foundation instability through machine learning algorithms; The data output layer is used to output the potential risk of foundation instability as a visualization result.

7. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 1 is characterized by: The numerical simulation fusion diagnosis module specifically includes a data association layer, a model construction layer, a model simulation layer, and a report generation layer; The data association block is used to dynamically associate the real-time monitoring data with the three-dimensional finite element model parameters through the design interface; The model building layer is used to perform three-dimensional finite element modeling based on the associated three-dimensional finite element model parameters; The model simulation layer is used to perform on-site simulation of the constructed three-dimensional finite element model using a machine learning model to obtain risk areas, key indicators and future forecast data; The report generation layer is used to generate simulation and diagnosis reports based on risk areas, key indicators and future forecast data.

8. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 7 is characterized by: After constructing the three-dimensional finite element model, a sensitivity analysis was performed on the constructed three-dimensional finite element model through one or more methods of historical cases or experimental data to identify key variables and understand the variable relationship of the model, and to improve the model by reselecting and adjusting the model parameters.

9. The large deformation early diagnosis system for foundation suitable for high-cold and high-altitude areas according to claim 8 is characterized by: Based on the associated three-dimensional finite element model parameters, three-dimensional finite element model building is performed, specifically: based on the set topography, stress field distribution, environmental parameters, and preset material properties, boundary conditions and loading conditions, the three-dimensional finite element model is constructed.

10. An early diagnosis method for large deformation of foundation suitable for high-cold and high-altitude areas, characterized by: The specific steps include: Acquire and output real-time monitoring data of the foundation site in real time; The real-time monitoring data is associated with the finite element model parameters to automatically generate a finite element model of the foundation and perform simulation, ultimately generating a simulation and diagnostic report.

Images