Tunnel deformation prediction method based on multi-source monitoring data fusion

Abstract

The invention relates to a tunnel deformation prediction method based on multi-source monitoring data fusion, and belongs to the technical field of tunnel deformation prediction, and the method comprises the following steps: S1, an early-stage preparation stage; s2, a data collection and analysis stage; s3, a model establishment and prediction stage; and S4, a result evaluation and application stage. According to the tunnel deformation prediction method based on multi-source monitoring data fusion, through accurate deformation prediction, an engineer is helped to carry out optimization design on a tunnel structure and select proper supporting measures before construction, unnecessary material waste and cost increase are avoided, and through a continuous monitoring and immediate feedback mechanism, the tunnel deformation prediction accuracy is improved. The method has the advantages that the method is simple and easy to implement, precious time is won for emergency evacuation and response measures, data support is provided for making a tunnel maintenance plan through accumulation and analysis of long-term monitoring data, maintenance work is precise and efficient, and the advantages of being high in prediction efficiency and prediction accuracy are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel deformation prediction, and in particular to a tunnel deformation prediction method based on multi-source monitoring data fusion. Background Art

[0002] Tunnels are important transportation projects connecting different regions. After frequent use and long-term operation, tunnel deformation has become a problem that needs attention due to the particularity of underground structures and external influences. Deformation monitoring and analysis are important means to ensure the stability of tunnel structures and safe operation. The causes of tunnel deformation are complex and diverse, mainly including natural factors such as groundwater level changes, earthquakes, rock deformation, temperature changes, and human factors such as excavation, support, and groundwater level changes during tunnel construction. These factors lead to stratum displacement and building deformation. If the deformation of the tunnel is not monitored and analyzed in time, effective measures cannot be taken to deal with potential safety issues.

[0003] However, with the increasing complexity and scale of tunnel projects, a single monitoring method often cannot fully and accurately reflect the deformation of the tunnel. Therefore, multi-source data fusion technology came into being. Multi-source data fusion technology refers to the technology of using relevant means to integrate all the information obtained through investigation and analysis, and to make a unified evaluation of the information, and finally obtain unified information. The purpose of developing this technology is to integrate various different data information, absorb the characteristics of different data sources, and then extract unified information from them that is better and richer than single data.

[0004] In summary, the tunnel deformation prediction method based on multi-source monitoring data fusion is a new prediction method developed on the basis of traditional monitoring methods, combining multi-source data fusion technology and machine learning algorithms. This method can more comprehensively and accurately reflect the deformation of the tunnel, provide a scientific basis for the repair and maintenance of the tunnel, and has important practical application value. Therefore, this application proposes a tunnel deformation prediction method based on multi-source monitoring data fusion to solve the above problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a tunnel deformation prediction method based on multi-source monitoring data fusion, which has the advantages of high prediction efficiency and high prediction accuracy, and solves the problems of low prediction efficiency and poor prediction accuracy of the existing tunnel deformation prediction methods.

[0006] To achieve the above object, the present invention provides the following technical solution: a tunnel deformation prediction method based on multi-source monitoring data fusion, comprising the following steps:

[0007] S1. Preliminary preparation stage: Before tunnel construction, geological exploration is carried out to understand the geological conditions. Based on the geological exploration results, a suitable construction plan and a method for predicting stratum displacement are formulated; monitoring equipment is arranged in the tunnel construction area to ensure that the monitoring equipment can accurately and in real time record the deformation data during the tunnel construction process;

[0008] S2, Data collection and analysis stage: During the tunnel construction process, the displacement, stress change and groundwater level change of the strata around the tunnel are monitored in real time, the monitoring data are recorded, and preliminary analysis is performed to understand the trend and law of tunnel deformation; the monitoring data are cleaned, outliers and noise are removed, and the data are interpolated and smoothed to improve the accuracy and reliability of the data;

[0009] S3, model building and prediction stage: select appropriate prediction methods according to the characteristics of geological exploration results and monitoring data; establish corresponding prediction models according to the selected prediction methods; verify the prediction models with known data, evaluate the accuracy and reliability of the models, and optimize and adjust the models according to the verification results to improve the prediction accuracy; input the monitoring data into the optimized prediction model, predict the tunnel deformation, and output the prediction results;

[0010] S4. Result evaluation and application stage: Evaluate the prediction results, analyze the prediction errors and uncertainties, and judge the applicability and reliability of the prediction method based on the evaluation results; apply the prediction results to the safety control of tunnel construction and the construction of subsequent projects. According to the prediction results, formulate corresponding protective measures and construction plans to reduce tunnel deformation and reduce damage risks; during the tunnel construction process and subsequent operations, continuously monitor the tunnel deformation, compare and analyze the monitoring data with the prediction results, and provide timely feedback to the design and construction personnel so as to adjust the construction plan and protective measures.

[0011] Furthermore, the geological conditions in S1 include stratigraphic properties, hydrogeological conditions, faults and cavities.

[0012] Furthermore, the monitoring equipment in S1 includes a displacement sensor, a stress sensor and a groundwater level monitor.

[0013] Furthermore, the prediction results in S3 include displacement and stress changes of the strata around the tunnel.

[0014] Furthermore, common prediction methods in S3 include numerical simulation method, empirical formula method, reference surface method and loophole method.

[0015] Furthermore, the numerical simulation method needs to construct a mechanical model of the tunnel section, and needs to consider the influencing factors of geological conditions, tunnel parameters and construction technology.

[0016] Furthermore, the numerical simulation method comprises the following steps:

[0017] S3-1. Mathematical modeling: Based on the physical background of the tunnel deformation problem, establish differential equations reflecting the relationship between various physical quantities in the tunnel deformation problem and their corresponding solution conditions, and realize digital modeling by establishing the Navier-Stokes equations and their solution conditions;

[0018] S3-2, determine the algorithm and coordinate system: according to the mathematical model established in S3-1, select the appropriate numerical calculation method; according to the geometric shape and boundary conditions of the problem, determine the appropriate coordinate system. The choice of coordinate system has an important impact on the accuracy and efficiency of numerical calculation;

[0019] S3-3. Grid division and discretization: Divide the solution area into a finite number of grids or cells; discretize the continuous mathematical model into algebraic equations on a finite number of grid points;

[0020] S3-4, Programming and Calculation: According to the selected calculation method and the discretized algebraic equation, compile the corresponding calculation program; run the compiled program and perform numerical calculations. During the calculation process, it is necessary to monitor the running status of the program to ensure the stability and accuracy of the calculation;

[0021] S3-5. Result processing and analysis: Process and analyze the large amount of data obtained from the calculation, compare and verify the results of numerical simulation with experimental results or theoretical analysis to evaluate the accuracy and reliability of the model. If large differences are found, it is necessary to adjust and optimize the mathematical model, calculation method or grid division.

[0022] Furthermore, commonly used numerical calculation methods include finite difference method, finite element method and finite volume method.

[0023] Furthermore, the division of the grid should take into account the geometric shape of the problem, boundary conditions and calculation accuracy factors; algebraic equations include two aspects: spatial discretization and temporal discretization. Spatial discretization is to divide the continuous spatial region into discrete grid points, while temporal discretization is to divide the continuous time process into discrete time steps.

[0024] Furthermore, processing and analysis include data visualization, error analysis, and sensitivity analysis. Visualization is to display the calculation results in the form of graphics or images in order to more intuitively understand the physical phenomena and laws of the problem.

[0025] Compared with the prior art, the present invention provides a tunnel deformation prediction method based on multi-source monitoring data fusion, which has the following beneficial effects:

[0026] 1. This tunnel deformation prediction method based on the fusion of multi-source monitoring data can identify subtle changes in deformation trends, warn of potential risks in advance, and reduce false alarms and missed reports by utilizing big data analysis technology. Accurate deformation prediction helps engineers optimize the design of tunnel structures before construction, select appropriate support measures, avoid unnecessary material waste and cost overruns, and gain precious time for emergency evacuation and response measures through continuous monitoring and instant feedback mechanisms. Through the accumulation and analysis of long-term monitoring data, it provides data support for the formulation of tunnel maintenance plans, realizes the precision and efficiency of maintenance work, and achieves the advantages of high prediction efficiency and high prediction accuracy.

[0027] 2. This tunnel deformation prediction method based on the fusion of multi-source monitoring data has significantly improved the prediction accuracy of tunnel deformation by integrating advanced mathematical models and real-time monitoring data, providing a more reliable scientific basis for project management and maintenance. The construction progress and monitoring frequency are adjusted according to the prediction results to ensure construction safety and efficiency and reduce the impact on the surrounding environment during construction. Through scientific and effective deformation prediction and management, the safe and stable operation of the tunnel is ensured, the public's confidence in infrastructure safety is enhanced, and the government's image and social satisfaction are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A prediction flow chart of a tunnel deformation prediction method based on multi-source monitoring data fusion according to the present invention;

[0029] Figure 2 The present invention is a simulation flow chart of a numerical simulation method in a tunnel deformation prediction method based on multi-source monitoring data fusion. DETAILED DESCRIPTION

[0030] The following will be combined with the embodiments of the present invention and the accompanying drawings to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] See also Figure 1 In this embodiment, a tunnel deformation prediction method based on multi-source monitoring data fusion includes the following steps:

[0032] S1. Preliminary preparation stage: Before tunnel construction, geological exploration is carried out to understand the geological conditions. Based on the geological exploration results, a suitable construction plan and a method for predicting stratum displacement are formulated; monitoring equipment is arranged in the tunnel construction area to ensure that the monitoring equipment can accurately and in real time record the deformation data during the tunnel construction process;

[0033] S2, Data collection and analysis stage: During the tunnel construction process, the displacement, stress change and groundwater level change of the strata around the tunnel are monitored in real time, the monitoring data are recorded, and preliminary analysis is performed to understand the trend and law of tunnel deformation; the monitoring data are cleaned, outliers and noise are removed, and the data are interpolated and smoothed to improve the accuracy and reliability of the data;

[0034] S3, model building and prediction stage: select appropriate prediction methods according to the characteristics of geological exploration results and monitoring data; establish corresponding prediction models according to the selected prediction methods; verify the prediction models with known data, evaluate the accuracy and reliability of the models, and optimize and adjust the models according to the verification results to improve the prediction accuracy; input the monitoring data into the optimized prediction model, predict the tunnel deformation, and output the prediction results;

[0035] S4. Result evaluation and application stage: Evaluate the prediction results, analyze the prediction errors and uncertainties, and judge the applicability and reliability of the prediction method based on the evaluation results; apply the prediction results to the safety control of tunnel construction and the construction of subsequent projects. According to the prediction results, formulate corresponding protective measures and construction plans to reduce tunnel deformation and reduce damage risks; during the tunnel construction process and subsequent operations, continuously monitor the tunnel deformation, compare and analyze the monitoring data with the prediction results, and provide timely feedback to the design and construction personnel so as to adjust the construction plan and protective measures.

[0036] In this embodiment, by utilizing big data analysis technology, it is possible to identify subtle changes in deformation trends, warn of potential risks in advance, and reduce false alarms and missed alarms. Accurate deformation prediction helps engineers optimize the design of tunnel structures before construction, select appropriate support measures, and avoid unnecessary material waste and cost overruns. Through continuous monitoring and instant feedback mechanisms, precious time is gained for emergency evacuation and response measures. Through the accumulation and analysis of long-term monitoring data, data support is provided for the formulation of tunnel maintenance plans, and maintenance work is made more precise and efficient. By integrating advanced mathematical models and real-time monitoring data, the prediction accuracy of tunnel deformation is significantly improved, providing a more reliable scientific basis for project management and maintenance. The construction progress and monitoring frequency are adjusted according to the prediction results to ensure construction safety and efficiency and reduce the impact on the surrounding environment during construction. Through scientific and effective deformation prediction and management, the safe and stable operation of the tunnel is ensured, the public's confidence in infrastructure safety is enhanced, the government's image and social satisfaction are improved, and the advantages of high prediction efficiency and high prediction accuracy are achieved.

[0037] In this embodiment, the geological conditions in S1 include stratum properties, hydrogeological conditions, faults and cavities; the monitoring equipment in S1 includes displacement sensors, stress sensors and groundwater level monitors.

[0038] In this embodiment, the prediction results in S3 include displacement and stress changes of the strata around the tunnel; common prediction methods in S3 include numerical simulation method, empirical formula method, reference surface method and leak method.

[0039] In this embodiment, the numerical simulation method needs to construct a mechanical model of the tunnel cross section, and needs to consider the influencing factors of geological conditions, tunnel parameters and construction technology.

[0040] See also Figure 2 In this embodiment, the numerical simulation method includes the following steps:

[0041] S3-1. Mathematical modeling: Based on the physical background of the tunnel deformation problem, establish differential equations reflecting the relationship between various physical quantities in the tunnel deformation problem and their corresponding solution conditions, and realize digital modeling by establishing the Navier-Stokes equations and their solution conditions;

[0042] S3-2, determine the algorithm and coordinate system: according to the mathematical model established in S3-1, select the appropriate numerical calculation method; according to the geometric shape and boundary conditions of the problem, determine the appropriate coordinate system. The choice of coordinate system has an important impact on the accuracy and efficiency of numerical calculation;

[0043] S3-3. Grid division and discretization: Divide the solution area into a finite number of grids or cells; discretize the continuous mathematical model into algebraic equations on a finite number of grid points;

[0044] S3-4, Programming and Calculation: According to the selected calculation method and the discretized algebraic equation, compile the corresponding calculation program; run the compiled program and perform numerical calculations. During the calculation process, it is necessary to monitor the running status of the program to ensure the stability and accuracy of the calculation;

[0045] S3-5. Result processing and analysis: Process and analyze the large amount of data obtained from the calculation, compare and verify the results of numerical simulation with experimental results or theoretical analysis to evaluate the accuracy and reliability of the model. If large differences are found, it is necessary to adjust and optimize the mathematical model, calculation method or grid division.

[0046] Specifically, commonly used numerical calculation methods include finite difference method, finite element method and finite volume method.

[0047] Specifically, the division of the grid should take into account the geometric shape of the problem, boundary conditions and calculation accuracy factors; algebraic equations include two aspects: spatial discretization and temporal discretization. Spatial discretization is to divide the continuous spatial region into discrete grid points, while temporal discretization is to divide the continuous time process into discrete time steps.

[0048] Specifically, processing and analysis include data visualization, error analysis, and sensitivity analysis. Visualization is the display of calculation results in the form of graphics or images in order to more intuitively understand the physical phenomena and laws of the problem.

[0049] The beneficial effects of the above embodiments are:

[0050] This tunnel deformation prediction method based on the fusion of multi-source monitoring data can identify subtle changes in deformation trends, warn of potential risks in advance, and reduce false alarms and missed reports by utilizing big data analysis technology. Accurate deformation prediction helps engineers optimize the design of tunnel structures before construction, select appropriate support measures, and avoid unnecessary material waste and cost overruns. Through continuous monitoring and instant feedback mechanisms, precious time is gained for emergency evacuation and response measures. Through the accumulation and analysis of long-term monitoring data, data support is provided for the formulation of tunnel maintenance plans, thereby achieving precision and efficiency in maintenance work and achieving the advantages of high prediction efficiency and high prediction accuracy.

[0051] This tunnel deformation prediction method based on multi-source monitoring data fusion significantly improves the prediction accuracy of tunnel deformation by integrating advanced mathematical models and real-time monitoring data, providing a more reliable scientific basis for project management and maintenance. It adjusts the construction progress and monitoring frequency according to the prediction results to ensure construction safety and efficiency and reduce the impact on the surrounding environment during construction. Through scientific and effective deformation prediction and management, it ensures the safe and stable operation of the tunnel, enhances the public's confidence in infrastructure safety, and improves the government's image and social satisfaction.

[0052] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A tunnel deformation prediction method based on multi-source monitoring data fusion, characterized in that: The following steps are involved: S1. Preliminary preparation stage: Before tunnel construction, geological exploration is carried out to understand the geological conditions. Based on the geological exploration results, a suitable construction plan and a method for predicting stratum displacement are formulated; monitoring equipment is arranged in the tunnel construction area to ensure that the monitoring equipment can accurately and in real time record the deformation data during the tunnel construction process; S2, Data collection and analysis stage: During the tunnel construction process, the displacement, stress change and groundwater level change of the strata around the tunnel are monitored in real time, the monitoring data are recorded, and preliminary analysis is performed to understand the trend and law of tunnel deformation; the monitoring data are cleaned, outliers and noise are removed, and the data are interpolated and smoothed to improve the accuracy and reliability of the data; S3, model building and prediction stage: select appropriate prediction methods according to the characteristics of geological exploration results and monitoring data; establish corresponding prediction models according to the selected prediction methods; verify the prediction models with known data, evaluate the accuracy and reliability of the models, and optimize and adjust the models according to the verification results to improve the prediction accuracy; input the monitoring data into the optimized prediction model, predict the tunnel deformation, and output the prediction results; S4. Result evaluation and application stage: Evaluate the prediction results, analyze the prediction errors and uncertainties, and judge the applicability and reliability of the prediction method based on the evaluation results; apply the prediction results to the safety control of tunnel construction and the construction of subsequent projects. According to the prediction results, formulate corresponding protective measures and construction plans to reduce tunnel deformation and reduce damage risks; during the tunnel construction process and subsequent operations, continuously monitor the tunnel deformation, compare and analyze the monitoring data with the prediction results, and provide timely feedback to the design and construction personnel so as to adjust the construction plan and protective measures.

2. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 1 is characterized by: The geological conditions in S1 include stratigraphic properties, hydrogeological conditions, faults and cavities.

3. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 1 is characterized in that: The monitoring equipment in S1 includes a displacement sensor, a stress sensor and a groundwater level monitor.

4. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 1 is characterized in that: The prediction results in S3 include the displacement and stress changes of the strata around the tunnel.

5. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 1 is characterized in that: Common prediction methods in S3 include numerical simulation method, empirical formula method, reference surface method and loophole method.

6. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 5 is characterized in that: The numerical simulation method requires the construction of a mechanical model of the tunnel section, and needs to consider the influencing factors of geological conditions, tunnel parameters and construction technology.

7. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 5 is characterized by: The numerical simulation method comprises the following steps: S3-1. Mathematical modeling: Based on the physical background of the tunnel deformation problem, establish differential equations reflecting the relationship between various physical quantities in the tunnel deformation problem and their corresponding solution conditions, and realize digital modeling by establishing the Navier-Stokes equations and their solution conditions; S3-2, determine the algorithm and coordinate system: according to the mathematical model established in S3-1, select the appropriate numerical calculation method; according to the geometric shape and boundary conditions of the problem, determine the appropriate coordinate system. The choice of coordinate system has an important impact on the accuracy and efficiency of numerical calculation; S3-3. Grid division and discretization: Divide the solution area into a finite number of grids or cells; discretize the continuous mathematical model into algebraic equations on a finite number of grid points; S3-4, Programming and Calculation: According to the selected calculation method and the discretized algebraic equation, compile the corresponding calculation program; run the compiled program and perform numerical calculations. During the calculation process, it is necessary to monitor the running status of the program to ensure the stability and accuracy of the calculation; S3-5. Result processing and analysis: Process and analyze the large amount of data obtained from the calculation, compare and verify the results of numerical simulation with experimental results or theoretical analysis to evaluate the accuracy and reliability of the model. If large differences are found, it is necessary to adjust and optimize the mathematical model, calculation method or grid division.

8. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 7 is characterized by: Commonly used numerical calculation methods include finite difference method, finite element method and finite volume method.

9. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 7 is characterized in that: The division of the grid should take into account the geometric shape of the problem, boundary conditions and calculation accuracy factors; algebraic equations include two aspects: spatial discretization and time discretization. Spatial discretization is to divide the continuous space area into discrete grid points, and time discretization is to divide the continuous time process into discrete time steps.

10. The tunnel deformation prediction method based on multi-source monitoring data fusion according to claim 7 is characterized in that: Processing and analysis include data visualization, error analysis and sensitivity analysis. Visualization is to display the calculation results in the form of graphics or images in order to more intuitively understand the physical phenomena and laws of the problem.

Images