Tunnel support dynamic design construction method based on rapid evaluation of surrounding rock level

Abstract

The invention discloses a tunnel support dynamic design construction method based on surrounding rock grade rapid evaluation, and relates to the technical field of tunnel support construction. The tunnel support dynamic design and construction method based on the rapid evaluation of the surrounding rock level comprises the following steps: S1, collecting early-stage investigation and design data, and compiling a tunnel construction organization design; and S2, tunnel excavation and supporting are carried out according to the design scheme, and tunnel advanced geological forecast and tunnel monitoring measurement are carried out according to conditions. According to the method, real-time evaluation on the stability of the surrounding rock is realized by adopting a field rapid test technology such as a point load test and a rebound method and combining with an advanced neural network analysis model, intelligent optimization design is performed on a supporting structure accordingly, monitoring on the surrounding rock in the construction process is combined, an evaluation model is corrected, and the stability of the surrounding rock is evaluated. The accuracy of evaluation results and the pertinence of design achievements are continuously improved, and safe and rapid construction is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel support construction, and in particular relates to a tunnel support dynamic design and construction method based on rapid evaluation of surrounding rock levels. Background Art

[0002] During the excavation and construction phase of a tunnel project, assessing surrounding rock stability is a key step in ensuring construction safety and quality. Surrounding rock stability directly impacts the design parameters of the support structure and the selection of construction methods. Therefore, accurate assessment of surrounding rock stability is crucial for developing a scientifically sound support plan.

[0003] Traditional surrounding rock stability assessment relies primarily on data obtained during the geological survey phase. While this information provides a preliminary understanding of geological conditions, it often fails to fully capture the surrounding rock conditions across all construction sections, particularly in long-distance, deep-buried tunnel projects. Furthermore, geological survey results are limited by drilling depth and location, and may not provide sufficiently accurate surrounding rock classification information.

[0004] In current engineering practice, construction teams typically sample the newly exposed rock mass after tunnel excavation and evaluate the surrounding rock grade through indoor rock mechanics tests. This method can relatively accurately determine the strength and stability of the surrounding rock, but the testing process is time-consuming. As construction progresses, the constant changes in the surrounding rock require dynamic adjustments to the support structure design. However, frequent design changes not only increase project costs but also extend the project period. More importantly, unreasonable support structures may be unable to adapt to the rapid changes in surrounding rock conditions, leading to safety hazards on the construction site, thereby endangering the lives of workers and the safe operation of mechanical equipment. Therefore, how to accurately assess the surrounding rock stability in real time during tunnel construction to guide design and construction has become a technical challenge that needs to be solved urgently in the field of tunnel engineering. Summary of the Invention

[0005] The purpose of the present invention is to provide a tunnel support dynamic design and construction method based on rapid evaluation of surrounding rock grade, so as to solve the problems raised in the above background technology.

[0006] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions:

[0007] The present invention provides a tunnel support dynamic design and construction method based on rapid evaluation of surrounding rock grade, comprising the following steps:

[0008] S1. Collect preliminary survey and design data and prepare tunnel construction organization design;

[0009] S2. Carry out tunnel excavation and support according to the design plan, and carry out tunnel advanced geological forecast and tunnel monitoring measurement as appropriate;

[0010] S3. Based on the test blocks and rocks obtained from excavation, rapid strength tests are conducted using the rebound method and point load test method;

[0011] S4. Use neural network model analysis to determine the surrounding rock level in real time and evaluate the surrounding rock stability;

[0012] S5. Based on the surrounding rock stability evaluation results, dynamic design of the support structure is carried out to guide the next excavation step;

[0013] S6. Compare the dynamic design plan with the original design plan. If there is any inconsistency, organize a design change necessity analysis to determine whether to make the change and clarify the next construction support plan;

[0014] S7. Complete the support of the excavated section, combine the monitoring data of the previously excavated section, incorporate neural network analysis according to the stress and deformation conditions, and modify the analysis model.

[0015] As a preferred embodiment of the present invention, with respect to the rebound test method described in S3, a rebound test is performed on the exposed rock surface using a rebound hammer to obtain a rock surface hardness index.

[0016] As a preferred embodiment of the present invention, with respect to the point load test method described in S3, a point load test is performed on the collected rock core sample to quickly evaluate the strength characteristics of the rock.

[0017] As a preferred solution of the present invention, for the neural network model described in S4, the structure of the multi-layer perceptron MLP and the convolutional neural network CNN is utilized to cope with complex nonlinear relationships.

[0018] As a preferred solution of the present invention, the dynamic design of the support structure described in S5 is carried out, the support form is adjusted, the support parameters are optimized, and additional reinforcement measures are added in special circumstances to construct a stable support structure.

[0019] As a preferred solution of the present invention, for the neural network analysis described in S7, the characteristics of the grey model and the neural network are combined to decompose the tunnel surrounding rock displacement into a deterministic trend term and an uncertain random term, and predict them separately.

[0020] Compared with the existing technology, the present invention provides a dynamic design and construction method for tunnel support based on rapid evaluation of surrounding rock levels. By acquiring surrounding rock information in real time and performing intelligent processing, combined with neural network model analysis, the tunnel support structure is dynamically designed to cope with rapid changes in surrounding rock conditions and ensure construction safety and efficiency.

[0021] One or more of the above technical solutions have the following beneficial effects:

[0022] This invention uses real-time, high-precision surrounding rock stability assessment to rapidly acquire surrounding rock information and conduct targeted dynamic design, quickly guiding construction. Specifically, by employing rapid on-site testing techniques such as point load testing and rebound methods, combined with advanced neural network analysis models, it enables immediate assessment of surrounding rock stability, enabling intelligent optimization of support structures. Furthermore, the assessment model is modified based on monitoring of the surrounding rock during construction, continuously improving the accuracy of assessment results and the targeted nature of design outcomes, enabling safe and rapid construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 It is a schematic diagram of the dynamic design and construction method of tunnel support of the present invention; DETAILED DESCRIPTION

[0025] To facilitate understanding of the features and effects of the present invention by those skilled in the art, the following provides a general description and definition of the terms and expressions used in the specification and claims. Unless otherwise indicated, all technical and scientific terms used herein have the ordinary meanings as understood by those skilled in the art regarding the present invention. In the event of conflict, the definitions in this specification shall prevail.

[0026] The theories or mechanisms described and disclosed herein, whether correct or incorrect, should not limit the scope of the present invention in any way, that is, the present invention can be implemented without being limited by any specific theory or mechanism.

[0027] Herein, all features such as values, amounts, amounts, and concentrations defined in numerical ranges or percentage ranges are for brevity and convenience only. Accordingly, the description of numerical ranges or percentage ranges should be considered to include and specifically disclose all possible subranges and individual values ​​within the range (including integers and fractions).

[0028] In this document, unless otherwise specified, “include,” “including,” “contains,” “has” or similar terms cover the meanings of “consisting of” and “mainly consisting of,” for example, “A includes a” covers the meanings of “A includes a and other” and “A only includes a.”

[0029] In this document, for the sake of brevity, not all possible combinations of the various technical features in each embodiment or example are described. Therefore, as long as there are no contradictions in the combination of these technical features, the various technical features in each embodiment or example can be combined in any way, and all possible combinations should be considered to be within the scope of this specification.

[0030] Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiments are only used to illustrate the present invention and are not used in limiting the scope of the present invention.In addition, should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall equally within the scope limited by the appended claims of the application.

[0031] The following examples were prepared using conventional instruments and equipment in the art. Experimental methods in the following examples, where specific conditions are not specified, were generally performed under conventional conditions or according to the conditions recommended by the manufacturer. The various raw materials used in the following examples, unless otherwise specified, were conventional commercially available products, with specifications conventional in the art. In the present specification and the following examples, unless otherwise specified, "%" indicates percentage by weight, "part" indicates parts by weight, and "ratio" indicates weight ratio.

[0032] Example 1

[0033] See also Figure 1 The present invention discloses a tunnel support dynamic design and construction method based on rapid evaluation of surrounding rock level, comprising the following steps:

[0034] S1. Collect preliminary survey and design data and prepare tunnel construction organization design;

[0035] S2. Carry out tunnel excavation and support according to the design plan, and carry out tunnel advanced geological forecast and tunnel monitoring measurement as appropriate;

[0036] S3. Based on the test blocks and rocks obtained from excavation, rapid strength tests are conducted using the rebound method and point load test method;

[0037] S4. Use neural network model analysis to determine the surrounding rock level in real time and evaluate the surrounding rock stability;

[0038] S5. Based on the surrounding rock stability evaluation results, dynamic design of the support structure is carried out to guide the next excavation step;

[0039] S6. Compare the dynamic design plan with the original design plan. If there is any inconsistency, organize a design change necessity analysis to determine whether to make the change and clarify the next construction support plan;

[0040] S7. Complete the support of the excavated section, combine the monitoring data of the previously excavated section, incorporate neural network analysis according to the stress and deformation conditions, and modify the analysis model.

[0041] 1. Preliminary preparation and data collection

[0042] Before tunnel construction, relevant geological survey reports, geological profiles, geotechnical parameters, and historical construction case studies are collected. This information is used to prepare the tunnel construction plan and preliminarily determine the construction method, support type, and necessary geological monitoring measures.

[0043] 2. Tunnel excavation and forecast monitoring

[0044] Tunnel excavation is carried out according to the preliminary design plan, and advanced geological prediction and on-site monitoring and measurement are conducted as needed. Prediction technologies such as geological radar or seismic wave reflection can be used to predict changes in the surrounding rock ahead and adjust the construction plan. Monitoring and measurement mainly include real-time monitoring of indicators such as displacement, convergence, and surface settlement to promptly determine changes in surrounding rock stability.

[0045] The tunnel monitoring and measurement in S2 mainly involves measuring the deformation and stress parameters of the surrounding rock and support structure during tunnel construction, and combining this with observations of the surrounding rock and support structure to determine their stability. If there is a possibility of instability, timely warnings should be issued and disposal measures should be proposed to ensure the safety and smooth progress of tunnel construction.

[0046] 1) Required test items

[0047] According to the characteristics of the tunnel in this project, the mandatory items for surrounding rock monitoring and measurement mainly include the following: observation inside and outside the tunnel, peripheral displacement, arch crown subsidence, surface subsidence, and bottom plate deformation (pilot tunnel in the multi-arch tunnel and level I side pilot pit of the main tunnel).

[0048] Tunnel mandatory measurements are routinely conducted to ensure surrounding rock stability and construction safety during construction. The measurement method is simple, the measurement density is high, and the information provided is intuitive and reliable. Continuing throughout the entire construction process, the measurements play a significant role in monitoring surrounding rock stability and guiding design and construction. With the completion of civil construction, the measurement work concludes.

[0049] 2) Optional test items

[0050] Optional testing projects expand and supplement the mandatory testing projects. They measure special, hazardous, or representative areas to provide a deeper understanding of surrounding rock stability and support effectiveness. They effectively monitor and evaluate completed support structures, provide reference information for unexcavated areas, and guide future design and construction. Optional testing projects are more complex to install and bury, involve more measurement items, and are time-consuming and costly. However, they allow for long-term observation after project completion.

[0051] For advanced geological prediction in S2

[0052] Tunnel advanced geological prediction work should be combined with geological survey data in the design documents, with engineering geological conditions as the core. Tunnel geological work should be strengthened, geological and geophysical exploration should be combined, geophysical exploration combinations should be optimized, and comprehensive applications should be applied to ensure safe, rapid, and high-quality construction without future risks. This ensures that tunnel construction achieves economic, social, and environmental benefits. The main contents of advanced geological prediction work include the following aspects:

[0053] 1) Predict the location of fault fracture zones and weak surrounding rocks (mudstone, marl, sandy mudstone, etc.) (including areas with developed fissures)

[0054] 2) Forecast groundwater enrichment, possible water gushing (bursting) and mud bursting areas.

[0055] When conducting advanced geological forecasting work, the main instruments and equipment used are TSP (or TGP).

[0056] 3. On-site rapid strength test

[0057] After the tunnel is excavated in sections, samples of the newly exposed surrounding rock are collected and strength tests are quickly carried out.

[0058] Furthermore, in view of the rebound test method in S3, a rebound test is performed on the exposed rock surface using a rebound tester to obtain the rock surface hardness index.

[0059] The rebound method for testing rock surface hardness determines rock hardness by measuring the rebound angle and number of rebounds after a steel ball impacts the rock surface. Specifically, when a steel ball impacts the rock surface with a certain energy, the higher the rock's hardness, the greater the rebound angle, and the greater the number of rebounds the ball experiences from the first rebound to its complete stop. This method utilizes the relationship between rock surface hardness and its elastic properties, indirectly reflecting rock hardness through the measurement of rebound angle and number of rebounds.

[0060] Test process: The rebound hammer consists of an elastic loading rod and a steel ball;

[0061] Test steps:

[0062] 1) Aim the steel ball of the rebound hammer at the rock surface and apply a certain impact energy;

[0063] 2) Measure the rebound distance or rebound angle after the steel ball impacts;

[0064] 3) Record the number of times the steel ball bounces until it stops completely.

[0065] Furthermore, with respect to the point load test method in S3, the strength characteristics of the rock can be quickly evaluated by performing a point load test on the collected rock core samples.

[0066] Testing process:

[0067] 1) Select appropriate rock specimens, the size and shape of which must meet standard requirements;

[0068] 2) Place the specimen between two spherical loading cones and apply concentrated load until the specimen fails. For regular long cylindrical rock specimens, radial loading is used; for regular short cylindrical rock specimens, axial loading is used; for cubes or irregular blocks, the direction of the smallest dimension is the loading direction, and the center is loaded.

[0069] 3) Apply the load steadily until the rock fails within 10-60 seconds. Record the maximum load at failure and the distance between the two cone ends.

[0070] 4) Calculate the point load strength of the rock based on the failure load and the geometric dimensions of the specimen;

[0071] 5) After the test, describe the failure mode of the specimen.

[0072] 4. Neural Network Model Analysis

[0073] The acquired field test data is fed into a pre-trained neural network model that has been trained and optimized using a large amount of historical geological and construction data. The model analyzes input parameters (such as rebound strength, point load strength, and other field monitoring data) to determine the grade and stability of the surrounding rock in real time.

[0074] Furthermore, for the neural network model in S4, the structure of multi-layer perceptron MLP and convolutional neural network CNN is utilized to cope with complex nonlinear relationships.

[0075] Based on the multi-layer perceptron MLP, it consists of an input layer, multiple hidden layers, and an output layer. Its core mechanisms include:

[0076] 1) Input layer: receives raw data.

[0077] 2) Hidden layer: Contains multiple fully connected layers. Each layer of neurons is fully connected to the previous layer and performs nonlinear transformation through weight matrix and activation function.

[0078] 3) Output layer: Outputs results according to task requirements, usually used for classification or regression tasks

[0079] Based on the convolutional neural network (CNN), it consists of convolutional layers, pooling layers, and fully connected layers. Its core mechanisms include:

[0080] 1) Convolutional Layer: Convolutional layers are used to extract local features such as edges and textures. Each neuron is connected only to a local region of the input, enabling local perception and parameter sharing.

[0081] 2) Pooling layer (such as Max Pooling): reduces the dimension while retaining the main features and enhancing translation invariance.

[0082] 3) Fully connected layer: Usually located at the end of the network, used for classification or regression tasks.

[0083] 5. Dynamic design of support structure

[0084] Based on the surrounding rock stability evaluation results output by the neural network model, dynamic design and optimization of the support structure are carried out. Specific adjustments include but are not limited to:

[0085] Support form: including adjustments to the selection of anchor rods, shotcrete, and steel arch frames.

[0086] Support parameters: such as optimization of anchor length and spacing, and shotcrete thickness.

[0087] Furthermore, according to the dynamic design of the support structure described in S5, the support form is adjusted, the support parameters are optimized, and additional reinforcement measures are added in special cases to construct a stable support structure.

[0088] 6. Design change review and implementation

[0089] Compare the dynamic design plan with the preliminary design plan. If any deviations are found, organize the design team to analyze the necessity of design changes. This analysis focuses on the impact of the changes on safety, cost, and schedule, and based on the results, decides whether to implement the changes. Define the post-change plan to guide subsequent construction.

[0090] 7. Continuous monitoring and model correction

[0091] After the current excavation section is supported, monitoring data (stress, deformation, etc.) from the excavated section is continuously fed back to the neural network model for training and correction. The improved model will more accurately respond to surrounding rock changes and enhance the scientific nature of subsequent design decisions.

[0092] Furthermore, for the neural network analysis of S7, the characteristics of the grey model and neural network are combined to decompose the displacement of the tunnel surrounding rock into a deterministic trend term and an uncertain random term, and then predict them separately.

[0093] Example 2

[0094] 1. Project Overview

[0095] The initial support for the right tunnel section at the tunnel exit, from K142+454 to K142+452, is the first piece of engineering work. The tunnel is a separated tunnel located on the main line, with a total length of 10,771 meters for both spans. The design speed is 80 km / h. The right span tunnel, with pile numbers K137+078 to K142+462, is 5,384 meters long, with a maximum depth of approximately 788 meters. The left span tunnel, with pile numbers ZK137+060 to ZK142+447, is 5,387 meters long, with a maximum depth of approximately 788 meters. A composite lining combining primary support and secondary lining is employed. The primary support consists of shotcrete, radial anchors, steel mesh, and a steel frame. The steel frames are connected with longitudinal steel bars and welded to the radial anchors and steel mesh, forming a close fit with the rock face, forming a load-bearing structure.

[0096] 2. Purpose of the first piece of supporting structure

[0097] The tunnel is an extra-long tunnel with complex engineering geological conditions and many uncertainties in construction. Problems that arise are difficult to address. To ensure the quality of the tunnel project, our project department carried out the initial support first-piece construction (K142+454 to K142+452). We conducted a comprehensive evaluation of the various processes, technologies, and quality indicators of the first-piece project, determined the optimal process, and established a model project to guide subsequent batch production and prevent and correct quality problems that may arise in subsequent batch production. The following goals were achieved through the first-piece construction:

[0098] 1. Construction organization inspection: Determine the best combination of personnel and machinery through the construction of the first piece of engineering.

[0099] 2. Data collection: The control methods for various technical indicators under this construction process are determined by the first project. The summarized technical parameters serve as the basis for guiding the control of large-scale construction.

[0100] 3. Summary of the first project

[0101] The first piece of initial support work in the right tunnel section from K142+454 to K142+452 has been completed, as summarized below:

[0102] (1) Preparation before construction

[0103] Before construction, the first construction organization design was prepared in accordance with the design drawings and relevant regulations and specifications, combined with the engineering geological and meteorological and hydrological conditions.

[0104] 1. Be familiar with the construction drawings, and do a good job in drawing review and technical briefing.

[0105] 2. According to the construction coordinates and the guide points provided by the design, carry out the positioning and leveling point survey and verification, and submit the measurement report to the supervising engineer for review.

[0106] (2) Construction technology

[0107] The tunnel is a separated tunnel. The main support forms for the initial (advanced) support of this section of the tunnel are large pipe shed, hollow grouting anchor shotcrete, steel mesh, steel frame, etc.

[0108] The pipe roof holes were drilled using a pipe roof drilling rig, the small grouting conduits were drilled manually with an air gun, and grouting was performed using a high-pressure pump. The steel mesh in the tunnel was processed outside the tunnel and transported to the tunnel for installation. The steel arch was fabricated outside the tunnel and trial-assembled into the tunnel. A wet spraying machine was used for the jet support.

[0109] 1. Grouting small tube

[0110] Small grouting tubes are used for the arch and side walls of this section of the tunnel. After drilling, steel pipes are inserted and then grouting is injected for anchoring. The drilling position and depth must be accurate; the steel pipes must be clean of oil, rust, and impurities; and the steel pipes must be inserted into the holes for at least 95% of their designed length.

[0111] 2. Steel mesh

[0112] The steel mesh can be laid after a layer of concrete has been sprayed onto the rock face and the small ducts have been grouted. Tunnel steel mesh is prefabricated outside the tunnel and used after cold-drawing and straightening the steel bars. The steel bars must be free of cracks, oil stains, particles, or flaky rust. The installation overlap length is 30 days. The steel mesh should be laid alongside the sprayed surface, generally with a gap of at least 3 cm. It should be securely connected to anchor rods or other fixing devices.

[0113] 3. Steel frame

[0114] I-beam steel frames are cold-formed. Welding during the frame fabrication process is free of false welds, cracks, weld bumps, and other surface defects. After fabrication, each frame is placed on a concrete floor for trial assembly. The tolerance for perimeter assembly is 3cm, and planar warpage is less than 2cm. The frame should be erected promptly after excavation or concrete spraying.

[0115] 4. Shotcrete

[0116] To ensure construction quality, minimize rebound, reduce dust, and increase the thickness of the primary spray layer, shotcrete is sprayed using a wet process. Anchor-sprayed support shotcrete is divided into initial and secondary spraying. Initial spraying is performed immediately after excavation (or staged excavation) is completed to quickly seal the exposed rock surface and prevent surface weathering and spalling. Secondary spraying is performed after the anchor rods, mesh, and steel frame are installed to quickly establish the overall force of the shotcrete-anchor support and suppress surrounding rock displacement. The spaces between the steel frames are leveled with concrete and provided with an adequate protective layer.

[0117] Without limitation, any person skilled in the art who is familiar with the technical field can make equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, and these changes should be covered by the protection scope of the present invention.

Claims

1. A tunnel support dynamic design and construction method based on rapid evaluation of surrounding rock grade, characterized by: The following steps are involved: S1. Collect preliminary survey and design data and prepare tunnel construction organization design; S2. Carry out tunnel excavation and support according to the design plan, and carry out tunnel advanced geological forecast and tunnel monitoring measurement as appropriate; S3. Based on the test blocks and rocks obtained from excavation, rapid strength tests are conducted using the rebound method and point load test method; S4. Use neural network model analysis to determine the surrounding rock level in real time and evaluate the surrounding rock stability; S5. Based on the surrounding rock stability evaluation results, dynamic design of the support structure is carried out to guide the next excavation step; S6. Compare the dynamic design plan with the original design plan. If there is any inconsistency, organize a design change necessity analysis to determine whether to make the change and clarify the next construction support plan; S7. Complete the support of the excavated section, combine the monitoring data of the previously excavated section, incorporate neural network analysis according to the stress and deformation conditions, and modify the analysis model.

2. The method for dynamic design and construction of tunnel support based on rapid evaluation of surrounding rock grade according to claim 1, characterized in that: According to the rebound test method described in S3, a rebound test is performed on the exposed rock surface using a rebound hammer to obtain the rock surface hardness index.

3. The method for dynamic design and construction of tunnel support based on rapid evaluation of surrounding rock grade according to claim 1 is characterized in that: With respect to the point load test method described in S3, the strength characteristics of the rock are quickly evaluated by performing a point load test on the collected rock core samples.

4. The method for dynamic design and construction of tunnel support based on rapid evaluation of surrounding rock grade according to claim 1, characterized in that: For the neural network model described in S4, the structure of multi-layer perceptron MLP and convolutional neural network CNN is utilized to cope with complex nonlinear relationships.

5. The method for dynamic design and construction of tunnel support based on rapid evaluation of surrounding rock grade according to claim 1, characterized in that: According to the dynamic design of the support structure described in S5, the support form is adjusted, the support parameters are optimized, and additional reinforcement measures are added in special cases to construct a stable support structure.

6. The method for dynamic design and construction of tunnel support based on rapid evaluation of surrounding rock grade according to claim 1, characterized in that: In view of the neural network analysis described in S7, the characteristics of the grey model and neural network are combined to decompose the tunnel surrounding rock displacement into a deterministic trend term and an uncertain random term, and then predict them separately.

Images