Method, system and equipment for determining advance grouting reinforcement opportunity of tunnel fault fracture zone and medium

Abstract

The invention discloses a tunnel fault fracture zone advanced grouting reinforcement opportunity determining method, system and equipment and a medium, and relates to the technical field of tunneling construction. The method comprises the following steps: inputting construction site data into a tunnel excavation model, and performing construction simulation according to a site excavation construction scheme to obtain simulation data; the simulation data comprises tunneling distance data and tunnel face outburst amount data; carrying out iterative loop training on the simulation data by utilizing a neural network, and carrying out prediction by utilizing the trained neural network to obtain a curve graph that the outburst amount of the tunnel face changes along with the tunneling distance; and determining a sudden change point according to the curve graph that the outburst amount of the tunnel face changes along with the tunneling distance, and determining the advanced grouting reinforcement opportunity of the tunnel fault fracture zone according to the tunneling distance value corresponding to the sudden change point. The stability of the surrounding rock can be dynamically evaluated, the problem of blind or excessive reinforcement in a traditional method is avoided, and the construction efficiency and safety are improved.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel excavation construction, and in particular to a method, system, equipment and medium for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel. Background Art

[0002] During tunnel excavation, when crossing fault fracture zones, complex geological conditions often lead to landslides, water inrush and other problems, affecting the construction progress. For this reason, advance grouting reinforcement measures are usually required to improve the stability of the rock mass. However, grouting too early will waste resources and affect efficiency, while grouting too late may reduce the reinforcement effect and pose a safety hazard. Therefore, how to accurately determine the best time for advance grouting has become a key issue in construction.

[0003] Traditional advance grouting relies on construction experience and geological exploration data, and grouting is carried out in advance before the fracture zone. Grouting materials are mostly cement slurry or cement-chemical slurry, which is injected into the cracks of the rock mass under pressure to consolidate the fracture zone. Although this method effectively improves the stability of the rock mass, it is often too conservative, and the advance grouting distance is long, resulting in waste of resources and slow progress. In addition, the traditional method lacks scientific quantitative standards, resulting in uncertain reinforcement effects. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system, equipment and medium for determining the timing of advance grouting reinforcement of a tunnel fault fracture zone, which can dynamically evaluate the stability of the surrounding rock, avoid the problems of blind or excessive reinforcement in traditional methods, and improve the efficiency and safety of construction.

[0005] To achieve the above object, the present invention provides the following solutions: A method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel, comprising: Acquire construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks; The construction site data is input into the tunnel excavation model, and construction simulation is performed according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data; The simulation data is iteratively trained using a neural network, and the trained neural network is used for prediction to obtain a curve graph showing the change of the face protrusion with the excavation distance; the neural network adopts a multi-layer perceptron or a convolutional neural network; The mutation point is determined according to the curve graph of the change of the face protrusion amount with the excavation distance, and the timing of advance grouting reinforcement of the fault fracture zone of the tunnel is determined according to the excavation distance value corresponding to the mutation point.

[0006] Optionally, the training process of the neural network is: Select a neural network structure and a corresponding activation function, and determine training parameters; the activation function uses either a ReLU function or a Leaky ReLU function; the training parameters include a learning rate, a batch size, and the number of iterations; the learning rate is between 0.001 and 0.01; The simulated data is input into a determined neural network structure, and training is performed with the goal of minimizing the loss between the network output and the predicted result label to obtain a finally trained neural network.

[0007] Optionally, the method for determining the curve graph of the face protrusion changing with the excavation distance is: Extracting the relationship data between the excavation distance and the face protrusion in the network prediction results, and smoothing the relationship data to eliminate noise or abnormal points to obtain preprocessed data; The pre-processed data is plotted into a curve graph using image drawing software or a programming library to show the evolution of the deformation of the tunnel face.

[0008] Optionally, the method for determining the mutation point is: The variation trend of the curve graph of the face protrusion amount changing with the excavation distance is analyzed by using the derivative or second-order derivative method, and the inflection point of the curve graph is determined as the identification standard of the mutation point.

[0009] Optionally, determining the timing of advance grouting reinforcement of the fault fracture zone of the tunnel according to the excavation distance value corresponding to the mutation point specifically includes: The current construction status of the tunnel is evaluated according to the excavation distance value corresponding to the mutation point, and the stability of the tunnel is dynamically evaluated in combination with the on-site real-time monitoring data, the geological conditions of the tunnel construction and the construction experience, so as to determine the best time for advance grouting reinforcement of the fault fracture zone of the tunnel.

[0010] The present invention also provides a system for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel, comprising: A data acquisition unit is used to obtain construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks; A construction simulation unit is used to input the construction site data into the tunnel excavation model, and perform construction simulation according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data; A network training unit is used to perform iterative cycle training on the simulation data using a neural network, and to perform prediction using the trained neural network to obtain a curve graph showing the change of the face protrusion with the excavation distance; the neural network adopts a multi-layer perceptron or a convolutional neural network; The reinforcement timing determination unit is used to determine the mutation point according to the curve diagram of the change of the face protrusion amount with the excavation distance, and determine the advance grouting reinforcement timing of the tunnel fault fracture zone according to the excavation distance value corresponding to the mutation point.

[0011] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method for determining the timing of advance grouting reinforcement of the fault fracture zone of the tunnel according to the above-mentioned method.

[0012] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel as described above.

[0013] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention discloses a method, system, equipment and medium for determining the timing of advance grouting reinforcement of a fault fracture zone of a tunnel. The method comprises inputting construction site data into a tunnel excavation model, and performing construction simulation according to a site excavation construction plan to obtain simulation data; the simulation data comprises excavation distance data and face protrusion data; iterative cycle training is performed on the simulation data using a neural network, and prediction is performed using the trained neural network to obtain a curve chart showing the face protrusion changing with the excavation distance; a mutation point is determined according to the curve chart showing the face protrusion changing with the excavation distance, and the timing of advance grouting reinforcement of the fault fracture zone of the tunnel is determined according to the excavation distance value corresponding to the mutation point. The present invention can dynamically evaluate the stability of the surrounding rock, avoid the problem of blind or excessive reinforcement in traditional methods, and improve the efficiency and safety of construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1 It is a flow chart of a method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel according to the present invention; Figure 2 Schematic diagram of the neural network structure in this embodiment; Figure 3 Graph showing the change in face protrusion with excavation distance in this embodiment. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention 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.

[0017] The purpose of the present invention is to provide a method, system, equipment and medium for determining the timing of advance grouting reinforcement of a tunnel fault fracture zone, which can dynamically evaluate the stability of the surrounding rock, avoid the problems of blind or excessive reinforcement in traditional methods, and improve the efficiency and safety of construction.

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] As a first aspect, the present invention provides Figure 1 A method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel is shown, comprising: Step 100: Acquire construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks.

[0020] Step 200: Input the construction site data into the tunnel excavation model, and perform construction simulation according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method, gradually carries out tunnel excavation, and obtains preliminary stress, displacement and broken zone response; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data.

[0021] Step 300: Iteratively train the simulated data using a neural network, and use the trained neural network to make predictions to obtain a curve of the face protrusion changing with the excavation distance; the neural network uses a multilayer perceptron or a convolutional neural network. Further processing includes: The excavation distance data and face protrusion data are obtained through simulation. The excavation distance data describes the progress of tunnel excavation, while the face protrusion data reflects the deformation of the face during the excavation process; the simulated data is trained using a neural network to improve the prediction accuracy. The neural network can choose a multi-layer perceptron (MLP) or a convolutional neural network (CNN), and the model structure is adjusted to adapt to the complex geological environment; the trained data is plotted into a curve graph of the face protrusion versus excavation distance, and the curve graph is generated by software such as Matplotlib or Python library for easy visualization analysis; the actual data is brought back to the neural network for retraining, and this step is repeated until the curve graph changes very little. The prediction accuracy is optimized by gradually iterating the training model.

[0022] Step 400: determining a mutation point according to a curve graph showing a change in the face protrusion as a function of the excavation distance, and determining a timing for advance grouting reinforcement of the fault fracture zone of the tunnel according to the excavation distance value corresponding to the mutation point.

[0023] As a specific implementation method, the training process of the neural network is: A neural network structure and a corresponding activation function are selected, and training parameters are determined; the activation function adopts either a ReLU function or a Leaky ReLU function; the training parameters include a learning rate, a batch size, and the number of iterations; the learning rate is between 0.001 and 0.01; the batch size is adjusted according to the amount of data and the complexity of the model, and the number of iterations is determined according to the convergence of the loss function.

[0024] The simulated data is input into the determined neural network structure, and training is performed with the goal of minimizing the loss between the network output and the predicted result label until the predetermined prediction accuracy is achieved to obtain the final trained neural network. The data set should include actual measurement data from multiple construction cycles to ensure the generalization ability of the training model.

[0025] As a specific implementation method, the method for determining the curve graph of the face protrusion changing with the excavation distance is: The relationship data between the tunneling distance and the tunnel face protrusion in the network prediction results are extracted, and the relationship data are smoothed to eliminate noise or abnormal points to obtain preprocessed data; the preprocessed data are plotted into a curve graph using image drawing software or programming libraries (such as Matplotlib, ggplot or Excel) to show the evolution process of tunnel face deformation and to intuitively observe the formation of mutation points.

[0026] As a specific implementation, the method for determining the mutation point is: The variation trend of the curve graph of the face protrusion as a function of the excavation distance is analyzed using a derivative or second-order derivative method to determine a significant variation point of the face protrusion, and the inflection point of the curve graph is determined as an identification criterion for a mutation point.

[0027] As a specific implementation method, determining the timing of advance grouting reinforcement of the fault fracture zone of the tunnel according to the excavation distance value corresponding to the mutation point specifically includes: The current construction status of the tunnel is evaluated according to the excavation distance value corresponding to the mutation point, and the stability of the tunnel is dynamically evaluated in combination with the on-site real-time monitoring data (such as displacement sensor and stress sensor data), the geological conditions of tunnel construction and construction experience, so as to determine the best time for advance grouting reinforcement of the fault fracture zone of the tunnel, and avoid construction risks caused by waste of resources or late grouting.

[0028] The above process can generate multiple curves of face protrusion and excavation distance. When the curve changes slightly and tends to be stable in multiple iterations, it can be regarded as the indicator point of the best grouting reinforcement time. This feature can effectively improve the accuracy of the prediction and ensure timely construction intervention.

[0029] Based on the above technical solution, the following is provided: Figure 2-Figure 3 The embodiments shown are used to explain in detail the processing flow and specific application process of each of the above steps.

[0030] Step 100: Acquire on-site construction data, establish a tunnel excavation model, and import the construction data into the tunnel excavation model.

[0031] As a further improvement of the above-mentioned method for determining the timing of advance grouting reinforcement of the fault fracture zone of the tunnel: the steps of establishing a tunnel excavation model using 3DEC or PFC include: according to the size of the tunnel excavation section, displacement constraints are imposed on the horizontal direction of the X-axis boundary, displacement constraints are imposed on the horizontal direction of the Y-axis, displacement constraints are imposed on the bottom surface boundary of the Z-axis, the top surface is set as a free boundary, and the upper top surface is simulated by applying a uniformly distributed load to simulate the self-weight of the upper rock mass.

[0032] The construction data should include surrounding rock data, initial support data and fault fracture zone data, including specific gravity, cohesion, friction angle, elastic modulus and Poisson's ratio.

[0033] Step 200: Simulate the tunnel excavation model according to the on-site excavation construction plan to obtain the excavation distance data and the face protrusion data; The steps of simulating the excavation of the tunnel excavation model according to the three-step reserved core soil method are as follows: (1) Divide the blocks of the tunnel excavation model; (2) Applying the self-weight stress field and the upper uniform load; (3) Circular excavation of reserved core soil for the upper step and initial support for the upper step; (4) Core soil excavation, middle step excavation, and initial support of the middle step; (5) Excavation of the lower step and initial support of the lower step.

[0034] Step 300: The obtained data is trained through a neural network to improve the prediction accuracy, and the excavation distance data and the face protrusion data are obtained and a curve graph of the face protrusion changing with the excavation distance is drawn; monitoring points or monitoring lines associated with the rock mass or block nodes of the face are set in the tunnel excavation model to monitor the position and changes of the face in real time.

[0035] Step 400: Bring the actual data back to the neural network to obtain a new curve graph. Repeat this step. When the curve graph changes very slightly, it means that the curve graph is close enough to the actual situation. According to the curve graph, the excavation distance value corresponding to the mutation point where the protrusion of the tunnel face changes with the excavation distance is found, which is the time for advance grouting reinforcement of the fault fracture zone of the tunnel.

[0036] Figure 2 A schematic diagram of a neural network model provided by an embodiment of the present invention is shown.

[0037] The neural network model is trained with known data to make preliminary predictions. In order to ensure that the prediction of the model is as consistent as possible with the actual situation, this embodiment adopts an iterative optimization method. This embodiment continuously feeds back the actual collected data to the neural network, retrains the model, and updates the curve graph. This process is repeated until the curve graph changes very slightly, which means that the model of this embodiment is close enough to the actual situation and can be used to guide actual construction.

[0038] Figure 3 This is a curve diagram of the change of the face protrusion with the excavation distance provided by the embodiment of the present invention. This embodiment identifies the mutation point of the face protrusion with the excavation distance by analyzing the curve diagram. This is the time for advance grouting reinforcement of the fault fracture zone of the tunnel.

[0039] At present, advance grouting technology is gradually combined with intelligent systems, especially using artificial intelligence technologies such as neural networks to improve the accuracy of reinforcement decisions. By analyzing the advance geological forecast data and real-time monitoring of construction parameters through neural networks, the geological conditions of the broken zone can be accurately identified, and the grouting strategy can be automatically adjusted according to the actual working conditions. This method can dynamically evaluate the stability of the surrounding rock and predict possible geological risks, thereby avoiding the problem of blind or excessive reinforcement in traditional methods. In addition, combined with the three-dimensional modeling of numerical simulation technology, neural networks can more intuitively analyze the grouting needs under complex geological conditions, optimize reinforcement plans, and improve construction efficiency and safety.

[0040] As a second aspect, the present invention further provides a system for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel, comprising: A data acquisition unit is used to obtain construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks; A construction simulation unit is used to input the construction site data into the tunnel excavation model, and perform construction simulation according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data; A network training unit is used to perform iterative cycle training on the simulation data using a neural network, and to perform prediction using the trained neural network to obtain a curve graph showing the change of the face protrusion with the excavation distance; the neural network adopts a multi-layer perceptron or a convolutional neural network; The reinforcement timing determination unit is used to determine the mutation point according to the curve diagram of the change of the face protrusion amount with the excavation distance, and determine the advance grouting reinforcement timing of the tunnel fault fracture zone according to the excavation distance value corresponding to the mutation point.

[0041] As a third aspect, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method for determining the timing of advance grouting reinforcement of the fault fracture zone of the tunnel according to the above-mentioned method.

[0042] As a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel as described above.

[0043] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0044] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for determining the timing of advance grouting reinforcement of a fault zone in a tunnel, characterized in that: include: Acquire construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks; The construction site data is input into the tunnel excavation model, and construction simulation is performed according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data; The simulation data is iteratively trained using a neural network, and the trained neural network is used for prediction to obtain a curve graph showing the change of the face protrusion with the excavation distance; the neural network adopts a multi-layer perceptron or a convolutional neural network; The mutation point is determined according to the curve graph of the change of the face protrusion amount with the excavation distance, and the timing of advance grouting reinforcement of the fault fracture zone of the tunnel is determined according to the excavation distance value corresponding to the mutation point.

2. The method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel according to claim 1 is characterized in that: The training process of the neural network is: Select a neural network structure and a corresponding activation function, and determine training parameters; the activation function uses either a ReLU function or a Leaky ReLU function; the training parameters include a learning rate, a batch size, and the number of iterations; the learning rate is between 0.001 and 0.01; The simulated data is input into a determined neural network structure, and training is performed with the goal of minimizing the loss between the network output and the predicted result label to obtain a finally trained neural network.

3. The method for determining the timing of advance grouting reinforcement of a fault zone in a tunnel according to claim 1 is characterized in that: The method for determining the curve graph of the face protrusion changing with the excavation distance is as follows: Extracting the relationship data between the excavation distance and the face protrusion in the network prediction results, and smoothing the relationship data to eliminate noise or abnormal points to obtain preprocessed data; The pre-processed data is plotted into a curve graph using image drawing software or a programming library to show the evolution of the deformation of the tunnel face.

4. The method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel according to claim 1, characterized in that: The method for determining the mutation point is: The variation trend of the curve graph of the face protrusion amount changing with the excavation distance is analyzed by using the derivative or second-order derivative method, and the inflection point of the curve graph is determined as the identification standard of the mutation point.

5. The method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel according to claim 1, characterized in that: The timing of advance grouting reinforcement of the fault fracture zone of the tunnel is determined according to the excavation distance value corresponding to the mutation point, specifically including: The current construction status of the tunnel is evaluated according to the excavation distance value corresponding to the mutation point, and the stability of the tunnel is dynamically evaluated in combination with the on-site real-time monitoring data, the geological conditions of the tunnel construction and the construction experience, so as to determine the best time for advance grouting reinforcement of the fault fracture zone of the tunnel.

6. A system for determining the timing of advance grouting reinforcement of a fault zone in a tunnel, characterized in that: include: A data acquisition unit is used to obtain construction site data; the construction site data includes surrounding rock data, initial support data and fault fracture zone data; the surrounding rock data includes physical and mechanical properties of the formation; the initial support data includes geometric parameters and material parameters of the support structure; the fault fracture zone data includes the width of the fracture zone and the development of cracks; A construction simulation unit is used to input the construction site data into the tunnel excavation model, and perform construction simulation according to the on-site excavation construction plan to obtain simulation data; the simulation data includes excavation distance data and face protrusion data; the construction simulation method adopts a three-step reserved core soil method; the tunnel excavation model is constructed using three-dimensional modeling software and calibrated using on-site data; A network training unit is used to perform iterative cycle training on the simulation data using a neural network, and to perform prediction using the trained neural network to obtain a curve graph showing the change of the face protrusion with the excavation distance; the neural network adopts a multi-layer perceptron or a convolutional neural network; The reinforcement timing determination unit is used to determine the mutation point according to the curve diagram of the change of the face protrusion amount with the excavation distance, and determine the advance grouting reinforcement timing of the tunnel fault fracture zone according to the excavation distance value corresponding to the mutation point.

7. An electronic device, characterized in that: It includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the method for determining the timing of advance grouting reinforcement of a fault fracture zone in a tunnel as described in any one of claims 1 to 5.

Images