Tunnel leaking stoppage reinforcement construction management monitoring system based on statistical analysis

Abstract

The invention discloses a tunnel leaking stoppage reinforcement construction management monitoring system based on statistical analysis, and relates to the technical field of statistical analysis, the system comprises a data acquisition module, a data analysis module, a construction control module and a monitoring early warning module, the leakage-disease correlation and the hazard level of each monitoring point are evaluated, and a treatment scheme is output; and the construction control module executes layered plugging grouting operation based on the treatment scheme, monitors and dynamically adjusts grouting control parameters in real time until construction of a single monitoring point is completed, and sequentially completes construction of all the monitoring points according to the treatment sequence determined by the treatment scheme. According to the method, the analysis of the tunnel leakage-disease correlation and the scientific evaluation of the hazard level are realized, and the treatment effect and the construction safety of the tunnel leaking stoppage reinforcement construction are improved in cooperation with layered leaking stoppage grouting construction and a real-time monitoring and early warning mechanism.

Description

Technical Field

[0001] The invention relates to the technical field of statistical analysis, in particular to a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis. Background Art

[0002] With the continuous development of data science and statistical analysis technology, its application in the engineering field is becoming more and more extensive. In tunnel engineering, especially for the treatment of leakage problems, traditional data analysis methods are often limited to simple statistics of a single data dimension, lack of in-depth mining of the correlation between multi-source data, and fail to make full use of statistical analysis methods to dynamically monitor and warn the construction process.

[0003] At present, the construction management of tunnel plugging and reinforcement mainly relies on isolated analysis of single disease data or leakage data, and fails to establish a data association model based on statistical analysis. At the same time, there is a lack of systematic research on data characteristics and propagation laws, which makes it difficult to formulate scientific governance plans from the data level, affecting the accuracy and reliability of construction results. Summary of the invention

[0004] In view of the problems existing in the existing tunnel plugging and reinforcement construction management system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to improve the management effect and construction safety of tunnel leakage plugging and reinforcement construction.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis, which includes a data acquisition module, the data acquisition module includes a sensor group arranged at the tunnel monitoring point, the sensor group is used to collect disease data and leakage data of each monitoring point; a data analysis module, the data analysis module establishes a hazard assessment model based on the disease data and leakage data, evaluates the leakage-disease correlation and the hazard level of each monitoring point, and outputs a treatment plan, the treatment plan includes the monitoring point processing order and its corresponding grouting control parameter initial value; a construction control module, the construction control module performs a layered plugging grouting operation based on the treatment plan, monitors and dynamically adjusts the grouting control parameters in real time until the construction of a single monitoring point is completed, and completes the construction of all monitoring points in sequence according to the processing order determined by the treatment plan; a monitoring and early warning module, the monitoring and early warning module is used to monitor the grouting control parameters and the safety status of the monitoring points in real time, and outputs an early warning signal when the safety status of the monitoring points reaches the early warning standard or the grouting control parameters are abnormal.

[0007] As a preferred solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis described in the present invention, the design process of the data analysis module is as follows: pre-process the collected disease data and leakage data to obtain a monitoring data sequence; extract features from the monitoring data sequence to obtain a feature data set; perform time series correlation analysis on the disease data and leakage data of the same monitoring point to obtain a leakage-disease correlation matrix; based on the leakage-disease correlation matrix and the feature data set, use a fuzzy comprehensive evaluation method to calculate the hazard index of each monitoring point; based on the distance between monitoring points and geological conditions, establish a hazard propagation model and calculate the hazard propagation coefficient; calculate the comprehensive hazard value based on the hazard index and the hazard propagation coefficient, and determine the processing order of the monitoring points; establish a grouting parameter prediction model based on the BP neural network and particle swarm optimization algorithm to generate the initial value of the grouting control parameter; generate a treatment plan according to the processing order of the monitoring points and the initial value of the grouting control parameter.

[0008] As a preferred solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis described in the present invention, the calculation process of the hazard index is as follows: establish an evaluation factor set, the evaluation factor set includes disease parameters and leakage parameters; divide the hazard degree into at least two hazard levels, and establish a comment set; based on the leakage-disease correlation matrix, determine the weight set of the evaluation factors; calculate the membership of each evaluation factor of the monitoring point to each hazard level, and generate a fuzzy evaluation matrix; use a weighted average fuzzy synthesis operation to process the weight set and the fuzzy evaluation matrix to obtain a fuzzy evaluation vector; assign the hazard level to the corresponding hazard level score, and calculate the hazard index through the inner product operation of the fuzzy evaluation vector and the hazard level score vector.

[0009] As an optimal solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis described in the present invention, the process of calculating the hazard propagation coefficient is as follows: obtaining the spatial coordinate data of the monitoring points, calculating and normalizing the Euclidean distance between the monitoring points to obtain a distance matrix; obtaining engineering geological parameters, the engineering geological parameters include rock fracture density, rock compressive strength, groundwater recharge, and fault development density; constructing a judgment matrix based on the engineering geological parameters, calculating the eigenvector of the judgment matrix and normalizing it to obtain a geological influence weight vector; quantifying and standardizing the geological parameters to obtain a geological condition matrix; calculating the inner product of the geological influence weight vector and the geological condition matrix to obtain a geological influence matrix; substituting the distance matrix into the exponential attenuation function to obtain a distance attenuation matrix; multiplying the distance attenuation matrix with the corresponding elements of the geological influence matrix to obtain a hazard propagation coefficient matrix.

[0010] As a preferred solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis described in the present invention, the process of establishing the grouting parameter prediction model is as follows: constructing the input feature vector of the grouting parameter prediction model and performing data preprocessing; establishing a sample set based on historical construction data; constructing a BP neural network structure, and optimizing the BP neural network parameters using a particle swarm optimization algorithm to obtain a grouting parameter prediction model.

[0011] As a preferred solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis of the present invention, the layered plugging grouting operation based on the treatment plan includes the following steps: receiving the treatment plan output by the data analysis module, extracting the monitoring point processing sequence and the initial value of the grouting control parameter; selecting the monitoring point to be processed according to the monitoring point processing sequence, and obtaining the disease data and leakage data collected by the sensor group; dividing the grouting construction layers based on the crack depth in the disease data, and dividing the grouting range into multiple construction layers according to the crack extension length; starting construction from the deepest layer, and inputting the initial value of the grouting control parameter into the grouting equipment; collecting the actual grouting parameters during the construction process, and calculating the deviation between the actual grouting parameters and the initial value of the grouting control parameter; performing dynamic adjustment of the grouting control parameter based on the engineering geological parameters and the deviation; monitoring the comprehensive hazard value of the current grouting layer to determine whether the completion standard is met, if the completion standard is not met, continue grouting, if the completion standard is met, enter the previous layer construction; after completing all grouting layers, use the fuzzy comprehensive evaluation method to evaluate the construction effect.

[0012] As a preferred solution of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis of the present invention, the disease data includes crack width, crack depth, crack extension length, joint deformation, construction joint cracking degree, hole size, and surrounding rock integrity; leakage data includes water seepage volume, water seepage pressure, and water turbidity.

[0013] In the second aspect, an embodiment of the present invention provides a tunnel plugging and reinforcement construction management and monitoring method based on statistical analysis, which includes collecting disease data and leakage data of each monitoring point through a sensor group of a data acquisition module; a data analysis module establishes a hazard assessment model based on the disease data and leakage data, evaluates the leakage-disease correlation and the hazard level of each monitoring point, and outputs a treatment plan; a construction control module performs layered plugging grouting operations according to the treatment plan until the construction of all monitoring points is completed.

[0014] The beneficial effects of the present invention are as follows: the present invention innovatively introduces the correlation analysis of disease data and leakage data into the evaluation model by constructing a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis, and considers the mutual influence between monitoring points in combination with the hazard propagation model, thereby achieving a scientific evaluation of the hazard level of the monitoring points and a reasonable determination of the processing order. At the same time, a grouting parameter prediction model is established through an improved BP neural network and particle swarm optimization algorithm, and the plugging and reinforcement construction is made more targeted and scientific by coordinating the layered plugging grouting construction and the dynamic parameter adjustment strategy. The system not only improves the accuracy and efficiency of tunnel plugging and reinforcement construction, but also ensures the safety of the construction process through real-time monitoring and early warning mechanisms, providing a practical technical solution for tunnel plugging and reinforcement construction management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0016] Figure 1 This is the workflow diagram of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis.

[0017] Figure 2 Design process flow chart for the data analysis module of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis.

[0018] Figure 3 This is a hierarchical plugging grouting construction flow chart for the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1, reference Figure 1~Figure 3 , which is the first embodiment of the present invention, provides a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis, including a data acquisition module, a data analysis module, a construction control module and a monitoring and early warning module. The work flow diagram is as follows Figure 1 As shown in the figure: Data acquisition module, the data acquisition module includes a sensor group installed at the tunnel monitoring point, the sensor group is used to collect disease data and leakage data. Among them, the disease data includes but is not limited to crack width, crack depth, crack extension length, joint deformation, construction joint cracking degree, hole size, surrounding rock integrity; leakage data includes but is not limited to water seepage, water seepage pressure, water turbidity.

[0023] Data analysis module: The data analysis module establishes a hazard assessment model based on disease data and leakage data, evaluates the leakage-disease correlation and the hazard level of each monitoring point, and outputs a treatment plan. The treatment plan includes the monitoring point processing order and its corresponding initial values ​​of grouting control parameters.

[0024] In traditional technical solutions, tunnel plugging and reinforcement construction management mainly relies on analysis and judgment of single disease data or leakage data, and lacks statistical analysis of the interaction between monitoring point diseases and leakage, resulting in a lack of systematicness in the formulation of treatment plans and unsatisfactory treatment effects.

[0025] In view of the above problems, the present invention proposes a hazard assessment model in the data analysis module. The flow chart of the data analysis module design process is as follows: Figure 2 As shown, the specific steps are as follows: pre-process the collected disease data and leakage data to obtain a monitoring data sequence, wherein the pre-processing includes outlier detection and elimination, missing value processing, data standardization filtering and smoothing, and time alignment. Feature extraction is performed on the monitoring data sequence to obtain a feature data set. Time series correlation analysis is performed on the disease data and leakage data of the same monitoring point to obtain a leakage-disease correlation matrix. The steps are as follows: extract disease data and leakage data from the same monitoring data sequence; calculate the correlation coefficients of disease data and leakage data in turn to generate a correlation coefficient matrix, mark the correlation coefficient matrix as a leakage-disease correlation matrix, and each element r in the matrix mn Indicates the correlation between the mth disease data and the nth leakage data.

[0026] Furthermore, based on the leakage-disease correlation matrix and the characteristic data set, the fuzzy comprehensive evaluation method is used to calculate the hazard index of each monitoring point. The steps are as follows: establish an evaluation factor set, including all disease parameters and leakage parameters; establish a comment set, and divide the hazard degree into k hazard levels (such as mild, general, severe and serious four hazard levels); based on the leakage-disease correlation matrix, use the correlation coefficient normalization method to determine the weight set of evaluation factors; use the triangle membership function to calculate the membership of each evaluation factor of the monitoring point to the k hazard levels, and generate a fuzzy evaluation matrix; use the weighted average fuzzy synthesis operation to process the weight set and the fuzzy evaluation matrix to obtain the fuzzy evaluation vector; assign the k hazard levels to the corresponding hazard level scores (such as 25, 50, 75, 100), and calculate the hazard index of the monitoring point by the inner product operation of the fuzzy evaluation vector and the hazard level score vector.

[0027] Furthermore, based on the distance between monitoring points and geological conditions, a hazard propagation model is established to calculate the hazard propagation coefficient. The steps are as follows: obtain the spatial coordinate data of each monitoring point, calculate the Euclidean distance between the monitoring points, and normalize the Euclidean distance to obtain the distance matrix D, where the matrix element d ij Represents the standardized distance value between monitoring point i and monitoring point j. Obtain the engineering geological parameters of the monitoring area, which include rock mass crack density, rock mass compressive strength, groundwater recharge, and fault development density obtained through geological drilling, geophysical testing, and engineering geological surveys; construct a pairwise comparison judgment matrix based on the engineering geological parameters, calculate the eigenvector of the judgment matrix and normalize it to obtain the geological influence weight vector W.

[0028] Furthermore, the geological parameters are quantified and standardized to obtain the geological condition matrix G, where the matrix element g ij Represents the quantitative value of the geological conditions between monitoring point i and monitoring point j. Perform an inner product operation on the geological influence weight vector W and the row vector of the geological condition matrix G to generate the geological influence matrix GI; substitute the distance matrix D into the exponential decay function , calculate the distance decay matrix DD, where The distance attenuation matrix DD is multiplied with the corresponding elements of the geological influence matrix GI to generate the hazard propagation coefficient matrix TC, where the element tc ij It represents the hazard transmission coefficient from monitoring point i to monitoring point j.

[0029] It should be noted that i and j in the present invention both represent the rows and columns of a matrix, indicating the index of a monitoring point.

[0030] Furthermore, the comprehensive hazard value is calculated based on the hazard index and the hazard propagation coefficient, and the processing order of the monitoring points is determined. The steps are as follows: construct the monitoring point weight matrix WM, and the element wm ij The hazard index vector H is represented by the i-th element h i and the jth element tc in the i-th row of the hazard propagation coefficient matrix TC ij The row vectors of the monitoring point weight matrix WM are summed to generate the monitoring point comprehensive weight vector CW. The element cw of the monitoring point comprehensive weight vector CW is i represents the comprehensive weight value of monitoring point i; summing up the column vectors of the hazard propagation coefficient matrix TC to generate the propagation impact vector PI, the element pi of the propagation impact vector PI i Indicates the degree to which the monitoring point i is affected by the propagation of other monitoring points; the element cw of the comprehensive weight vector CW of the monitoring point i and the element pi of the propagation influence vector PI i Add together to generate the comprehensive hazard value vector CH of the monitoring point. The element ch of the comprehensive hazard value vector CH of the monitoring point is i Indicates the comprehensive hazard level of monitoring point i. Sort the monitoring points from large to small according to the element values ​​of the monitoring point comprehensive hazard value vector CH to generate a monitoring point processing sequence.

[0031] Furthermore, a grouting parameter prediction model is established based on BP neural network and particle swarm optimization algorithm to generate the initial value of grouting control parameters. The establishment process of the grouting parameter prediction model is as follows: construct the input feature vector of the grouting parameter prediction model and perform data preprocessing. The feature vector includes disease data, leakage data, geological condition parameters, and comprehensive hazard value.

[0032] Furthermore, an improved BP neural network structure is constructed. The network structure design adopts a composite structure of an input layer, three hidden layers and an output layer. The number of nodes in the input layer is the dimension z of the feature vector after dimensionality reduction, and the number of nodes in the three hidden layers are 2z, 1.5z and z respectively, to enhance the feature extraction ability of the network. The hidden layer activation function uses the ReLU function to avoid the gradient disappearance problem. The output layer uses a linear activation function, and the number of output nodes is 3, corresponding to the three parameters of grouting pressure, grouting flow and grouting time. At the same time, a dropout mechanism is introduced in the network, and the dropout rate is set to 0.3 to prevent the model from overfitting.

[0033] Furthermore, a sample set was established based on historical construction data and data enhancement was performed. The monitoring data, geological parameters and grouting construction parameters of historical leakage control projects of the same type were collected, and the data set was divided into a training set, a validation set and a test set in a ratio of 7:2:1. New samples were generated by adding Gaussian noise to the training samples, the SMOTE algorithm was used to deal with the sample imbalance problem, and the sliding window method was used to expand the time series related samples, thereby expanding the scale and diversity of the training data set.

[0034] Furthermore, an improved particle swarm optimization algorithm is used to optimize the BP neural network parameters. The connection weights and thresholds of the BP neural network are encoded as particle position vectors, and a fitness function is constructed with the weighted mean square error between the predicted output and the actual grouting parameters as the main indicator. At the same time, the L2 regularization term is introduced to prevent overfitting, and a parameter constraint penalty term is added. The optimization algorithm adopts a configuration with a particle swarm size of 100 and a maximum number of iterations of 200. The learning factor c1=c2=2, and the inertia weight adopts an adaptive strategy based on dynamic adjustment of the fitness value. The crossover mutation operation is introduced to improve the population diversity and ensure the optimization effect.

[0035] Furthermore, the optimized BP neural network model was trained and validated. The network was trained using the mini-batch gradient descent method, the batch size was set to 32, the learning rate used the cosine annealing strategy, and the number of training rounds was controlled by the early stopping mechanism, with a maximum setting of 1000 rounds. In the validation phase, the validation set was used to evaluate the model performance, and K-fold cross validation was used to evaluate the model stability, and RMSE, MAE, and R were calculated. 2 In the testing phase, the test set is used for final performance evaluation, and the prediction error distribution is analyzed by comparing the predicted value with the actual value.

[0036] Furthermore, the initial values ​​of the grouting control parameters are generated, and a model evaluation and update mechanism is established. The feature vector of the monitoring point to be processed is input into the trained model to obtain the initial prediction value, and the prediction result is processed with engineering constraints. The grouting pressure constraint is not more than 80% of the allowable pressure of the rock mass and the smaller value of the maximum pressure of the equipment; the grouting flow constraint considers the product of the safety factor, the fracture area and the slurry filling speed; the grouting time constraint is based on the theoretical slurry dosage and the actual grouting flow to calculate the minimum limit.

[0037] Furthermore, a treatment plan is generated according to the processing order of the monitoring points and the initial values ​​of the grouting control parameters.

[0038] Preferably, the data analysis module realizes the quantitative analysis of the interaction between the disease and leakage at the monitoring point by establishing the leakage-disease correlation matrix and the hazard propagation model, and builds a complete hazard assessment system by combining fuzzy comprehensive evaluation and geological conditions, which can scientifically assess the degree of hazard at each monitoring point and determine the optimal treatment order. At the same time, the improved BP neural network and particle swarm optimization algorithm are used to establish the grouting parameter prediction model, realize the intelligent configuration of the grouting parameters, ensure the effective implementation of the treatment plan through layered plugging grouting operations and real-time parameter adjustment, improve the pertinence and efficiency of plugging construction, reduce the uncertainty caused by human experience judgment, and significantly improve the controllability and stability of the plugging effect.

[0039] The construction control module performs layered plugging grouting operations based on the treatment plan, monitors in real time and dynamically adjusts the grouting control parameters until the construction of a single monitoring point is completed, and completes the construction of all monitoring points in sequence according to the processing order of the monitoring points. Figure 3 shown.

[0040] Specifically, the construction control module first receives the treatment plan output by the data analysis module, extracts the monitoring point processing sequence and the corresponding initial values ​​of the grouting control parameters. The first monitoring point to be processed is selected according to the monitoring point processing sequence, and the real-time disease data and leakage data of the monitoring point are obtained from the sensor group. The grouting construction layers are divided based on the crack depth data, and the grouting range is divided into multiple construction layers according to the crack extension length. Construction starts from the deepest layer, and the initial values ​​of the grouting control parameters are input into the grouting equipment.

[0041] Furthermore, the grouting operation is started, and various parameters in the construction process are collected in real time through the sensor group. The change relationship of each parameter is analyzed in combination with the leakage-disease correlation matrix, and the deviation between the actual grouting parameters (measured grouting pressure, grouting flow, grouting time) and the initial value of the grouting control parameters is calculated. Based on the engineering geological parameters and deviation analysis results, the grouting control parameters are dynamically adjusted. The steps are as follows: first, the deviation between the actual grouting pressure and the initial value of the grouting pressure is calculated. When the comprehensive hazard value of the monitoring point has not decreased significantly and the deviation is within 80% of the allowable pressure of the rock mass, the grouting pressure is gradually increased in steps of 0.5 MPa; secondly, the deviation between the actual grouting flow rate and the initial value of the grouting flow rate is calculated. When the crack width change rate tends to be stable, the grouting flow rate is adjusted to the product of the safety factor, the crack area and the slurry filling speed; then, the deviation between the actual grouting time and the initial value of the grouting time is calculated, and the minimum limit is calculated based on the theoretical slurry dosage and the actual grouting flow rate, and the grouting time is adjusted accordingly; finally, it is ensured that the adjustment of the grouting pressure and grouting flow rate meets the requirements of the slurry diffusion radius, and the influence of parameter adjustment on the disease control effect is evaluated through the leakage-disease correlation matrix.

[0042] Furthermore, the comprehensive hazard value of the current grouting layer is continuously monitored. When the water seepage volume is reduced to the set threshold and the crack width converges to the target value, the current layer is judged to have reached the completion standard. If the standard is not met, the grouting operation continues; if the standard is met, the construction of the previous layer is started. After all grouting layers are completed, the hazard index of the monitoring point is recalculated using the fuzzy comprehensive evaluation method, and the construction effect is evaluated in combination with the hazard propagation coefficient. If the comprehensive hazard value of the monitoring point reaches the control target, its status is updated to completed; if it does not meet the standard, the characteristic vector is re-entered into the grouting parameter prediction model, a new initial value of the control parameter is generated, and the layered construction step is returned.

[0043] Furthermore, the comprehensive hazard value of the current grouting layer is continuously monitored. When the water seepage volume is reduced to the set threshold and the crack width converges to the target value, the current layer is judged to have reached the completion standard. If the standard is not met, the grouting operation continues; if the standard is met, the construction of the previous layer is started. After all grouting layers are completed, the hazard index of the monitoring point is recalculated using the fuzzy comprehensive evaluation method, and the construction effect is evaluated in combination with the hazard propagation coefficient. If the comprehensive hazard value of the monitoring point reaches the control target, its status is updated to completed; if it does not meet the standard, the characteristic vector is re-entered into the grouting parameter prediction model, a new initial value of the control parameter is generated, and the layered construction step is returned.

[0044] Furthermore, the next point to be processed is selected according to the monitoring point processing sequence, and the above process is repeated until the construction of all monitoring points is completed. Finally, the changes in the comprehensive hazard values ​​of each monitoring point are summarized and analyzed to form a construction summary report. The entire implementation process realizes precise and layered plugging and reinforcement construction management through real-time analysis of disease data and leakage data and dynamic optimization of grouting parameters.

[0045] Preferably, the construction control module adopts a layered construction strategy from deep to shallow and a double-layer verification mechanism (single-layer completion standard and comprehensive hazard value assessment of monitoring points), which realizes dynamic optimization and adjustment of grouting parameters and full control of construction quality, effectively improving the accuracy and controllability of leak plugging and reinforcement construction.

[0046] The monitoring and early warning module is used to monitor the grouting control parameters and the safety status of the monitoring point in real time, and output a warning signal when the safety status of the monitoring point reaches the warning standard or the grouting control parameters are abnormal.

[0047] It should be noted that the early warning standards include the comprehensive hazard value of the monitoring point reaching the warning value (pre-set), the grouting control parameters exceeding the safety range (for example, the grouting pressure exceeds 80% of the allowable pressure of the rock mass, the grouting flow is abnormal, etc.), the monitoring point leakage or disease data sudden change (such as abnormal changes in indicators such as seepage volume, seepage pressure, and crack width), etc.

[0048] Furthermore, this embodiment also provides a tunnel plugging and reinforcement construction management and monitoring method based on statistical analysis, including collecting disease data and leakage data of each monitoring point through the sensor group of the data acquisition module; the data analysis module establishes a hazard assessment model based on the disease data and leakage data, evaluates the leakage-disease correlation and the hazard level of each monitoring point, and outputs a treatment plan; the construction control module performs layered plugging grouting operations according to the treatment plan until the construction of all monitoring points is completed.

[0049] In summary, the present invention constructs a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis, innovatively introduces the correlation analysis of disease data and leakage data into the evaluation model, and considers the mutual influence between monitoring points in combination with the hazard propagation model, thereby achieving a scientific evaluation of the hazard level of the monitoring point and a reasonable determination of the processing order. At the same time, a grouting parameter prediction model is established through an improved BP neural network and particle swarm optimization algorithm, and the layered plugging grouting construction and dynamic parameter adjustment strategy are combined to make the plugging and reinforcement construction more targeted and scientific. The system not only improves the accuracy and efficiency of tunnel plugging and reinforcement construction, but also ensures the safety of the construction process through real-time monitoring and early warning mechanisms, providing a practical technical solution for tunnel plugging and reinforcement construction management.

[0050] Example 2, reference Figure 1~Figure 3 , which is the second embodiment of the present invention, and this embodiment provides a tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0051] In order to verify the feasibility and effectiveness of the present invention, a highway tunnel was selected as the experimental object for simulation experiments. The tunnel is 2,486 meters long and is located in a mountainous area in North China. The surrounding rock is mainly granite and groundwater is well developed. During the operation of the tunnel, multiple leaks and structural defects occurred, and plugging and reinforcement treatment was urgently needed.

[0052] First, 24 monitoring points were set up in the tunnel, each equipped with a crack width sensor (measuring range 0-10mm, accuracy 0.01mm), a crack depth detector (measuring range 0-500mm, accuracy 0.1mm), a water seepage sensor (measuring range 0-100L / h, accuracy 0.1L / h) and a water pressure sensor (measuring range 0-1MPa, accuracy 0.001MPa). The experimental collection period is 30 days, and the data sampling interval is 1 hour.

[0053] Next, the disease data and leakage data of each monitoring point were collected through the data acquisition module. Among them, the crack width range is 0.15~4.82mm, the crack depth range is 35~286mm, the seepage range is 0.8~42.6L / h, and the seepage pressure range is 0.02~0.45MPa. After all the data were processed for outliers and standardized, they were input into the data analysis module for processing.

[0054] Subsequently, the data analysis module calculated the leakage-disease correlation matrix based on the collected data. The analysis found that the correlation coefficient between water seepage pressure and crack width reached 0.82, indicating that the two had a significant positive correlation; the correlation coefficient between water seepage and crack depth was 0.76, also showing a strong positive correlation. Based on the fuzzy comprehensive evaluation method, the 24 monitoring points were divided into four hazard levels: severe (6 points), heavy (8 points), general (7 points) and mild (3 points).

[0055] Then, considering the geological conditions on site, the calculated engineering geological parameters include: rock mass crack density 1.2~3.6 / m, rock mass compressive strength 42~68MPa, groundwater recharge 15~45m 3 / d. The hazard propagation coefficient between monitoring points was calculated through the hazard propagation model, ranging from 0.12 to 0.85. After comprehensively considering the hazard index and propagation coefficient, the final monitoring point processing sequence was determined.

[0056] Furthermore, the improved BP neural network structure was used to train the grouting parameter prediction model. The network used 860 sets of historical construction data as training samples, and the validation set and test set contained 246 and 123 sets of data, respectively. After 1000 rounds of training, the root mean square error (RMSE) of the model on the test set was 0.156, the mean absolute error (MAE) was 0.128, and the determination coefficient (R 2 ) reaches 0.912, indicating that the model has good prediction accuracy.

[0057] Finally, the initial value range of the grouting control parameters generated based on the prediction model is: grouting pressure 0.8~2.4MPa, grouting flow rate 15~45L / min, grouting time 40~120min. The construction control module performs construction according to the layered grouting scheme. For cracks with a depth of more than 200mm, three layers of grouting are used, 150~200mm is used for two layers of grouting, and less than 150mm is used for single layer grouting.

[0058] Preferably, the comparative indicators of the method of the present invention compared with the traditional construction method are shown in Table 1.

[0059] Table 1 Comparative indexes of the method of the present invention compared with the traditional construction method It can be seen from Table 1 that the method of the present invention has significant advantages over the traditional construction method. The construction efficiency is improved by about 67%, the construction rework rate is reduced by 73.4%, and the comprehensive treatment cost is reduced by 23.5%. These improvements fully demonstrate the practicality and advancement of the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis proposed by the present invention.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis, characterized in that: include, A data acquisition module, wherein the data acquisition module includes a sensor group arranged at a tunnel monitoring point, and the sensor group is used to collect disease data and leakage data of each monitoring point; A data analysis module, wherein the data analysis module establishes a hazard assessment model based on the disease data and the leakage data, assesses the leakage-disease correlation and the hazard level of each monitoring point, and outputs a treatment plan, wherein the treatment plan includes a monitoring point processing sequence and its corresponding initial values ​​of grouting control parameters; A construction control module, which performs layered plugging grouting operations based on the treatment plan, monitors in real time and dynamically adjusts grouting control parameters until the construction of a single monitoring point is completed, and completes the construction of all monitoring points in sequence according to the processing order determined by the treatment plan; The monitoring and early warning module is used to monitor the grouting control parameters and the safety status of the monitoring points in real time, and output a warning signal when the safety status of the monitoring points reaches the early warning standard or the grouting control parameters are abnormal.

2. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 1, characterized in that: The design process of the data analysis module is as follows: Preprocess the collected disease data and leakage data to obtain a monitoring data sequence; Extracting features from the monitoring data sequence to obtain a feature data set; Conduct time series correlation analysis on the disease data and leakage data of the same monitoring point to obtain the leakage-disease correlation matrix; Based on the leakage-disease correlation matrix and the characteristic data set, a fuzzy comprehensive evaluation method is used to calculate the hazard index of each monitoring point; Based on the distance between monitoring points and geological conditions, a hazard propagation model is established and the hazard propagation coefficient is calculated; Calculate a comprehensive hazard value based on the hazard index and the hazard transmission coefficient, and determine a processing order for monitoring points; Establishing a grouting parameter prediction model based on BP neural network and particle swarm optimization algorithm to generate the initial value of the grouting control parameter; A treatment plan is generated according to the processing order of the monitoring points and the initial values ​​of the grouting control parameters.

3. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 2 is characterized by: The calculation process of the hazard index is as follows: Establishing an evaluation factor set, wherein the evaluation factor set includes a disease parameter and a leakage parameter; Classify the hazard level into at least two hazard levels and establish a comment set; Based on the leakage-disease correlation matrix, the weight set of evaluation factors is determined; Calculate the membership degree of each evaluation factor of the monitoring point to each hazard level and generate a fuzzy evaluation matrix; Processing the weight set and the fuzzy evaluation matrix using a weighted average fuzzy synthesis operation to obtain a fuzzy evaluation vector; The hazard level is assigned a corresponding hazard level score, and the hazard index is calculated by performing an inner product operation of the fuzzy evaluation vector and the hazard level score vector.

4. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 2 is characterized by: The process of calculating the hazard propagation coefficient is as follows: Obtain the spatial coordinate data of the monitoring points, calculate and normalize the Euclidean distances between the monitoring points to obtain the distance matrix; Obtaining engineering geological parameters, including rock mass fissure density, rock mass compressive strength, groundwater recharge, and fault development density; Constructing a judgment matrix based on the engineering geological parameters, calculating and normalizing the eigenvector of the judgment matrix, and obtaining a geological influence weight vector; Quantifying and standardizing the geological parameters to obtain a geological condition matrix; Calculating the inner product of the geological influence weight vector and the geological condition matrix to obtain a geological influence matrix; Substituting the distance matrix into the exponential decay function to obtain a distance decay matrix; The distance attenuation matrix is ​​multiplied by corresponding elements of the geological influence matrix to obtain a hazard propagation coefficient matrix.

5. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 2, characterized in that: The establishment process of the grouting parameter prediction model is as follows: Construct the input feature vector of the grouting parameter prediction model and perform data preprocessing; Establish a sample set based on historical construction data; The BP neural network structure is constructed, and the particle swarm optimization algorithm is used to optimize the BP neural network parameters to obtain the grouting parameter prediction model.

6. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 1, characterized in that: The layered plugging grouting operation based on the treatment scheme comprises the following steps: Receive the treatment plan output by the data analysis module, extract the monitoring point processing sequence and the initial value of the grouting control parameter; Selecting a monitoring point to be processed according to the monitoring point processing sequence, and acquiring the disease data and leakage data collected by the sensor group; Divide the grouting construction layers based on the crack depth in the disease data, and divide the grouting range into multiple construction layers according to the crack extension length; Starting construction from the deepest layer, the initial value of the grouting control parameter is input into the grouting equipment; Collecting actual grouting parameters during the construction process, and calculating the deviation between the actual grouting parameters and the initial value of the grouting control parameters; Based on the engineering geological parameters and the deviation, dynamically adjust the grouting control parameters; Monitor the comprehensive hazard value of the current grouting layer to determine whether it has reached the completion standard. If it has not reached the completion standard, continue grouting. If it has reached the completion standard, proceed to the next layer of construction. After completing all the grouting layers, the fuzzy comprehensive evaluation method is used to evaluate the construction effect.

7. The tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis as claimed in claim 1, characterized in that: The disease data include crack width, crack depth, crack extension length, joint deformation, construction joint cracking degree, hole size, and surrounding rock integrity; The leakage data include water seepage volume, water seepage pressure, and water turbidity.

8. A tunnel plugging and reinforcement construction management and monitoring method based on statistical analysis, based on the tunnel plugging and reinforcement construction management and monitoring system based on statistical analysis according to any one of claims 1 to 7, characterized in that: Also includes, Collect disease data and leakage data of each monitoring point through the sensor group of the data acquisition module; The data analysis module establishes a hazard assessment model based on disease data and leakage data, assesses the leakage-disease correlation and the hazard level of each monitoring point, and outputs a control plan; The construction control module performs layered plugging and grouting operations according to the treatment plan until the construction of all monitoring points is completed.

Images