Complex stratum TBM tunneling parameter real-time prediction method

Abstract

The invention relates to the technical field of tunneling parameter prediction, in particular to a complex stratum TBM tunneling parameter real-time prediction method. According to the technical scheme, the method comprises the steps of data collection and preprocessing, model selection and training, model prediction and evaluation, and result application and feedback. According to the data collection and preprocessing, operation parameters are collected in real time through various sensors on TBM equipment, wherein the operation parameters comprise the cutterhead rotating speed, the penetration degree, the thrust, the torque, the total thrust, the gripper shoe pressure, the propelling speed, the current and the power. Real-time prediction of the TBM tunneling parameters of the complex stratum is achieved by fusing the machine learning algorithm, the tunneling parameters can be optimized in real time, and the construction efficiency is improved; the tunneling process is stabilized to guarantee the engineering quality; tool abrasion is reduced, energy consumption is reduced, and the construction cost is reduced; equipment faults and accidents are prevented, and construction safety is guaranteed; and construction technology innovation can be promoted, intelligent construction management is achieved, the comprehensive benefits of TBM construction are comprehensively improved, and efficient, safe and intelligent development of tunnel (roadway) engineering is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of tunneling parameter prediction, and in particular to a real-time prediction method for TBM tunneling parameters in complex strata. Background Art

[0002] As an advanced tunnel (lane) construction equipment, the full-face rock tunnel boring machine (TBM) has been widely used in various tunnel and coal mine tunnel projects. However, when conducting tunneling operations under complex stratum conditions, it faces many severe challenges.

[0003] 1. Uncertainty in tunneling parameter control

[0004] At present, the control of TBM excavation parameters depends largely on the driver's experience. The driver adjusts key excavation parameters such as cutter head speed, thrust, torque, etc. based on his own experience and subjective judgment of the on-site situation. This method has significant limitations, because it is difficult for the driver to accurately predict the changing laws of the geological conditions of the formation, and it is impossible to accurately grasp the complex relationship between excavation parameters and formation characteristics. When the formation conditions suddenly change, such as suddenly entering a hard rock formation from a soft rock formation or encountering complex situations such as a rock fracture zone or an area rich in groundwater, the driver often cannot optimize and adjust the excavation parameters in a timely and accurate manner, which may lead to low excavation efficiency, increased tool wear, increased construction costs, and may even cause engineering accidents, affecting the construction progress and project quality.

[0005] 2. Hysteresis in response to formation changes

[0006] The geological conditions of complex strata are highly uneven and uncertain. During the excavation process, factors such as the hardness, strength, integrity of the strata and groundwater conditions may change at any time. Due to the lack of effective real-time monitoring and prediction methods, the TBM system has a significant lag in responding to stratum changes. Traditional construction methods usually conduct post-analysis and adjustments after problems arise during construction. This passive response method is not only inefficient, but also difficult to fundamentally solve the problem. For example, when the tool is excessively worn due to encountering hard rock, it may have a significant impact on the excavation progress. At this time, replacing the tool will not only increase the construction cost, but also cause construction interruptions and extend the construction period.

[0007] (III) Limitations of existing technologies

[0008] Although there are some technologies and methods for TBM excavation parameter control, most of these methods have certain limitations. Although some traditional mathematical models and empirical formulas can reflect the relationship between excavation parameters and stratum conditions to a certain extent, the accuracy and applicability of these models are greatly limited due to the complexity and diversity of the strata. At the same time, although the existing monitoring technology can obtain some basic construction parameters, it has limited ability to obtain detailed geological information inside the stratum, making it difficult to accurately predict and adjust the excavation parameters in real time. In addition, as tunnel (lane) engineering advances to deeper and more complex strata, the accuracy and real-time requirements for TBM excavation parameter control are getting higher and higher, and the existing technical means can no longer meet the needs of actual engineering.

[0009] In summary, the present application proposes a method for real-time prediction of TBM excavation parameters in complex strata. Summary of the invention

[0010] The purpose of the present invention is to propose a real-time prediction method for TBM excavation parameters in complex strata to address the problem in the background technology that TBM excavation parameters are still mainly operated by the driver based on experience, and the changing rules of the excavation parameters cannot be accurately known, and it is difficult to make timely optimization decisions on the excavation parameters when the geological conditions of the strata change.

[0011] The technical solution of the present invention is a method for real-time prediction of TBM excavation parameters in complex strata, comprising the following steps:

[0012] Data collection and preprocessing:

[0013] Various sensors on the TBM equipment collect operating parameters in real time, including cutterhead speed, penetration, thrust, torque, total thrust, gripper pressure, propulsion speed, current, and power. At the same time, the surrounding rock grade is determined as the geological parameter in combination with the geological survey report and the judgment of the on-site geological engineer;

[0014] The collected data were cleaned, the integrity was checked and the missing data were supplemented by linear interpolation, outliers were identified and removed, and the data were mapped to the [0,1] interval using the maximum-minimum normalization method;

[0015] Model selection and training:

[0016] The SVR and AdaBoost fusion algorithms are used. SVR determines the hyperplane and obtains the decision function by solving a specific optimization problem. AdaBoost trains weak learners by adjusting sample weights and combines them into strong learners.

[0017] First, use SVR for preliminary prediction, then use the SVR prediction results and the original input features as AdaBoost input, divide the data into training set and test set by 90% and 10%, use five-fold cross validation to optimize the SVR hyperparameters and train the model, determine the type and number of AdaBoost weak learners and train them, and finally fuse them to get the prediction model;

[0018] Model prediction and evaluation:

[0019] During the excavation process, parameters are acquired in real time and normalized before being input into the model to obtain real-time prediction values, and the model is dynamically updated using online learning;

[0020] Use the coefficient of determination, mean absolute error, and mean square error to evaluate the prediction effect and draw a comparison curve;

[0021] Application of results and feedback:

[0022] Provide optimization suggestions to drivers based on prediction results, establish a decision support system to comprehensively analyze multiple factors to generate optimization plans and monitor early warnings;

[0023] Collect actual data and compare and analyze the predicted results, optimize and adjust the model, including improving data collection accuracy, adjusting model parameter structure, introducing new variables, and regularly updating and paying attention to new technologies.

[0024] Optionally, the data is being cleaned. During data cleaning, for missing thrust data, the formula Make an estimate supplement, where F t is the thrust value at the missing moment, F t-1 and F t+1 is the thrust value at adjacent moments, and t is the time variable.

[0025] Optionally, in data normalization, the normalization formula for a parameter is x min and x max are the minimum and maximum values ​​of the parameter in the data set, respectively.

[0026] Optionally, the optimization problem solved by SVR is The constraints are

[0027]

[0028] Where w is the normal vector of the hyperplane, b is the intercept, The input data x i The function mapped to the high-dimensional feature space, C is the penalty parameter used to control the complexity of the model and the tolerance to errors, ∈ is the parameter of the insensitive loss function, ξ i and is a slack variable.

[0029] Optionally, the decision function of SVR is

[0030] Among them, α i and is the Lagrange multiplier, K(x i ,x) is the kernel function. Commonly used kernel functions include linear kernel functions Polynomial Kernel Function Where c and d are constants, Gaussian kernel function Where σ is the kernel function parameter.

[0031] Optionally, the sample weight update formula in AdaBoost is in, e t is the error rate of the weak learner on the training set, and are the weights of sample i at the tth and t+1th iterations, y i is the actual value of the sample, h t (x i ) is the prediction value of the tth weak learner for sample i.

[0032] Optionally, in the result application, the excavation parameter decision support system generates an optimization plan based on the formation conditions and construction requirements, using preset rules and algorithms, combined with the model prediction results, construction technology and equipment performance, and issues an early warning when the deviation between the actual parameters and the predicted parameters exceeds the threshold.

[0033] Optionally, in the model feedback improvement, new construction data and geological information can be incorporated into the model when regularly updating and maintaining it, and attention can be paid to the development of new machine learning technologies to improve the performance of the prediction method by increasing the accuracy and frequency of data collection, adjusting model hyperparameters or structure, and introducing new feature variables.

[0034] Optionally, during the data collection process, high-precision sensors are used to monitor the current and power parameters in real time to ensure the accuracy and stability of the data, and the sensors are calibrated regularly.

[0035] Optionally, during the model selection and training process, when SVR uses a Gaussian kernel function, the optimal combination of the Gaussian kernel function parameter σ and the penalty parameter C is determined by cross-validation combined with a grid search method, wherein the parameter range of the grid search is pre-set based on historical data and experience.

[0036] Compared with the prior art, the present invention has at least one of the following beneficial technical effects:

[0037] 1. The present invention accurately predicts the excavation parameters, so that the TBM can be adjusted in time with the changes in the strata. If the rock hardness changes, the cutter head speed and thrust are automatically adjusted, which reduces the downtime adjustment time, provides real-time optimization suggestions for the driver, speeds up the operation decision-making, and increases the effective working time of the equipment. The parameters are adjusted by predicting the changes in the strata in advance, reducing the probability of tool wear and equipment failure, and reducing construction interruptions. For example, if the hard strata are predicted, the tool can be adjusted in advance to avoid damage to the tool, and abnormal warnings can be handled in time to ensure the continuity of construction.

[0038] 2. Real-time prediction and adjustment of parameters ensure the stability of the excavation process, reduce over-excavation and under-excavation, reduce disturbance to the stratum, ensure uniform cross-section of the tunnel (tunnel) and stability of the surrounding rock mass, provide a good foundation for support lining, and improve the tunnel (tunnel) forming quality and overall structural safety. Accurate prediction makes the tunnel (tunnel) excavation profile conform to the design, optimizes lining construction, improves lining durability and waterproof performance, and reduces quality problems such as lining cracks and leakage.

[0039] 3. Reasonable prediction of parameters can reduce tool wear, extend tool life, reduce replacement times and procurement costs, and avoid the time and manpower consumption of frequent tool replacement. Optimizing parameters can make TBM run efficiently, reduce energy consumption, save energy costs such as electricity, and have significant benefits in long-term large-scale projects. Accurate prediction and monitoring can reduce the probability of construction accidents, reduce casualties, equipment damage, and downtime and repair costs, and ensure economic benefits.

[0040] 4. Real-time monitoring and prediction of parameter abnormalities and early warnings to prevent equipment overload and damage and other failures from causing safety accidents, and ensure the safe operation of equipment. Stable excavation and reasonable parameter control reduce the risk of geological disasters such as collapse and water inrush, provide accurate information to support safety management and control, and ensure the safety of construction personnel.

[0041] 5. Use advanced machine learning algorithms to provide new technical means for the industry, promote progress and innovation in construction technology, and enhance the technical level and competitiveness of my country's engineering construction. Establish a decision support system to comprehensively analyze multiple factors to achieve intelligent management, automatically generate plan warnings, reduce manual intervention, and promote the intelligent and automated development of tunnel (lane) construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The figure is a flow chart of a real-time prediction method for TBM excavation parameters in complex strata. DETAILED DESCRIPTION

[0043] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0044] Example 1

[0045] like Figure 1As shown in the figure, the present invention proposes a real-time prediction method for TBM excavation parameters in complex strata, including data collection and preprocessing, model selection and training, model prediction and evaluation, result application and feedback. The steps are described in detail below.

[0046] 1. Data Collection and Preprocessing

[0047] Data collection

[0048] Through various sensors installed on the TBM equipment, the following operating parameters are collected in real time: cutter head speed (n, unit: rpm), penetration (p, unit: mm / rev), thrust (F, unit: kN), torque (T, unit: kN·m), total thrust (F total , unit: kN), gripper pressure (P shoe , unit: MPa), propulsion speed (v, unit: m / min), current (I, unit: ampere), power (P, unit: kilowatt).

[0049] At the same time, combined with the geological survey report and the professional judgment of the on-site geological engineer, the surrounding rock grade (G, discrete values ​​can be used to represent different grades) is determined as a geological parameter.

[0050] Data preprocessing

[0051] Data cleaning:

[0052] Check the integrity of the data to ensure that all parameters have corresponding values. For missing data points, if the adjacent data points in the time series change relatively smoothly, use linear interpolation to supplement them. t , it is known that the thrust data at adjacent moments are F t-1 and F t+1 , then by the formula Perform estimation supplement, where t is the time variable.

[0053] Identify and eliminate outliers. Set a reasonable threshold range and treat data outside this range as outliers. For thrust F, according to the performance parameters of the equipment and previous construction experience, set the normal thrust range to [F min ,F max ], if the thrust value F collected at a certain moment i Satisfy F i <F min or F i >F max , then remove the data point.

[0054] Data normalization:

[0055] The maximum-minimum normalization method is used to map each parameter data to the [0,1] interval to eliminate the influence of different parameter dimensions and facilitate the training and calculation of subsequent models. For a certain parameter x, cutter head speed n, the normalization formula is:

[0056]

[0057] Among them, x min and x max are the minimum and maximum values ​​of the parameter in the data set, respectively.

[0058] 2. Model Selection and Training

[0059] Model selection

[0060] This scheme adopts the algorithm of SVR (support vector machine) and AdaBoost fusion to predict the excavation parameters.

[0061] Support vector machine (SVR) principle:

[0062] The basic idea of ​​SVR is to find an optimal hyperplane in the feature space so that the distance from the sample point to the hyperplane is maximized. For a given training data set {(x i ,y i )},i=1,2,…,n, where x i is the input feature vector, which is a vector composed of operating parameters and geological parameters in this embodiment, i is the corresponding target output, which includes tunneling parameters such as thrust and cutterhead speed. SVR determines the hyperplane by solving the following optimization problem:

[0063]

[0064] subject to

[0065]

[0066] Where w is the normal vector of the hyperplane, b is the intercept, The input data x i The function mapped to the high-dimensional feature space, C is the penalty parameter used to control the complexity of the model and the tolerance to errors, ∈ is the parameter of the insensitive loss function, ξ i and is a slack variable used to handle noise and outliers in the data.

[0067] After solving the above optimization problem, the decision function is obtained:

[0068]

[0069] Among them, α i and is the Lagrange multiplier, K(x i ,x) is the kernel function. Commonly used kernel functions include linear kernel functions Polynomial Kernel Function Where c and d are constants, Gaussian kernel function Wherein σ is a kernel function parameter. In this embodiment, a suitable kernel function is selected according to actual data conditions.

[0070] AdaBoost principle:

[0071] AdaBoost is an iterative ensemble learning algorithm that trains a series of weak learners (usually simple classifiers or regressors) by continuously adjusting the weights of training samples and combining these weak learners into a strong learner. i ,y i )}, i = 1, 2, ..., n, initially assigning the same weight to each sample In each iteration, a weak learner h is trained t , and then according to the error rate e of the weak learner on the training set t To update the sample weights:

[0072]

[0073] Where I(.) is an indicator function, which is 1 when the condition is met and 0 otherwise.

[0074] The sample weight update formula is:

[0075]

[0076] in, is the weight coefficient of the weak learner.

[0077] Finally, multiple weak learners are combined into a strong learner:

[0078]

[0079] Among them, T is the number of iterations, that is, the number of weak learners.

[0080] Fusion strategy:

[0081] First, use SVR to make a preliminary prediction of the excavation parameters and obtain the prediction results Then, Together with the original input feature vector x, it is used as the input feature of AdaBoost. AdaBoost further optimizes and adjusts the prediction results of SVR based on multiple weak learners to obtain the final prediction results.

[0082] Dataset Partitioning

[0083] The preprocessed data is divided into a training set and a test set at a ratio of 90% and 10% respectively. The training set is used for model training and parameter adjustment, and the test set is used to evaluate the generalization ability and prediction effect of the model.

[0084] Training process

[0085] SVR Training:

[0086] Select a suitable kernel function (such as a Gaussian kernel function) and determine the initial value range of the kernel function parameter σ and the penalty parameter C.

[0087] Five-fold cross validation is used to optimize hyperparameters. The training set is divided into five parts, and four of them are selected as training subsets and one as validation subset each time. The SVR model is trained on the training subset, and the model performance is evaluated on the validation subset. By continuously adjusting the kernel function parameter σ and the penalty parameter C, the performance of the model on the validation set is optimized. The specific evaluation indicators can be the mean square error (MSE) or the mean absolute error (MAE).

[0088] For a selected set of hyperparameter values, the entire training set is used for model training to obtain a trained SVR model.

[0089] AdaBoost training:

[0090] Determine the type of weak learners (such as decision tree) and the initial value range of the number T of weak learners.

[0091] The prediction results of SVR and the original input feature vector x as input, and the sample weights are initialized as n is the number of training samples.

[0092] Perform iterative training:

[0093] In each iteration, a weak learner h is trained according to the current sample weight t .

[0094] Calculate the error rate e of the weak learner on the training set t , and calculate the weight coefficient α of the weak learner according to the error rate t .

[0095] Using the formula Update sample weights to prepare for the next iteration.

[0096] After T iterations, the trained AdaBoost model is obtained.

[0097] SVR and AdaBoost fusion:

[0098] The trained SVR model and AdaBoost model are combined to obtain the final prediction model. When predicting, the real-time collected operating parameters and geological parameters are first input into the SVR model to obtain the preliminary prediction results. Then The original input features are input into the AdaBoost model to obtain the final tunneling parameter prediction results.

[0099] 3. Model prediction and evaluation

[0100] Real-time prediction

[0101] During the TBM excavation process, the current operating parameters and geological parameters are obtained in real time. After being normalized by data preprocessing, they are input into the trained prediction model to obtain the real-time prediction values ​​of the main TBM excavation parameters, including cutter head speed and thrust.

[0102] In order to adapt to the changes in ground conditions and equipment operating status during the excavation process, the model is dynamically updated using online learning. When new data is generated, it is added to the training set, and the model is retrained and adjusted at a certain time interval or data accumulation level to ensure the real-time and accuracy of the model.

[0103] Prediction effect evaluation

[0104] The following indicators are used to evaluate the prediction effect of the model:

[0105] Coefficient of determination (R 2 ):

[0106]

[0107] Among them, y i is the actual value, is the predicted value, is the average of the actual values. 2 The value range is between [0,1]. The closer it is to 1, the better the model fits the data and the stronger its predictive ability.

[0108] Mean Absolute Error (MAE):

[0109]

[0110] MAE represents the average absolute error between the predicted value and the actual value. The smaller the value, the more accurate the prediction.

[0111] Mean Squared Error (MSE):

[0112]

[0113] MSE reflects the square mean of the error between the predicted value and the actual value. Similarly, the smaller the value, the better the model performance.

[0114] Evaluate the model on the test set and calculate the values ​​of the above evaluation indicators. At the same time, draw a comparison curve between the predicted value and the actual value to intuitively show the prediction effect of the model on different data points. By analyzing the evaluation indicators and comparison curves, comprehensively evaluate the accuracy, stability and generalization ability of the model.

[0115] IV. Application of Results and Feedback

[0116] Optimization decision of tunneling parameters

[0117] Based on the excavation parameter values ​​predicted by the model, combined with the actual project situation and construction experience, the optimized excavation parameter suggestions are provided to the TBM driver. When the formation hardness is predicted to increase, the thrust and cutter head speed are automatically adjusted to a reasonable range according to the equipment performance and previous construction data to ensure excavation efficiency and tool life. This function is achieved by setting the corresponding parameter warning and automatic adjustment mechanism in the TBM control system.

[0118] Establish a tunneling parameter decision support system, which comprehensively analyzes the model prediction results with construction technology, equipment performance and other factors. The system generates corresponding tunneling parameter optimization solutions based on different stratum conditions and construction requirements using pre-set rules and algorithms. At the same time, the system monitors parameter changes during tunneling in real time. When the deviation between the actual parameters and the predicted parameters exceeds a certain threshold, it issues an adjustment warning in a timely manner, providing a decision-making basis for construction management personnel so that they can take timely measures to make adjustments.

[0119] Feedback and Improvement

[0120] During the actual construction process, we continuously collected the actual excavation parameters and construction effect data of the TBM and compared and analyzed them with the model prediction results. Based on the actual feedback, we deeply analyzed the source and distribution characteristics of the model prediction error and found out the possible problems, including data collection errors, unreasonable model structure, and insufficient consideration of the complexity of stratum changes.

[0121] Based on the feedback analysis results, the model is further optimized and adjusted. The accuracy and frequency of data collection are increased, the hyperparameters or structure of the model are adjusted, and new characteristic variables are introduced to better reflect the actual conditions of the formation and equipment. At the same time, the model is regularly updated and maintained, and new construction data and geological information are incorporated into the model training to adapt to changes in different engineering sites and formation conditions. In addition, we closely follow the development of new algorithms and technologies in the field of machine learning, and promptly introduce advanced methods and technologies into TBM excavation parameter prediction, continuously improve the performance and accuracy of the prediction method, and achieve continuous improvement and innovation of the method.

[0122] The present invention can enable the TBM to always maintain the best working state under different formation conditions by accurately predicting the excavation parameters, including the cutterhead speed and thrust. When encountering complex formation changes, the system can adjust the parameters in time to avoid low excavation efficiency caused by unreasonable parameters. When the rock hardness increases, the thrust is automatically increased and the cutterhead speed is appropriately reduced to ensure the smooth progress of excavation, reduce unnecessary downtime and adjustment time, and thus improve the overall excavation efficiency. Provide real-time optimization suggestions for TBM drivers, so that drivers can quickly make correct operational decisions without having to rely on experience to explore and try, which greatly shortens the time for parameter adjustment, increases the effective working time of the equipment, and thus improves construction efficiency.

[0123] Among them, accurate parameter prediction can effectively reduce construction interruptions caused by excessive tool wear, equipment failure, etc. By predicting stratum changes in advance and adjusting parameters, the wear rate of key components such as tools can be reduced and their service life can be extended. When it is predicted that hard strata will be entered, the thrust and speed can be adjusted in advance to reduce the impact load of the tool, avoid sudden damage to the tool and cause construction interruptions, ensure construction continuity, and improve construction efficiency.

[0124] In addition, it can promptly detect abnormal conditions in equipment operation, such as excessive thrust and abnormal torque, and notify construction personnel in advance through the early warning system to handle them, thus avoiding long-term downtime for maintenance due to the deterioration of the problem and reducing the impact of construction interruptions on the construction period.

[0125] In this embodiment, real-time prediction and adjustment of excavation parameters help maintain the stability of the excavation process. Stable cutterhead speed, thrust and torque parameters can make the excavation of the tunnel (lane) section more uniform and reduce the occurrence of over-excavation and under-excavation. In soft rock formations, by accurately controlling the thrust and speed, excessive disturbance of the rock mass around the tunnel (lane) due to excessive thrust can be avoided, thereby ensuring the forming quality of the tunnel (lane). A stable excavation process can also reduce the disturbance to the formation, reduce the risk of formation deformation and collapse, provide good basic conditions for subsequent support and lining work, and ensure the quality of the entire tunnel (lane) project. Accurate prediction of excavation parameters can make the excavation profile of the tunnel (lane) more in line with the design requirements, thereby improving the construction quality of the tunnel (lane) lining. When the cross-sectional dimensions of the tunnel (lane) are accurate, the amount of lining material can be more reasonable, and the force of the lining structure is more uniform, which can effectively improve the durability and waterproof performance of the lining. Reduce quality problems such as tunnel (tunnel) lining cracks and leakage caused by unstable excavation process, improve the overall waterproofness and structural safety of the tunnel (tunnel), and ensure the long-term stability of project quality.

[0126] It is worth noting that, in this embodiment, by reasonably predicting the excavation parameters and optimizing the use of the cutter according to the formation conditions, the wear of the cutter can be significantly reduced. The thrust and speed are adjusted at the right time to avoid excessive wear of the cutter in hard rock and extend the service life of the cutter. The number of tool changes is reduced, and the cost of tool purchase and replacement is reduced. Tool replacement not only takes a lot of time and manpower, but also the purchase cost of new cutters is high. Accurate parameter prediction can effectively reduce this part of the cost and improve the economic benefits of construction. The optimized excavation parameters make the operation of TBM equipment more efficient and reduce energy waste. By accurately controlling the cutter head speed and thrust, the equipment can operate at the lowest energy consumption under the premise of meeting the excavation requirements. Reducing energy costs such as power consumption during construction. In the long run, for large-scale tunnel (lane) engineering, the reduction in energy costs will be a considerable cost saving, which will help reduce the overall construction cost. Accurate parameter prediction and real-time monitoring can effectively reduce the probability of construction accidents. Construction accidents not only cause casualties and equipment damage, but also cause project shutdowns and additional repair costs. Through the application of this method, accidents can be prevented and avoided in advance, the huge cost losses caused by accidents can be reduced, and the smooth progress of construction and economic benefits can be guaranteed.

[0127] Furthermore, the operating parameters of TBM equipment, such as torque, thrust, and current, can be monitored and predicted in real time. When abnormal changes occur in the parameters, they can be detected and warned in time. When the torque suddenly increases, it may indicate that the tool is stuck or the formation is abnormally hard. The system will issue a warning in time, and the construction personnel can take corresponding measures to avoid damage to the equipment due to overload, thereby preventing safety accidents caused by equipment failure. Through accurate prediction and control of excavation parameters, the TBM equipment can be ensured to operate within a safe working range, reduce the threat to the life safety of construction personnel caused by equipment failure and accidents, and improve the overall safety of the construction site.

[0128] This method uses advanced machine learning algorithms, SVR and AdaBoost fusion, to provide a new technical means for TBM excavation parameter prediction. This technological innovation can not only be applied to the field of TBM construction, but also provide reference and reference for other similar engineering construction, and promote the technological progress of the entire engineering construction industry. It is encouraged to continuously explore and apply new technologies and methods during the construction process, promote the continuous innovation and development of construction technology, and improve my country's technical level and international competitiveness in the field of infrastructure construction such as tunnel (tunnel) engineering. By establishing an excavation parameter decision support system, the model prediction results are comprehensively analyzed with multiple factors such as construction technology and equipment performance, and the intelligent management of TBM construction is realized. The system can automatically generate optimization plans and adjust warnings based on real-time data, reduce the uncertainty of manual intervention, and improve the scientificity and accuracy of construction management. It lays the foundation for realizing the intelligent control of the whole process of tunnel (tunnel) construction, helps to improve construction efficiency, quality and safety, and promotes the development of tunnel (tunnel) construction towards intelligence and automation, which is in line with the development trend of future engineering construction.

[0129] The above specific embodiments are only several optional embodiments of the present invention. Based on the technical solutions of the present invention and the relevant inspirations of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

Claims

1. A real-time prediction method for TBM excavation parameters in complex strata, characterized in that: The following steps are involved: Data collection and preprocessing: Various sensors on the TBM equipment collect operating parameters in real time, including cutterhead speed, penetration, thrust, torque, total thrust, gripper pressure, propulsion speed, current, and power. At the same time, the surrounding rock grade is determined as the geological parameter in combination with the geological survey report and the judgment of the on-site geological engineer; The collected data were cleaned, the integrity was checked and the missing data were supplemented by linear interpolation, outliers were identified and removed, and the data were mapped to the [0,1] interval using the maximum-minimum normalization method; Model selection and training: The SVR and AdaBoost fusion algorithms are used. SVR determines the hyperplane and obtains the decision function by solving a specific optimization problem. AdaBoost trains weak learners by adjusting sample weights and combines them into strong learners. First, use SVR for preliminary prediction, then use the SVR prediction results and the original input features as AdaBoost input, divide the data into training set and test set by 90% and 10%, use five-fold cross validation to optimize the SVR hyperparameters and train the model, determine the type and number of AdaBoost weak learners and train them, and finally fuse them to get the prediction model; Model prediction and evaluation: During the excavation process, parameters are acquired in real time and normalized before being input into the model to obtain real-time prediction values, and the model is dynamically updated using online learning; Use the coefficient of determination, mean absolute error, and mean square error to evaluate the prediction effect and draw a comparison curve; Application of results and feedback: Provide optimization suggestions to drivers based on prediction results, establish a decision support system to comprehensively analyze multiple factors to generate optimization plans and monitor early warnings; Collect actual data and compare and analyze the predicted results, optimize and adjust the model, including improving data collection accuracy, adjusting model parameter structure, introducing new variables, and regularly updating and paying attention to new technologies.

2. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: The data is being cleaned. During data cleaning, for the missing thrust data, the formula is used Make an estimate supplement, where F t is the thrust value at the missing moment, F t-1 and F t+1 is the thrust value at adjacent moments, and t is the time variable.

3. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1 is characterized in that: In data normalization, the normalization formula for a parameter is x min and x max are the minimum and maximum values ​​of the parameter in the data set, respectively.

4. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: The optimization problem solved by SVR is The constraints are Where w is the normal vector of the hyperplane, b is the intercept, The input data x i The function mapped to the high-dimensional feature space, C is the penalty parameter used to control the complexity of the model and the tolerance to errors, ∈ is the parameter of the insensitive loss function, ξ i and is a slack variable.

5. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1 is characterized in that: The decision function of SVR is Among them, α i and is the Lagrange multiplier, K(x i ,x) is the kernel function. Commonly used kernel functions include linear kernel functions Polynomial Kernel Function Where c and d are constants, Gaussian kernel function Where σ is the kernel function parameter.

6. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: The sample weight update formula in AdaBoost is: in, e t is the error rate of the weak learner on the training set, and are the weights of sample i at the tth and t+1th iterations, y i is the actual value of the sample, h t (x i ) is the prediction value of the tth weak learner for sample i.

7. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: In the application of the results, the excavation parameter decision support system generates an optimization plan based on the formation conditions and construction requirements, using preset rules and algorithms, combined with the model prediction results, construction technology and equipment performance, and issues an early warning when the deviation between the actual parameters and the predicted parameters exceeds the threshold.

8. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: In the model feedback improvement, new construction data and geological information are incorporated into the regular update and maintenance of the model, attention is paid to the development of new machine learning technologies, and the performance of the prediction method is improved by increasing the accuracy and frequency of data collection, adjusting model hyperparameters or structure, and introducing new feature variables.

9. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: During the data collection process, high-precision sensors are used to monitor the current and power parameters in real time to ensure the accuracy and stability of the data, and the sensors are calibrated regularly.

10. The method for real-time prediction of TBM excavation parameters in complex strata according to claim 1, characterized in that: In the model selection and training process, when SVR uses a Gaussian kernel function, the optimal combination of the Gaussian kernel function parameter σ and the penalty parameter C is determined by cross-validation combined with a grid search method, wherein the parameter range of the grid search is pre-set based on historical data and experience.

Images