A shield tunneling mud cake blockage prediction method, system, terminal and storage medium

Abstract

The application discloses a kind of shield tunneling mud cake jam prediction method, system, terminal and storage medium, the method includes: obtaining the low-fidelity data of target tunnel, according to low-fidelity data training low-fidelity neural network obtains low-fidelity model;High-fidelity data is obtained, and input to low-fidelity model and output low-fidelity predicted value;High-fidelity data and low-fidelity predicted value are fused to obtain extended input data, and high-fidelity residual network is trained to obtain high-fidelity residual model, and according to low-fidelity model and high-fidelity residual model obtains target multi-fidelity model;The shield tunneling data of target tunnel is obtained, input to target multi-fidelity model and output mud cake jam risk prediction result.The application is initially modeled by using low-fidelity data, reduces the dependence on high-fidelity data, reduces data processing cost, also improves model prediction accuracy by active learning strategy, to improve the accuracy of mud cake jam risk prediction.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a shield tunneling mud cake blockage prediction method, system, terminal and computer-readable storage medium. Background Art

[0002] Shield tunneling technology, with its efficient and continuous construction capabilities, has become a mainstream method in modern tunnel construction. However, mud cake blockage during shield tunneling remains a major bottleneck hindering project progress and safety. Mud cake blockage not only significantly reduces construction efficiency and prolongs project duration, but can also cause construction interruptions, equipment failures, and serious safety incidents.

[0003] Currently, there are two main methods for predicting mud cake blockage risks: one is a model trained based on high-fidelity data (actual shield tunneling data where the "mud cake" phenomenon occurs). This type of method can more accurately reflect the actual working conditions on site. However, due to the high cost and difficulty of collecting high-fidelity data and the limited number of samples, the model is not stable enough when faced with complex and dynamic construction environments. The other is a simulation model built based on low-fidelity data. Although this type of method can quickly establish a model using low-fidelity data and has low data collection costs, due to the large differences between low-fidelity data and actual working conditions, its prediction results are often insufficiently accurate and difficult to meet the actual needs of the project.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the Invention

[0005] The main purpose of the present invention is to provide a shield tunneling mud cake blockage prediction method, system, terminal and storage medium, aiming to solve the problems that the existing technology based on high-fidelity data training models are not stable enough when facing complex and dynamic construction environments; the models based on low-fidelity data training often have insufficient prediction accuracy and are difficult to meet the actual needs of the project.

[0006] To achieve the above object, the present invention provides a method for predicting mud cake blockage in shield tunneling, which comprises the following steps:

[0007] Obtaining low-fidelity data of a target tunnel, and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model;

[0008] Acquiring high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value;

[0009] Fusing the high-fidelity data with the low-fidelity prediction value to obtain extended input data, training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model;

[0010] Shield excavation data of the target tunnel is obtained, the shield excavation data is input into the target multi-fidelity model, and a mud cake blockage risk prediction result is output.

[0011] Optionally, the shield tunneling mud cake blockage prediction method, wherein the step of obtaining low-fidelity data of the target tunnel and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model, specifically includes:

[0012] Obtaining a shield mud cake risk map of a target tunnel, performing data conversion on key parameters of the shield mud cake risk map to obtain characteristic parameters;

[0013] Performing feature simulation on the feature parameters to obtain engineering feature parameters, and combining the feature parameters with the engineering feature parameters to obtain low-fidelity data;

[0014] A low-fidelity neural network is constructed, and the low-fidelity neural network is iteratively trained according to the low-fidelity data. If the number of iterations of the low-fidelity neural network reaches a first preset number, it is determined that the low-fidelity neural network has completed training, thereby obtaining a low-fidelity model.

[0015] Optionally, the shield tunneling mud cake blockage prediction method, wherein the step of obtaining high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value, specifically includes:

[0016] Acquiring geological drilling data along the tunnel of the target tunnel and operating parameters of a shield machine, and performing normalization processing and outlier extraction processing on the geological drilling data along the tunnel and the operating parameters to obtain high-fidelity data;

[0017] The high-fidelity data is input into the low-fidelity model, and a preliminary prediction of the mud cake blockage probability is performed on the high-fidelity data to obtain a low-fidelity prediction value.

[0018] Optionally, the shield tunneling mud cake blockage prediction method, wherein the high-fidelity data is fused with the low-fidelity prediction value to obtain extended input data, and a corresponding high-fidelity residual network is trained based on the extended input data to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained based on the low-fidelity model and the high-fidelity residual model, specifically includes:

[0019] Obtaining data features of the low-fidelity prediction value, concatenating the data features with various input features of the high-fidelity data to obtain a target feature vector, and obtaining extended input data based on the target feature vector;

[0020] Dividing the extended input data according to a preset ratio to obtain an initial training set and an unseen high-fidelity data set, and performing model training on a high-fidelity residual network based on the initial training set to obtain an initial high-fidelity residual model;

[0021] Inputting the unseen high-fidelity data set into the initial high-fidelity residual model, and performing multiple predictions on the unseen high-fidelity data set according to a Monte Carlo random dropout method to obtain multiple prediction residuals, calculating the mean of all the prediction residuals, and calculating the corresponding variance based on the mean;

[0022] sorting the data samples of the unseen high-fidelity data set according to the variance to obtain a sorting result, and extracting samples from the sorting result according to a variance threshold to obtain a target data sample;

[0023] The target data sample is combined with the initial training set according to a sampling strategy with replacement to obtain a new target training set, and the high-fidelity residual network is model trained according to the new target training set to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained based on the low-fidelity model and the high-fidelity residual model.

[0024] Optionally, the shield tunneling mud cake blockage prediction method, wherein the high-fidelity residual network is trained according to the new target training set to obtain a high-fidelity residual model, and a target high-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, specifically includes:

[0025] Iteratively training the high-fidelity residual network according to the new target training set, and if the number of iterations of the high-fidelity residual network reaches a second preset number, determining that the high-fidelity residual network has completed training, thereby obtaining a high-fidelity residual model;

[0026] Adding the low-fidelity prediction value to all the prediction residuals to obtain a multi-fidelity prediction value, and performing fitting correction on the multi-fidelity prediction value according to a correction formula to obtain a final prediction result;

[0027] A multi-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, and parameters of the multi-fidelity model are corrected according to the final prediction result to obtain a target multi-fidelity model.

[0028] Optionally, in the shield tunneling mud cake blockage prediction method, the correction formula is:

[0029] ;

[0030] in, For the final prediction result, is the predicted probability output by the low-fidelity model, is the probability residual output by the high-fidelity residual network, and All are linear regression correction coefficients.

[0031] Optionally, the shield tunneling mud cake blockage prediction method, wherein the shield tunneling data of the target tunnel is obtained, the shield tunneling data is input into the target multi-fidelity model, and the mud cake blockage risk prediction result is output, further comprising:

[0032] If the predicted probability of the mud cake blockage risk prediction result is less than the preset probability, it is determined that the target tunnel does not have the mud cake blockage risk;

[0033] If the predicted probability of the mud cake blockage risk prediction result is greater than or equal to the preset probability, it is determined that the target tunnel has a mud cake blockage risk, and a risk warning signal is generated to alert corresponding construction personnel.

[0034] Optionally, in the shield tunneling mud cake blockage prediction method, the shield tunneling mud cake blockage prediction system includes:

[0035] a first model training module, configured to obtain low-fidelity data of a target tunnel, and train a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model;

[0036] a data prediction module, configured to obtain high-fidelity data of the target tunnel, input the high-fidelity data into the low-fidelity model, and output a low-fidelity prediction value;

[0037] a second model training module, configured to fuse the high-fidelity data with the low-fidelity prediction values ​​to obtain extended input data, train a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtain a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model;

[0038] The risk prediction module is used to obtain shield tunneling data of the target tunnel, input the shield tunneling data into the target multi-fidelity model, and output a mud cake blockage risk prediction result.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a shield tunneling mud cake blockage prediction program stored on the memory and runnable on the processor, and when the shield tunneling mud cake blockage prediction program is executed by the processor, the steps of the shield tunneling mud cake blockage prediction method described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a shield tunneling mud cake blockage prediction program, and when the shield tunneling mud cake blockage prediction program is executed by the processor, the steps of the shield tunneling mud cake blockage prediction method as described above are implemented.

[0041] In the present invention, low-fidelity data of the target tunnel is obtained, and a low-fidelity neural network is trained based on the low-fidelity data to obtain a low-fidelity model; high-fidelity data of the target tunnel is obtained, and the high-fidelity data is input into the low-fidelity model to output a low-fidelity prediction value; the high-fidelity data and the low-fidelity prediction value are fused to obtain extended input data, and a corresponding high-fidelity residual network is trained based on the extended input data to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained based on the low-fidelity model and the high-fidelity residual model; shield excavation data of the target tunnel is obtained, and the shield excavation data is input into the target multi-fidelity model to output a mud cake blockage risk prediction result. The present invention uses low-fidelity data for preliminary modeling, reducing reliance on high-fidelity data and lowering data acquisition and processing costs. It also accelerates model convergence through an active learning strategy and uses a residual network to correct model deficiencies to improve model prediction accuracy, thereby improving the accuracy of mudcake blockage risk prediction. It uses the MCD (Monte-Carlo Dropout) method to quantify prediction uncertainty and combines it with an active learning strategy to dynamically update the training set, effectively capturing rare mudcake blockage samples and enhancing the model's ability to recognize minority class samples. It also uses low-fidelity data for preliminary modeling, reducing reliance on high-fidelity data and lowering data acquisition and processing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a preferred embodiment of the shield tunneling mud cake blockage prediction method of the present invention;

[0043] Figure 2 Schematic diagram of shield mud cake blockage risk in the shield tunneling mud cake blockage prediction method of the present invention;

[0044] Figure 3 This is a structural diagram of a preferred embodiment of the shield tunneling mud cake blockage prediction system of the present invention;

[0045] Figure 4Schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), such directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0048] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features specified as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that ordinary technicians in this field can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0049] The shield tunneling mud cake blockage prediction method described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the shield tunneling mud cake blockage prediction method includes the following steps:

[0050] Step S10: Obtain low-fidelity data of the target tunnel, and train a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model.

[0051] The step S10 includes:

[0052] Step S11: obtaining a shield mud cake risk map of a target tunnel, performing data conversion on key parameters of the shield mud cake risk map to obtain characteristic parameters;

[0053] Step S12: performing feature simulation on the feature parameters to obtain engineering feature parameters, and combining the feature parameters with the engineering feature parameters to obtain low-fidelity data;

[0054] Step S13, constructing a low-fidelity neural network, iteratively training the low-fidelity neural network according to the low-fidelity data, and if the number of iterations of the low-fidelity neural network reaches a first preset number, determining that the low-fidelity neural network is trained and obtaining a low-fidelity model.

[0055] Specifically, in the embodiments of the present application, in order to solve the problems that the existing prediction method based on high-fidelity data has insufficient generalization ability in actual application due to high data acquisition cost and limited sample size, and the model based on low-fidelity data has insufficient precision, and the traditional model is difficult to capture the key minority class information because the mud cake blocking event accounts for a very low proportion in the overall data. Therefore, the present application aims to fuse the advantages of low-fidelity data and high-fidelity data, and introduce MCD (Monte-Carlo Dropout, Monte-Carlo Dropout) assisted active learning strategy, significantly improve the accuracy and robustness of mud cake blocking risk prediction, reduce the data acquisition cost, meet the actual needs of shield tunneling construction safety and efficiency, specifically, first, use the existing empirical formula, risk map and kernel density estimation method to generate low-fidelity data, wherein the low-fidelity data refers to data with lower quality, lower precision or incomplete data, such data usually contains noise, error or information loss, and may not completely and accurately reflect the true situation, the generation of low-fidelity data is based on the characteristic parameters summarized in the shield mud cake risk map, and the shield mud cake risk map is as shown in Figure 2 Figure 2 Ic in the above formula represents the viscosity index of the soil, Ip represents the plasticity index of the soil, and by converting the key parameters in the shield mud cake risk map into numerical form, the characteristic parameters (i.e. plastic limit-water content and liquid limit-water content) are generated; then, other characteristics (i.e. engineering characteristic parameters) consistent with the actual engineering characteristics are simulated and generated by the KDE (Kernel Density Estimation, Kernel Density Estimation) method, such as cutter head speed, cutter head torque, total thrust and penetration, etc., and finally a complete low-fidelity data is formed.

[0056] After obtaining the low-fidelity data, the low-fidelity neural network is trained according to the low-fidelity data, the low-fidelity data is used as input, and the MLP (Multi-Layer Perceptron, Multi-Layer Perceptron) regression type neural network (6x64x128x32x1 network structure) is used for training. In the training, the mean square error is used as the loss function, the optimizer is selected as Adam, the learning rate is set to 0.001, and the number of training iterations is 200. After training, the low-fidelity neural network model can output the probability of mud cake blocking, i.e. the low-fidelity prediction value.

[0057] ​Step S20: Acquire high-fidelity data of the target tunnel, input the high-fidelity data into the low-fidelity model, and output a low-fidelity prediction value.

[0058] The step S20 includes:

[0059] Step S21: obtaining geological drilling data along the tunnel of the target tunnel and operating parameters of the shield machine, and performing normalization processing and outlier extraction processing on the geological drilling data along the tunnel and the operating parameters to obtain high-fidelity data;

[0060] Step S22: input the high-fidelity data into the low-fidelity model, perform a preliminary prediction of the mud cake blockage probability on the high-fidelity data, and obtain a low-fidelity prediction value.

[0061] Specifically, in an embodiment of the present invention, after obtaining a low-fidelity model, high-fidelity data actually collected at the shield tunneling site needs to be input into the low-fidelity model to obtain a low-fidelity prediction value. The corresponding high-fidelity data acquisition process is specifically as follows: geological drilling data along the tunnel of the target tunnel (for example, plastic limit, liquid limit, water content, etc.) and operating parameters of the shield machine (for example, cutterhead speed, cutterhead torque, total thrust, penetration, etc.) are obtained, and the geological drilling data along the tunnel and the operating parameters are normalized and outlier extracted to obtain high-fidelity data; then, the high-fidelity data is input into the low-fidelity model, and a preliminary prediction of the mud cake blockage probability is performed on the high-fidelity data to obtain a low-fidelity prediction value, which is used as a preliminary estimate of the mud cake blockage probability.

[0062] Step S30: Fusing the high-fidelity data with the low-fidelity prediction value to obtain extended input data, and training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model.

[0063] The step S30 includes:

[0064] Step S31: obtaining data features of the low-fidelity prediction value, concatenating the data features with various input features of the high-fidelity data to obtain a target feature vector, and obtaining extended input data based on the target feature vector;

[0065] Step S32: partitioning the extended input data according to a preset ratio to obtain an initial training set and an unseen high-fidelity data set, and performing model training on a high-fidelity residual network based on the initial training set to obtain an initial high-fidelity residual model;

[0066] Step S33, inputting the unseen high-fidelity dataset into the initial high-fidelity residual model, and performing multiple predictions on the unseen high-fidelity dataset according to a Monte Carlo random discard method to obtain multiple predicted residuals, calculating the mean of all the predicted residuals, and calculating the corresponding variance according to the mean;

[0067] Step S34, performing uncertainty sorting on the data samples of the unseen high-fidelity dataset according to the variance to obtain a sorting result, and performing sample extraction on the sorting result according to a variance threshold to obtain target data samples;

[0068] Step S35, combining the target data samples with the initial training set according to a sampling-with-replacement strategy to obtain a new target training set, performing model training on the high-fidelity residual network according to the new target training set to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model according to the low-fidelity model and the high-fidelity residual model.

[0069] Specifically, after obtaining the low-fidelity predicted value, it is necessary to fuse the low-fidelity predicted value with the high-fidelity data to form extended input data. In the embodiment of the present application, a feature splicing method is adopted, that is, the data features of the low-fidelity predicted value are obtained, the data features are spliced with each input feature of the high-fidelity data to obtain a target feature vector, and the extended input data is obtained according to the target feature vector. The input features in the fused extended input data are the combination of the features of the high-fidelity data and the low-fidelity predicted value, and the output features are the target features of the high-fidelity data minus the low-fidelity predicted value. Then, the high-fidelity residual network is trained based on the extended input data to learn the residual between the low-fidelity predicted value and the actual high-fidelity data, and a high-fidelity residual model is obtained.

[0070] In this training process, the MCD method is used to perform multiple inferences on samples in high-fidelity data, calculate the mean and variance of the predicted output, actively select samples with higher uncertainty based on the uncertainty index to update the training set, and repeatedly train the high-fidelity residual network. Specifically, the extended input data used for high-fidelity residual model training is divided into an initial training set and an unseen high-fidelity data set according to a preset ratio, wherein the initial training set is used for the preliminary training of the high-fidelity residual network, and the unseen high-fidelity data set is used for active learning and updating; first, the initial training set is used for training The high-fidelity residual network is trained according to the initial training set to obtain an initial high-fidelity residual model. Subsequently, the initial high-fidelity residual model is used to predict samples in the unseen high-fidelity dataset. Specifically, the same input sample in the unseen high-fidelity dataset is predicted T times (for example, 10 times) by using the Monte Carlo random dropout method, and the mean and variance of the T-times prediction output are calculated, and the variance is used as an indicator to measure the uncertainty of the prediction; then, the data samples of the unseen high-fidelity dataset are predicted according to the variance. Uncertainty sorting is performed to obtain a sorting result, and sample extraction is performed on the sorting result according to a variance threshold in order to select a certain proportion of samples with larger variance to obtain a target data sample, i.e., a data sample with the highest uncertainty, and a sampling strategy with replacement is adopted to add it to the initial training set, i.e., the target data sample is combined with the initial training set to obtain a new target training set; and model training is performed on the high-fidelity residual network according to the new target training set until the initial high-fidelity residual model reaches a second preset number of training times, then the high-fidelity residual network is determined to have completed training, and a high-fidelity residual model is obtained; finally, the low-fidelity prediction value is added to all the prediction residuals to obtain a multi-fidelity prediction value. In order to further improve the prediction accuracy, the multi-fidelity prediction value is fitted and corrected by linear regression. Specifically, the multi-fidelity prediction value is fitted and corrected according to a correction formula to obtain a final prediction result, a multi-fidelity model is obtained based on the low-fidelity model and the high-fidelity residual model, and the parameters of the multi-fidelity model are corrected according to the final prediction result to obtain a target multi-fidelity model.

[0071] Wherein, the correction formula is: ;in, For the final prediction result, is the predicted probability output by the low-fidelity model, is the probability residual output by the high-fidelity residual network, and All are linear regression correction coefficients.

[0072] Step S40: Acquire shield tunneling data of the target tunnel, input the shield tunneling data into the target multi-fidelity model, and output a mud cake blockage risk prediction result.

[0073] Specifically, in an embodiment of the present invention, the trained target multi-fidelity model is used to predict new data collected in real time at the shield tunneling site, and output the probability of mud cake blockage. Specifically, the shield tunneling data of the target tunnel is obtained, the shield tunneling data is input into the target multi-fidelity model, and the mud cake blockage risk prediction result is output.

[0074] Furthermore, if the predicted probability of the mud cake blockage risk prediction result is less than a preset probability (e.g., 50%), it is determined that the target tunnel does not have a mud cake blockage risk; if the predicted probability of the mud cake blockage risk prediction result is greater than or equal to the preset probability, it is determined that the target tunnel does have a mud cake blockage risk, and a risk warning signal is generated to alert the corresponding construction personnel, thereby providing timely decision support for the construction site and ensuring construction safety and efficiency. The present invention uses low-fidelity data for preliminary modeling, reducing reliance on high-fidelity data and lowering data acquisition and processing costs. It also accelerates model convergence through an active learning strategy and uses a residual network to correct model deficiencies to improve the model's prediction accuracy, thereby improving the accuracy of mud cake blockage risk prediction. It uses a Monte Carlo Dropout method to quantify prediction uncertainty and combines it with an active learning strategy to dynamically update the training set, effectively capturing rare mud cake blockage samples and enhancing the model's recognition ability for minority class samples. It also uses low-fidelity data for preliminary modeling, reducing reliance on high-fidelity data and reducing data acquisition and processing costs.

[0075] Furthermore, if Figure 3 As shown, based on the above-mentioned shield tunneling mud cake blockage prediction method, the present invention also provides a shield tunneling mud cake blockage prediction system, wherein the shield tunneling mud cake blockage prediction system includes:

[0076] A first model training module 51 is configured to obtain low-fidelity data of a target tunnel, and train a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model;

[0077] a data prediction module 52 for acquiring high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value;

[0078] a second model training module 53 for fusing the high-fidelity data with the low-fidelity prediction values ​​to obtain extended input data, training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model;

[0079] The risk prediction module 54 is used to obtain shield tunneling data of the target tunnel, input the shield tunneling data into the target multi-fidelity model, and output a mud cake blockage risk prediction result.

[0080] Furthermore, if Figure 4 As shown, based on the above-mentioned shield tunneling mud cake blockage prediction method, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 4 Only some of the components of the terminal are shown, but it should be understood that implementation of all of the shown components is not required, and more or fewer components may be implemented instead.

[0081] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as the terminal's hard drive or memory. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, etc. equipped with the terminal. Furthermore, the memory 20 may include both the terminal's internal storage unit and an external storage device. The memory 20 is used to store application software installed on the terminal and various types of data, such as program code for the terminal. The memory 20 may also be used to temporarily store data that has been output or is about to be output. In one embodiment, the memory 20 stores a shield tunneling mud cake blockage prediction program 40, which can be executed by the processor 10, thereby implementing the shield tunneling mud cake blockage prediction method of the present application.

[0082] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 20, such as executing the shield tunneling mud cake blockage prediction method.

[0083] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0084] In one embodiment, when the processor 10 executes the shield tunneling mud cake blockage prediction program 40 in the memory 20, the following steps are implemented:

[0085] Obtaining low-fidelity data of a target tunnel, and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model;

[0086] Acquiring high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value;

[0087] Fusing the high-fidelity data with the low-fidelity prediction value to obtain extended input data, training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model;

[0088] Shield excavation data of the target tunnel is obtained, the shield excavation data is input into the target multi-fidelity model, and a mud cake blockage risk prediction result is output.

[0089] The step of obtaining low-fidelity data of the target tunnel and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model specifically includes:

[0090] Obtaining a shield mud cake risk map of a target tunnel, performing data conversion on key parameters of the shield mud cake risk map to obtain characteristic parameters;

[0091] Performing feature simulation on the feature parameters to obtain engineering feature parameters, and combining the feature parameters with the engineering feature parameters to obtain low-fidelity data;

[0092] A low-fidelity neural network is constructed, and the low-fidelity neural network is iteratively trained according to the low-fidelity data. If the number of iterations of the low-fidelity neural network reaches a first preset number, it is determined that the low-fidelity neural network has completed training, thereby obtaining a low-fidelity model.

[0093] The step of obtaining high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value specifically includes:

[0094] Acquiring geological drilling data along the tunnel of the target tunnel and operating parameters of a shield machine, and performing normalization processing and outlier extraction processing on the geological drilling data along the tunnel and the operating parameters to obtain high-fidelity data;

[0095] The high-fidelity data is input into the low-fidelity model, and a preliminary prediction of the mud cake blockage probability is performed on the high-fidelity data to obtain a low-fidelity prediction value.

[0096] The high-fidelity data is fused with the low-fidelity prediction value to obtain extended input data, a corresponding high-fidelity residual network is trained according to the extended input data to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, specifically including:

[0097] Obtaining data features of the low-fidelity prediction value, concatenating the data features with various input features of the high-fidelity data to obtain a target feature vector, and obtaining extended input data based on the target feature vector;

[0098] Dividing the extended input data according to a preset ratio to obtain an initial training set and an unseen high-fidelity data set, and performing model training on a high-fidelity residual network based on the initial training set to obtain an initial high-fidelity residual model;

[0099] Inputting the unseen high-fidelity data set into the initial high-fidelity residual model, and performing multiple predictions on the unseen high-fidelity data set according to a Monte Carlo random dropout method to obtain multiple prediction residuals, calculating the mean of all the prediction residuals, and calculating the corresponding variance based on the mean;

[0100] sorting the data samples of the unseen high-fidelity data set according to the variance to obtain a sorting result, and extracting samples from the sorting result according to a variance threshold to obtain a target data sample;

[0101] The target data sample is combined with the initial training set according to a sampling strategy with replacement to obtain a new target training set, and the high-fidelity residual network is model trained according to the new target training set to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained based on the low-fidelity model and the high-fidelity residual model.

[0102] The step of performing model training on the high-fidelity residual network according to the new target training set to obtain a high-fidelity residual model, and obtaining a target high-fidelity model according to the low-fidelity model and the high-fidelity residual model, specifically includes:

[0103] Iteratively training the high-fidelity residual network according to the new target training set, and if the number of iterations of the high-fidelity residual network reaches a second preset number, determining that the high-fidelity residual network has completed training, thereby obtaining a high-fidelity residual model;

[0104] Adding the low-fidelity prediction value to all the prediction residuals to obtain a multi-fidelity prediction value, and performing fitting correction on the multi-fidelity prediction value according to a correction formula to obtain a final prediction result;

[0105] A multi-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, and parameters of the multi-fidelity model are corrected according to the final prediction result to obtain a target multi-fidelity model.

[0106] Wherein, the correction formula is:

[0107] ;

[0108] in, For the final prediction result, is the predicted probability output by the low-fidelity model, is the probability residual output by the high-fidelity residual network, and All are linear regression correction coefficients.

[0109] The method further includes obtaining shield tunneling data of the target tunnel, inputting the shield tunneling data into the target multi-fidelity model, and outputting a mud cake blockage risk prediction result.

[0110] If the predicted probability of the mud cake blockage risk prediction result is less than the preset probability, it is determined that the target tunnel does not have the mud cake blockage risk;

[0111] If the predicted probability of the mud cake blockage risk prediction result is greater than or equal to the preset probability, it is determined that the target tunnel has a mud cake blockage risk, and a risk warning signal is generated to alert corresponding construction personnel.

[0112] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a shield tunneling mud cake blockage prediction program, and when the shield tunneling mud cake blockage prediction program is executed by a processor, the steps of the shield tunneling mud cake blockage prediction method described above are implemented.

[0113] In summary, the present invention provides a method, system, terminal and storage medium for predicting shield tunneling mud cake blockage. The method includes: obtaining low-fidelity data of a target tunnel, training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model; obtaining high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value; fusing the high-fidelity data with the low-fidelity prediction value to obtain extended input data, and training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model; obtaining shield tunneling data of the target tunnel, inputting the shield tunneling data into the target multi-fidelity model, and outputting a mud cake blockage risk prediction result. The present invention combines low-fidelity data with high-fidelity data through a multi-fidelity model framework, which can effectively improve model training efficiency. By fully integrating low-fidelity data with high-fidelity data, the residual network is used to correct the deficiencies of the low-fidelity model, significantly improving the accuracy of mud cake blockage risk prediction. The MCD (Monte-Carlo Dropout) method is used to quantify prediction uncertainty, and the training set is dynamically updated in combination with an active learning strategy to effectively capture rare mud cake blockage samples and enhance the model's recognition ability for minority class samples. Low-fidelity data is also used for preliminary modeling to reduce dependence on high-fidelity data and lower data acquisition and processing costs.

[0114] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or terminal comprising the element.

[0115] Of course, those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program. The program can be stored in a computer-readable storage medium that can be read by a computer. When executed, the program can include the processes in the above-described method embodiments. The computer-readable storage medium can be a memory, a magnetic disk, an optical disk, etc.

[0116] It should be understood that the application of the present invention is not limited to the above examples. For those skilled in the art, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A shield tunneling mud cake blockage prediction method, characterized in that: The shield tunneling mud cake blockage prediction method includes: Obtaining low-fidelity data of a target tunnel, and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model; Acquiring high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value; Fusing the high-fidelity data with the low-fidelity prediction value to obtain extended input data, training a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model; The high-fidelity data is fused with the low-fidelity prediction value to obtain extended input data, a corresponding high-fidelity residual network is trained according to the extended input data to obtain a high-fidelity residual model, and a target multi-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, specifically including: Obtaining data features of the low-fidelity prediction value, concatenating the data features with various input features of the high-fidelity data to obtain a target feature vector, and obtaining extended input data based on the target feature vector; Dividing the extended input data according to a preset ratio to obtain an initial training set and an unseen high-fidelity data set, and performing model training on a high-fidelity residual network based on the initial training set to obtain an initial high-fidelity residual model; Inputting the unseen high-fidelity data set into the initial high-fidelity residual model, and performing multiple predictions on the unseen high-fidelity data set according to a Monte Carlo random dropout method to obtain multiple prediction residuals, calculating the mean of all the prediction residuals, and calculating the corresponding variance based on the mean; sorting the data samples of the unseen high-fidelity data set according to the variance to obtain a sorting result, and extracting samples from the sorting result according to a variance threshold to obtain a target data sample; Combining the target data sample with the initial training set according to a sampling strategy with replacement to obtain a new target training set, performing model training on the high-fidelity residual network according to the new target training set to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model; The high-fidelity residual network is trained according to the new target training set to obtain a high-fidelity residual model, and a target high-fidelity model is obtained according to the low-fidelity model and the high-fidelity residual model, specifically including: Iteratively training the high-fidelity residual network according to the new target training set, and if the number of iterations of the high-fidelity residual network reaches a second preset number, determining that the high-fidelity residual network has completed training, thereby obtaining a high-fidelity residual model; Adding the low-fidelity prediction value to all the prediction residuals to obtain a multi-fidelity prediction value, and performing fitting correction on the multi-fidelity prediction value according to a correction formula to obtain a final prediction result; Obtaining a multi-fidelity model based on the low-fidelity model and the high-fidelity residual model, and modifying parameters of the multi-fidelity model based on the final prediction result to obtain a target multi-fidelity model; Shield excavation data of the target tunnel is obtained, the shield excavation data is input into the target multi-fidelity model, and a mud cake blockage risk prediction result is output.

2. The shield tunneling mud cake blockage prediction method according to claim 1, characterized in that: The step of obtaining low-fidelity data of the target tunnel and training a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model specifically includes: Obtaining a shield mud cake risk map of a target tunnel, performing data conversion on key parameters of the shield mud cake risk map to obtain characteristic parameters; Performing feature simulation on the feature parameters to obtain engineering feature parameters, and combining the feature parameters with the engineering feature parameters to obtain low-fidelity data; A low-fidelity neural network is constructed, and the low-fidelity neural network is iteratively trained according to the low-fidelity data. If the number of iterations of the low-fidelity neural network reaches a first preset number, it is determined that the low-fidelity neural network has completed training, thereby obtaining a low-fidelity model.

3. The shield tunneling mud cake blockage prediction method according to claim 1, characterized in that: The obtaining of high-fidelity data of the target tunnel, inputting the high-fidelity data into the low-fidelity model, and outputting a low-fidelity prediction value specifically includes: Acquiring geological drilling data along the tunnel of the target tunnel and operating parameters of a shield machine, and performing normalization processing and outlier extraction processing on the geological drilling data along the tunnel and the operating parameters to obtain high-fidelity data; The high-fidelity data is input into the low-fidelity model, and a preliminary prediction of the mud cake blockage probability is performed on the high-fidelity data to obtain a low-fidelity prediction value.

4. The shield tunneling mud cake blockage prediction method according to claim 1, characterized in that: The correction formula is: ； in, For the final prediction result, is the predicted probability output by the low-fidelity model, is the probability residual output by the high-fidelity residual network, and All are linear regression correction coefficients.

5. The shield tunneling mud cake blockage prediction method according to claim 1, characterized in that: The method further includes: obtaining shield tunneling data of the target tunnel, inputting the shield tunneling data into the target multi-fidelity model, and outputting a mud cake blockage risk prediction result; and If the predicted probability of the mud cake blockage risk prediction result is less than the preset probability, it is determined that the target tunnel does not have the mud cake blockage risk; If the predicted probability of the mud cake blockage risk prediction result is greater than or equal to the preset probability, it is determined that the target tunnel has a mud cake blockage risk, and a risk warning signal is generated to alert corresponding construction personnel.

6. A shield tunneling mud cake blockage prediction system, characterized in that: The shield tunneling mud cake blockage prediction system is applied to the shield tunneling mud cake blockage prediction method according to any one of claims 1 to 5, and the shield tunneling mud cake blockage prediction system includes: a first model training module, configured to obtain low-fidelity data of a target tunnel, and train a low-fidelity neural network based on the low-fidelity data to obtain a low-fidelity model; a data prediction module, configured to obtain high-fidelity data of the target tunnel, input the high-fidelity data into the low-fidelity model, and output a low-fidelity prediction value; a second model training module, configured to fuse the high-fidelity data with the low-fidelity prediction values ​​to obtain extended input data, train a corresponding high-fidelity residual network based on the extended input data to obtain a high-fidelity residual model, and obtain a target multi-fidelity model based on the low-fidelity model and the high-fidelity residual model; The risk prediction module is used to obtain shield tunneling data of the target tunnel, input the shield tunneling data into the target multi-fidelity model, and output a mud cake blockage risk prediction result.

7. A terminal, characterized in that: The terminal includes: a memory, a processor, and a shield tunneling mud cake blockage prediction program stored in the memory and runnable on the processor. When the shield tunneling mud cake blockage prediction program is executed by the processor, the steps of the shield tunneling mud cake blockage prediction method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a shield tunneling mud cake blockage prediction program, which, when executed by a processor, implements the steps of the shield tunneling mud cake blockage prediction method according to any one of claims 1 to 5.

Images