Tunnel surrounding rock deformation prediction method, system and equipment

Abstract

The invention discloses a tunnel surrounding rock deformation prediction method, system and equipment. The tunnel surrounding rock deformation prediction method comprises the steps that actual multi-source data in the tunneling process of a tunnel boring machine (TBM) are obtained, and the multi-source data at least comprise surrounding rock deformation monitoring data, tunneling data of the tunnel boring machine and vibration signal data; the multi-source data is input into a pre-trained prediction model, a prediction result of the tunnel surrounding rock deformation condition in the TBM tunneling process is obtained, and the prediction model is pre-trained with the pre-obtained multi-source data as a training sample and the tunnel surrounding rock deformation condition as a label. According to the embodiment of the invention, the method can achieve the advanced prediction of the deformation of the surrounding rock through the real-time data in the construction process of the tunnel boring machine, provides a scientific basis for the construction parameter optimization and risk early warning of the tunnel boring machine, reduces the workload of manual monitoring, and improves the construction automation level.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of civil engineering, in particular to a tunnel surrounding rock deformation prediction method, system and device. BACKGROUND

[0002] In the tunnel boring machine (TBM) tunnel construction, the surrounding rock deformation prediction is directly related to the construction safety, the support structure optimization and the tunneling efficiency. The stability of the surrounding rock not only affects the normal operation of the TBM equipment, but also may cause engineering disasters such as collapse and ground subsidence. Therefore, accurately predicting the surrounding rock deformation is crucial for dynamically adjusting the tunneling parameters (such as the advancing speed, the cutterhead torque, the support timing, etc.). However, the traditional prediction method relies on limited geological survey data and empirical formulas, which is difficult to adapt to complex and variable stratum conditions, resulting in low prediction accuracy and poor real-time performance, and cannot meet the needs of modern intelligent construction.

[0003] The traditional surrounding rock deformation prediction is mainly based on geological exploration data (such as drilling sampling and geological radar) and theoretical analytical models (such as the Fenn formula). However, the geological survey data is limited and difficult to fully reflect the spatial variability of the rock mass; the empirical formula assumes that the surrounding rock is homogeneous and isotropic, ignoring the nonlinear, rheological characteristics of the rock mass and the influence of TBM tunneling disturbance; and it cannot dynamically respond to geological mutations (such as fracture zones and aquifers) in the construction process. Thus, the traditional method has large prediction errors under complex geological conditions, which is difficult to support fine construction decisions.

[0004] The existing technology has the following disadvantages: the traditional deformation prediction is mostly based on surrounding rock deformation monitoring, the data is single, the artificial dependence is strong, and intelligent prediction cannot be realized; the existing multi-source data fusion effect is poor, and the traditional prediction model has poor adaptability to complex geological conditions; the prediction result lags behind the actual deformation development, and it is difficult to timely warn.

[0005] In view of the above problems, the present application proposes a TBM tunneling surrounding rock deformation prediction method based on multi-source data fusion, which overcomes the problems of single data form and inaccurate prediction of the traditional method. SUMMARY

[0006] In view of the above defects or deficiencies in the prior art, it is desirable to provide a tunnel surrounding rock deformation prediction method, system and device, which can utilize real-time data in the tunnel boring machine construction process, realize advanced prediction of surrounding rock deformation, thereby providing a scientific basis for tunnel boring machine construction parameter optimization and risk warning, and reducing the workload of manual monitoring, improving the construction automation level.

[0007] In a first aspect, an embodiment of the present application provides a tunnel surrounding rock deformation prediction method, comprising:

[0008] Obtain actual multi-source data in a tunneling process of a tunnel boring machine, wherein the multi-source data at least includes surrounding rock deformation monitoring data, tunneling data of the tunnel boring machine and vibration signal data;

[0009] Input the multi-source data into a pre-trained prediction model to obtain a prediction result of a tunnel surrounding rock deformation condition in the tunneling process of the tunnel boring machine, wherein the prediction model is pre-trained with pre-obtained multi-source data as training samples and the tunnel surrounding rock deformation condition as a label.

[0010] In some examples, before the multi-source data is input into the pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation condition in the tunneling process of the tunnel boring machine, the method further includes:

[0011] Obtain multi-source data;

[0012] Optimize each type of multi-source data in the multi-source data respectively;

[0013] After the optimization, extract features of each type of multi-source data;

[0014] Fuse the features of each type of multi-source data to obtain input features;

[0015] Train an initial prediction model according to the input features to obtain the pre-trained prediction model.

[0016] In some examples, the optimization of each type of multi-source data includes:

[0017] Remove outliers in each type of multi-source data;

[0018] After removing the outliers in each type of multi-source data, normalize each type of multi-source data.

[0019] In some examples, the extraction of features of each type of multi-source data after the optimization includes:

[0020] Divide tunneling cycles from the tunneling data, and extract tunneling data features according to the divided tunneling cycles, wherein the tunneling data features include mean, variance and range of the tunneling data;

[0021] Extract surrounding rock deformation monitoring data features from the surrounding rock deformation monitoring data, wherein the surrounding rock deformation monitoring data features include settlement, convergence value and deformation rate;

[0022] Extract vibration signal data features from the vibration signal data, wherein the vibration signal data features include time domain features and frequency domain features.

[0023] In some examples, the feature fusion is performed on the features of each type of multi-source data to obtain input features, including:

[0024] The multi-dimensional feature construction is performed according to the features of each type of multi-source data to obtain the input features.

[0025] In some examples, the initial prediction model is trained according to the input features to obtain the pre-trained prediction model, including:

[0026] The input features are input into the initial prediction model, and the initial prediction model is trained according to the loss between the output of the initial prediction model and the label until the loss between the output of the initial prediction model and the label meets a set requirement, to obtain the pre-trained prediction model.

[0027] In some examples, the prediction result of the tunnel surrounding rock deformation condition includes a tunnel surrounding rock deformation prediction value and a deformation level.

[0028] In some examples, after obtaining the prediction result of the tunnel surrounding rock deformation condition in the tunnel boring machine tunneling process, the method further includes:

[0029] According to the prediction result of the tunnel surrounding rock deformation condition in the tunnel boring machine tunneling process, the construction decision of the tunnel boring machine is adjusted.

[0030] In a second aspect, an embodiment of the present application provides a tunnel surrounding rock deformation prediction system, including:

[0031] An acquisition module is configured to obtain actual multi-source data in a tunnel boring machine tunneling process, wherein the multi-source data at least includes surrounding rock deformation monitoring data, tunnel boring machine tunneling data, and vibration signal data.

[0032] A prediction module is configured to input the multi-source data into a pre-trained prediction model to obtain a prediction result of a tunnel surrounding rock deformation condition in the tunnel boring machine tunneling process, wherein the prediction model is pre-trained with pre-obtained multi-source data as training samples and tunnel surrounding rock deformation conditions as labels.

[0033] In a third aspect, an embodiment of the present application provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the tunnel surrounding rock deformation prediction method according to the first aspect and any possible implementation of the first aspect is implemented.

[0034] The embodiment of the present application significantly improves the accuracy and reliability of surrounding rock deformation prediction through the fusion of multi-source data, realizes the advanced prediction of surrounding rock deformation by using real-time data in the tunnel boring machine construction process, can capture the nonlinear characteristics and mutation trend of surrounding rock deformation, and further provides a scientific basis for the construction parameter optimization and risk warning of the tunnel boring machine, and reduces the workload of manual monitoring and improves the automation level of construction.

[0035] Additional aspects and advantages of the present application will be made apparent by the following description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0036] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments thereof as taken in conjunction with the accompanying drawings:

[0037] Figure 1 Flow chart of a tunnel surrounding rock deformation prediction method according to an embodiment of the present application;

[0038] Figure 2 Schematic diagram of a multi-source data fusion algorithm framework of a tunnel surrounding rock deformation prediction method according to an embodiment of the present application;

[0039] Figure 3 Schematic diagram of a tunnel surrounding rock deformation monitoring result of a tunnel surrounding rock deformation prediction method according to an embodiment of the present application;

[0040] Figure 4 Schematic diagram of a complete cycle section of tunnel boring machine excavation data of a tunnel surrounding rock deformation prediction method according to an embodiment of the present application;

[0041] Figure 5 Schematic diagram of tunnel boring machine vibration signal information of a tunnel surrounding rock deformation prediction method according to an embodiment of the present application

[0042] Figure 6 Structural block diagram of a tunnel surrounding rock deformation prediction system according to an embodiment of the present application;

[0043] Figure 7 A structural schematic diagram of a computing device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0044] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that, for the sake of description, only the parts related to the application are shown in the drawings.

[0045] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0046] The tunnel surrounding rock deformation prediction method, system and device according to the embodiments of the present application are described below in combination with the drawings.

[0047] The tunnel boring machine (TBM) tunneling parameter prediction method, system and device according to the embodiments of the present application can realize TBM tunneling surrounding rock deformation prediction based on multi-source data fusion, solving the technical problems of single data form, untimely and inaccurate prediction in related technologies.

[0048] Figure 1 The tunnel surrounding rock deformation prediction method according to one embodiment of the present application is shown in the flowchart as Figure 1 The tunnel surrounding rock deformation prediction method according to one embodiment of the present application includes the following steps:

[0049] S101: Obtain actual multi-source data in the tunnel boring machine (TBM) tunneling process, wherein the multi-source data at least includes surrounding rock deformation monitoring data, tunnel boring machine tunneling data and vibration signal data.

[0050] S102: Input the multi-source data into a pre-trained prediction model to obtain a prediction result of the tunnel surrounding rock deformation condition of the tunnel boring machine tunneling process, wherein the prediction model is pre-trained with the pre-obtained multi-source data as training samples and the tunnel surrounding rock deformation condition as labels.

[0051] In one embodiment of the present application, before the multi-source data is input into the pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation condition of the tunnel boring machine tunneling process, it further includes: obtaining multi-source data; respectively optimizing each type of multi-source data in the multi-source data; extracting features of each type of multi-source data after optimization; performing feature fusion on the features of each type of multi-source data to obtain input features; training an initial prediction model according to the input features to obtain the pre-trained prediction model.

[0052] In this example, the optimization processing of each type of multi-source data in the multi-source data includes: removing outliers in each type of multi-source data; and after removing the outliers in each type of multi-source data, normalizing each type of multi-source data.

[0053] In the above description, the multi-source data is multiple, which is pre-obtained multi-source data of the tunnel boring machine tunneling process.

[0054] Further, the feature extraction of each type of multi-source data after the optimization processing comprises: dividing the tunneling cycle from the tunneling data, and extracting the tunneling data features according to the divided tunneling cycle, wherein the tunneling data features comprise the mean, variance and range of the tunneling data; extracting the surrounding rock deformation monitoring data features from the surrounding rock deformation monitoring data, wherein the surrounding rock deformation monitoring data features comprise the settlement, convergence value and deformation rate; and extracting the vibration signal data features from the vibration signal data, wherein the vibration signal data features comprise the time domain features and frequency domain features.

[0055] In the above example, the feature fusion of the features of each type of multi-source data obtains the input features, comprising: performing multi-dimensional feature construction according to the features of each type of multi-source data to obtain the input features.

[0056] After the feature fusion of the features of each type of multi-source data obtains the input features, the initial prediction model is trained according to the input features to obtain the pre-trained prediction model, comprising: inputting the input features into the initial prediction model, and training the initial prediction model according to the loss between the output of the initial prediction model and the label until the loss between the output of the initial prediction model and the label meets the set requirement, to obtain the pre-trained prediction model.

[0057] In the above description, the prediction result of the tunnel surrounding rock deformation condition comprises but is not limited to the tunnel surrounding rock deformation prediction value and the deformation grade.

[0058] That is, the embodiment of the present application obtains the actual multi-source data in the tunnel boring machine tunneling process when the tunnel boring machine tunnels, and then inputs the actual multi-source data into the trained prediction model, so as to predict the tunnel surrounding rock deformation condition. Specifically, it includes two stages of training of the prediction model and prediction of the tunnel surrounding rock deformation condition by applying the trained prediction model. In the training stage of the prediction model, the features of each type of multi-source data are extracted, and the features of each type of multi-source data are fused to obtain the input features, and then the initial prediction model is trained according to the input features to obtain the pre-trained prediction model. Figures 2 to 5 As shown in Figure 2 Specifically, it comprises:

[0059] (1) As shown in

[0060] (1) As shown in Figure 3 The TBM tunneling data, the TBM device itself records a large amount of data, and the real-time collection of the key parameters such as cutter thrust, torque, speed, penetration, etc. as the TBM tunneling data reflects the mechanical response of the surrounding rock in the tunneling process.

[0061] (2) As shown in Figure 4As shown, the surrounding rock deformation monitoring data, using total station, convergence meter or optical fiber sensor to measure tunnel vault settlement, horizontal convergence value and other deformation indicators as surrounding rock deformation monitoring data, it should be noted that the data acquisition frequency needs to be synchronized with the excavation data acquisition, to ensure time consistency.

[0062] (3) as shown in Figure 5 TBM vibration signal data, acceleration sensors are deployed at key positions such as cutter head and main bearing, XYZ three direction vibration signals are collected, and time-frequency domain characteristics of vibration signals and other TBM vibration signal data are obtained. The data acquisition frequency needs to be synchronized with the excavation data acquisition, to ensure time consistency.

[0063] The collected three types of data (multi-source data) are respectively constructed into local databases, and the three types of data are further preprocessed, mainly including the following preprocessing steps:

[0064] Data outlier processing: for TBM excavation data and surrounding rock deformation monitoring data, data can be removed according to the box plot (IQR) method, first calculate the interquartile range (IQR = Q3-Q1), outliers are data outside the lower and upper limits, upper limit = Q3+1.5IQR, lower limit = Q1-1.5IQR.

[0065] For TBM vibration signal data, a dynamic threshold method based on sliding window can be used, a sliding window (such as 60s window, step 10s) is used to calculate the mean and standard deviation of the data in the window, if a data point exceeds (μ±kσ) range of the current window (k = 2-3), it is determined as an outlier, which is removed.

[0066] Data normalization: normalize the three types of data to a comparable interval, which is convenient for subsequent feature fusion, and use Min-Max normalization.

[0067] Standardized value = (x-min) / (max-min)

[0068] Data alignment: on the one hand, the three types of data are selected as the excavation data, surrounding rock deformation monitoring data and TBM vibration signal data recorded at the same time of TBM excavation. The processing method is to correspond according to the time of excavation data recording, and the three types of data in the same time period are segmented first. On the other hand, the data range is aligned, because the sampling frequencies of the sensors are not consistent, the number of data recorded by time is not consistent, the processing method is to align according to the lowest sampling frequency, in the case of high frequency sampling, the average value in the low frequency sampling time interval is calculated.

[0069] (2) Feature extraction

[0070] (1) From the TBM tunneling data, the tunneling cycle is divided, and the statistical features (mean, variance, extreme value, etc.) are extracted, as follows: First, the pre-processed TBM tunneling data is extracted, and the data value of the cutterhead thrust is picked up according to time. If the cutterhead thrust changes from 0 to a non-0 value, the time is the starting point of tunneling. If the cutterhead thrust changes from a non-0 value to 0, the time is the end point of tunneling. Second, based on the tunneling cycle segment data table data, the average value of the stable segment thrust is calculated (only considering the thrust data in the range of 25% to 75% for average value calculation). Along the time from front to back, the first thrust greater than the average thrust is recorded as the stable segment starting time. Along the time from back to front, the first thrust greater than the average thrust is recorded as the stable segment ending time. Finally, according to the four picked-up times, a complete tunneling cycle is divided into the rising segment, the stable segment, and the falling segment, and the tunneling data mean, variance, and range of the stable segment are calculated.

[0071] (2) From the surrounding rock deformation monitoring data, the settlement, convergence value, and deformation rate are extracted, specifically, the pre-processed surrounding rock deformation monitoring data is extracted, and the settlement, convergence value, and deformation rate are extracted according to the tunneling time and TBM tunneling data.

[0072] (3) Time domain features and frequency domain features are extracted from the TBM vibration signal. Specifically, according to the pre-processed three-axis time domain data, the three-axis peak-to-peak value (PP), root mean square value (RMS), kurtosis coefficient (K), skewness coefficient (S), and margin coefficient (C) are extracted using batch processing. In the frequency domain, the three-axis vibration signal is converted into a frequency domain signal using Fourier transform, and then the signal's spectral barycenter frequency f c , low-frequency energy ratio R low , wavelet packet energy entropy H, and CMV index are extracted using batch processing.

[0073] (Three) Feature fusion and model construction

[0074] The feature vectors of the three types of data are fused to construct a unified multi-dimensional feature space. The feature fusion method can be used for dimension expansion of the features, specifically:

[0075] Input features = [TBM tunneling data features] + [surrounding rock deformation monitoring data features] + [TBM vibration signal data features].

[0076] An artificial intelligence algorithm is used to establish the mapping relationship between the features and the surrounding rock deformation. The preferred artificial intelligence algorithms include but are not limited to deep neural networks, random forests, support vector regression, etc., and a prediction model is constructed.

[0077] The corresponding algorithm framework is constructed, and the data is divided according to the training set: test set = 7:3. The output features of the prediction model are the predicted values and deformation levels of the surrounding rock deformation.

[0078] (iv) Model training, using the historical data constructed above to train the prediction model, and testing the model effect on the test set. After completing the test, real-time collected multi-source data can be input to output the predicted value of surrounding rock deformation and deformation level.

[0079] In the above description, the surrounding rock deformation level is divided as follows: first, according to all historical data of the training set and the test set, the surrounding rock deformation monitoring data is respectively counted according to the numerical size of settlement, convergence, etc. Then, the maximum value and the minimum value are taken as control points, and the predicted surrounding rock deformation value in the range of 75%-maximum value is first-level deformation, in the range of 50%-75% is second-level deformation, in the range of 25%-50% is third-level deformation, and in the range of minimum value-25% is fourth-level deformation.

[0080] After obtaining the prediction result of the tunnel surrounding rock deformation condition of the tunnel boring machine excavation process, further comprising: adjusting the construction decision of the tunnel boring machine according to the prediction result of the tunnel surrounding rock deformation condition of the tunnel boring machine excavation process.

[0081] According to the tunnel surrounding rock deformation prediction method, the accuracy and reliability of the surrounding rock deformation prediction are significantly improved through the fusion of multi-source data. The real-time data in the tunnel boring machine construction process is used to realize the advanced prediction of the surrounding rock deformation, which can capture the nonlinear characteristics and mutation trend of the surrounding rock deformation, thereby providing a scientific basis for the tunnel boring machine construction parameter optimization and risk warning, and reducing the workload of manual monitoring and improving the construction automation level.

[0082] Figure 6 is a structural block diagram of a tunnel surrounding rock deformation prediction system according to an embodiment of the present application, as Figure 6 shown, the tunnel surrounding rock deformation prediction system according to an embodiment of the present application comprises: an acquisition module 610 and a prediction module 620, wherein:

[0083] The acquisition module 610 is used to obtain actual multi-source data in the tunnel boring machine excavation process, wherein the multi-source data at least includes surrounding rock deformation monitoring data, tunnel boring machine excavation data and vibration signal data;

[0084] The prediction module 620 is used to input the multi-source data into the pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation condition of the tunnel boring machine excavation process, wherein the prediction model is pre-trained with the pre-obtained multi-source data as training samples and the tunnel surrounding rock deformation condition as labels.

[0085] According to the tunnel surrounding rock deformation prediction system provided in the embodiments of the present application, the accuracy and reliability of surrounding rock deformation prediction are significantly improved through the fusion of multi-source data, real-time data in the tunnel boring machine construction process is utilized to realize the advanced prediction of surrounding rock deformation, the nonlinear characteristics and mutation trend of surrounding rock deformation can be captured, and then, scientific basis is provided for the construction parameter optimization and risk warning of the tunnel boring machine, and the workload of manual monitoring is reduced and the construction automation level is improved.

[0086] It should be noted that the specific implementation of the tunnel surrounding rock deformation prediction system in the embodiments of the present application is similar to the specific implementation of the tunnel surrounding rock deformation prediction method in the embodiments of the present application, and specific reference can be made to the description in the method part, which will not be repeated here.

[0087] Reference will be made to the accompanying drawings Figure 7 , Figure 7 A structural schematic diagram of a computing device suitable for implementing the embodiments of the present application is shown.

[0088] As shown in Figure 7 , the computer system includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage portion 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for operation instructions of the system are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0089] The following components are connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage portion 1008 including a hard disk, and the like; and a communication portion 1009 including a network interface card such as a LAN card, a modem, and the like. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 1010 as necessary, so that a computer program read therefrom is installed in the storage portion 1008 as necessary.

[0090] In particular, according to the embodiments of the present application, the above-mentioned flowcharts Figure 1The described processes can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product that includes a computer program tangibly embodied on a computer readable medium, the computer program including program code for executing the methods illustrated in the flowcharts. In such an embodiment, the computer program includes program code for executing the methods illustrated in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1009, and / or installed from the removable media 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-described functions defined in the system of the present application are executed.

[0091] It should be noted that the computer readable medium shown in the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that can send, propagate or transfer a program for use by or in connection with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF or the like, or any suitable combination of the above.

[0092] The computer program product of the present application can be a computer program embodied on a non-transitory computer readable medium. When the program is executed by a processor, the processor can perform the operations described above with regard to the flow charts and block diagrams of the present application. Although the computer program of the present application is illustrated as a whole, the computer program can be divided into a plurality of parts to be executed by a plurality of processors respectively.

[0093] The units or modules described in the embodiments of the present application can be implemented by software, or by hardware. The described units or modules can also be implemented in a processor. In some cases, the names of the units or modules do not constitute a limitation on the units or modules themselves.

[0094] As another aspect, the present application also provides a computer readable storage medium, which can be included in the computing device described in the above embodiments, or can exist separately and not be assembled into the computing device. The computer readable storage medium stores one or more programs, and when the programs are used by one or more processors to execute the tunnel surrounding rock deformation prediction method described in the present application. That is: obtaining actual multi-source data in the tunnel boring machine tunneling process, wherein the multi-source data at least includes surrounding rock deformation monitoring data, tunnel boring machine tunneling data and vibration signal data;

[0095] Inputting the multi-source data into a pre-trained prediction model to obtain a prediction result of the tunnel surrounding rock deformation in the tunnel boring machine tunneling process, wherein the prediction model is pre-trained with pre-obtained multi-source data as training samples and tunnel surrounding rock deformation as labels.

[0096] The above description is merely exemplary of the application and of the application of the principles thereof and the application is not limited to the disclosed technical features merely in the specific combination described. Rather, the scope of the disclosure is both the technical solutions and the disclosed technical features in any possible combination, as well as any other technical solutions which, without departing from the disclosed concept, can be attained by the technical features disclosed herein or their equivalent features. For example, technical solutions formed by replacing the disclosed technical features with technical features having similar functions (not limited to the disclosed technical features) disclosed in the application.

Claims

1. A method for predicting deformation of surrounding rock in tunnels, characterized in that, include: Obtain actual multi-source data during the tunnel boring machine's excavation process, wherein the multi-source data includes at least surrounding rock deformation monitoring data, tunnel boring machine excavation data, and vibration signal data; The multi-source data is input into a pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation during the tunnel boring machine's tunneling process. The prediction model is pre-trained using the pre-obtained multi-source data as training samples and the tunnel surrounding rock deformation as labels.

2. The method for predicting tunnel surrounding rock deformation according to claim 1, characterized in that, Before inputting the multi-source data into the pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation during the tunnel boring machine's excavation process, the method further includes: Obtain multi-source data; Optimize each type of multi-source data in the multi-source data separately; After optimization, features of each type of multi-source data are extracted; Feature fusion is performed on the features of each type of multi-source data to obtain the input features; The initial prediction model is trained based on the input features to obtain the pre-trained prediction model.

3. The method for predicting tunnel surrounding rock deformation according to claim 2, characterized in that, The optimization processing for each type of multi-source data in the multi-source data includes: Remove outliers from each category of multi-source data; After removing outliers from each category of multi-source data, the data from each category is normalized.

4. The method for predicting tunnel surrounding rock deformation according to claim 2, characterized in that, After optimization, the features of each type of multi-source data are extracted, including: The tunneling data is divided into tunneling cycles, and tunneling data features are extracted based on the divided tunneling cycles. The tunneling data features include the mean, variance, and range of the tunneling data. Extract features from surrounding rock deformation monitoring data, including settlement, convergence value, and deformation rate; Vibration signal data features are extracted from vibration signal data, wherein the vibration signal data features include time domain features and frequency domain features.

5. The method for predicting tunnel surrounding rock deformation according to claim 2, characterized in that, The feature fusion of features from each type of multi-source data to obtain input features includes: Multidimensional features are constructed based on the characteristics of each type of multi-source data to obtain the input features.

6. The method for predicting tunnel surrounding rock deformation according to any one of claims 2-5, characterized in that, The step of training the initial prediction model based on the input features to obtain the pre-trained prediction model includes: The input features are input into the initial prediction model, and the initial prediction model is trained based on the output of the initial prediction model and the loss before the label until the output of the initial prediction model and the loss before the label meet the set requirements, thus obtaining a pre-trained prediction model.

7. The method for predicting tunnel surrounding rock deformation according to claim 1, characterized in that, The predicted results of the tunnel surrounding rock deformation include the predicted value of the tunnel surrounding rock deformation and the deformation level.

8. The method for predicting tunnel surrounding rock deformation according to claim 1, characterized in that, After obtaining the predicted results of the tunnel surrounding rock deformation during the tunnel boring machine's excavation process, the method further includes: Based on the predicted results of the tunnel surrounding rock deformation during the tunnel boring machine's excavation process, the construction decision of the tunnel boring machine is adjusted.

9. A tunnel surrounding rock deformation prediction system, characterized in that, include: The acquisition module is used to obtain actual multi-source data during the tunnel boring machine's tunneling process. The multi-source data includes at least surrounding rock deformation monitoring data, tunnel boring machine tunneling data, and vibration signal data. The prediction module is used to input the multi-source data into a pre-trained prediction model to obtain the prediction result of the tunnel surrounding rock deformation during the tunnel boring machine's tunneling process. The prediction model is pre-trained using the pre-obtained multi-source data as training samples and the tunnel surrounding rock deformation as labels.

10. A computing device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the tunnel surrounding rock deformation prediction method according to any one of claims 1-8.

Images