Intelligent monitoring and early warning method for shallow-buried aeolian sand weak surrounding rock tunnel construction

Abstract

The invention relates to the technical field of aeolian sand tunnel construction, in particular to an intelligent monitoring and early warning method and device for shallow-buried aeolian sand weak surrounding rock tunnel construction, and the method comprises the steps: collecting a plurality of tunnel monitoring data of a shallow-buried aeolian sand weak surrounding rock tunnel, and carrying out the consistency processing of the data, and calculating a correlation coefficient matrix of the standard matrix, calculating a characteristic value and a characteristic vector of the correlation coefficient matrix, determining a principal component vector of the characteristic vector according to an accumulated contribution rate of the characteristic value, mapping a plurality of tunnel monitoring data into a principal component space, and obtaining a plurality of tunnel monitoring data. And obtaining fused data. Therefore, the problems that in the related technology, due to the fact that the data island phenomenon is serious, the data processing capacity is limited, the data processing capacity depends on artificial experience, and an early warning model is difficult to deal with complex geological conditions, information splitting is caused, risk factors and trends are difficult to accurately recognize, and tunnel construction safety and quality are affected are solved.

Description

Technical Field

[0001] The present application relates to the technical field of aeolian sand tunnel construction, and in particular to an intelligent monitoring and early warning method and device for shallow buried aeolian sand tunnel with soft surrounding rock. Background Art

[0002] In the related technology, early warning and monitoring are carried out in the complex construction environment of shallow aeolian sand and soft surrounding rock tunnels, which usually include several groups of monitoring systems, wireless relay equipment, gateway equipment, monitoring host and remote server, and each part works together to realize the early warning and monitoring functions.

[0003] However, in the relevant technologies, on the one hand, data islands are serious, and there is a lack of effective integration between different monitoring systems, resulting in information fragmentation, making it difficult to form a comprehensive and coherent dynamic portrait of tunnel construction; on the other hand, traditional methods have limited data processing capabilities and often rely on manual experience and judgment, making it difficult to accurately identify potential risk factors and their changing trends in real time. In addition, faced with complex geological conditions such as the fluidity of aeolian sand and the instability of weak surrounding rocks, traditional early warning models are difficult to accurately predict construction risks, and there are high false alarm and missed alarm rates, which seriously threaten the safety and quality of tunnel construction and need to be improved urgently. Summary of the invention

[0004] The present application provides an intelligent monitoring and early warning method and device for shallow-buried aeolian sand and soft surrounding rock tunnel construction, in order to solve the problem in related technologies that due to serious data island phenomenon, limited data processing capacity and reliance on manual experience and early warning models that are difficult to cope with complex geological conditions, information fragmentation occurs, and it is difficult to accurately identify risk factors and trends, thus affecting the safety and quality of tunnel construction.

[0005] The first aspect of the present application provides an intelligent monitoring and early warning method for the construction of a shallow-buried aeolian sand and soft rock tunnel, comprising the following steps: collecting multiple tunnel monitoring data of a shallow-buried aeolian sand and soft rock tunnel; performing consistency processing on the multiple tunnel monitoring data to obtain multiple tunnel data that meet preset conditions; standardizing the multiple tunnel data to obtain a standard matrix, and calculating a correlation coefficient matrix of the standard matrix to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix; determining a principal component vector of the eigenvalue according to a cumulative contribution rate of the eigenvalue to map the multiple tunnel monitoring data into a principal component space to obtain fused data; and constructing a tunnel dynamic model of the shallow-buried aeolian sand and soft rock tunnel using the fused data to obtain an actual risk assessment result of the shallow-buried aeolian sand and soft rock tunnel.

[0006] Through the above technical scheme, the embodiment of the present application can provide comprehensive information for subsequent analysis by collecting multiple tunnel monitoring data; perform consistency processing on the data to ensure that the data quality meets the conditions and reduce data problems; standardize the data to obtain a standard matrix and further calculate the correlation coefficient matrix, eigenvalues ​​and eigenvectors to mine the internal relationship of the data; determine the principal component vector based on the cumulative contribution rate of the eigenvalues, map the tunnel monitoring data to the principal component space to obtain fused data, and achieve data dimensionality reduction and denoising; finally, use the fused data to construct a tunnel dynamic model to obtain actual risk assessment results, which can accurately assess risks, effectively respond to complex construction environments, and ensure construction safety and quality.

[0007] Optionally, in one embodiment of the present application, the collecting of multiple tunnel monitoring data of a shallow-buried aeolian sand and soft rock tunnel includes: based on multiple monitoring points set on the tunnel periphery, arch and key support structures of the shallow-buried aeolian sand and soft rock tunnel, collecting deformation and stress distribution in the multiple tunnel monitoring data; and / or based on the tunnel section, obtaining convergence deformation and arch settlement in the multiple tunnel monitoring data.

[0008] Through the above technical solution, the embodiment of the present application can collect deformation and stress distribution based on multiple monitoring points around the tunnel, the arch and the key support structure, obtain key data of key parts in a targeted manner, accurately grasp the stress and deformation of these parts, and help to timely discover potential structural safety problems. On the other hand, based on the tunnel section, the convergence deformation and the arch settlement can intuitively reflect the stability changes of the tunnel section, providing an important basis for analyzing the overall deformation trend of the tunnel. The combination of the two can collect tunnel monitoring data more comprehensively and accurately, and provide reliable support for subsequent analysis and early warning.

[0009] Optionally, in one embodiment of the present application, the consistency processing of the multiple tunnel monitoring data includes: data cleaning of the multiple tunnel monitoring data; data calibration of the multiple tunnel monitoring data; time synchronization of the multiple tunnel monitoring data; data format unification of the multiple tunnel monitoring data; data association of the multiple tunnel monitoring data; and data verification of the multiple tunnel monitoring data.

[0010] Through the above technical scheme, the embodiment of the present application can improve data quality by removing noise, outliers and duplicate data through data cleaning; correct deviations caused by factors such as instruments and environment through data calibration to ensure data accuracy; unify the data in the time dimension through time synchronization to facilitate the analysis of data change trends; solve the processing problems caused by format differences through data format unification; explore the intrinsic connections between data through data association to enhance the understanding of tunnel status; and further ensure data reliability through data verification, so that the processed data is more standardized, accurate and interrelated, laying a solid foundation for subsequent tunnel construction analysis, risk assessment and other work.

[0011] Optionally, in one embodiment of the present application, the expression of the correlation coefficient matrix is:

[0012]

[0013] in, X norm is a standard matrix, and p is the total number of eigenvalues.

[0014] Through the above technical solution, the embodiment of the present application can provide a clear and standardized quantitative method to describe the linear correlation between the variables. The expression is based on a standard matrix and clear calculation rules, that is, the matrix element values ​​are determined by performing specific operations on the corresponding elements, which can accurately reflect the strength of the correlation between the data. At the same time, key parameters such as the total number of eigenvalues ​​are clearly introduced, so that the entire calculation process is standardized and orderly, which is helpful for the subsequent accurate analysis of data features and mining of data internal laws based on the correlation coefficient matrix, and provides a reliable and scientific basis for further calculation of eigenvalues, eigenvectors, and risk assessment related to tunnel construction.

[0015] Optionally, in one embodiment of the present application, the calculation formula of the cumulative contribution rate is:

[0016]

[0017] Among them, λ i is the i-th eigenvalue, p is the total number of eigenvalues, and k is the number of selected eigenvalues.

[0018] Through the above technical scheme, the embodiment of the present application can clearly and unambiguously quantify the contribution of each eigenvalue in the whole, which is conducive to accurately measuring the impact of each eigenvalue on data changes, so as to reasonably select the principal component vector according to the contribution rate, and achieve data dimensionality reduction while ensuring that the data information loss is acceptable, thereby providing a scientific basis for subsequent more efficient analysis and processing of tunnel monitoring data, construction of accurate tunnel dynamic models, and assessment of construction risks.

[0019] The second aspect of the present application provides an intelligent monitoring and early warning device for the construction of a shallow-buried aeolian sand and soft rock tunnel, comprising: a data acquisition module for collecting multiple tunnel monitoring data of a shallow-buried aeolian sand and soft rock tunnel; a data processing module for performing consistency processing on the multiple tunnel monitoring data to obtain multiple tunnel data that meet preset conditions; a standardization module for standardizing the multiple tunnel data to obtain a standard matrix, and calculating a correlation coefficient matrix of the standard matrix to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix; a data fusion module for determining the principal component vector of the eigenvalue according to the cumulative contribution rate of the eigenvalue to map the multiple tunnel monitoring data into the principal component space to obtain fused data; a monitoring and early warning module for constructing a tunnel dynamic model of the shallow-buried aeolian sand and soft rock tunnel using the fused data to obtain an actual risk assessment result of the shallow-buried aeolian sand and soft rock tunnel.

[0020] Through the above technical scheme, the embodiment of the present application can provide comprehensive information for subsequent analysis by collecting multiple tunnel monitoring data; perform consistency processing on the data to ensure that the data quality meets the conditions and reduce data problems; standardize the data to obtain a standard matrix and further calculate the correlation coefficient matrix, eigenvalues ​​and eigenvectors to mine the internal relationship of the data; determine the principal component vector based on the cumulative contribution rate of the eigenvalues, map the tunnel monitoring data to the principal component space to obtain fused data, and achieve data dimensionality reduction and denoising; finally, use the fused data to construct a tunnel dynamic model to obtain actual risk assessment results, which can accurately assess risks, effectively respond to complex construction environments, and ensure construction safety and quality.

[0021] Optionally, in one embodiment of the present application, the data acquisition module includes: a first acquisition unit, used to collect deformation and stress distribution in the multiple tunnel monitoring data based on multiple monitoring points set on the tunnel periphery, arch and key support structure of the shallow buried aeolian sand soft rock tunnel; a second acquisition unit, used to obtain convergence deformation and arch settlement in the multiple tunnel monitoring data based on the tunnel section.

[0022] Through the above technical solution, the embodiment of the present application can collect deformation and stress distribution based on multiple monitoring points around the tunnel, the arch and the key support structure, obtain key data of key parts in a targeted manner, accurately grasp the stress and deformation of these parts, and help to timely discover potential structural safety problems. On the other hand, based on the tunnel section, the convergence deformation and the arch settlement can intuitively reflect the stability changes of the tunnel section, providing an important basis for analyzing the overall deformation trend of the tunnel. The combination of the two can collect tunnel monitoring data more comprehensively and accurately, and provide reliable support for subsequent analysis and early warning.

[0023] Optionally, in one embodiment of the present application, the data processing module includes: a cleaning unit for performing data cleaning on the multiple tunnel monitoring data; a calibration unit for performing data calibration on the multiple tunnel monitoring data; a synchronization unit for performing time synchronization on the multiple tunnel monitoring data; a unification unit for unifying the data formats of the multiple tunnel monitoring data; an association unit for performing data association on the multiple tunnel monitoring data; and a verification unit for performing data verification on the multiple tunnel monitoring data.

[0024] Through the above technical scheme, the embodiment of the present application can improve data quality by removing noise, outliers and duplicate data through data cleaning; correct deviations caused by factors such as instruments and environment through data calibration to ensure data accuracy; unify the data in the time dimension through time synchronization to facilitate the analysis of data change trends; solve the processing problems caused by format differences through data format unification; explore the intrinsic connections between data through data association to enhance the understanding of tunnel status; and further ensure data reliability through data verification, so that the processed data is more standardized, accurate and interrelated, laying a solid foundation for subsequent tunnel construction analysis, risk assessment and other work.

[0025] Optionally, in one embodiment of the present application, the expression of the correlation coefficient matrix is:

[0026]

[0027] in, X norm is a standard matrix, and p is the total number of eigenvalues.

[0028] Through the above technical solution, the embodiment of the present application can provide a clear and standardized quantitative method to describe the linear correlation between the variables. The expression is based on a standard matrix and clear calculation rules, that is, the matrix element values ​​are determined by performing specific operations on the corresponding elements, which can accurately reflect the strength of the correlation between the data. At the same time, key parameters such as the total number of eigenvalues ​​are clearly introduced, so that the entire calculation process is standardized and orderly, which is helpful for the subsequent accurate analysis of data features and mining of data internal laws based on the correlation coefficient matrix, and provides a reliable and scientific basis for further calculation of eigenvalues, eigenvectors, and risk assessment related to tunnel construction.

[0029] Optionally, in one embodiment of the present application, the calculation formula of the cumulative contribution rate is:

[0030]

[0031] Among them, λ iis the i-th eigenvalue, p is the total number of eigenvalues, and k is the number of selected eigenvalues.

[0032] Through the above technical scheme, the embodiment of the present application can clearly and unambiguously quantify the contribution of each eigenvalue in the whole, which is conducive to accurately measuring the impact of each eigenvalue on data changes, so as to reasonably select the principal component vector according to the contribution rate, and achieve data dimensionality reduction while ensuring that the data information loss is acceptable, thereby providing a scientific basis for subsequent more efficient analysis and processing of tunnel monitoring data, construction of accurate tunnel dynamic models, and assessment of construction risks.

[0033] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent monitoring and early warning method for shallow buried aeolian sand and soft surrounding rock tunnel construction as described in the above embodiment.

[0034] A fourth aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction.

[0035] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned intelligent monitoring and early warning method for the construction of shallow-buried aeolian sand and soft surrounding rock tunnels.

[0036] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0038] Figure 1 A flowchart of an intelligent monitoring and early warning method for shallow buried aeolian sand and soft surrounding rock tunnel construction provided according to an embodiment of the present application;

[0039] Figure 2 This is a structural schematic diagram of an intelligent monitoring and early warning device for shallow-buried aeolian sand and soft surrounding rock tunnel construction provided according to an embodiment of the present application;

[0040] Figure 3 The figure is a structural example diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0042] The following describes the intelligent monitoring and early warning method and device for the construction of a shallow-buried aeolian sand soft rock tunnel in the embodiment of the present application with reference to the accompanying drawings. In view of the related technologies mentioned in the above background technology, due to the serious data island phenomenon, limited data processing capacity and reliance on manual experience and early warning models that are difficult to cope with complex geological conditions, resulting in information fragmentation and difficulty in accurately identifying risk factors and trends, thereby affecting the safety and quality of tunnel construction, the present application provides an intelligent monitoring and early warning method for the construction of a shallow-buried aeolian sand soft rock tunnel, in which multiple tunnel monitoring data can be collected to provide comprehensive information for subsequent analysis; data consistency processing is performed to ensure that data quality meets the conditions and reduce data problems; data is standardized to obtain a standard matrix and further calculate the correlation coefficient matrix, eigenvalues ​​and eigenvectors, so as to mine the internal relationship of the data; the principal component vector is determined based on the cumulative contribution rate of the eigenvalues, and the tunnel monitoring data is mapped to the principal component space to obtain fused data, so as to achieve data dimension reduction and denoising; finally, the fused data is used to construct a tunnel dynamic model to obtain the actual risk assessment results, which can accurately assess the risk, effectively cope with the complex construction environment, and ensure the safety and quality of construction. This solves the problem in related technologies of severe data silos, limited data processing capabilities, reliance on manual experience, and early warning models that are difficult to cope with complex geological conditions, resulting in information fragmentation and difficulty in accurately identifying risk factors and trends, thus affecting the safety and quality of tunnel construction.

[0043] Specifically, Figure 1 A flow chart of an intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction provided in an embodiment of the present application.

[0044] like Figure 1 As shown, the intelligent monitoring and early warning method for shallow buried aeolian sand soft surrounding rock tunnel construction includes the following steps:

[0045] In step S101, a plurality of tunnel monitoring data of a shallowly buried aeolian sand soft rock tunnel is collected.

[0046] It can be understood that tunnel monitoring is the process of measuring the physical quantities of the tunnel and its surrounding environment using various instruments and equipment during tunnel construction and operation. The monitoring data includes but is not limited to arch subsidence data, peripheral convergence data, surface settlement data and surrounding rock pressure data.

[0047] Specifically, data can be collected through sensor networks, video surveillance, construction records, geological survey data, external data sources, and other methods or channels. The sensor network is to arrange various sensors at the tunnel construction site and surrounding areas, such as displacement sensors, stress sensors, vibration sensors, environmental parameter sensors, etc., to monitor and record key information such as the tunnel's structural response, geological changes, and construction environment in real time. Video surveillance uses high-definition cameras to monitor key locations such as the inside of the tunnel and the entrances and exits in real time, and record image data during the construction process. Video data can not only be used to intuitively observe the construction status, but also to extract useful information through image processing technology, such as but not limited to personnel flow, equipment operation, etc. Construction records are collected through manual recording or automated recording systems. Parameters during the construction process, such as but not limited to excavation speed, support structure installation, grouting volume, concrete strength, etc., reflect the specific operation process and effect of tunnel construction. Geological survey data is to obtain basic information such as the lithology, structure, and hydrogeological conditions of the stratum where the tunnel is located by combining the previous geological survey report and on-site geological observations. External data sources may include, but are not limited to, data from external agencies such as meteorological stations and hydrological monitoring stations, which are used to assess the risks of natural disasters that may be encountered during construction (such as, but not limited to, heavy rains, floods, landslides, etc.).

[0048] Optionally, in one embodiment of the present application, multiple tunnel monitoring data of a shallow-buried aeolian sand and soft rock tunnel are collected, including: based on multiple monitoring points set on the tunnel periphery, arch and key support structures of the shallow-buried aeolian sand and soft rock tunnel, deformation and stress distribution in multiple tunnel monitoring data are collected; and / or based on the tunnel section, convergence deformation and arch settlement in multiple tunnel monitoring data are obtained.

[0049] In the actual implementation process, monitoring points are set up around the tunnel, on the arch and key support structures, and precision measuring instruments such as tunnel convergence meters, levels, and high-precision total stations are used to conduct regular or continuous observations of the measuring points to obtain key data such as deformation and stress distribution, covering aspects such as excavation face stability and support structure response. Horizontal baseline monitoring methods or three-dimensional laser scanning technology can also be used to accurately measure the tunnel section to obtain data such as the tunnel's convergence deformation and arch subsidence.

[0050] Specifically, deformation refers to the displacement of the tunnel wall and surrounding rock mass after tunnel excavation due to the redistribution of surrounding rock stress and the application of support structure; stress distribution refers to the distribution and change law of internal stress in the surrounding rock after tunnel excavation; the stability of the excavation face is one of the key issues in the tunnel construction process. By monitoring the deformation and stress distribution of the excavation face, the stability state of the excavation face can be evaluated, whether there is a risk of collapse or roof fall, and corresponding reinforcement measures can be taken; the support structure is an important means to maintain the stability of the tunnel. By monitoring the stress and deformation of the support structure, it can be evaluated whether it meets the design requirements and whether it is necessary to adjust the support parameters or take other reinforcement measures.

[0051] The embodiments of the present application can utilize sensor networks to monitor key information in real time with the help of various sensors, record image data through video monitoring and extract useful content with the help of image processing technology, use construction records to reflect the construction operation process and effect, combine geological survey data to grasp the basic information related to the stratum, and refer to external data sources to evaluate the risk of natural disasters, etc. At the same time, it is also optional to collect deformation and stress distribution based on monitoring points set on the tunnel periphery, arch and key support structures, and obtain convergence deformation and arch settlement based on the tunnel section, so as to obtain rich and key tunnel monitoring data in a comprehensive, multi-angle and targeted manner, and provide strong data support for subsequent related analysis and tunnel construction and operation.

[0052] In step S102, consistency processing is performed on a plurality of tunnel monitoring data to obtain a plurality of tunnel data satisfying a preset condition.

[0053] It is understandable that consistency processing is the process of adjusting and standardizing tunnel monitoring data obtained from multiple sources or different measurement methods. Due to the fact that multiple instruments with different precision, different measurement time intervals, different measurement personnel and other factors may be used in tunnel monitoring, the obtained data may have differences in format, precision, range, etc. For example, some data may be accurate to two decimal places, while others may only be accurate to integer places; or some data are measured once an hour, while others are measured once a day. Through consistency processing, these data can be compared and analyzed under the same standards.

[0054] Optionally, in one embodiment of the present application, consistency processing is performed on multiple tunnel monitoring data, including: data cleaning of multiple tunnel monitoring data; data calibration of multiple tunnel monitoring data; time synchronization of multiple tunnel monitoring data; data format unification of multiple tunnel monitoring data; data association of multiple tunnel monitoring data; and data verification of multiple tunnel monitoring data.

[0055] Specifically, data cleaning is a data preprocessing step, which mainly includes but is not limited to reviewing, verifying and correcting the original data to improve the data quality, as follows:

[0056] 1) Data review is to identify errors, missing values ​​and outliers in the data. For erroneous data, for example, in tunnel monitoring data, data that is obviously inconsistent with the actual situation may appear due to instrument failure, human recording errors, etc., such as recording a negative number when measuring distance, or the data format is wrong; for missing values, it means that some attribute values ​​of some data records in the data set are missing. In tunnel monitoring, some monitoring data may be missing due to sensor failure, transmission problems or data record omissions. For example, the arch subsidence data of a certain measuring point in the tunnel was not recorded at a certain moment; for outliers, it refers to data that obviously deviates from other data points. These data may be caused by measurement errors, special working conditions (such as emergencies during tunnel construction), etc.

[0057] 2) Data verification mainly checks whether the data conforms to certain rules and logic. In tunnel monitoring data processing, this may involve checking whether the correlation between data is reasonable. For example, according to theory and experience, the tunnel vault settlement and peripheral convergence are correlated to a certain extent. If the change trends of these two data are completely opposite and do not conform to physical laws, there may be a problem.

[0058] 3) Data correction There are many ways to deal with missing values. If the record containing the missing value has little impact on the overall analysis, or the missing data accounts for a high proportion, you can consider deleting the entire record containing the missing value. You can also use the mean, median or mode to fill the missing value. For erroneous data, it is usually necessary to find out the cause of the error. If it is a record error, it can be directly modified to the correct value. If the data error is caused by instrument failure, it may be necessary to re-measure or estimate based on other relevant data. For outliers, it is necessary to handle them with caution. First, it is necessary to determine whether the outliers are caused by real special circumstances. For example, during the construction of a tunnel, a blasting operation may cause a short abnormal peak in the surrounding convergence data. If it can be determined that this is the case, the outlier can be retained and recorded as data for special working conditions; if the outlier is caused by measurement errors and other reasons, and it has a greater interference with the overall data analysis, it can be considered to be corrected or deleted. Correction of outliers can use smoothing methods, such as the moving average method, to correct the outliers to values ​​that are more coordinated with the surrounding data; or if it is determined that the outliers are unreasonable, they can be deleted directly, but the impact on the overall data quality and analysis results after deletion should also be considered.

[0059] Data calibration refers to adjusting the data by a certain method so that the data can accurately reflect the real state of the measured object. For some instruments and equipment, calibration can be performed by adjusting the hardware. For example, some high-precision pressure boxes are equipped with calibration screws. The zero point and range of the pressure box can be adjusted by rotating the calibration screws, so that the pressure box can accurately measure pressure under different pressure environments. Use software algorithms to calibrate the data. For example, for measurement data affected by temperature, a temperature compensation model can be established. By building a temperature sensor into the instrument, the ambient temperature is obtained in real time, and then the measurement data is corrected in the software according to the pre-established relationship between temperature and measurement error (such as including but not limited to linear relationship or polynomial relationship). Use known standard reference values ​​to calibrate the data. In tunnel monitoring, some standard reference points or reference objects can be set in the laboratory or on site. For example, some benchmark points with known elevations are set in the tunnel, and these benchmark points are measured regularly with high-precision measuring instruments as standard references, and then these benchmark points are used to calibrate the elevation data of other monitoring points.

[0060] Time synchronization, which can also be understood as time axis alignment, refers to the careful adjustment of monitoring data from different data sources (such as displacement monitors, stress sensors, environmental parameter monitors, etc.) according to the same time base to ensure that all data points can be compared and analyzed within the same time frame. This process usually involves technical means such as timestamp calibration, data interpolation or resampling to ensure the consistency and continuity of data in the time dimension.

[0061] Data format unification, which can also be understood as unit standardization, is the process of converting all monitoring data into the same unit of measurement to facilitate comprehensive analysis and comparison across physical quantities. It aims to eliminate the barriers to comparison and analysis between different monitoring data and parameters caused by inconsistent units, ensure that all data are processed in the same dimension or scale, and improve data consistency and comparability.

[0062] Data association refers to the process of discovering and establishing the intrinsic relationship between different data items in tunnel monitoring data. These data items can be different monitoring indicators at the same monitoring location (such as but not limited to the arch subsidence data and peripheral convergence data at the same measuring point), or data at different monitoring locations that are spatially or temporally associated (such as but not limited to the surrounding rock pressure data of adjacent monitoring sections).

[0063] Data verification can verify the accuracy of data by checking the correlation between data. For example, if the correlation between the vault settlement data and the surrounding convergence data of a certain measuring point does not conform to normal physical laws and engineering experience, it may indicate that at least one of the two data is wrong or interfered by abnormal factors. Data quality problems can be discovered and corrected in a timely manner to improve data reliability.

[0064] The embodiments of the present application can improve data quality by removing errors, missing values ​​and outliers through data cleaning; correct errors caused by instruments, environment and other factors through data calibration to ensure data accuracy; make all data consistent in the time dimension through time synchronization to facilitate subsequent analysis; solve the inconvenience caused by format differences through data format unification; help to explore the intrinsic connection between data through data association to better understand the tunnel status; further ensure data reliability through data verification. The combination of these processes makes the multiple tunnel data finally obtained meet the conditions, laying a solid data foundation for more accurate subsequent tunnel-related analysis, evaluation and decision-making.

[0065] In step S103, the plurality of tunnel data are standardized to obtain a standard matrix, and a correlation coefficient matrix of the standard matrix is ​​calculated to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix.

[0066] In the actual implementation process, after standardizing multiple tunnel data, these standardized data are arranged in a matrix in a certain order to obtain a standard matrix, and the data after consistency processing are standardized to obtain X norm The matrix calculation process is as follows:

[0067] Standardize the p-dimensional sample observation data X:

[0068]

[0069] in,

[0070] The correlation coefficient matrix is ​​a matrix used to measure the strength of the linear relationship between each column (i.e., each monitoring indicator) in the standard matrix. The expression of the correlation coefficient matrix for the above standard matrix is:

[0071]

[0072] in, The correlation coefficient matrix can intuitively show the linear correlation between different tunnel monitoring indicators. The value of the correlation coefficient is between -1 and 1. The closer the absolute value is to 1, the stronger the linear correlation between the two indicators; the closer the absolute value is to 0, the weaker the linear correlation. By analyzing the correlation coefficient matrix, we can understand whether the different monitoring indicators are positively correlated (correlation coefficient greater than 0), negatively correlated (correlation coefficient less than 0) or almost uncorrelated.

[0073] Furthermore, the eigenvalues ​​and eigenphasors of the correlation coefficient matrix are calculated. By analyzing the eigenvalues ​​and eigenvectors, the tunnel monitoring data can be reduced in dimension (for example, the main components can be extracted using eigenvalues ​​and eigenvectors in principal component analysis), or used for data classification and clustering analysis, to help better understand the inherent structure and laws of tunnel monitoring data.

[0074] The embodiment of the present application can standardize multiple tunnel data to eliminate the differences in dimensions and orders of magnitude between the data, convert the data to a unified scale, make the data comparable, and avoid unreasonable results in subsequent calculations and analyses due to these differences. After obtaining the standard matrix, the correlation coefficient matrix is ​​calculated, which can intuitively show the strength of the linear relationship between the various monitoring indicators and help to gain a deeper understanding of the internal correlation structure of the data. Further calculation of the eigenvalues ​​and eigenvectors of the correlation coefficient matrix can clarify the variance size and main change direction of the data in all directions. In this way, the data can be reduced in dimension, such as extracting the main components in principal component analysis, and can also be used for data classification and clustering analysis, effectively mining the internal laws of the data, and providing strong support for efficient processing and accurate analysis of tunnel data.

[0075] In step S104, the principal component vector of the eigenvector is determined according to the cumulative contribution rate of the eigenvalue, so as to map the plurality of tunnel monitoring data into the principal component space to obtain fused data.

[0076] Specifically, the cumulative contribution rate of the eigenvalue is selected from the first k principal components and is defined by the eigenvalue λ:

[0077]

[0078] Among them, λ i is the i-th eigenvalue, p is the total number of eigenvalues, and k is the number of selected eigenvalues. A larger contribution rate indicates that the corresponding principal component contains stronger information about the original variable. Generally, the cumulative contribution rate of more than 85% is used as the criterion for selecting the principal component, so as to maximize the retention of the original information, and finally map the p-dimensional vector to the selected k-dimensional coordinate space.

[0079] Furthermore, the fused data is obtained through principal component analysis transformation. The principal component analysis transformation is based on the orthogonal linear relationship of information volume. The linear projection method is used to project the data into a new coordinate space so that the new component vectors are distributed according to the amount of information. The first principal component contains the largest amount of information. The calculation process is as follows:

[0080]

[0081] Among them, F1 is the first principal component, F k is the kth principal component, a ij is the principal component coefficient and should satisfy:

[0082] 1) F i , F j Mutually unrelated (i≠j, i,j=1,2,…,p);

[0083] 2) The variance of F1 is greater than the variance of F2 which is greater than the variance of F3;

[0084] 3)

[0085] The embodiment of the present application can determine the principal component vector of the feature vector based on the cumulative contribution rate of the eigenvalue, scientifically and rationally screen out the most representative components, and achieve dimensionality reduction while retaining the main information of multiple tunnel monitoring data. The data is then mapped to the principal component space to obtain fused data, which can not only remove redundant information and noise in the original data, making the data more concise and presenting key features more concentratedly, but also facilitate the subsequent data visualization, classification, anomaly detection and other analysis work, thereby more efficiently and accurately grasping the overall condition of the tunnel, and providing strong support for tunnel construction and operation-related decisions.

[0086] In step S105, a tunnel dynamic model of a shallow-buried aeolian sand tunnel with soft surrounding rock is constructed using the fused data to obtain an actual risk assessment result of the shallow-buried aeolian sand tunnel with soft surrounding rock.

[0087] It can be understood that the tunnel dynamic model can simulate and predict the construction status of the tunnel in real time based on the monitoring data after data fusion processing, and can capture the dynamic changes of the tunnel during the construction process, including but not limited to key parameters such as tunnel deformation, stress distribution, and response of support structures.

[0088] In the actual implementation process, the tunnel dynamic model can reflect the construction status of the tunnel in real time, including the stress changes and deformation of the surrounding rock, the stress state of the support structure, etc. Using advanced sensing technology and Internet of Things technology, the model can realize comprehensive monitoring of the tunnel construction process to ensure the real-time and accuracy of the data. At the same time, combined with big data analysis technology, the model can deeply explore the laws and trends behind the data and provide strong support for construction decisions.

[0089] On the one hand, based on real-time monitoring, the tunnel dynamic model also has a strong risk assessment capability. Through risk assessment algorithms and expert systems, the model can dynamically assess the potential risks in the tunnel construction process based on monitoring data. These assessment results can not only help engineers identify risk sources in a timely manner, but also provide accurate risk level judgments, providing a scientific basis for taking targeted risk control measures.

[0090] On the other hand, the tunnel dynamic model can also realize accurate judgment of construction risks. By comparing monitoring data with safety thresholds, the model can quickly identify situations beyond the safety range and issue early warning signals. This early warning mechanism not only improves the safety of the construction process, but also can take effective preventive measures before risks occur to avoid or reduce losses.

[0091] The embodiments of the present application can achieve comprehensive monitoring through advanced sensing and Internet of Things technologies to ensure real-time and accurate data. Combined with big data analysis, it can deeply explore data regularity and trends to assist in construction decision-making. It also has powerful risk assessment capabilities. With the help of risk assessment algorithms and expert systems, it can dynamically assess potential risks based on monitoring data, help engineers identify risk sources, judge risk levels, and provide a scientific basis for taking prevention and control measures. At the same time, it can also accurately judge construction risks by comparing data with safety thresholds, issue early warning signals in a timely manner, improve construction safety, and prevent risks in advance to avoid or reduce losses.

[0092] According to the intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction proposed in the embodiment of the present application, comprehensive information can be provided for subsequent analysis by collecting multiple tunnel monitoring data; the data is processed for consistency to ensure that the data quality meets the conditions and reduce data problems; the data is standardized to obtain a standard matrix and the correlation coefficient matrix, eigenvalues ​​and eigenvectors are further calculated to mine the internal relationship of the data; the principal component vector is determined based on the cumulative contribution rate of the eigenvalues, and the tunnel monitoring data is mapped to the principal component space to obtain fused data to achieve data dimensionality reduction and denoising; finally, the fused data is used to construct a tunnel dynamic model to obtain the actual risk assessment results, which can accurately assess the risks, effectively respond to complex construction environments, and ensure construction safety and quality.

[0093] Next, the intelligent monitoring and early warning device for shallow buried aeolian sand and soft surrounding rock tunnel construction proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0094] Figure 2 It is a block diagram of an intelligent monitoring and early warning device for shallow-buried aeolian sand and soft surrounding rock tunnel construction according to an embodiment of the present application.

[0095] like Figure 2 As shown, the intelligent monitoring and early warning device 10 for shallow buried aeolian sand soft surrounding rock tunnel construction includes: a data acquisition module 100, a data processing module 200, a standardization module 300, a data fusion module 400 and a monitoring and early warning module 500.

[0096] Specifically, the data collection module 100 is used to collect a plurality of tunnel monitoring data of a shallowly buried aeolian sand soft surrounding rock tunnel.

[0097] The data processing module 200 is used to perform consistency processing on a plurality of tunnel monitoring data to obtain a plurality of tunnel data that meet preset conditions.

[0098] The standardization module 300 is used to standardize a plurality of tunnel data to obtain a standard matrix, and calculate a correlation coefficient matrix of the standard matrix to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix.

[0099] The data fusion module 400 is used to determine the principal component vector of the eigenvector according to the cumulative contribution rate of the eigenvalue, so as to map the multiple tunnel monitoring data into the principal component space to obtain fused data.

[0100] The monitoring and early warning module 500 is used to construct a tunnel dynamic model of a shallow-buried aeolian sand and soft surrounding rock tunnel by using fused data, so as to obtain an actual risk assessment result of the shallow-buried aeolian sand and soft surrounding rock tunnel.

[0101] Optionally, in one embodiment of the present application, the data acquisition module 100 includes: a first acquisition unit and a second acquisition unit.

[0102] Among them, the first collection unit is used to collect deformation and stress distribution in multiple tunnel monitoring data based on multiple monitoring points set up on the tunnel periphery, arch and key support structure of the shallow buried aeolian sand soft rock tunnel.

[0103] The second acquisition unit is used to obtain the convergence deformation and the vault settlement in the multiple tunnel monitoring data based on the tunnel section.

[0104] Optionally, in one embodiment of the present application, the data processing module 200 includes: a cleaning unit, a calibration unit, a synchronization unit, a unification unit, an association unit and a verification unit.

[0105] Among them, the cleaning unit is used to clean the data of multiple tunnel monitoring data.

[0106] The calibration unit is used to calibrate the data of multiple tunnel monitoring data.

[0107] The synchronization unit is used to synchronize the time of multiple tunnel monitoring data.

[0108] The unification unit is used to unify the data formats of multiple tunnel monitoring data.

[0109] The association unit is used to associate multiple tunnel monitoring data.

[0110] The verification unit is used to verify the data of multiple tunnel monitoring data.

[0111] Optionally, in one embodiment of the present application, the expression of the correlation coefficient matrix is:

[0112]

[0113] in, X norm is a standard matrix, and p is the total number of eigenvalues.

[0114] Optionally, in one embodiment of the present application, the calculation formula of the cumulative contribution rate is:

[0115]

[0116] Among them, λ i is the i-th eigenvalue, p is the total number of eigenvalues, and k is the number of selected eigenvalues.

[0117] It should be noted that the aforementioned explanation of the embodiment of the intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction is also applicable to the intelligent monitoring and early warning device for shallow-buried aeolian sand and soft surrounding rock tunnel construction of this embodiment, and will not be repeated here.

[0118] According to the intelligent monitoring and early warning device for shallow-buried aeolian sand and soft surrounding rock tunnel construction proposed in the embodiment of the present application, it is possible to provide comprehensive information for subsequent analysis by collecting multiple tunnel monitoring data; perform consistency processing on the data to ensure that the data quality meets the conditions and reduce data problems; standardize the data to obtain a standard matrix and further calculate the correlation coefficient matrix, eigenvalues ​​and eigenvectors to mine the internal relationship of the data; determine the principal component vector based on the cumulative contribution rate of the eigenvalues, map the tunnel monitoring data to the principal component space to obtain fused data, and achieve data dimensionality reduction and denoising; finally, use the fused data to construct a tunnel dynamic model to obtain actual risk assessment results, which can accurately assess risks, effectively respond to complex construction environments, and ensure construction safety and quality.

[0119] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0120] A memory 301 , a processor 302 , and a computer program stored in the memory 301 and executable on the processor 302 .

[0121] When the processor 302 executes the program, the intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction provided in the above embodiment is implemented.

[0122] Furthermore, the electronic device further comprises:

[0123] The communication interface 303 is used for communication between the memory 301 and the processor 302 .

[0124] The memory 301 is used to store computer programs that can be run on the processor 302 .

[0125] The memory 301 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0126] If the memory 301, the processor 302 and the communication interface 303 are implemented independently, the communication interface 303, the memory 301 and the processor 302 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0127] Optionally, in a specific implementation, if the memory 301, the processor 302 and the communication interface 303 are integrated on a chip, the memory 301, the processor 302 and the communication interface 303 can communicate with each other through an internal interface.

[0128] The processor 302 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0129] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction.

[0130] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned intelligent monitoring and early warning method for the construction of a shallow-buried aeolian sand and soft surrounding rock tunnel.

[0131] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0132] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0133] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0134] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0135] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0136] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0137] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0138] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An intelligent monitoring and early warning method for shallow buried aeolian sand soft rock tunnel construction, characterized in that: The following steps are involved: Collect monitoring data of multiple tunnels in shallow aeolian sand and soft surrounding rock tunnels; Performing consistency processing on the plurality of tunnel monitoring data to obtain a plurality of tunnel data satisfying preset conditions; Standardizing the plurality of tunnel data to obtain a standard matrix, and calculating a correlation coefficient matrix of the standard matrix to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix; Determine the principal component vector of the eigenvector according to the cumulative contribution rate of the eigenvalue, so as to map the plurality of tunnel monitoring data into the principal component space to obtain fused data; The fused data is used to construct a tunnel dynamic model of the shallow-buried aeolian sand and soft surrounding rock tunnel to obtain an actual risk assessment result of the shallow-buried aeolian sand and soft surrounding rock tunnel.

2. The method according to claim 1, characterized in that The multiple tunnel monitoring data collected for the shallowly buried aeolian sand soft rock tunnel include: Based on multiple monitoring points set on the tunnel periphery, arch and key support structure of the shallow buried aeolian sand soft rock tunnel, the deformation and stress distribution in the multiple tunnel monitoring data are collected; And / or based on the tunnel section, the convergence deformation and the crown settlement in the plurality of tunnel monitoring data are obtained.

3. The method according to claim 1, characterized in that The performing consistency processing on the plurality of tunnel monitoring data includes: Performing data cleaning on the plurality of tunnel monitoring data; Performing data calibration on the plurality of tunnel monitoring data; Performing time synchronization on the multiple tunnel monitoring data; Unifying the data formats of the plurality of tunnel monitoring data; Performing data association on the plurality of tunnel monitoring data; The multiple tunnel monitoring data are verified.

4. The method according to claim 1, characterized in that: The expression of the correlation coefficient matrix is: in, X norm is a standard matrix, and p is the total number of eigenvalues.

5. The method according to claim 4, characterized in that The calculation formula of the cumulative contribution rate is: Among them, λ i is the i-th eigenvalue, p is the total number of eigenvalues, and k is the number of selected eigenvalues.

6. An intelligent monitoring and early warning device for shallow buried aeolian sand and soft surrounding rock tunnel construction, characterized in that: include: Data acquisition module, used to collect multiple tunnel monitoring data of shallow buried aeolian sand soft rock tunnel; A data processing module, used for performing consistency processing on the plurality of tunnel monitoring data to obtain a plurality of tunnel data meeting preset conditions; A standardization module, used for standardizing the plurality of tunnel data to obtain a standard matrix, and calculating a correlation coefficient matrix of the standard matrix to calculate eigenvalues ​​and eigenvectors of the correlation coefficient matrix; A data fusion module, used for determining the principal component vector of the eigenvector according to the cumulative contribution rate of the eigenvalue, so as to map the plurality of tunnel monitoring data into the principal component space to obtain fused data; The monitoring and early warning module is used to construct a tunnel dynamic model of the shallow-buried aeolian sand and soft surrounding rock tunnel by using the fused data to obtain the actual risk assessment result of the shallow-buried aeolian sand and soft surrounding rock tunnel.

7. The device according to claim 6, characterized in that The acquisition module comprises: The first collection unit is used to collect deformation and stress distribution in the monitoring data of the plurality of tunnels based on a plurality of monitoring points set on the tunnel periphery, the arch and the key support structure of the shallow buried aeolian sand soft rock tunnel; The second acquisition unit is used to obtain the convergence deformation and the vault settlement in the plurality of tunnel monitoring data based on the tunnel section.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent monitoring and early warning method for shallow buried aeolian sand and soft surrounding rock tunnel construction as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the intelligent monitoring and early warning method for shallow-buried aeolian sand and soft surrounding rock tunnel construction as described in any one of claims 1 to 5.

10. A computer program product, characterized in that It comprises a computer program, characterized in that the computer program is executed to implement the intelligent monitoring and early warning method for the construction of a shallow-buried aeolian sand and soft surrounding rock tunnel as described in any one of claims 1 to 5.

Images