Early warning method and system for metro double-side extension large-scale foundation pit separated warehouse analysis construction

Abstract

The invention provides an early warning method and system for metro double-side extension large foundation pit separated warehouse analysis construction. And multi-dimensional fusion processing is carried out on the multi-source heterogeneous data of the underground complex of the subway station, so that effective integration and utilization of the data are realized. Spatial interpolation and dynamic characteristic simulation are carried out by adopting a Kriging interpolation algorithm, a three-dimensional geologic structure dynamically changing along with construction is generated, and the accuracy and prediction capability of a geologic model are improved. And in combination with a parameterized multi-scale modeling technology, seamless conversion from two-dimensional engineering drawings and three-dimensional scanning data to three-dimensional representation data of the underground complex of the subway station is realized, and the practicability and integrity of the model are enhanced. A multi-objective optimization algorithm is used for carrying out three-dimensional finite element numerical simulation warehouse division analysis, the construction plan of the subway station underground complex is optimized, and the construction efficiency is improved. The construction process is digitally simulated and monitored in real time, trend prediction and anomaly detection are achieved, the safety and quality of subway station underground complex construction are ensured, and the construction risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an early warning method and system for compartment analysis and construction of a large-scale foundation pit for double-sided expansion of a subway. Background Art

[0002] As an important urban infrastructure, the three-dimensional modeling and construction management of subway station underground complexes have always been the focus of research in the engineering field. Traditional subway station modeling methods mainly rely on two-dimensional drawings and a single data source, which is difficult to fully reflect the complexity of underground space. In recent years, with the development of technologies such as three-dimensional laser scanning and geological exploration, multi-source data fusion has become a new trend in underground space modeling. Some researchers have proposed a subway station modeling method based on BIM (Building Information Modeling) to improve the accuracy and integrity of the model by integrating multiple information. At the same time, in terms of construction management, some scholars have begun to explore the application of artificial intelligence and big data analysis technologies to the optimization and monitoring of the construction process; especially when the large foundation pits on both sides of the subway station are divided into compartments, there are strict requirements for the dynamic response capabilities in the modeling and construction management of the subway station.

[0003] However, the existing technology still has some shortcomings. First, the fusion processing of multi-source heterogeneous data still faces challenges, especially when processing data of different scales and formats, it is difficult to achieve seamless connection. Secondly, traditional modeling methods often ignore the dynamic changes of the geological environment and cannot accurately reflect the long-term evolution of underground space. Furthermore, the existing construction management methods are mostly focused on static planning and lack the ability to respond to dynamic changes in the construction process in real time. Finally, in terms of anomaly detection and early warning, the sensitivity and accuracy of existing methods need to be improved, and it is difficult to detect and deal with potential construction risks in a timely manner. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an early warning method and system for compartment analysis and construction of large-scale foundation pits for subway double-sided construction, which is used to improve the efficiency and accuracy of compartment analysis and construction early warning of large-scale foundation pits for subway double-sided construction.

[0005] The present invention provides an early warning method for compartment analysis and construction of large-scale foundation pits for subway double-sided expansion, comprising: Perform multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the subway station underground complex to obtain a comprehensive data set; Performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm to obtain a three-dimensional geological structure that changes dynamically with construction; Performing parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; A three-dimensional finite element numerical simulation analysis of the adjacent station expansion pit is performed on the three-dimensional representation data of the subway station structure by a multi-objective optimization algorithm to obtain a target compartment scheme; Performing a construction process simulation on the target compartment scheme and the three-dimensional representation data of the subway station structure to obtain digital representation data of the construction process including time and cost information; Time series analysis and multi-dimensional feature extraction are performed on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and trend prediction and anomaly detection are performed on the construction process feature vector set through a support vector regression algorithm to obtain construction process prediction results and abnormal alarm data.

[0006] The present invention also provides an early warning system for analyzing the construction of large-scale foundation pits on both sides of a subway, including: The fusion module is used to perform multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the underground complex of the subway station to obtain a comprehensive data set; A simulation module, for performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm, to obtain a three-dimensional geological structure including dynamic changes with construction; A modeling module is used to perform parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; A compartment division module is used to perform a compartment division analysis of the three-dimensional finite element numerical simulation of the adjacent station expansion pit on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm to obtain a target compartment division plan; A simulation module, used to simulate the construction process of the target compartment scheme and the three-dimensional representation data of the subway station structure, and obtain digital representation data of the construction process including time and cost information; The detection module is used to perform time series analysis and multi-dimensional feature extraction on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and perform trend prediction and anomaly detection on the construction process feature vector set through a support vector regression algorithm to obtain construction process prediction results and abnormal alarm data.

[0007] In the technical solution provided by the present invention, a comprehensive data set is obtained by multi-dimensional fusion processing of multi-source heterogeneous data of the underground complex of the subway station collected in advance, which realizes the effective integration of data from different sources and different formats, and provides a comprehensive and unified data basis for subsequent analysis. This fusion processing not only improves the integrity and consistency of the data, but also greatly reduces data redundancy and improves data processing efficiency. Secondly, the Kriging interpolation algorithm is used to perform spatial interpolation and dynamic characteristic simulation on the comprehensive data set to obtain a three-dimensional geological structure that changes dynamically with construction, which significantly improves the accuracy and prediction ability of the geological model. The Kriging interpolation algorithm takes into account spatial correlation and can more accurately estimate the geological parameters of unknown points, while the dynamic characteristic simulation captures the changing characteristics of the geological structure over time, providing more reliable geological information for engineering design and construction. Then, the pre-collected two-dimensional engineering drawings, three-dimensional scanning data and three-dimensional geological structures are parametrically modeled at multiple scales to obtain three-dimensional representation data of the subway station structure containing multi-system information. This innovative modeling method realizes seamless conversion from two-dimensional to three-dimensional, and organically combines geological information with engineering structure information, greatly improving the integrity and practicality of the model. The characteristics of multi-scale modeling enable the model to adapt to different accuracy requirements, and it can reflect the overall structure and show local details. The three-dimensional finite element numerical simulation of the adjacent station expansion pit is carried out on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm, and the target compartment scheme is obtained, which greatly improves the scientificity and rationality of the construction planning. Intelligent compartmentation takes into account multiple objective functions, such as construction efficiency, cost control, safety, etc., and can find the best balance between multiple key indicators, providing strong support for project management. The construction process is simulated for the target compartment scheme and the three-dimensional representation data of the subway station structure, and the digital representation data of the construction process containing time and cost information is obtained. This simulation process can not only foresee potential construction problems, but also optimize the construction progress and resource allocation, significantly improve construction efficiency and reduce risks. Finally, the digital representation data of the construction process and the real-time construction data collected in real time are subjected to time series analysis and multi-dimensional feature extraction to obtain the feature vector set of the construction process, and the trend prediction and anomaly detection of the feature vector set of the construction process are carried out through the support vector regression algorithm to obtain the prediction results of the construction process and the abnormal alarm data. It realizes real-time monitoring and early warning of the construction process, can detect abnormal situations in time, prevent safety accidents and ensure construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 The present invention is a flowchart of an early warning method for compartment analysis and construction of a large-scale foundation pit for subway double-sided expansion in an embodiment of the present invention.

[0010] Figure 2 It is a schematic diagram of an early warning system for compartmental analysis and construction of large-scale foundation pits for subway double-sided expansion in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0013] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0014] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , Figure 1 Flow chart of an early warning method for analyzing and constructing a large-scale foundation pit for subway double-sided expansion according to an embodiment of the present invention. Figure 1 As shown, the following steps are included: S101, performing multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the subway station underground complex to obtain a comprehensive data set; S102, performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm to obtain a three-dimensional geological structure that changes dynamically with construction; S103, performing parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings, three-dimensional scanning data and three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; S104, using a multi-objective optimization algorithm to perform a three-dimensional finite element numerical simulation analysis of the adjacent station expansion pit on the three-dimensional representation data of the subway station structure, and obtain a target compartment scheme; S105, simulating the construction process of the target compartment scheme and the three-dimensional representation data of the subway station structure to obtain digital representation data of the construction process including time and cost information; S106. Perform time series analysis and multi-dimensional feature extraction on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and perform trend prediction and anomaly detection on the construction process feature vector set through a support vector regression algorithm to obtain a construction process prediction result and abnormal alarm data.

[0015] Specifically, the multi-source heterogeneous data collected in advance are subjected to multi-dimensional fusion processing. These data include geological survey reports, construction drawings, historical monitoring data, etc. Through data cleaning, standardization, feature extraction and other steps, the data from different sources are unified in format and coordinate system. For example, for geological drilling data, it may be necessary to remove outliers, unify depth units, extract key stratigraphic information, etc. The principal component analysis algorithm is used for dimensionality reduction to reduce data redundancy, and the tensor decomposition algorithm is used to mine the potential relationship between data. The final comprehensive data set contains geological, structural, environmental and other information. Next, the Kriging interpolation algorithm is used to perform spatial interpolation and dynamic characteristic simulation on the comprehensive data set. Kriging interpolation is a geostatistical method that can consider spatial correlation and is suitable for the interpolation of geological data. In the data, the variogram analysis is first performed on the data, the spatial correlation is calculated, and then the interpolation estimation is performed using this information. At the same time, the temporal change trend of geological characteristics is considered, and the dynamic characteristic function is constructed to predict the geological state at future time points. It not only fills the data gaps between sampling points, but also reflects the dynamic change characteristics of geological structures.

[0016] Subsequently, parametric multi-scale modeling was performed on the pre-collected 2D engineering drawings and 3D scanning data and the 3D geological structure obtained in the previous step. First, the 2D drawings were vectorized to extract key structural lines and feature points. For the 3D scanning data, point cloud noise reduction and filtering were performed to extract key structural features. Then, these data were fused with the 3D geological structure to construct a parametric geometric model. Multi-scale modeling allows structural details to be represented at different scales. For example, key structural nodes can be represented at centimeter-level accuracy, while non-critical areas can be represented at meter-level accuracy. This method not only ensures the accuracy of the model, but also improves the modeling efficiency. Next, a multi-objective optimization algorithm was used to perform a compartment analysis of the 3D finite element numerical simulation of the foundation pit for the adjacent station expansion on the 3D representation data of the subway station structure. Compartmentalization refers to dividing the entire project into multiple relatively independent construction units. Multiple objectives such as structural complexity, construction difficulty, and resource allocation were considered. First, the 3D representation data was spatially divided, and then the structural complexity and construction difficulty of each sub-area were evaluated. A multi-objective genetic algorithm was used to optimize the compartmentalization scheme to balance factors such as construction efficiency, cost, and safety.

[0017] Then, the construction process simulation is carried out for the target compartment scheme and the three-dimensional representation data of the subway station structure. First, the construction process is decomposed and a preliminary construction schedule is formulated. Then, resource allocation and cost estimation are carried out, and the discrete event simulation algorithm is used to simulate the entire construction process. This simulation takes into account factors such as equipment operation and personnel operation, and can reflect various situations that may be encountered in actual construction. Finally, time series analysis and multi-dimensional feature extraction are carried out on the digital representation data of the construction process and the real-time construction data collected in real time. First, the data is synchronized and aligned, and then time window division and feature engineering are carried out. Principal component analysis is used to reduce the dimension and extract key features. Then, the support vector regression algorithm is used to build a prediction model to predict the future construction status. At the same time, abnormal thresholds and judgment rules are set to identify potential abnormal points and generate abnormal alarm data.

[0018] By executing the above steps, a comprehensive data set is obtained by multi-dimensional fusion processing of the multi-source heterogeneous data of the subway station underground complex collected in advance, which realizes the effective integration of data from different sources and different formats, and provides a comprehensive and unified data basis for subsequent analysis. This fusion processing not only improves the integrity and consistency of the data, but also greatly reduces data redundancy and improves data processing efficiency. Secondly, the Kriging interpolation algorithm is used to perform spatial interpolation and dynamic characteristic simulation on the comprehensive data set to obtain a three-dimensional geological structure that changes dynamically with construction, which significantly improves the accuracy and prediction ability of the geological model. The Kriging interpolation algorithm takes into account spatial correlation and can more accurately estimate the geological parameters of unknown points, while the dynamic characteristic simulation captures the changing characteristics of the geological structure over time, providing more reliable geological information for engineering design and construction. Then, the pre-collected two-dimensional engineering drawings, three-dimensional scanning data and three-dimensional geological structures are parametrically modeled at multiple scales to obtain three-dimensional representation data of the subway station structure containing multi-system information. This innovative modeling method realizes seamless conversion from two-dimensional to three-dimensional, and organically combines geological information with engineering structure information, greatly improving the integrity and practicality of the model. The characteristics of multi-scale modeling enable the model to adapt to different accuracy requirements, and it can reflect the overall structure and show local details. The three-dimensional finite element numerical simulation of the adjacent station expansion pit is carried out on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm, and the target compartment scheme is obtained, which greatly improves the scientificity and rationality of the construction planning. Intelligent compartmentation takes into account multiple objective functions, such as construction efficiency, cost control, safety, etc., and can find the best balance between multiple key indicators, providing strong support for project management. The construction process is simulated for the target compartment scheme and the three-dimensional representation data of the subway station structure, and the digital representation data of the construction process containing time and cost information is obtained. This simulation process can not only foresee potential construction problems, but also optimize the construction progress and resource allocation, significantly improve construction efficiency and reduce risks. Finally, the digital representation data of the construction process and the real-time construction data collected in real time are subjected to time series analysis and multi-dimensional feature extraction to obtain the feature vector set of the construction process, and the trend prediction and anomaly detection of the feature vector set of the construction process are carried out through the support vector regression algorithm to obtain the prediction results of the construction process and the abnormal alarm data. It realizes real-time monitoring and early warning of the construction process, can detect abnormal situations in time, prevent safety accidents and ensure construction quality.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Data cleaning is performed on the pre-collected multi-source heterogeneous data of the subway station underground complex to remove outliers and noise data, and obtain preliminarily processed multi-source data; (2) Perform data standardization on the multi-source data after preliminary processing, unify the dimensions and units of different data sources, and obtain standardized multi-source data; (3) Perform feature extraction on the standardized multi-source data, extract the key features of each data source, and obtain multi-source feature data; (4) Perform dimensionality reduction processing on multi-source feature data through principal component analysis algorithm to obtain feature data after dimensionality reduction; (5) Performing data alignment on the feature data after dimensionality reduction to obtain aligned feature data; (6) Perform multi-dimensional correlation analysis on the aligned feature data through the tensor decomposition algorithm to obtain correlated feature data; (7) Calculate the data fusion weight of the associated feature data to obtain the data fusion weight coefficient; (8) Perform weighted fusion on the associated feature data according to the data fusion weight coefficient to obtain preliminary fusion data, and perform data consistency check on the preliminary fusion data to obtain verified fusion data; (9) Perform spatiotemporal interpolation on the verified fused data to obtain complete fused data, and then unify the data format of the complete fused data to obtain a comprehensive data set.

[0020] Specifically, data cleaning is performed to remove outliers and noise data. Outliers refer to data points that deviate significantly from the normal range, such as extreme readings caused by equipment failure. Noise data is inaccurate data caused by random fluctuations or interference. By setting a reasonable threshold, statistical methods such as box plots or Z-score methods are used to identify and eliminate these data, thereby obtaining preliminarily processed multi-source data. Next, the preliminarily processed multi-source data is standardized to unify the dimensions and units of different data sources. This is crucial because data from different sources may use different units or scales. For example, geological data may be in meters, while structural data may be in centimeters. Through standardization, all data are converted to the same scale range, usually [0,1] or [-1,1]. Commonly used standardization methods include minimum-maximum normalization and Z-score normalization. The processed data is convenient for subsequent analysis and comparison.

[0021] Then, feature extraction is performed on the standardized multi-source data to extract the key features of each data source. Feature extraction aims to extract the information that best represents the essential characteristics of the data from the original data. For geological data, the features that may be extracted include stratum thickness, lithology category, porosity, etc. For structural data, it may include key node coordinates, component size, etc. By reducing the data dimension, the efficiency of subsequent processing is improved. Then, the principal component analysis (PCA) algorithm is used to reduce the dimension of the multi-source feature data. PCA is a commonly used unsupervised learning method that projects the original high-dimensional data into a new low-dimensional space through linear transformation while retaining the main information of the data. PCA first calculates the covariance matrix of the data, then solves the eigenvalues ​​and eigenvectors, and selects the eigenvectors corresponding to the largest eigenvalues ​​as the new basis. This can greatly reduce the data dimension while retaining the main variability of the data.

[0022] The next key step is to align the feature data after dimensionality reduction. Data alignment ensures that data from different sources are consistent in time and space. For example, data collected at different time points are mapped to the same time axis, or spatial data in different coordinate systems are converted to a unified reference system. This lays the foundation for subsequent multi-dimensional correlation analysis. Subsequently, multi-dimensional correlation analysis is performed on the aligned feature data using the tensor decomposition algorithm. Tensor decomposition is an effective tool for processing multi-dimensional data and can reveal multi-dimensional relationships hidden in the data. Common tensor decomposition methods include Tucker decomposition and CP decomposition. It can capture the potential correlation between different data sources and provide an important basis for subsequent data fusion.

[0023] Next, the data fusion weight is calculated for the associated feature data. The weight calculation takes into account the reliability, importance and relevance of each data source. Commonly used methods include expert scoring method, entropy weight method and hierarchical analysis method. The calculated weight coefficient reflects the contribution of each data source to the final fusion result. Then, the associated feature data is weighted fused according to the data fusion weight coefficient to obtain preliminary fusion data. The process of weighted fusion can be understood as integrating the information of different data sources to obtain a more comprehensive and reliable description. Subsequently, the preliminary fusion data is checked for data consistency to ensure the reliability and coherence of the fusion results. The consistency check can be achieved through cross-validation or comparison with known reliable reference data.

[0024] Finally, the verified fused data is interpolated in time and space to fill in the data gaps. Time and space interpolation takes into account the temporal and spatial distribution characteristics of the data. Common methods include Kriging interpolation and inverse distance weighted method. The complete fused data obtained after interpolation covers the entire study area and time range. The last step is to unify the data format of the complete fused data to ensure that all data conform to the predetermined format standards for subsequent application and analysis. For example, in a subway station expansion and construction project, the initial data included geotechnical parameters of 100 geological drilling points, 3D laser scanning point cloud data of 1,000 square meters, and 10 sets of 2D construction drawings. The data cleaning stage identified and deleted 5% of outliers, such as obviously deviated stratum thickness data. Standardization processing unified data of different units (such as meters, centimeters, and megapascals) to the [0,1] interval. The feature extraction stage extracted 20 key features from the geological data, including the average thickness of each stratum, strength parameters, etc. The principal component analysis reduced the original 100-dimensional feature space to 30 dimensions, retaining 95% of the information. Data alignment unifies data collected at different times onto a timeline based on the project start date. Tensor decomposition reveals the correlation pattern between geological conditions, structural loads, and settlement deformation. Weight calculation gives a weight of 0.4 to geological data, 0.35 to structural data, and 0.25 to monitoring data. After weighted fusion, data consistency checks found and corrected 2% of data inconsistencies. The final spatiotemporal interpolation expands the originally discrete data points into a 100m × 100m × 50m three-dimensional spatial grid, forming a continuous digital expression of the underground space.

[0025] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Partition the comprehensive data set to obtain a partitioned data set, perform variogram analysis on each sub-region in the partitioned data set, calculate the spatial correlation, and obtain the variogram parameters; (2) Perform Kriging weight calculation on each sub-region according to the variation function parameters to obtain the interpolation weight coefficient, and normalize the interpolation weight coefficient to obtain the normalized interpolation weight; (3) Perform local Kriging interpolation on each sub-region in the partitioned data set, estimate the unknown points by normalizing the interpolation weights, and obtain preliminary interpolation results; (4) Perform boundary processing on the preliminary interpolation results to obtain continuous interpolation data; (5) Perform time series analysis on the continuous interpolation data to identify the time variation trend of geological characteristics and obtain time variation characteristic data. Based on the time variation characteristic data, a dynamic characteristic function is constructed to describe the variation law of geological parameters over time and obtain the dynamic characteristic function. (6) Using dynamic characteristic functions to perform time extrapolation on continuous interpolation data, the geological state at future time points is predicted to obtain predicted geological data; (7) Conduct uncertainty analysis on the predicted geological data, evaluate the reliability of the prediction results, obtain confidence interval data, and revise the predicted geological data based on the confidence interval data to obtain revised geological prediction data; (8) The revised geological prediction data is reconstructed in three-dimensional space to generate a three-dimensional geological structure that changes dynamically with construction.

[0026] Specifically, the comprehensive data set is partitioned to obtain a partitioned data set. The purpose of data partitioning is to divide the entire study area into several sub-areas in order to more accurately capture local spatial variability. For each sub-area, a variogram analysis is performed, the spatial correlation is calculated, and the variogram parameters are obtained. The variogram is a function that describes the correlation between spatial variables, and its expression is:

[0027] in, is the variance function value, is the distance between sampling points, The interval is The sample logarithm of and The location and The sample value at .

[0028] Kriging weights are calculated for each sub-region according to the variation function parameters to obtain the interpolation weight coefficient. Kriging interpolation is the optimal linear unbiased estimation method, and its interpolation formula is:

[0029] in, is the predicted value of the point to be estimated, is the weight of the i-th known point, is the number of known points involved in the estimation.

[0030] The interpolation weight coefficients are normalized to obtain normalized interpolation weights. Normalization ensures that the sum of all weights is 1, which ensures the unbiasedness of the estimate. Then, local Kriging interpolation is performed on each sub-region in the partitioned data set, and the unknown points are estimated by normalized interpolation weights to obtain preliminary interpolation results. Next, the preliminary interpolation results are subjected to boundary processing to obtain continuous interpolation data. Boundary processing solves the possible discontinuity problem between sub-regions and ensures a smooth transition of the interpolation results in the entire study area. Time series analysis is performed on the continuous interpolation data to identify the time-varying trends of geological characteristics and obtain time-varying characteristic data. Time series analysis methods include moving average, exponential smoothing, etc. A dynamic characteristic function is constructed based on the time-varying characteristic data to describe the changing patterns of geological parameters over time. The dynamic characteristic function can be expressed as:

[0031] in, is the geological parameter over time The change function of , a, b, c are unknown coefficients, is a random error term.

[0032] Through the dynamic characteristic function, the continuous interpolation data is extrapolated in time to predict the geological state at future time points and obtain the predicted geological data. The predicted geological data is subjected to uncertainty analysis to evaluate the reliability of the prediction results and obtain the confidence interval data. Uncertainty analysis takes into account factors such as model error and parameter uncertainty, and usually uses the Monte Carlo simulation method. The predicted geological data is corrected according to the confidence interval data to obtain the corrected geological prediction data, which improves the reliability of the prediction results. Finally, the corrected geological prediction data is reconstructed in three-dimensional space to generate a three-dimensional geological structure that changes dynamically with construction. In the process of three-dimensional space reconstruction, a three-dimensional interpolation algorithm (such as trilinear interpolation) is used to convert discrete prediction data points into a continuous three-dimensional spatial expression.

[0033] For example, in a subway station expansion construction project, the study area is a spatial range of 100m×100m×50m, with a total of 200 geological drilling sampling points. First, the study area is divided into 10 sub-areas, each with about 20 sampling points. Perform a variogram analysis on each sub-area to obtain the variogram parameters. For example, the variogram of the first sub-area is a spherical model with a base value of 0.8 and a range of 15m. The Kriging weights are calculated based on the variogram parameters. For the estimated point (50,50,25), the 5 nearest known points are selected for interpolation, and the normalized interpolation weights are 0.3, 0.25,0.2, 0.15, and 0.1, respectively. These weights are used to estimate the unknown points and obtain the geological parameter values ​​of the point. Repeat this process for all sub-areas, and perform boundary processing to obtain continuous interpolation data for the entire study area. Time series analysis shows that the stratum settlement rate changes as a quadratic function, and the dynamic characteristic function is fitted. (Unit: mm / day). This function is used to predict the geological state in the next three months. Uncertainty analysis shows that the 95% confidence interval of the prediction result is ±2 mm.

[0034] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Perform vector processing on the pre-collected two-dimensional engineering drawings, extract key structural lines and feature points, obtain vectorized drawing data, and perform coordinate system conversion on the vectorized drawing data to obtain vector data in a unified coordinate system; (2) Perform point cloud denoising and filtering on the 3D scanning data to obtain simplified point cloud data, and perform feature recognition on the simplified point cloud data through a feature extraction algorithm to extract key structural features and obtain a set of structural feature points; (3) Perform data fusion on the vector data and structural feature point set of the unified coordinate system, establish the correspondence between the two-dimensional drawing and the three-dimensional scanning data, obtain preliminary fusion data, and build a parametric geometric model based on the preliminary fusion data, define structural parameters and constraints, and obtain a parametric geometric expression; (4) Perform multi-scale decomposition on the parameterized geometric expression to obtain multi-scale structural hierarchical data, and perform detail enhancement on the multi-scale structural hierarchical data to obtain enhanced multi-scale data; (5) Spatial registration is performed on the enhanced multi-scale data and the three-dimensional geological structure to establish the spatial relationship between the geological environment and the engineering structure, thus obtaining the three-dimensional representation data of the subway station structure containing multi-system information.

[0035] Specifically, two-dimensional engineering drawings are vectorized to convert the geometric information in the drawings into a vector format that can be recognized and processed by computers. Vectorization includes steps such as edge detection, line tracking, and polygon recognition. Through these steps, key structural lines and feature points are extracted to obtain vectorized drawing data. Subsequently, the coordinate system of the vectorized drawing data is converted to unify the local coordinate systems that may be used in different drawings into a global coordinate system to obtain vector data of the unified coordinate system. Next, the three-dimensional scanning data is subjected to point cloud denoising and filtering. Point cloud data is composed of a large number of discrete three-dimensional coordinate points, which usually contain noise and redundant information. The denoising process uses a statistical outlier removal algorithm to remove points that are obviously deviated from the main body. The filtering uses a voxel grid method to divide the space into equal-sized cubic grids, and the points in each grid are replaced by their centroids to obtain simplified point cloud data. Then, the simplified point cloud data is feature identified by a feature extraction algorithm to extract key structural features. Common feature extraction methods include normal vector estimation, curvature calculation, and local feature descriptors, etc., through which a set of structural feature points is obtained. The next important step is to fuse the vector data and the structural feature point set of the unified coordinate system. To establish the correspondence between the 2D drawing and the 3D scan data, the iterative closest point (ICP) algorithm is usually used for registration. The ICP algorithm iteratively minimizes the distance between the two sets of data to achieve precise alignment. After fusion, the preliminary fused data is obtained, and a parametric geometric model is constructed based on this data. Parametric modeling defines structural parameters and constraints, so that the model can flexibly change shape and size by adjusting parameters to obtain a parametric geometric expression.

[0036] The purpose of multi-scale decomposition of parameterized geometric expressions is to capture structural details at different scales. Multi-scale decomposition usually uses wavelet transform or Laplace pyramid algorithm to decompose the original model into hierarchical structures of different resolutions to obtain multi-scale structural hierarchical data. Subsequently, the multi-scale structural hierarchical data is enhanced in detail, and the detailed performance of the model at each scale is improved through techniques such as high-frequency information compensation or super-resolution reconstruction to obtain enhanced multi-scale data. Finally, the enhanced multi-scale data and the three-dimensional geological structure are spatially registered to establish the spatial relationship between the geological environment and the engineering structure. Using spatial registration algorithms, such as feature-based registration or intensity-based registration methods, the engineering structure model is accurately positioned in the geological environment, thereby obtaining three-dimensional representation data of the subway station structure containing multi-system information.

[0037] For example, in a subway station expansion and construction project, the initial data included 10 sets of 2D CAD engineering drawings and 3D laser scanning point cloud data covering an area of ​​1,000 square meters. After the 2D drawings were vectorized, 5,000 key structural lines and 2,000 feature points were extracted. The coordinate system conversion unified all data to the National Geodetic Coordinate System 2000. The 3D point cloud data originally contained 500 million points, which were reduced to 20 million points through noise reduction and filtering, retaining the main structural information. The feature extraction algorithm identified 500,000 structural feature points from the streamlined point cloud, including key components such as walls, columns, and pipes. During the data fusion process, the ICP algorithm was used for 20 iterations, and finally the precise alignment of 2D and 3D data was achieved, and the fusion error was controlled within 5 mm. The parametric geometric model defines 200 key parameters and 500 constraints, which can flexibly adjust important dimensions such as platform width and column spacing. Multi-scale decomposition divides the model into 5 scale levels, ranging from centimeter-level accuracy to meter-level accuracy. After detail enhancement, the highest resolution can reach millimeter level. Finally, by matching with the three-dimensional geological structure, the precise correspondence between the engineering structure and the surrounding geological environment within a depth of 50 meters was achieved, forming a comprehensive three-dimensional representation dataset containing multi-system information such as structure, geology, and equipment.

[0038] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Perform spatial division on the three-dimensional representation data of the subway station structure, obtain an initial zoning scheme based on the expansion scope of the acquired neighboring stations, and optimize the boundaries of the initial zoning scheme to obtain an optimized zoning scheme; (2) Evaluate the structural complexity of each sub-region in the optimized zoning scheme. Use the three-dimensional finite element algorithm to calculate the structural density and connectivity indicators including neighboring stations to obtain complexity score data. Then, perform a preliminary bin division on the sub-regions based on the complexity score data to obtain candidate bin division schemes. (3) Conduct a construction difficulty analysis on the candidate warehouse division schemes to obtain a construction difficulty index, and adjust the candidate warehouse division schemes according to the construction difficulty index to obtain an adjusted warehouse division scheme; (4) Conduct resource allocation simulation on the adjusted warehouse allocation plan to obtain resource demand data, and balance and optimize the warehouse allocation plan based on the resource demand data to obtain a balanced warehouse allocation plan; (5) The balanced warehouse allocation scheme is optimized through a multi-objective optimization algorithm to obtain the target warehouse allocation scheme.

[0039] Specifically, the intelligent compartmentalization analysis of the three-dimensional structural characterization data of subway stations is a complex process. First, the three-dimensional structural characterization data of subway stations is spatially divided to obtain an initial partitioning scheme. Using the octree segmentation algorithm, the entire three-dimensional space is recursively divided into several subspaces according to the acquired neighboring station expansion range, until the complexity of each subspace meets the preset threshold. Subsequently, the boundaries of the initial partitioning scheme are optimized, and the sub-area boundaries are adjusted using the Markov random field model to better adapt to the structural characteristics, thereby obtaining an optimized partitioning scheme. The structural complexity of each sub-area in the optimized partitioning scheme is evaluated by three-dimensional finite element algorithm calculations, and the structural density and connectivity indicators are calculated. Structural density index The calculation formula is:

[0040] in, is the volume of the structural member within the sub-region, is the total volume of the subregion. Connectivity index The calculation formula is:

[0041] in, is the number of components connected to other sub-areas, is the total number of components in the sub-area. Based on these two indicators, the complexity score data is obtained, and the sub-areas are initially divided into warehouses to obtain candidate warehouse division schemes.

[0042] Next, we analyze the construction difficulty of the candidate warehouse solutions and obtain the construction difficulty index. The calculation formula is:

[0043] in, , , , is the weight coefficient, is the accessibility indicator, is the spatial constraint index. The candidate compartmentalization scheme is adjusted according to the construction difficulty index to obtain the adjusted compartmentalization scheme.

[0044] The resource allocation simulation is performed on the adjusted warehouse allocation plan, and the resource requirements of each warehouse are calculated using the linear programming model to obtain the resource requirement data. The objective function of the resource allocation model is:

[0045] in, Is to use resources Allocate to sub-warehouse The cost, is the allocation decision variable. The warehouse allocation scheme is balanced and optimized according to the resource demand data to obtain the balanced warehouse allocation scheme. Finally, the balanced warehouse allocation scheme is optimized by multi-objective genetic algorithm. The mathematical expression of the multi-objective optimization problem is:

[0046] in, is the objective function vector, including construction efficiency, cost, safety and other objectives, and They are inequality and equality constraints respectively. This optimization problem is solved by multi-objective genetic algorithm, and finally the target warehouse division scheme is obtained.

[0047] For example, the three-dimensional representation data of a subway station expansion project contains 1 million grid cells. The initial space division uses the octree algorithm to divide the space into 64 sub-regions. After boundary optimization, the number of sub-regions is adjusted to 58. In the structural complexity evaluation, the structural density index and connectivity index of each sub-region are calculated. For example, the structural density of a sub-region , connectivity The initial division merged 58 sub-areas into 20 candidate sub-areas. In the construction difficulty analysis, the weight coefficient is assumed to be , , , , the construction difficulty index of a sub-warehouse The resource allocation simulation takes into account three types of resources: human resources, equipment, and materials. The linear programming model contains 60 decision variables and 100 constraints. The multi-objective genetic algorithm sets the population size to 100 and the evolutionary generations to 500. The final target warehouse solution contains 15 warehouses, and the average construction difficulty index of each warehouse is 0.65, which increases the resource utilization rate by 15%.

[0048] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Decompose the construction process of the target warehouse plan to obtain a detailed process list, and formulate a preliminary construction schedule based on the detailed process list to obtain an initial schedule; (2) Allocate resources to the initial schedule to obtain a resource allocation plan, and adjust the initial schedule based on the resource allocation plan to obtain an optimized schedule; (3) Conduct construction cost estimation for the optimized schedule, calculate the direct and indirect costs of each process, obtain cost estimation data, and optimize the schedule based on the cost estimation data to obtain a cost-optimized schedule; (4) Using discrete event simulation algorithm to simulate the construction process of the cost-optimized schedule, obtain construction process simulation data, and perform statistical analysis on the construction process simulation data to obtain construction performance evaluation results; (5) Based on the results of the construction performance evaluation, the construction plan is optimized and adjusted, the schedule and resource allocation are updated, and digital representation data of the construction process containing time and cost information is obtained.

[0049] Specifically, the construction process of the target warehouse plan is decomposed, and the work breakdown structure (WBS) technology is used to break down the construction tasks of each warehouse into specific processes. The process decomposition takes into account the construction logic, technical requirements and resource constraints to obtain a detailed process list. Subsequently, a preliminary construction schedule is formulated based on the detailed process list, and the critical path method (CPM) is used to determine the dependencies and time arrangements between processes to obtain an initial schedule. Next, resources are allocated to the initial schedule. The resource allocation process uses a resource balancing algorithm, taking into account the availability and efficiency of resources such as manpower, equipment and materials. The algorithm first identifies resource conflicts, and then resolves the conflicts by adjusting the start time of non-critical processes to obtain a resource allocation plan. According to the resource allocation plan, the initial schedule is adjusted, which may involve adjusting the sequence of processes or modifying the duration, and finally an optimized schedule is obtained.

[0050] The next important step is to estimate the construction cost of the optimized schedule. Cost estimation includes the calculation of direct and indirect costs. Direct costs include material costs, labor costs, and equipment costs, which are obtained through bill of quantities and unit price analysis. Indirect costs include management fees, taxes, etc., which are calculated through the proportion method or quota method. These calculations result in cost estimation data, and then the cost-time trade-off analysis (TCTO) technology is used to optimize the schedule. TCTO analysis adjusts the construction period and resource allocation to find the lowest total cost solution and obtain the cost-optimized schedule. Then, the construction process of the cost-optimized schedule is simulated by the discrete event simulation algorithm. Discrete event simulation regards the construction process as a series of discrete events, simulating factors such as construction environment, equipment operation, and personnel operation. During the simulation process, the Monte Carlo method is used to generate random variables to simulate the uncertainty in construction, such as weather effects, equipment failures, etc. The simulation results obtain the simulation data of the construction process, including the actual start and end time of each process, resource utilization, cost consumption, and other information.

[0051] Statistical analysis is performed on the construction process simulation data to calculate key performance indicators, such as the completion rate of the construction period, the cost control rate, and the resource utilization efficiency. The construction performance evaluation results are obtained through these indicators to provide a basis for subsequent optimization. Finally, the construction plan is optimized and adjusted according to the construction performance evaluation results. The optimization process uses heuristic algorithms, such as simulated annealing or genetic algorithms, to adjust the process schedule, resource allocation, and construction methods while meeting the constraints to improve the overall construction efficiency. The optimization results update the schedule and resource allocation, and finally obtain the digital representation data of the construction process containing time and cost information.

[0052] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Synchronize and align the digital representation data of the construction process and the real-time construction data collected in real time to obtain aligned time series data, and clean the aligned time series data to obtain cleaned time series data; (2) Divide the cleaned time series data into time windows, set an appropriate time window size, obtain a segmented time series data set, and perform feature engineering on the segmented time series data set to extract time domain and frequency domain features to obtain a preliminary feature set; (3) The preliminary feature set is reduced in dimension through principal component analysis to obtain the feature data after dimension reduction, and the feature importance of the feature data after dimension reduction is evaluated to obtain the feature vector set of the construction process; (4) Model training is performed on the construction process feature vector set through support vector regression algorithm to construct a prediction model to obtain a trained prediction model. The trained prediction model is then used to predict the construction status at a future time point to obtain a construction process prediction result. (5) Perform anomaly detection on the predicted results of the construction process, set anomaly thresholds and judgment rules, identify potential anomaly points, and obtain anomaly alarm data.

[0053] It should be noted that the two types of data are synchronized and aligned to ensure the consistency of timestamps. The dynamic time warping (DTW) algorithm is used to align data with different sampling frequencies and time scales to the same time axis to obtain aligned time series data. Subsequently, the aligned time series data is cleaned, including removing outliers, filling missing values, and eliminating noise. The local outlier factor (LOF) algorithm is used for outlier detection, the multiple interpolation method is used for missing value filling, and the wavelet transform denoising is used for noise elimination, and finally the cleaned time series data is obtained. Next, the cleaned time series data is divided into time windows. The size of the time window is determined according to the data characteristics and analysis objectives. The sliding window technology is usually used, and the window size may vary from a few hours to a few days. After division, a segmented time series data set is obtained, and each segment contains complete data within a certain time range. Then, feature engineering is performed on the segmented time series data set to extract time domain and frequency domain features. The time domain features include statistics such as mean, standard deviation, kurtosis, and skewness, while the frequency domain features are extracted through fast Fourier transform (FFT), including main frequency components, power spectrum density, etc. These features constitute the preliminary feature set.

[0054] Subsequently, the preliminary feature set was reduced in dimension by principal component analysis (PCA). PCA calculates the covariance matrix of the features, finds the main eigenvectors, projects the high-dimensional data into a low-dimensional space, and retains the main variability of the data. The feature data after dimensionality reduction not only reduces the amount of data, but also removes redundant information. Then, the feature importance of the feature data after dimensionality reduction is evaluated, and the importance score of each feature is calculated using the random forest algorithm. The features with higher scores are selected to form the construction process feature vector set. Next, the support vector regression (SVR) algorithm is used to train the model of the construction process feature vector set. SVR is a powerful regression algorithm that can handle nonlinear relationships. During the training process, grid search and cross-validation are used to determine the optimal kernel function and hyperparameters. After the training is completed, a prediction model is obtained, which can capture the complex patterns and trends in the construction process. Subsequently, the trained prediction model is used to predict the construction status at future time points to obtain the construction process prediction results.

[0055] Finally, anomaly detection is performed on the predicted results of the construction process. Anomaly detection uses a density-based local anomaly detection algorithm (LOF) to set anomaly thresholds and judgment rules. The LOF algorithm calculates the local density of each data point relative to its neighborhood, and anomalies usually have lower local density. By comparing the LOF score with the preset threshold, potential anomalies are identified and anomaly alarm data is generated.

[0056] For example, the digital representation data of the construction process of a subway station expansion project includes 1,000 monitoring points, and data is collected at each point every hour for 30 days. Real-time construction data is collected every 15 minutes. The data synchronization and alignment process unifies the two types of data to the hourly scale, resulting in 72,000 data points. The data cleaning stage identifies and processes about 2% of outliers and missing values. The time window division uses a 6-hour sliding window to obtain 120 time windows. Feature engineering extracts 20 time domain features and 10 frequency domain features from each window. PCA dimensionality reduction reduces 30-dimensional features to 10 dimensions, retaining 95% of the information. Feature importance evaluation selects the 7 most important features to form a feature vector set. The SVR model training uses 80% of the data as the training set and 20% as the test set. The average absolute error of the model on the test set is 2.5%. The prediction model predicts the construction status in the next 7 days. The anomaly detection set the LOF threshold to 1.5 and identified 15 potential anomalies, of which 10 were confirmed to be true anomalies that require further attention and processing.

[0057] In a specific embodiment, the process of performing anomaly detection on the construction process prediction results, setting anomaly thresholds and judgment rules, identifying potential anomalies, and obtaining anomaly alarm data may specifically include the following steps: (1) Perform data standardization on the prediction results of the construction process, convert different indicators to the same scale, obtain standardized prediction data, and conduct historical data comparison and analysis on the standardized prediction data, calculate the deviation from the historical normal value, and obtain the deviation data; (2) Performing statistical analysis on the deviation data to obtain statistical characteristic values, and setting preliminary abnormal thresholds based on the statistical characteristic values ​​to obtain preliminary threshold settings; (3) fine-tuning the initial threshold setting to obtain an adjusted threshold setting, and formulating an abnormality judgment rule based on the adjusted threshold setting to obtain an abnormality judgment rule set; (4) Dynamic threshold calculation is performed on the standardized prediction data through the sliding window method. According to the time-varying characteristics of the data, a dynamic threshold sequence is obtained. The dynamic threshold sequence is then integrated with the anomaly judgment rule set to obtain an anomaly detection scheme. (5) According to the anomaly detection scheme, abnormal data points are identified on the standardized prediction data to obtain abnormal alarm data.

[0058] It should be noted that the construction process prediction results are standardized to convert different indicators to the same scale. The standardization process uses the Z-score method to obtain standardized prediction data, which is then compared and analyzed with historical data to calculate the deviation from the historical normal value. Then, the deviation data is statistically analyzed to calculate the mean. and standard deviation , these statistical characteristic values ​​are used to set the preliminary anomaly threshold. The preliminary anomaly threshold is usually set as:

[0059] in, k is an adjustable parameter, usually with a value of 2 or 3. This gives the initial threshold setting. is the preliminary abnormal threshold, which indicates the boundary value for judging whether a data point is abnormal. The mean of the deviation data reflects the average difference between the forecast value and the historical normal value. It is the standard deviation of the deviation data, which indicates the degree of dispersion of the deviation.

[0060] Subsequently, the initial threshold setting is fine-tuned. The fine-tuning process takes into account expert experience and historical abnormal data, and the adjustment formula is:

[0061] in, is the threshold adjustment value, It is the adjustment amount determined based on expert knowledge. Based on the adjusted threshold setting, anomaly judgment rules are formulated to form an anomaly judgment rule set.

[0062] Next, the dynamic threshold is calculated for the standardized prediction data using the sliding window method. The local statistical features are calculated in each window, and the dynamic threshold calculation formula is:

[0063] in, and The time The mean and standard deviation in the window. Get the dynamic threshold sequence .

[0064] Finally, the dynamic threshold sequence is fused with the anomaly judgment rule set to form an anomaly detection scheme. The fusion process uses the weighted average method:

[0065] in, is the weight coefficient. It is the final anomaly detection threshold. According to this anomaly detection scheme, the abnormal data points of the standardized prediction data are identified to obtain the abnormal alarm data.

[0066] The embodiment of the present invention also provides an early warning system for analyzing the construction of large-scale foundation pits on both sides of a subway. Figure 2 As shown in the figure, the early warning system for the analysis and construction of the large foundation pit on both sides of the subway specifically includes: The fusion module 201 is used to perform multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the underground complex of the subway station to obtain a comprehensive data set; A simulation module 202 is used to perform spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm to obtain a three-dimensional geological structure that changes dynamically with construction; Modeling module 203, used to perform parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; The compartment division module 204 is used to perform a compartment division analysis of the three-dimensional finite element numerical simulation of the adjacent station expansion pit on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm to obtain a target compartment division scheme; A simulation module 205 is used to simulate the construction process of the target compartment scheme and the three-dimensional representation data of the subway station structure to obtain digital representation data of the construction process including time and cost information; The detection module 206 is used to perform time series analysis and multi-dimensional feature extraction on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and perform trend prediction and anomaly detection on the construction process feature vector set through a support vector regression algorithm to obtain construction process prediction results and abnormal alarm data.

[0067] Through the collaborative work of the above modules, the multi-source heterogeneous data of the pre-collected subway station underground complex are processed in multiple dimensions to obtain a comprehensive data set, which realizes the effective integration of data from different sources and in different formats, and provides a comprehensive and unified data basis for subsequent analysis. This fusion processing not only improves the integrity and consistency of the data, but also greatly reduces data redundancy and improves data processing efficiency. Secondly, the Kriging interpolation algorithm is used to perform spatial interpolation and dynamic characteristic simulation on the comprehensive data set to obtain a three-dimensional geological structure that changes dynamically with construction, which significantly improves the accuracy and prediction ability of the geological model. The Kriging interpolation algorithm takes into account spatial correlation and can more accurately estimate the geological parameters of unknown points, while the dynamic characteristic simulation captures the changing characteristics of the geological structure over time, providing more reliable geological information for engineering design and construction. Then, the pre-collected two-dimensional engineering drawings, three-dimensional scanning data and three-dimensional geological structures are parametrically modeled at multiple scales to obtain three-dimensional representation data of the subway station structure containing multi-system information. This innovative modeling method realizes a seamless transition from two-dimensional to three-dimensional, and organically combines geological information with engineering structure information, greatly improving the integrity and practicality of the model. The characteristics of multi-scale modeling enable the model to adapt to different accuracy requirements, and it can reflect the overall structure and show local details. The three-dimensional finite element numerical simulation of the adjacent station expansion pit is carried out on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm, and the target compartment scheme is obtained, which greatly improves the scientificity and rationality of the construction planning. Intelligent compartmentation takes into account multiple objective functions, such as construction efficiency, cost control, safety, etc., and can find the best balance between multiple key indicators, providing strong support for project management. The construction process is simulated for the target compartment scheme and the three-dimensional representation data of the subway station structure, and the digital representation data of the construction process containing time and cost information is obtained. This simulation process can not only foresee potential construction problems, but also optimize the construction progress and resource allocation, significantly improve construction efficiency and reduce risks. Finally, the digital representation data of the construction process and the real-time construction data collected in real time are subjected to time series analysis and multi-dimensional feature extraction to obtain the feature vector set of the construction process, and the trend prediction and anomaly detection of the feature vector set of the construction process are carried out through the support vector regression algorithm to obtain the prediction results of the construction process and the abnormal alarm data. It realizes real-time monitoring and early warning of the construction process, can detect abnormal situations in time, prevent safety accidents and ensure construction quality.

[0068] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the embodiments, a person skilled in the art should understand that the specific implementation modes of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. An early warning method for analyzing the construction of large foundation pits on both sides of a subway, characterized by: include: Perform multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the subway station underground complex to obtain a comprehensive data set; Performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm to obtain a three-dimensional geological structure that changes dynamically with construction; Performing parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; A three-dimensional finite element numerical simulation analysis of the adjacent station expansion pit is performed on the three-dimensional representation data of the subway station structure by a multi-objective optimization algorithm to obtain a target compartment scheme; Performing a construction process simulation on the target compartment scheme and the three-dimensional representation data of the subway station structure to obtain digital representation data of the construction process including time and cost information; Time series analysis and multi-dimensional feature extraction are performed on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and trend prediction and anomaly detection are performed on the construction process feature vector set through a support vector regression algorithm to obtain construction process prediction results and abnormal alarm data.

2. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 1 is characterized in that: The step of performing multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the subway station underground complex to obtain a comprehensive data set includes: The pre-collected multi-source heterogeneous data of the subway station underground complex is cleaned to remove outliers and noise data, and the preliminarily processed multi-source data is obtained; Performing data standardization on the preliminarily processed multi-source data to unify the dimensions and units of different data sources to obtain standardized multi-source data; Performing feature extraction on the standardized multi-source data to extract key features of each data source to obtain multi-source feature data; Performing dimensionality reduction processing on the multi-source feature data by using a principal component analysis algorithm to obtain feature data after dimensionality reduction; Performing data alignment on the feature data after dimension reduction to obtain aligned feature data; Performing multi-dimensional correlation analysis on the aligned feature data by using a tensor decomposition algorithm to obtain correlation feature data; Performing data fusion weight calculation on the associated feature data to obtain a data fusion weight coefficient; Performing weighted fusion on the associated feature data according to the data fusion weight coefficient to obtain preliminary fusion data, and performing data consistency check on the preliminary fusion data to obtain verified fusion data; The verified fused data is subjected to spatiotemporal interpolation to obtain complete fused data, and the complete fused data is subjected to data format unification processing to obtain the comprehensive data set.

3. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 1 is characterized in that: The step of performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using the Kriging interpolation algorithm to obtain a three-dimensional geological structure that changes dynamically with construction includes: Partitioning the comprehensive data set to obtain a partitioned data set, performing a variogram analysis on each sub-region in the partitioned data set, calculating spatial correlation, and obtaining variogram parameters; Performing Kriging weight calculation on each sub-region according to the variation function parameters to obtain an interpolation weight coefficient, and normalizing the interpolation weight coefficient to obtain a normalized interpolation weight; Performing local Kriging interpolation on each sub-region in the partitioned data set, estimating unknown points by using the normalized interpolation weights, and obtaining a preliminary interpolation result; Performing boundary processing on the preliminary interpolation result to obtain continuous interpolation data; Performing time series analysis on the continuous interpolation data to identify the time variation trend of geological characteristics and obtain time variation characteristic data, and constructing a dynamic characteristic function based on the time variation characteristic data to describe the variation law of geological parameters over time and obtain the dynamic characteristic function; Performing time extrapolation on the continuous interpolation data through the dynamic characteristic function to predict the geological state at a future time point to obtain predicted geological data; Performing uncertainty analysis on the predicted geological data, evaluating the reliability of the prediction results, obtaining confidence interval data, and correcting the predicted geological data according to the confidence interval data to obtain corrected geological prediction data; The revised geological prediction data is reconstructed in three-dimensional space to generate a three-dimensional geological structure that changes dynamically with construction.

4. The early warning method for the analysis and construction of large-scale foundation pits for two-sided subway construction according to claim 1 is characterized in that: The step of performing parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information includes: Performing vector processing on the pre-collected two-dimensional engineering drawings, extracting key structural lines and feature points to obtain vectorized drawing data, and performing coordinate system conversion on the vectorized drawing data to obtain vector data of a unified coordinate system; Performing point cloud denoising and filtering on the three-dimensional scanning data to obtain simplified point cloud data, and performing feature recognition on the simplified point cloud data through a feature extraction algorithm to extract key structural features to obtain a structural feature point set; Performing data fusion on the vector data of the unified coordinate system and the set of structural feature points, establishing a corresponding relationship between the two-dimensional drawing and the three-dimensional scanning data, obtaining preliminary fusion data, and constructing a parametric geometric model based on the preliminary fusion data, defining structural parameters and constraints, and obtaining a parametric geometric expression; Performing multi-scale decomposition on the parameterized geometric expression to obtain multi-scale structural hierarchical data, and performing detail enhancement on the multi-scale structural hierarchical data to obtain enhanced multi-scale data; The enhanced multi-scale data and the three-dimensional geological structure are spatially aligned to establish a spatial relationship between the geological environment and the engineering structure, thereby obtaining three-dimensional representation data of the subway station structure containing multi-system information.

5. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 1 is characterized in that: The step of performing a three-dimensional finite element numerical simulation bin analysis of the adjacent station expansion pit on the three-dimensional representation data of the subway station structure by a multi-objective optimization algorithm to obtain a target bin solution includes: Performing spatial division on the three-dimensional representation data of the subway station structure, obtaining an initial partitioning scheme according to the acquired extension scope of neighboring stations, and optimizing the boundaries of the initial partitioning scheme to obtain an optimized partitioning scheme; Performing a structural complexity evaluation on each sub-region in the optimized zoning scheme, calculating the structural density and connectivity index including neighboring stations by a three-dimensional finite element algorithm, obtaining complexity score data, and performing a preliminary bin division on the sub-regions based on the complexity score data to obtain a candidate bin division scheme; Performing a construction difficulty analysis on the candidate warehouse division scheme to obtain a construction difficulty index, and adjusting the candidate warehouse division scheme according to the construction difficulty index to obtain an adjusted warehouse division scheme; Performing resource allocation simulation on the adjusted warehouse division plan to obtain resource demand data, and performing balance optimization on the warehouse division plan according to the resource demand data to obtain a balanced warehouse division plan; The balanced warehouse partitioning scheme is optimized by a multi-objective optimization algorithm to obtain a target warehouse partitioning scheme.

6. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 1 is characterized in that: The step of simulating the construction process of the target compartment scheme and the three-dimensional representation data of the subway station structure to obtain digital representation data of the construction process containing time and cost information includes: Decomposing the target warehouse division plan into construction procedures to obtain a detailed procedure list, and formulating a preliminary construction schedule according to the detailed procedure list to obtain an initial schedule; Allocating resources to the initial schedule to obtain a resource allocation plan, and adjusting the initial schedule according to the resource allocation plan to obtain an optimized schedule; Conducting construction cost estimation on the optimized schedule, calculating direct cost and indirect cost of each process to obtain cost estimation data, and conducting cost optimization on the schedule according to the cost estimation data to obtain a cost-optimized schedule; The construction process of the cost-optimized schedule is simulated by a discrete event simulation algorithm to obtain construction process simulation data, and the construction process simulation data is statistically analyzed to obtain a construction performance evaluation result; The construction plan is optimized and adjusted according to the construction performance evaluation results, the schedule and resource allocation are updated, and digital representation data of the construction process including time and cost information is obtained.

7. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 6 is characterized in that: The steps of performing time series analysis and multi-dimensional feature extraction on the digital representation data of the construction process and the real-time collected real-time construction data to obtain a construction process feature vector set, and performing trend prediction and anomaly detection on the construction process feature vector set by a support vector regression algorithm to obtain a construction process prediction result and anomaly alarm data include: Performing data synchronization and alignment on the digital representation data of the construction process and the real-time construction data collected in real time to obtain aligned time series data, and performing data cleaning on the aligned time series data to obtain cleaned time series data; Divide the cleaned time series data into time windows, set a suitable time window size, obtain a segmented time series data set, and perform feature engineering on the segmented time series data set to extract time domain and frequency domain features to obtain a preliminary feature set; Performing dimensionality reduction processing on the preliminary feature set through principal component analysis to obtain feature data after dimensionality reduction, and performing feature importance evaluation on the feature data after dimensionality reduction to obtain a construction process feature vector set; Model training is performed on the construction process feature vector set by using a support vector regression algorithm to construct a prediction model to obtain a trained prediction model, and the trained prediction model is used to predict the construction status at a future time point to obtain a construction process prediction result; Anomaly detection is performed on the construction process prediction results, anomaly thresholds and judgment rules are set, potential anomaly points are identified, and anomaly alarm data is obtained.

8. The early warning method for the analysis and construction of large-scale foundation pits for two-sided expansion of subways according to claim 7 is characterized in that: The step of performing anomaly detection on the construction process prediction result, setting anomaly thresholds and judgment rules, identifying potential anomaly points, and obtaining anomaly alarm data includes: Performing data standardization processing on the construction process prediction results, converting different indicators to the same scale to obtain standardized prediction data, and performing historical data comparison analysis on the standardized prediction data, calculating the deviation from the historical normal value, and obtaining deviation data; Performing statistical analysis on the deviation data to obtain statistical characteristic values, and setting a preliminary abnormal threshold value according to the statistical characteristic value to obtain a preliminary threshold value setting; Performing threshold fine-tuning on the preliminary threshold setting to obtain an adjusted threshold setting, and formulating an abnormality judgment rule based on the adjusted threshold setting to obtain an abnormality judgment rule set; Performing dynamic threshold calculation on the standardized prediction data by a sliding window method, obtaining a dynamic threshold sequence according to the time variation characteristics of the data, and fusing the dynamic threshold sequence with the anomaly judgment rule set to obtain an anomaly detection scheme; Abnormal data points are identified on the standardized prediction data according to the abnormal detection scheme to obtain abnormal alarm data.

9. An early warning system for the analysis and construction of large-scale foundation pits on both sides of subways, used to execute the early warning method for the analysis and construction of large-scale foundation pits on both sides of subways as claimed in any one of claims 1 to 8, characterized in that: include: The fusion module is used to perform multi-dimensional fusion processing on the pre-collected multi-source heterogeneous data of the underground complex of the subway station to obtain a comprehensive data set; A simulation module, for performing spatial interpolation and dynamic characteristic simulation on the comprehensive data set by using a Kriging interpolation algorithm, to obtain a three-dimensional geological structure including dynamic changes with construction; A modeling module is used to perform parametric multi-scale modeling on the pre-collected two-dimensional engineering drawings and three-dimensional scanning data and the three-dimensional geological structure to obtain three-dimensional representation data of the subway station structure containing multi-system information; A compartment division module is used to perform a compartment division analysis of the three-dimensional finite element numerical simulation of the adjacent station expansion pit on the three-dimensional representation data of the subway station structure through a multi-objective optimization algorithm to obtain a target compartment division plan; A simulation module, used to simulate the construction process of the target compartment scheme and the three-dimensional representation data of the subway station structure, and obtain digital representation data of the construction process including time and cost information; The detection module is used to perform time series analysis and multi-dimensional feature extraction on the digital representation data of the construction process and the real-time construction data collected in real time to obtain a construction process feature vector set, and perform trend prediction and anomaly detection on the construction process feature vector set through a support vector regression algorithm to obtain construction process prediction results and abnormal alarm data.

Images