Tunnel portal slope risk identification and analysis system based on artificial intelligence

Abstract

The invention discloses a tunnel portal slope risk identification and analysis system based on artificial intelligence, and relates to the field of data processing. Wherein a risk factor investigation and acquisition module, a portal risk simulation processing module, a tunnel risk simulation processing module, a risk factor conjoint analysis module and a slope risk identification and analysis module are arranged; the risk factor investigation and acquisition module is used for acquiring data information of a tunnel construction area; the hole risk simulation processing module is used for constructing a slope damage model according to the obtained data information; the tunnel risk simulation processing module is used for constructing a support failure model according to the obtained data information; the risk factor conjoint analysis module is used for generating a risk influence database; the slope risk identification and analysis module is used for acquiring corresponding risk identification data; according to the invention, the accuracy in the risk identification and analysis process is improved to a certain extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a tunnel portal slope risk identification and analysis system based on artificial intelligence. BACKGROUND

[0002] In the process of tunnel construction, the tunnel portal inevitably removes the rock-soil body of the slope toe due to the excavation of the slope and the excavation of the tunnel body, forming an unfavorable free surface, and the original balance state of the slope body is broken, thereby causing the instability of the entrance and exit slope, leading to the covering of the tunnel portal and the extrusion of the portal, thereby seriously threatening the safety of tunnel construction and operation. Therefore, identifying and analyzing the risk of the tunnel portal slope can improve the stability in the process of tunnel construction to a certain extent.

[0003] Through retrieval, the corresponding tunnel portal risk identification method in the prior art is to divide the tunnel portal into regions, monitor and analyze the obtained regional division results, and determine the final risk region according to the monitoring results. However, in this process, there is a certain waste of resources in the process of multiple regional division monitoring of the tunnel portal, and the risk region may be segmented in the multiple division process, thereby affecting the accuracy of risk identification to a certain extent. Therefore, how to avoid the resource waste caused by regional division in the process of tunnel portal risk identification and the lack of accuracy is a problem that needs to be solved. Therefore, the present application proposes a tunnel portal slope risk identification and analysis system based on artificial intelligence. SUMMARY

[0004] The purpose of the present application is to solve the problem of insufficient risk identification accuracy caused by excessive dependence on a single slope parameter in the prior art, and to propose a tunnel portal slope risk identification and analysis system based on artificial intelligence.

[0005] In order to achieve the above-mentioned purpose, the present application adopts the following technical scheme: A tunnel portal slope risk identification and analysis system based on artificial intelligence, comprising a slope risk identification system, wherein the slope risk identification system comprises a risk factor investigation and collection module, a portal risk simulation processing module, a tunnel risk simulation processing module, a risk factor joint analysis module and a slope risk identification and analysis module. The risk factor investigation and collection module is used to collect geological feature data and construction monitoring data corresponding to the corresponding tunnel construction area, and risk factor data and risk event data corresponding to the tunnel portal slope. The portal risk simulation processing module is used to set a portal slope physical model according to the corresponding geological feature data, risk factor data and risk event data, obtain corresponding slope deformation and damage characteristic data, and construct a slope damage model. The tunnel risk simulation processing module is used to set up a physical model of the tunnel entrance based on the corresponding geological feature data, risk factor data and risk event data, obtain the corresponding support deformation and failure feature data, and construct a support failure model. The risk factor joint analysis module is used to set up a three-dimensional construction model based on the geological feature data and construction monitoring data corresponding to the tunnel construction area, map the slope failure model and support failure model into the three-dimensional construction model, set risk feature sequences at various locations in the three-dimensional construction model, analyze and process the data information corresponding to the corresponding models in the risk feature sequences, obtain the corresponding joint influence coefficients, and construct a risk influence database based on the joint influence coefficients and the corresponding models. The slope risk identification and analysis module is used to traverse the corresponding three-dimensional construction model according to the construction monitoring data, compare and analyze the risk impact database corresponding to the corresponding risk feature sequence, integrate the analysis results of each risk feature sequence, and obtain risk identification data.

[0006] The above technical solution further includes: the process of collecting geological feature data and construction monitoring data corresponding to the tunnel construction area includes: A monitoring and acquisition unit is set up, which includes a geological monitoring terminal and multiple monitoring and acquisition terminals. Geological feature data corresponding to the tunnel construction area are collected through geological monitoring terminals; The monitoring data collected by the monitoring and acquisition terminal includes environmental monitoring data, working condition monitoring data, structural safety monitoring data, and equipment status monitoring data within the corresponding tunnel construction area.

[0007] Furthermore, the process of collecting risk factor data and risk event data for the corresponding tunnel portal slope includes: Set up survey and data collection units to collect survey data within the corresponding tunnel engineering area, and set up risk factor collection terminals and risk event collection terminals; The risk factor collection terminal analyzes and processes the survey data based on artificial intelligence algorithms to obtain corresponding feature keywords. It then uses NER technology to extract and identify information from the obtained feature keywords to obtain corresponding risk factor data. The risk event acquisition terminal identifies risk event types based on natural language processing algorithms, obtains feature datasets corresponding to the respective risk event types, analyzes and processes the obtained feature datasets sequentially using clustering analysis algorithms, obtains risk factor data evaluation indicators corresponding to the respective risk event types, and marks the obtained data as risk event data.

[0008] Further, the process of constructing the slope failure model comprises: setting a slope test simulation unit and a slope test processing unit; acquiring corresponding geological feature data through the slope test simulation unit, and constructing a virtual opening slope structure three-dimensional image, performing slice processing on the virtual opening slope structure three-dimensional image, acquiring corresponding slope structure slice images, and acquiring corresponding similar material mixing ratios at each pixel point position in the slope structure slice images based on similar matching and dimensional analysis, and setting an opening slope physical model according to the similar material mixing ratios of each pixel point; acquiring corresponding risk factor data and historical construction monitoring data, and analyzing and processing the obtained data information to acquire corresponding slope working condition information; setting corresponding working condition variable data according to the type of the corresponding slope working condition information, sequentially performing variable combination on the working condition variable data corresponding to different slope working condition information, acquiring corresponding slope simulation test data groups, and performing numerical simulation on each slope simulation test data group based on FLAC3D numerical simulation software to acquire corresponding test data information; The slope test processing unit analyzes and processes the test data information corresponding to the corresponding slope simulation test data groups, sets corresponding test data sets according to the corresponding slope simulation test data groups, respectively compares and analyzes the corresponding test data information in the test data sets with the risk event data, and acquires corresponding slope deformation and failure characteristic data. The obtained slope deformation and failure characteristic data is analyzed and trained based on a deep learning algorithm to construct a corresponding slope failure model.

[0009] Further, the process of constructing the support failure model comprises: setting a tunnel test simulation unit and a tunnel test processing unit; acquiring corresponding geological feature data through the tunnel test simulation unit, constructing a corresponding opening tunnel physical model according to the construction method of the opening slope physical model, and acquiring corresponding tunnel working condition information according to the risk factor data and the historical construction monitoring data; setting a tunnel simulation test data group according to the tunnel working condition information, performing numerical simulation on the corresponding tunnel simulation test data group based on FLAC3D numerical simulation software, and acquiring corresponding test data information; The tunnel test processing unit compares and analyzes the test data information of the corresponding tunnel simulation test data group with the corresponding risk event data, acquires corresponding support deformation and failure characteristic data, and analyzes and trains the obtained support deformation and failure characteristic data based on a deep learning algorithm to construct a corresponding support failure model.

[0010] Further, the process of setting the three-dimensional construction model comprises: setting a model analysis unit; obtaining corresponding geological feature data through the model analysis unit, constructing an initial three-dimensional construction model, mapping the obtained construction monitoring data into the initial three-dimensional construction model for updating processing, obtaining a corresponding three-dimensional construction model, and mapping the slope failure model and the support failure model into the three-dimensional construction model according to the corresponding positions to obtain a real-time three-dimensional construction model.

[0011] Further, the process of constructing the risk influence database comprises: intelligently slicing the real-time three-dimensional construction model to obtain corresponding tunnel portal slice images, and marking each tunnel portal slice image; setting a risk feature sequence according to each pixel point in each tunnel portal slice image, setting a corresponding risk feature sub-sequence in the risk feature sequence according to the test data information corresponding to the slope simulation test data group and the tunnel simulation test data group in the slope failure model and the support failure model, respectively, and performing horizontal combination, vertical combination, and comprehensive combination on the obtained risk feature sub-sequence, respectively; the horizontal combination is a combination result of the test data information corresponding to each risk feature sub-sequence in each risk feature sequence in the corresponding tunnel portal slice image under different working condition information; the vertical combination is a combination result of the test data information corresponding to each risk feature sub-sequence in the risk feature sequence at the corresponding position in different tunnel portal slice images under different working condition information; the comprehensive combination is a combination result of the test data information corresponding to each risk feature sub-sequence in the risk feature sequence at different positions in different tunnel portal slice images under different working condition information; setting a corresponding combination data set for the test data information corresponding to the slope simulation test data group and the tunnel simulation test data group in the horizontal combination, the vertical combination, and the comprehensive combination, respectively, performing joint analysis on the obtained combination data set, and obtaining a joint influence coefficient between risk event data corresponding to different working condition information between corresponding positions; setting a risk influence data table according to the corresponding risk feature sequence in the real-time three-dimensional construction model according to the obtained joint influence coefficient; integrating the risk influence data tables in each risk feature sequence to construct a risk influence database.

[0012] Further, the process of obtaining risk identification data comprises: Obtaining construction monitoring data, mapping the latest obtained construction monitoring data into the real-time three-dimensional construction model respectively, obtaining corresponding working condition information from the corresponding risk feature sequence in the real-time three-dimensional construction model according to the corresponding construction monitoring data, inputting the obtained working condition information into the corresponding slope failure model and support failure model respectively, obtaining corresponding slope deformation failure feature data and tunnel deformation failure feature data, and marking the obtained feature data as sequence identification data; According to the corresponding joint influence coefficient in the risk influence database, the risk feature data in each risk feature sequence is verified and analyzed, and corresponding verification identification data is obtained; Comparing and analyzing the sequence identification data corresponding to each risk feature sequence with the verification identification data, obtaining the corresponding verification accuracy, and obtaining the corresponding risk identification data of the corresponding risk feature sequence according to the corresponding verification accuracy.

[0013] The present application has the following advantages: 0、In the present application, the real-time three-dimensional construction model is set up, and the risk identification process is dynamically managed according to the tunnel construction process. In addition, corresponding risk feature sequences are set up at different positions in the real-time three-dimensional construction model, and the working condition information corresponding to different risk feature sequences of different types and different variables is respectively combined horizontally, vertically and comprehensively, and the joint influence coefficient between different risk feature sequences is obtained. According to the real-time three-dimensional construction model and the joint influence coefficient, a risk influence database corresponding to the risk event data is constructed, and multiple verifications are carried out from multiple dimensions of the sequence identification data of the corresponding position risk feature sequence and the verification identification data of other risk feature sequences to the risk feature sequence according to the risk influence database, thereby improving the accuracy of the risk identification process to a certain extent.

[0014] 1、In the present application, corresponding portal slope physical models and portal tunnel physical models are set up in the corresponding tunnel construction area, and simulation test processing is carried out according to the corresponding physical models. According to the test data information corresponding to the simulation test results, the slope failure model and the support failure model corresponding to different risk event data are set up respectively, and the corresponding slope failure model and support failure model are set up according to the corresponding tunnel construction area, thereby improving the flexibility of the tunnel portal slope risk identification analysis system. In addition, the corresponding slope failure model and support failure model are constructed by simulation test analysis method, which reduces the cost in the process of constructing the risk identification system to a certain extent. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A structure diagram of a tunnel portal slope risk identification analysis system based on artificial intelligence is provided for the present application; Figure 2This is a flowchart illustrating an artificial intelligence-based tunnel entrance slope risk identification and analysis system proposed in this invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1 like Figure 1 As shown, the present invention proposes an artificial intelligence-based tunnel portal slope risk identification and analysis system, which includes a slope risk identification system. The slope risk identification system includes a risk factor investigation and collection module, a portal risk simulation and processing module, a tunnel risk simulation and processing module, a risk factor joint analysis module, and a slope risk identification and analysis module.

[0018] In this embodiment, the slope risk identification system is used to identify risks associated with the stability control of the tunnel entrance slope in water-rich weathered granite gneiss tunnels and the corresponding tunnel entrance slope during tunnel construction, thereby improving safety during tunnel construction. Its specific implementation process includes, for example: Figure 2 As shown, it includes the following steps: Step S1: Collect geological feature data and construction monitoring data corresponding to the tunnel construction area, as well as risk factor data and risk event data of the corresponding tunnel portal slope; Step S2: Based on the corresponding geological feature data, risk factor data, and risk event data, set up a physical model of the tunnel entrance slope, obtain the corresponding slope deformation and failure characteristic data, and construct a slope failure model; Step S3: Based on the corresponding geological feature data, risk factor data, and risk event data, set up the physical model of the tunnel entrance, obtain the corresponding support deformation and failure characteristic data, and construct the support failure model; Step S4: Set up a three-dimensional construction model based on the geological feature data and construction monitoring data corresponding to the tunnel construction area, and map the slope failure model and support failure model into the three-dimensional construction model; Step S5: Set risk feature sequences at various locations within the 3D construction model, analyze and process the data information corresponding to the models within the risk feature sequences, obtain the corresponding joint impact coefficients, and construct a risk impact database based on the joint impact coefficients and the corresponding models. Step S6: According to the construction monitoring data, the corresponding three-dimensional construction model is traversed respectively, the risk influence database corresponding to the risk characteristic sequence is compared and analyzed, the analysis results at each risk characteristic sequence are verified, and risk identification data is obtained.

[0019] The risk factor investigation and collection module is used for collecting geological feature data and construction monitoring data corresponding to the corresponding tunnel construction area, and risk factor data and risk event data corresponding to the tunnel portal slope. The specific implementation process includes: The monitoring and collection unit and the investigation and collection unit are set up. The monitoring and collection unit is provided with a geological monitoring terminal and a plurality of monitoring and collection terminals, which are respectively used for collecting geological feature data and construction monitoring data corresponding to the corresponding tunnel engineering area; The geological monitoring terminal is used for obtaining the geological feature data corresponding to the corresponding tunnel construction area, and the geological feature data includes corresponding topographic and geomorphic feature data, geological structure feature data and other data information related to tunnel construction; The monitoring and collection terminal includes environmental monitoring equipment, working condition monitoring equipment, structural safety monitoring equipment and equipment state monitoring equipment, and the corresponding monitoring and collection terminal is remotely intelligently managed based on artificial intelligence technology during data collection process, wherein: The environmental monitoring equipment is used for obtaining meteorological monitoring data and air quality monitoring data corresponding to the corresponding tunnel construction area; The working condition monitoring equipment is used for obtaining construction working condition data corresponding to the corresponding tunnel construction area; The structural safety monitoring equipment is used for obtaining stress and strain data and displacement monitoring data at the corresponding position during the corresponding tunnel construction process; The equipment state monitoring equipment is used for obtaining vibration signal data and equipment state data; The monitoring data obtained by the corresponding monitoring and collection terminal are analyzed and processed to obtain corresponding construction monitoring data. The monitoring risk factor data includes corresponding meteorological monitoring data, air quality monitoring data, construction working condition data, stress and strain data, displacement monitoring data, vibration signal data and equipment state data; The investigation and collection unit is used for investigating and collecting investigation data corresponding to the corresponding tunnel engineering area, and obtaining relevant investigation data provided by the geological exploration party, design party, construction party, supervision party and construction party of the engineering area tunnel; The risk factor collection terminal and the risk event collection terminal are respectively arranged in the investigation and collection unit; The risk factor collection terminal is used for risk factor analysis of the obtained relevant investigation data, and the process includes: Obtain relevant investigation data, extract keywords and feature information from the obtained relevant investigation data based on the natural language processing algorithm corresponding to the artificial intelligence technology, and preset the feature keyword database corresponding to the corresponding type feature data; Respectively extract keywords based on the TF-IDF algorithm according to the feature keyword database corresponding to the corresponding feature type, and obtain the corresponding feature keywords according to the keyword extraction result; Extract and identify information from the obtained feature keywords based on NER technology, and obtain the corresponding feature data according to the information extraction and identification result; According to the feature data obtained according to the corresponding feature keyword database type, the obtained feature data is marked as corresponding risk factor data, and the risk factor data includes corresponding climate feature risk factor data, geological feature risk factor data and construction feature risk factor data; The risk event collection terminal is used for risk event analysis on the obtained relevant investigation data, and the process includes: According to the natural language processing algorithm related to the artificial intelligence technology, the obtained relevant investigation data is identified according to the risk event type, and the feature data set corresponding to the corresponding risk event type is obtained; The obtained feature data set is evaluated according to the intensity standard, the corresponding risk event type in the feature data set is marked as sample data, the corresponding risk factor data type in the obtained sample data is comprehensively sorted, and the feature data subset corresponding to the corresponding sample data is obtained; The feature data subset is analyzed and processed based on the clustering analysis algorithm to analyze and process the data corresponding to the corresponding risk factor data, and the risk factor data evaluation index corresponding to the corresponding risk event type is obtained, and the process includes: Integrate and process the evaluation indexes corresponding to each risk factor data in the feature data subset to obtain the intensity level corresponding to the corresponding risk event type, wherein the intensity level includes the evaluation index interval corresponding to the corresponding risk factor data; The obtained risk event type and the corresponding evaluation index are marked and processed to obtain the corresponding risk event data.

[0020] The opening risk simulation processing module is used to set the opening slope physical model according to the corresponding geological feature data, risk factor data and risk event data, obtain the corresponding slope deformation and damage feature data, and build a slope damage model, and the specific implementation process includes: Set the slope test simulation unit and the slope test processing unit; The slope test simulation unit is used to set the opening slope physical model test, and obtain the corresponding test data information, and the process includes: Obtaining the geological feature data obtained from the corresponding tunnel portal section, constructing a virtual portal slope structure three-dimensional image according to the geological feature data, performing slice processing on the virtual portal slope structure three-dimensional image, and obtaining the corresponding slope structure slice image; Marking processing is performed on each pixel point in the obtained slope structure slice image, and each pixel point is analyzed and processed according to the marking processing result, and the rock-soil body at the corresponding pixel point in each slope structure slice image is analyzed and processed in turn; According to the analysis and processing of the corresponding pixel point, the corresponding rock-soil material database is set according to the corresponding rock-soil material property; According to the rock-soil material database, the rock-soil body at the corresponding pixel point is set according to the pixel dimension data; According to the pixel dimension data corresponding to the corresponding pixel point, the material mixing dimension data of the corresponding test material is obtained, and the material mixing dimension data is the dimension data corresponding to the similar material mixing ratio determined according to the mechanical test; The material mixing dimension data corresponding to the pixel dimension data corresponding to each pixel point is integrated, and the corresponding portal slope physical model is constructed in turn; The obtained portal slope physical model is analyzed and processed, and the obtained portal slope physical model is set in turn according to the test process, and the corresponding test data information is obtained; Obtaining the portal slope physical model, and performing damage simulation experiment according to the material information corresponding to the corresponding pixel point in the corresponding portal slope physical model; Setting the slope working condition information, the slope working condition information includes slope cutting, tunnel construction, climate change and other working conditions; According to the corresponding pixel point in the corresponding portal slope physical model, the corresponding pixel point is set according to the slope working condition information, and the corresponding working condition variable data is set according to the slope working condition information, the working condition variable data is the quantitative data corresponding to the corresponding type of slope working condition information, and each quantitative data is increased in turn; According to the corresponding pixel point, the corresponding working condition variable data corresponding to the corresponding slope working condition information is simulated, the corresponding slope simulation test data group is obtained, and the corresponding slope simulation test data group is simulated based on FLAC3D, Geo-slope2D and other numerical simulation software, and the corresponding test data information is obtained; The slope test processing unit is used for analyzing and processing the obtained test data information, and constructing a slope damage model, and the process includes: Obtain the relevant experimental data information, and analyze and process the experimental data information corresponding to the slope working conditions of the corresponding pixels in the physical model of the tunnel entrance slope and the corresponding working condition variables in the slope working conditions information. Set the corresponding experimental dataset, experimental data subset, and experimental data elements respectively, where: The test datasets correspond to the test data subsets corresponding to the corresponding pixels in the physical model of the tunnel entrance slope; The subsets of test data correspond to test data elements corresponding to different slope working conditions within a pixel. The test data elements correspond to the test data information corresponding to different working condition variables of the corresponding type of slope working condition information; Outlier analysis was performed on the obtained experimental dataset, experimental data subset, and corresponding experimental data elements based on machine learning models, and the corresponding outliers were filtered out. Based on the experimental dataset, experimental data subsets and corresponding experimental data elements obtained by filtering, data processing is performed to obtain slope deformation and failure characteristic data of corresponding experimental data elements in each experimental data subset within the corresponding experimental dataset, as well as slope deformation and failure characteristic data of corresponding experimental data elements between each experimental data subset. Based on the obtained slope deformation and failure characteristic data, deep learning algorithms were used to analyze and train the corresponding slope failure models. It should be further explained that, in the specific implementation process, the slope failure model is verified and analyzed based on real tunnel portal slope events to determine whether the corresponding slope failure model conforms to the occurrence process of tunnel portal slope events. If it does, the corresponding slope failure model is saved; otherwise, the slope failure model is retrained.

[0021] The tunnel risk simulation processing module is used to set up a physical model of the tunnel entrance based on relevant geological feature data, risk factor data, and risk event data, obtain relevant support deformation and failure characteristic data, and construct a support failure model. Its specific implementation process includes: Set up a tunnel test simulation unit and a tunnel test processing unit; The tunnel test simulation unit acquires risk factor data for the excavation of the tunnel portal section, sets up a physical model test of the tunnel portal section, and obtains corresponding test numerical data. The process involves acquiring risk factor data for the excavation of the tunnel portal section, obtaining the physical model of the portal slope based on the slope risk simulation processing module, and deriving the similarity ratio of the tunnel physical model based on the similarity theory and dimensional analysis method according to the corresponding risk factor data. According to the similar ratio derivation result of the corresponding tunnel opening section model, the mixing ratio of the similar material corresponding to each pixel position of the tunnel opening section physical model is obtained, and the corresponding tunnel opening section physical model is constructed according to the mixing ratio of the similar material corresponding to each pixel position. The obtained tunnel opening section physical model is subjected to test simulation analysis and processing to obtain tunnel working condition information involved in the tunnel excavation process, including various tunnel working condition types such as corresponding tunnel opening slope collapse, tunnel construction, climate change, support type, etc. Based on the corresponding type of tunnel working condition information, the tunnel opening tunnel physical model is set with corresponding tunnel simulation test data group, and the obtained corresponding tunnel simulation test data group is subjected to numerical simulation based on FLAC3D, Geo-slope2D, etc. Numerical simulation software, respectively obtaining corresponding test data information. The tunnel test processing unit is used to compare and analyze the test data information of the corresponding tunnel simulation test data group and the corresponding risk event data, and obtain the corresponding support deformation and damage characteristic data. The obtained support deformation and damage characteristic data is analyzed and trained based on the deep learning algorithm to construct a corresponding support damage model. It needs to be further explained that in the specific implementation process, the support damage model is verified and analyzed based on the real tunnel opening slope event to determine whether the corresponding support damage model conforms to the occurrence process of the tunnel opening slope event. If it is, save the corresponding support damage model, otherwise, retrain the support damage model.

[0022] The risk factor joint analysis module is used to set a three-dimensional construction model according to the geological feature data and construction monitoring data corresponding to the tunnel construction area, map the slope damage model and support damage model into the three-dimensional construction model, set a risk feature sequence according to each position in the three-dimensional construction model, analyze and process the data information corresponding to the corresponding model in the risk feature sequence, obtain the corresponding joint influence coefficient, and construct a risk influence database according to the joint influence coefficient and the corresponding model. The specific implementation process includes: Set the model analysis unit and the joint analysis unit; The model analysis unit is used to obtain the corresponding geological feature data, construct an initial three-dimensional construction model in the tunnel construction area, map the obtained construction monitoring data into the initial three-dimensional construction model for updating processing, obtain the corresponding three-dimensional construction model, map the slope damage model and support damage model into the three-dimensional construction model according to the corresponding position, and obtain the real-time three-dimensional construction model. It needs to be further explained that in the specific implementation process, the real-time three-dimensional construction model is obtained according to the construction process in the tunnel construction area, wherein the initial three-dimensional construction model is obtained according to the analyzed tunnel construction monitoring data, and the real-time three-dimensional construction model is obtained according to the unanalyzed tunnel construction monitoring data, wherein the corresponding slope failure model and support failure model are updated and verified in real time according to the corresponding construction monitoring process, and the corresponding deep learning algorithm is trained, verified, analyzed and processed based on the artificial intelligence algorithm to improve the accuracy of the slope risk identification process in the corresponding tunnel construction area. The joint analysis unit is used to obtain the corresponding joint influence coefficient and construct a risk influence database, and the process includes: Intelligent slicing processing is performed on the real-time three-dimensional construction model, and corresponding tunnel portal slice images are obtained, and each tunnel portal slice image is marked; According to the corresponding pixel points in each tunnel portal slice image, a risk feature sequence is set, and it is marked as , wherein is the corresponding risk feature sequence, and P is the corresponding marked tunnel portal slice image; According to the corresponding slope simulation test data group and tunnel simulation test data group in the slope failure model and support failure model, the corresponding risk feature subsequence is set in the risk feature sequence, wherein the slope simulation test data group is marked as , the corresponding test data information is marked as , , , and the tunnel simulation test data group is marked as , the corresponding test data information is marked as , , , and the corresponding risk feature subsequence is marked as and ; The obtained risk feature subsequences are respectively combined horizontally, vertically and comprehensively; The horizontal combination is the combination result of the test data information corresponding to each risk feature subsequence in each risk feature sequence in the corresponding tunnel portal slice image, the corresponding combination result is marked as and , and the corresponding combination data set is marked as ; The longitudinal combination is a combination result of each risk feature subsequence in the risk feature sequence at the corresponding position in different tunnel portal slice images under different working condition information, and the corresponding combination result is marked as , and the corresponding combination data set is marked as . The comprehensive combination is a combination result of each risk feature subsequence in the risk feature sequence at different positions in different tunnel portal slice images under different working condition information, and the corresponding combination result is marked as , and the corresponding combination data set is marked as . The combination data sets corresponding to the slope simulation test data group and the tunnel simulation test data group in the transverse combination, the longitudinal combination and the comprehensive combination are jointly analyzed, and a joint influence coefficient between the risk event data corresponding to different working condition information between the corresponding positions is obtained; The corresponding joint influence coefficient is marked as F, wherein: , wherein and are weight coefficients of the corresponding test data information in the corresponding combination data set, is a corresponding error term coefficient; , wherein is a weight coefficient of the longitudinal combination result of the corresponding risk feature sequence, is a corresponding error term coefficient; , wherein , and are weight coefficients in the corresponding combination data set, is a corresponding error term coefficient; According to the obtained joint influence coefficient, a risk influence data table is set according to the corresponding risk feature sequence in the real-time three-dimensional construction model; The risk influence data tables in each risk feature sequence are integrated to construct a risk influence database.

[0023] The slope risk identification analysis module is used to traverse the corresponding three-dimensional construction model according to the construction monitoring data, to perform comparative analysis according to the corresponding risk influence database at the corresponding risk feature sequence, to verify the analysis results at each risk feature sequence, to obtain risk identification data, and the specific implementation process includes: setting a risk identification unit and a risk verification unit; The risk identification unit is used to obtain the identification analysis results in the risk influence database corresponding to each risk feature sequence, and the process includes: Obtain construction monitoring data, map the latest obtained construction monitoring data into the real-time three-dimensional construction model respectively, obtain corresponding working condition information according to corresponding risk feature sequences in the real-time three-dimensional construction model according to corresponding construction monitoring data, input the obtained working condition information into corresponding slope damage models and support damage models respectively, obtain corresponding slope deformation damage feature data and tunnel deformation damage feature data, and mark the obtained feature data as sequence identification data; Verify and analyze the risk feature data in each risk feature sequence according to the corresponding joint influence coefficient in the risk influence database, and obtain corresponding verification identification data; The risk verification unit is used for verifying the analysis results of each risk feature sequence to obtain risk identification data, and the process includes: Compare and analyze the sequence identification data corresponding to each risk feature sequence with the verification identification data, obtain the corresponding verification accuracy, compare the obtained verification accuracy threshold with the corresponding verification threshold, and analyze; If the corresponding verification accuracy is greater than or equal to the verification threshold, the corresponding risk identification data is output; If the corresponding verification accuracy is less than the verification threshold, the corresponding risk identification data is not output; According to the comparative analysis structure, obtain the corresponding risk identification data corresponding to the risk feature sequence.

[0024] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and deformations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence-based tunnel portal slope risk identification and analysis system, comprising a slope risk identification system, characterized in that, The slope risk identification system includes a risk factor investigation and collection module, a portal risk simulation and processing module, a tunnel risk simulation and processing module, a risk factor joint analysis module, and a slope risk identification and analysis module. The risk factor investigation and collection module is used to collect geological feature data and construction monitoring data corresponding to the tunnel construction area, as well as risk factor data and risk event data of the corresponding tunnel portal slope; The tunnel entrance risk simulation processing module is used to set up a physical model of the tunnel entrance slope based on the corresponding geological feature data, risk factor data and risk event data, obtain the corresponding slope deformation and failure feature data, and construct a slope failure model. The tunnel risk simulation processing module is used to set up a physical model of the tunnel entrance based on the corresponding geological feature data, risk factor data and risk event data, obtain the corresponding support deformation and failure feature data, and construct a support failure model. The risk factor joint analysis module is used to set up a three-dimensional construction model based on the geological feature data and construction monitoring data corresponding to the tunnel construction area, map the slope failure model and support failure model into the three-dimensional construction model, set risk feature sequences at various locations in the three-dimensional construction model, analyze and process the data information corresponding to the corresponding models in the risk feature sequences, obtain the corresponding joint influence coefficients, and construct a risk influence database based on the joint influence coefficients and the corresponding models. The slope risk identification and analysis module is used to traverse the corresponding three-dimensional construction model according to the construction monitoring data, compare and analyze the risk impact database corresponding to the corresponding risk feature sequence, verify the analysis results of each risk feature sequence, and obtain risk identification data.

2. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 1, characterized in that, The process of collecting geological feature data and construction monitoring data corresponding to the tunnel construction area includes: A monitoring and acquisition unit is set up, which includes a geological monitoring terminal and multiple monitoring and acquisition terminals. Geological feature data corresponding to the tunnel construction area are collected through geological monitoring terminals; Construction monitoring data corresponding to the tunnel construction area is collected through the monitoring and acquisition terminal.

3. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 2, characterized in that, The process of collecting risk factor data and risk event data for the corresponding tunnel portal slope includes: Set up survey and data collection units to collect survey data within the corresponding tunnel engineering area, and set up risk factor collection terminals and risk event collection terminals; The risk factor collection terminal analyzes and processes the survey data based on artificial intelligence algorithms to obtain corresponding feature keywords. It then uses NER technology to extract and identify information from the obtained feature keywords to obtain corresponding risk factor data. The risk event acquisition terminal identifies risk event types based on natural language processing algorithms, obtains feature datasets corresponding to the respective risk event types, analyzes and processes the obtained feature datasets sequentially using clustering analysis algorithms, obtains risk factor data evaluation indicators corresponding to the respective risk event types, and marks the obtained data as risk event data.

4. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 3, characterized in that, The process of constructing a slope failure model includes: Set up a slope test simulation unit and a slope test treatment unit; The corresponding geological feature data were obtained through the slope test simulation unit, and a three-dimensional image of the virtual tunnel entrance slope structure was constructed. The three-dimensional image of the virtual tunnel entrance slope structure was sliced ​​to obtain the corresponding slope structure slice image. The corresponding similar material mixing ratio was obtained for each pixel in the slope structure slice image based on the similarity ratio and dimensional analysis method. The physical model of the tunnel entrance slope was set according to the similar material mixing ratio of each pixel. Obtain relevant risk factor data and historical construction monitoring data, and analyze and process the obtained data to obtain relevant slope condition information; According to the type of slope working condition information, set the corresponding working condition variable data in sequence, combine the working condition variable data corresponding to different slope working conditions in sequence, obtain the corresponding slope simulation test data set, and perform numerical simulation on each slope simulation test data set based on FLAC3D numerical simulation software to obtain the corresponding test data information. The slope test processing unit acquires and analyzes the test data information corresponding to the corresponding slope simulation test data group, sets up the corresponding test dataset according to the corresponding slope simulation test data group, compares and analyzes the corresponding test data information in the test dataset with the risk event data, and obtains the corresponding slope deformation and failure characteristic data. The obtained slope deformation and failure characteristic data are analyzed and trained based on deep learning algorithms to construct corresponding slope failure models.

5. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 4, characterized in that, The process of constructing a support failure model includes: Set up a tunnel test simulation unit and a tunnel test processing unit; The corresponding geological feature data are obtained through the tunnel test simulation unit. The corresponding tunnel physical model is constructed according to the construction method of the tunnel entrance slope physical model. The corresponding tunnel working condition information is obtained according to the risk factor data and historical construction monitoring data. Based on the tunnel working condition information, a tunnel simulation test data group is set up, and numerical simulation is performed on the corresponding tunnel simulation test data group using FLAC3D numerical simulation software to obtain the corresponding test data information. The tunnel test processing unit compares and analyzes the test data information of the corresponding tunnel simulation test data group with the corresponding risk event data to obtain the corresponding support deformation and failure characteristic data. The obtained support deformation and failure characteristic data is then analyzed and trained based on a deep learning algorithm to construct the corresponding support failure model.

6. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 5, characterized in that, The process of setting up a 3D construction model includes: Set up a model analysis unit; obtain relevant geological feature data through the model analysis unit, construct an initial three-dimensional construction model, map the obtained construction monitoring data into the initial three-dimensional construction model for update processing, obtain the corresponding three-dimensional construction model, map the slope failure model and support failure model into the three-dimensional construction model according to their respective positions, and obtain the real-time three-dimensional construction model.

7. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 6, characterized in that, The process of building a risk impact database includes: The real-time 3D construction model is intelligently sliced ​​to obtain corresponding tunnel entrance slice images, and each tunnel entrance slice image is marked. Risk feature sequences are set according to the corresponding pixels in the slice images of each tunnel entrance. Within each risk feature sequence, corresponding risk feature sub-sequences are set according to the test data information corresponding to the slope simulation test data group and tunnel simulation test data group in the slope failure model and support failure model. The obtained risk feature sub-sequences are then combined horizontally, vertically, and comprehensively. The horizontal combination refers to the combination of test data information corresponding to each risk feature subsequence within each risk feature sequence in the corresponding tunnel portal slice image under different working conditions. The longitudinal combination refers to the combination of test data information corresponding to each risk feature subsequence in the risk feature sequence at the corresponding position in the slice image of different tunnel entrances under different working conditions. The comprehensive combination is the result of combining the test data information corresponding to each risk feature subsequence in the risk feature sequence at different locations within different tunnel portal slice images under different working conditions. For the test data information corresponding to the slope simulation test data group and tunnel simulation test data group within the horizontal combination, vertical combination and comprehensive combination, set up corresponding combination datasets, perform joint analysis on the obtained combination datasets, and obtain the joint influence coefficient between the risk event data corresponding to different working conditions at the corresponding locations; Based on the obtained joint impact coefficients, risk impact data tables are set up according to the corresponding risk characteristic sequences in the real-time three-dimensional construction model. The risk impact data tables within each risk characteristic sequence are integrated to construct a risk impact database.

8. The tunnel entrance slope risk identification and analysis system based on artificial intelligence according to claim 7, characterized in that, The process of obtaining risk identification data includes: Acquire construction monitoring data and map the latest acquired construction monitoring data into the real-time three-dimensional construction model. The corresponding risk feature sequence in the real-time three-dimensional construction model obtains the corresponding working condition information based on the corresponding construction monitoring data. The obtained working condition information is then input into the corresponding slope failure model and support failure model to obtain the corresponding slope deformation failure feature data and tunnel deformation failure feature data. The obtained feature data is then marked as sequence identification data. Based on the joint impact coefficients in the risk impact database, the risk characteristic data in each risk characteristic sequence are verified and analyzed to obtain the corresponding verification and identification data. The sequence identification data corresponding to each risk feature sequence is compared and analyzed with the verification identification data to obtain the corresponding verification accuracy. Based on the corresponding verification accuracy, the risk identification data corresponding to the corresponding risk feature sequence is obtained.

Images