Loess tunnel portal side slope linear deformation precision monitoring system

Abstract

The present application discloses a loess tunnel portal side slope linear deformation precision monitoring system, and relates to the field of geotechnical engineering and surveying and mapping technology.The system comprises a sensing network layer, a data acquisition and transmission layer, a cloud platform and data analysis layer, and an application display layer.The present application reconstructs the displacement data of discrete monitoring points into continuous full-field displacement and strain distribution through Kriging interpolation, and then analyzes the displacement vector field as a whole, calculates the maximum shear strain field, accurately locates the abnormal area of deformation gradient mutation, merges these abnormal point sets into independent clusters according to spatial proximity and deformation consistency, and accurately outlines the geometric trajectory of the potential slip surface or crack through curve fitting.This technical path fundamentally changes the limitations of point monitoring, can non-contact and automatically identify the hidden linear damage trend that is difficult to find with the naked eye, and provides fine data support for slope stability evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geotechnical engineering and surveying technology, in particular to a linear deformation precision monitoring system for the side slope of a loess tunnel portal. BACKGROUND

[0002] Tunnels and underground works are key nodes in the construction of transportation, water conservancy and other infrastructure, and the stability of their portal sections directly determines the safety of the entire project. For loess strata, due to their large pores, vertical joint development, strong water sensitivity and other special engineering geological characteristics, under the action of tunnel excavation unloading, rainfall infiltration and other factors, the side slope of the portal is prone to instability phenomena such as traction collapse and cracking, which poses a serious threat to construction safety, operational order and even life and property safety. Therefore, real-time, accurate and intelligent monitoring of the deformation of the side slope of the loess tunnel portal is a long-term and urgent major requirement in the field of geotechnical engineering.

[0003] Currently, the monitoring technology in this field mainly relies on traditional geodetic surveying, contact-type sensor methods and emerging remote sensing measurement techniques. However, these technologies have significant limitations when dealing with linear deformation monitoring of loess slopes: first, traditional point monitoring methods cannot effectively capture the continuous evolution process of the through-going slip surface or crack from initiation, expansion to penetration, making it difficult to predict sudden failures, and the monitoring results are discrete and incomplete; second, existing technologies usually analyze deformation monitoring and environmental triggers in isolation, lacking depth integration and intelligent prediction capabilities; third, optical measurement methods are easily disturbed by construction dust, rain and fog, leading to interruptions in monitoring data and making it difficult to meet the requirements of continuous monitoring. These defects make it difficult for existing technology systems to fully and reliably ensure the safety of loess tunnel portal projects.

[0004] In summary, the existing monitoring technology has the core pain point of being unable to accurately perceive linear deformation characteristics. Therefore, developing a high-reliability system that can integrate multi-source data for early warning is of great significance for breaking through industry technical bottlenecks and improving the safety level of tunnel projects. SUMMARY

[0005] The purpose of the present application is to make up for the deficiencies of the prior art, and provide a loess tunnel portal side slope linear deformation precision monitoring system, which can reconstruct the continuous full-field displacement and strain distribution of the discrete monitoring point displacement data through Kriging interpolation, and then analyze the displacement vector field as a whole, accurately locate the abnormal area of deformation gradient mutation by calculating the maximum shear strain field, merge these abnormal point sets into independent clusters according to spatial proximity and deformation consistency, and accurately outline the geometric trajectory of the potential sliding surface or crack through curve fitting, which fundamentally changes the limitations of point monitoring, can non-contact and automatically identify the hidden linear damage trend that is difficult to find with the naked eye, provides fine data support for slope stability evaluation, and makes the early warning from blind to precise.

[0006] The present application provides the following technical solutions to solve the above technical problems: a loess tunnel portal side slope linear deformation precision monitoring system, the composition of the system includes: a sensing network layer, a data acquisition and transmission layer, a cloud platform and data analysis layer, and an application display layer.

[0007] The sensing network layer includes a reference subsystem arranged in a stable area and a monitoring subsystem arranged in a to-be-monitored side slope area, and is arranged in the to-be-monitored side slope area to provide a measurement reference and a monitoring object for spatial deformation.

[0008] The data acquisition and transmission layer communicates with the sensing network layer, and is used for automatically collecting three-dimensional spatial data and on-site environment parameters of the monitoring object in the sensing network layer, and transmitting the data to the cloud platform and data analysis layer.

[0009] The cloud platform and data analysis layer include a data fusion module for processing multi-source data, a linear deformation analysis module for identifying linear deformation characteristics of the side slope, and an AI intelligent early warning module for risk prediction.

[0010] The application display layer is used for dynamically displaying linear deformation characteristic attribute information, geometric morphological polynomial curves and early warning information generated by the cloud platform and data analysis layer.

[0011] Further, the reference subsystem is composed of a base station array arranged at stable reference points, and a reference prism and a GNSS receiver serving as absolute references are installed on the base station array, which serves as an absolute coordinate reference and a deformation reference system of the entire monitoring system.

[0012] The monitoring subsystem is composed of a plurality of intelligent targets arranged on the side slope surface, which is used to represent the deformation of the slope body.

[0013] Further, each intelligent target of the monitoring subsystem is integrated with:

[0014] Prism: for automatic aiming of total station;

[0015] RFID tag: built-in unique ID code, for target identity recognition and rapid inventory;

[0016] Bluetooth module: for short-range wireless wake-up and communication of targets;

[0017] Battery: power supply component for providing continuous power for the RFID tag and Bluetooth module.

[0018] Further, the data acquisition and transmission layer includes:

[0019] Measurement robot network: composed of automated total stations, which communicate with the system host through wireless network bridges, and cyclically measure the angle and distance of the base station array of the reference subsystem and the intelligent targets of the monitoring subsystem, obtaining their three-dimensional coordinate data;

[0020] Close-range photogrammetry module: industrial camera coaxially installed at the measurement robot station, periodically collecting high-definition images of the slope, for shooting the slope under extreme weather, and calculating the two-dimensional displacement of each intelligent target from the continuous image sequence;

[0021] Environmental parameter sensing module: real-time monitoring of environmental parameters such as precipitation, soil moisture, temperature, and humidity of the slope;

[0022] Intelligent edge gateway: responsible for collecting data from total stations, industrial cameras, and sensor arrays, and transmitting encrypted data to the cloud platform and data analysis layer through wireless networks.

[0023] Further, the data fusion module in the cloud platform and data analysis layer is configured to perform the following data fusion process:

[0024] Data alignment and input: receiving three-dimensional coordinate data from each intelligent target of the measurement robot, and two-dimensional displacement of each intelligent target from the close-range photogrammetry module, and aligning the two types of data on the timestamp;

[0025] Constructing state space model: taking the state vector of the previous time as the system state, and the measurement data of the current time as the observation value, to construct the state space model of Kalman filter;

[0026] Adaptive filtering: in the filtering process, the observation residual covariance of each measurement sensor is calculated in real time, and the observation noise matrix of the filter is adjusted accordingly;

[0027] Three-dimensional estimated output: through the prediction and update cycle of Kalman filter, the three-dimensional displacement vector sequence of each intelligent target after fusion processing is output.

[0028] Furthermore, the linear deformation analysis module is configured to execute a process that identifies and delineates continuous linear deformation features from discrete point displacement data. The input to this process is a sequence of three-dimensional displacement vectors for each intelligent target point from the data fusion module, and the output is linear feature geometric information describing potential anomalies. Specifically, the process is as follows:

[0029] Construction of the full-field displacement and strain field based on Kriging interpolation: Receive the three-dimensional displacement vectors of each intelligent target point output by the data fusion engine; for the third displacement vector... The horizontal displacement vector of each target point is , This represents the east-west displacement component. The north-south displacement component has the following coordinates: For any point to be determined within the slope area Its displacement components and It is obtained through the Kriging interpolation algorithm, that is ,in, It is a point The value of the function to be estimated, It is a known point The measured value, These are the weights assigned to each known point, resulting in two continuous displacement field functions for the entire computational domain: and Based on the full-field continuous displacement function and Build In-plane differential components And calculate the maximum shear strain value. ;

[0030] Deformation anomaly identification based on strain field and vector field analysis: based on maximum shear strain distribution and horizontal displacement vector field Set a shear strain threshold based on historical data. , will satisfy All pixels and regions were initially identified as strain anomaly areas, constituting a candidate feature point set for potential linear deformation features. Each candidate point Its location is attached. Shear strain values ​​and divergence values;

[0031] Linear feature clustering and spatial curve fitting: Using the Euclidean distance as a metric, candidate points that are spatially close are grouped into the same cluster. Each cluster Represents an independent, continuous transformation, for each cluster obtained from clustering. The points in the image are identified as data points As data points, a least square method is used to fit a polynomial curve of the geometric shape of the linear deformation feature, and based on the fitted curve and the original data, the attributes of the linear feature are calculated, including the sequence of geographic coordinates, the total length , the average shear strain , the average displacement , the attributes of all curve features are constructed into a linear feature list Each item in the list contains all the geometric and attribute information of a linear deformation feature.

[0032] Further, the AI intelligent early warning module is configured as a time series prediction and decision engine based on a long short-term memory network. The module is driven by linear deformation feature attribute information and real-time environmental data to perform the following processes:

[0033] Receive the attribute information of the identified linear features, the three-dimensional displacement vector sequence of the data fusion module, and the environmental parameter sequence in the environmental parameter perception module;

[0034] Align and fuse the received data to construct a unified multi-dimensional input feature vector for time Prediction;

[0035] The multi-dimensional input feature vector is input into the long short-term memory network model, which is composed of an input layer, multiple LSTM layers and a fully connected output layer. For the input feature vector, the fully connected output layer is mapped to the prediction output, i.e. The displacement of the monitoring point after time , displacement rate .

[0036] Further, the AI intelligent early warning module is preset with multiple levels of warning thresholds, including displacement threshold , and displacement rate threshold , The predicted value and output by the long short-term memory network model are compared with the thresholds in real time:

[0037] When or , L1 level warning is triggered;

[0038] When or , L2 level warning is triggered;

[0039] Once the early warning is triggered, the system automatically generates an early warning report, and pushes the early warning level, predicted value, and affected area to the application display layer through SMS, email, and the platform built-in message center.

[0040] Compared with the prior art, the loess tunnel portal side slope linear deformation precision monitoring system has the following beneficial effects:

[0041] Firstly, the present application reconstructs the discrete monitoring point displacement data into continuous full-field displacement and strain distribution through Kriging interpolation, then analyzes the displacement vector field as a whole, calculates the maximum shear strain field, accurately locates the abnormal area of deformation gradient mutation, merges these abnormal point sets into independent clusters according to spatial proximity and deformation consistency, and accurately outlines the geometric trajectory of the potential sliding surface or crack through curve fitting. This technical path fundamentally changes the limitations of point monitoring, can non-contact and automatically identify the hidden linear damage trend that is difficult to find with the naked eye, provides fine data support for slope stability evaluation, and makes the early warning from blind to accurate.

[0042] Other advantages, objects, and features of the present application will be in part apparent and in part pointed out hereinafter in the specification, and will be learned from a reading of the following specification and by practice thereof, based on the associated drawings. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, without creative labor, other drawings can also be obtained from these drawings.

[0044] Figure 1 The operation flowchart of the loess tunnel portal side slope linear deformation precision monitoring system is shown in the figure.

[0045] Figure 2 The flowchart of linear deformation feature identification in the loess tunnel portal side slope linear deformation precision monitoring system is shown in the figure.

[0046] Figure 3 The composition schematic diagram of the loess tunnel portal side slope linear deformation precision monitoring system is shown in the figure. DETAILED DESCRIPTION

[0047] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the specific embodiments, structures, features and effects according to the present application are described in detail below in combination with the drawings and preferred embodiments.

[0048] Embodiment One

[0049] This embodiment is aimed at the problem of the instability of the side-slope of the tunnel portal in loess due to special geological characteristics and external effects. It relies on the linear deformation precision monitoring system to carry out application, as shown in Figure 3 The system obtains basic data through the sensing network layer, completes multi-source data collection and transmission through the data collection and transmission layer, realizes data fusion, deformation identification and intelligent early warning through the cloud platform and data analysis layer, and finally presents key information through the application display layer, breaking through the limitations of traditional monitoring such as discretization and weak anti-interference, and providing technical support for tunnel engineering safety.

[0050] (I) Sensing network layer deployment and work

[0051] The sensing network layer includes a reference subsystem and a monitoring subsystem, wherein:

[0052] Reference subsystem

[0053] Deployment and equipment: survey the surrounding area of the tunnel portal, select a stable area to deploy a base station array, install a reference prism and a GNSS receiver at each reference point, ensure that the center of the prism is aligned with the reference point coordinates and the receiver signal is stable, the reference prism provides measurement reference for the subsequent measurement robot, i.e. automatic total station, when the measurement robot measures the coordinates of the intelligent target of the monitoring subsystem, it will also measure the coordinates of the reference prism, by comparing the real-time measurement coordinates of the reference prism with the initial calibrated absolute coordinates, it can be judged whether there is error in the measurement process, and then the measurement data of the monitoring subsystem is corrected to ensure the accuracy of the measurement results; the GNSS receiver continuously receives satellite signals, calculates and updates the absolute coordinates of the reference point in real time, when the surrounding environment causes the reference point coordinates to fluctuate slightly, the GNSS receiver can capture this change in time, providing a dynamic updated absolute coordinate reference and deformation reference system for the entire monitoring system, avoiding the influence of reference point coordinate drift on the reliability of monitoring data.

[0054] Monitoring subsystem

[0055] Deployment and equipment: survey the side-slope surface, deploy intelligent targets, the targets are built-in prisms, RFID tags, Bluetooth modules and batteries, the prisms provide automatic aiming for the total station, synchronize displacement with the deformation of the slope body, provide target points for coordinate measurement, the RFID tags contain unique IDs and are associated with target position information, identity recognition and inventory are realized through the card reader, the Bluetooth module supports near-distance wake-up and parameter configuration, daily hibernation reduces power consumption, the battery powers the tags and Bluetooth modules, and is adapted to outdoor environment to ensure endurance.

[0056] (II) Data collection and transmission layer operation

[0057] Data acquisition and transmission layer connects the sensor network and the cloud platform, including measurement robot network, close-range photogrammetry module, environmental parameter sensing module and intelligent edge gateway, wherein:

[0058] Measurement robot network

[0059] Acquisition process: composed of automatic total station, communicates with the system host through wireless network bridge, measures the reference prism coordinates first, then measures the angle and distance of the intelligent target in turn, combines with the total station's own coordinates, and calculates the three-dimensional coordinates of the target by triangulation principle.

[0060] Data transmission: after the measurement is completed, the total station transmits the data to the host through the wireless network bridge, the host checks the data format and integrity, and the abnormal data triggers retransmission or marking suspicious.

[0061] Close-range photogrammetry module

[0062] Installation and acquisition: install industrial camera coaxially with total station and calibrate parameters, take high-definition image sequence with timestamp under extreme weather conditions.

[0063] Data processing and transmission: after the camera compresses the image, it is transmitted to the host, which checks the image clarity and timestamp, and invalid images are not involved in subsequent processing.

[0064] Environmental parameter sensing module

[0065] Deployment and acquisition: deploy sensor array in the side slope area, precipitation sensor is placed on the slope top without shelter, soil moisture content sensor is placed according to soil depth and area, temperature and humidity sensor is placed in well-ventilated and light-protected place, data is collected and timestamped at preset period.

[0066] Data transmission: sensors transmit data to the host through wired or wireless means, the host checks the data rationality, marks abnormal data and associates sensor information for maintenance.

[0067] Intelligent edge gateway

[0068] Data collection and encryption: receive multi-source data: coordinates, images, environmental parameters forwarded by the host, store and check integrity according to type and source, encrypt data to generate data packets with check code.

[0069] Transmission to cloud platform: transmit encrypted data packets to cloud platform through dedicated wireless network, monitor transmission status in real time, adjust parameters to ensure stable and efficient data transmission, cloud platform decrypts and checks code after receiving, parses and stores data.

[0070] (Three) cloud platform and data analysis layer processing

[0071] The cloud platform and data analysis layer are responsible for processing, analyzing, and providing intelligent early warnings of multi-source data transmitted from the data acquisition and transmission layer. It consists of a data fusion module, a linear deformation analysis module, and an AI intelligent early warning module. Its specific operation process is as follows:

[0072] Data fusion module

[0073] The data fusion module receives two types of data from the cloud platform storage unit: one type is the 3D coordinate data of the smart targets from the measurement robot network, containing data for each smart target. In timestamp Three-dimensional coordinates ,in East-west coordinates North-South coordinates The data consists of two parts: first, elevation coordinates, which directly reflect the spatial position of the target; and second, two-dimensional displacement data of the intelligent target from the close-range photogrammetry module. Through matching and analysis of continuous image sequences, the displacement of each target at the timestamp is calculated. Below relative to the initial time Horizontal displacement components ,in For east-west displacement, The data represents the north-south displacement and can supplement total station data under extreme weather conditions, but it lacks elevation information and its accuracy is affected by image resolution. The timestamps of the measurement robot network and the close-range photogrammetry module are aligned.

[0074] Model Construction and Filtering: Centered on the "spatial state of the intelligent target," the system state vector is defined as the state vector at the previous moment. The target's three-dimensional displacement vector and displacement rate, namely: In the formula, (Cumulative displacement in the east-west direction) (Cumulative displacement in the north-south direction) (Cumulative displacement in the elevation direction) , , These represent the displacement velocities in the corresponding directions, and the observation vector is defined as the current time step. The multi-source measurement data, namely: In the formula, (East-west displacement calculated by total station) (North-South displacement calculated by total station) (Elevation displacement calculated by total station) , For horizontal displacement data measured by close-range photogrammetry, a state transition matrix is ​​used. Describe the target from arrive The displacement evolution pattern at time step, and the observation matrix Establish the mapping relationship between system state and observation data, and construct the model system equations: ,in Let the system noise have a mean of 0 and a covariance of . Gaussian distribution, observation equation: ,in To observe the noise, it follows a pattern with a mean of 0 and a covariance of . Gaussian distribution, observation noise covariance of traditional Kalman filtering Since the values ​​are fixed and cannot adapt to dynamic changes in the measurement environment, this module achieves adaptive adjustment by calculating the covariance of the observation residuals in real time: First, the observation residuals are calculated. ,in For based on The predicted state at time step is obtained; subsequently, the covariance matrix of the residuals is calculated using the sliding window method. Finally, the observed noise covariance will be... Updated to The weighting values ​​ensure that the filtering process can dynamically adjust the level of trust in different data sources based on the actual measurement accuracy.

[0075] 3D Prediction Output

[0076] The "prediction-update" loop of Kalman filtering is as follows: First, prediction is performed using the system equations. State estimate at time 1 And calculate the prediction error covariance. Then the Kalman gain was calculated. This gain reflects the degree to which the observed data contributes to the state correction; finally, the state estimate is updated using the observed data. and update the error covariance. ,in The identity matrix is ​​derived from the updated state vector. Extracting the three-dimensional displacement components, we obtain the value of each smart target in... Three-dimensional displacement vector after fusion at time step All displacement vectors under all timestamps are organized according to target number to form a continuous three-dimensional displacement vector sequence. This sequence possesses both the three-dimensional integrity of a total station and the anti-interference capability of close-range photogrammetry, providing a high-precision data foundation for subsequent linear deformation analysis.

[0077] Linear Deformation Analysis Module

[0078] The linear deformation analysis module converts the displacement data of discrete intelligent targets into a continuous slope deformation field by Kriging interpolation, strain field analysis, clustering and curve fitting, and accurately identifies potential sliding surfaces, cracks and other linear deformation features. The specific steps are as follows:

[0079] Full-field displacement and strain field construction based on Kriging interpolation

[0080] Clearly input data: three-dimensional displacement vector sequence of each intelligent target from the data fusion module, taking the horizontal displacement component as the analysis object, the horizontal displacement vector of each target , , the corresponding plane coordinates are (determined by the initial measurement of the total station, consistent with the geographical coordinates of the slope surface), and the Kriging interpolation algorithm is used to construct the full-field continuous displacement field: for any one point in the slope area, the calculation of its horizontal displacement components (east-west direction) and (north-south direction) is , where represents the estimated displacement component or ) of the point , represents the displacement component measurement value or ) of the known target , is the weight assigned to each target , and satisfies , by executing the interpolation on all grid points in the slope area, the continuous horizontal displacement field functions and of the entire slope are obtained.

[0081] Strain field calculation based on displacement field: strain field reflects the deformation difference inside the slope, and is the key to identifying potential damage areas. In the plane (slope surface plane), three basic strain components are calculated: east-west direction normal strain , north-south direction normal strain , and shear strain ; further calculate the maximum shear strain: the maximum shear strain directly reflects the risk of shear failure of the slope, the formula is: , The larger the value, the more intense the shear deformation of the point, and the more likely it is to slide or crack.

[0082] Deformation anomaly area identification based on strain field and vector field analysis

[0083] Set the shear strain threshold , when When the shear deformation of the point exceeds the stable range, there is a risk of damage, and by traversing the entire strain field grid of the slope, all points that meet the condition are marked as "strain anomaly points", which form a candidate feature point set of potential linear deformation features Each candidate point is accompanied by its position coordinates , shear strain value and divergence value (divergence value reflects the convergence or divergence of local deformation, positive value corresponds to crack expansion; negative value corresponds to compression deformation).

[0084] Linear feature clustering and spatial curve fitting

[0085] Perform candidate point clustering: take "spatial proximity" as the clustering criterion, use Euclidean distance as the measure, set the distance threshold , and merge points in the candidate point set with Euclidean distance less than into the same cluster Each cluster represents an independent, continuous deformation area (such as a potential sliding surface or a crack), and for each cluster , all points ( ) contained in it are taken as data points, and a polynomial curve is fitted using the least squares method to describe the geometric shape of the linear deformation feature, and the polynomial degree is determined according to the shape complexity of the cluster. The fitting goal is to minimize the sum of squared residuals of all data points to the curve, and based on the fitted curve and the original data, the linear deformation feature attributes of each cluster are extracted, including: geographical coordinate sequence, total length , average shear strain , average displacement The linear deformation feature attributes of all clusters are arranged into a list , and each item in the list corresponds to a linear deformation feature, containing its geometric shape (fitting curve parameters, coordinate sequence, total length) and deformation intensity information, providing feature input for AI intelligent early warning.

[0086] AI intelligent early warning module

[0087] The AI intelligent early warning module takes the long short-term memory network (LSTM) as the algorithm core, integrates linear deformation feature data and environmental parameter data, realizes accurate prediction of the deformation trend of the slope in the future period of time, and triggers early warning through multiple threshold values, providing a time window for engineering decision-making, and the specific operation process is as follows:

[0088] Data reception and filtering: The system receives three types of core input data: first, linear feature attribute data from the linear deformation analysis module, including the total length of all linear deformation features. Mean shear strain Average displacement The data includes: 1) geographic coordinate sequence; 2) three-dimensional displacement vector sequence of intelligent targets from the data fusion module, which selects displacement data of 5-10 key targets around the linear deformation feature, whose deformation can directly reflect the evolution trend of the linear feature; and 3) real-time environmental parameter sequence from the environmental parameter perception module, including precipitation, soil moisture content, atmospheric temperature, and relative humidity, which are key external factors that induce loess slope deformation.

[0089] Multidimensional feature vector construction: based on "prediction time" "as the goal" To predict the time window, the preprocessed data of various types are aligned according to the time dimension to construct the time frame. Unified multidimensional input feature vector .

[0090] LSTM Network Structure Design and Model Training: The multi-dimensional input feature vector is input into a Long Short-Term Memory (LSTM) network model. The LSTM network consists of an input layer, multiple LSTM layers, and a fully connected output layer. The input feature vector is mapped to the predicted output through the fully connected output layer. Displacement of monitoring points after time Displacement rate .

[0091] Multi-level warning threshold comparison: The AI ​​intelligent warning module has multiple preset warning thresholds, including displacement thresholds. , and displacement rate threshold , The predicted values ​​output by the Long Short-Term Memory network model and Real-time comparison with threshold:

[0092] when or If so, an L1 level warning will be triggered;

[0093] when or If so, an L2 level warning will be triggered;

[0094] Once an alert is triggered, the system automatically generates an alert report and pushes the alert level, forecast value, and affected area to the application display layer via SMS, email, and the platform's built-in message center.

[0095] (Four) Application display layer

[0096] The application display layer, as the "interaction window" of the system, is used for visual display of monitoring data and analysis results, and provides convenient query and management functions for users, i.e. a Web terminal and a mobile terminal visualization platform, which forms a "data output-visualization presentation" linkage relationship with the cloud platform and the data analysis layer:

[0097] Platform base: restore the edge slope terrain, tunnel structure and monitoring equipment in the form of a three-dimensional model to realize spatial positioning;

[0098] Data display: display equipment status, support time axis backtracking, area filtering and early warning record query.

[0099] In summary, the working principle of the loess tunnel portal edge slope linear deformation precision monitoring system is formed, and a closed-loop monitoring system of "data acquisition-fusion analysis-feature recognition-intelligent early warning" is formed. Not only can the linear deformation features such as hidden slip surface and cracks of loess slope be accurately identified, but also the deformation trend can be predicted in advance to provide sufficient time window for engineering emergency disposal, which can effectively improve the precision and intelligent level of loess tunnel portal edge slope monitoring, and provide a complete technical solution for safety monitoring of similar geotechnical engineering.

[0100] Embodiment two

[0101] On the basis of embodiment one, as shown in Figure 1 , the embodiment provides specific steps of the loess tunnel portal edge slope linear deformation precision monitoring system in the edge slope linear deformation monitoring, which are:

[0102] (1) System initialization and layout

[0103] Establish a reference subsystem on the stable bedrock / foundation behind the slope: install an observation pier, and set an ultra-high precision prism or GNSS receiver on the pier.

[0104] Install a monitoring subsystem: layout intelligent targets at selected points, and each target contains a prism, an RFID tag, a Bluetooth module and a power supply component.

[0105] Install a measurement robot at a stable position near the portal and calibrate it, and install an industrial camera coaxially on the measurement robot.

[0106] Install a micro-meteorological station at the slope site, which contains rain, soil moisture, temperature and humidity sensors.

[0107] Deploy an intelligent edge gateway, and configure its communication with the measurement robot, the industrial camera, the meteorological station and the cloud platform.

[0108] (2) Automatic data acquisition

[0109] The measuring robot initiates scanning: according to a preset schedule or trigger command, it automatically and cyclically aims at the prisms of the reference subsystem and all smart targets of the monitoring subsystem.

[0110] Total station data acquisition: The surveying robot records the angle and distance measurements of each prism and calculates its high-precision three-dimensional coordinates.

[0111] Close-range photography-assisted shooting: During the scanning intervals of the measurement robot or in extreme weather, the industrial camera automatically captures a high-definition image sequence of the slope, and camera calibration ensures that the image is associated with the measurement coordinate system.

[0112] Simultaneous collection of environmental parameters: The micro-weather station continuously records precipitation, soil moisture content, temperature, and humidity data in real time.

[0113] Bluetooth wake-up and identification: Wake up the target via Bluetooth when necessary for communication or quick inventory checks.

[0114] (3) Data transmission and edge processing

[0115] Data aggregation: The intelligent edge gateway receives coordinate data from the measuring robot, image data from the industrial camera, and environmental data from the weather station in real time.

[0116] Edge preprocessing: The gateway performs preliminary filtering, compression, and timestamp alignment on the raw data.

[0117] Encrypted transmission: The gateway encrypts and transmits the pre-processed data packets to the cloud platform via wireless / wired network.

[0118] (4) Cloud-based data fusion processing

[0119] Data reception and alignment: The cloud platform receives data to ensure that the total station coordinate data and image data are accurately synchronized in time.

[0120] Adaptive data fusion: The three-dimensional coordinates of discrete points obtained by the total station are fused with the two-dimensional displacements calculated from the image sequence. An adaptive filtering algorithm is used to dynamically process the data, eliminate errors, and output a more reliable and accurate three-dimensional displacement vector sequence for each smart target.

[0121] (5) Linear deformation feature recognition (e.g.) Figure 2 (As shown)

[0122] Construction of full-field displacement and strain field: Based on the fused displacement data of all smart targets, a continuous displacement field distribution covering the entire slope area is generated through spatial interpolation algorithm. Based on the continuous displacement field, the strain field distribution of the entire slope, especially the maximum shear strain field, is calculated.

[0123] Abnormal deformation zone identification: Analyze the displacement vector field and the maximum shear strain field, set a strain threshold, identify the area where the shear strain exceeds the threshold, and mark it as a potential linear deformation feature candidate point.

[0124] Feature point clustering and curve fitting:

[0125] Cluster the candidate points that are spatially adjacent and have similar strain characteristics into independent clusters.

[0126] For each cluster of points, use curve fitting algorithm to accurately depict the geometric shape and spatial trajectory of the linear deformation feature.

[0127] Feature attribute calculation: Calculate the attribute information of each fitted curve: geographic coordinate sequence, total length, average shear strain value, average displacement, etc. Generate a linear deformation feature list containing all identified features and their attributes.

[0128] (6) AI intelligent prediction and early warning

[0129] Data preparation: Receive linear deformation feature attribute information, displacement vector sequence of each target, and real-time environmental parameters.

[0130] LSTM time series prediction: Fuse the above multi-source data into a unified time series input feature vector, input it into the trained long short-term memory network LSTM model, and the model predicts the predicted displacement and displacement rate of the key monitoring points in the future time period Δt.

[0131] Multi-level early warning decision: Compare the predicted displacement and displacement rate with the preset multi-level early warning threshold in real time. If the predicted value exceeds the threshold, the corresponding level of warning is triggered.

[0132] Early warning information generation and push: Automatically generate early warning reports containing warning level, predicted value, affected area, and recommended measures.

[0133] Through various ways such as SMS, email, platform message center, etc., real-time push early warning information to relevant management personnel.

[0134] (7) Application display and interaction

[0135] Three-dimensional visualization display: Based on BIM+GIS three-dimensional real scene model on Web / Mobile platform.

[0136] Dynamic presentation: Real-time or near real-time display of displacement and strain cloud maps of the slope, superimposed display of the geometric trajectory of the identified linear deformation features, and eye-catching warning information.

[0137] Interactive query: Users can click to view detailed attributes, historical evolution, and associated environmental data of any linear feature.

[0138] Device status monitoring: show the online status and power of each device in the sensor network layer, i.e. the target, the measuring robot, and the gateway.

[0139] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed with the preferred embodiments as above, it is not intended to limit the present application. Any person skilled in the art can make some minor changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, as long as the changes or modifications do not deviate from the technical solution of the present application. Any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still falls within the scope of the technical solution of the present application.

Claims

1. A loess tunnel portal side slope linear deformation precision monitoring system, characterized in that, The system comprises a sensing network layer, a data acquisition and transmission layer, a cloud platform and data analysis layer, and an application display layer. The sensing network layer comprises a reference subsystem arranged in a stable area and a monitoring subsystem arranged in a to-be-monitored high slope area, and is arranged in the to-be-monitored high slope area to provide a measurement reference and a monitoring object for spatial deformation. The data acquisition and transmission layer communicates with the sensing network layer, comprises a measurement robot network composed of an automatic total station, a close-range photogrammetry module, an environmental parameter sensing module and an intelligent edge gateway, and is used for automatically acquiring three-dimensional spatial data and on-site environmental parameters of the monitoring object in the sensing network layer and transmitting the data to the cloud platform and data analysis layer. The cloud platform and data analysis layer comprises a data fusion module for processing multi-source data, a linear deformation analysis module for identifying linear deformation characteristics of a slope, and an AI intelligent early warning module for risk prediction, the data fusion module fuses three-dimensional coordinate data and two-dimensional displacement data into a three-dimensional displacement vector sequence through Kalman adaptive filtering, the linear deformation analysis module constructs a full-field displacement and strain field based on Kriging interpolation, identifies an abnormal area through a maximum shear strain threshold, and outlines a geometric trajectory of a potential sliding surface and a crack through clustering and curve fitting, and the AI intelligent early warning module predicts displacement and rate based on a long short-term memory network and triggers multi-level early warning. The linear deformation analysis module is configured to perform a process of identifying and outlining continuous linear deformation characteristics from discrete point displacement data, the process takes three-dimensional displacement vector sequences of intelligent target points from the data fusion module as input, and outputs geometric information of linear characteristics of potential abnormalities, and the process specifically comprises: Based on the Kriging interpolation of the full field displacement and strain field construction: receiving the data fusion engine output of each intelligent target point of three-dimensional displacement vector, for the three-dimensional displacement vector in the first target point of the horizontal displacement vector is , , is the east-west direction displacement component, is the north-south direction displacement component, the coordinates are , for any one point in the slope area to be solved , its displacement component and is obtained by Kriging interpolation algorithm, that is , wherein, is the estimated function value of point , is the measured value of the known point , is the weight assigned to each known point, so as to obtain two continuous displacement field functions of the whole calculation area: and , based on the full field continuous displacement function and , the differential component in the plane is constructed , and the maximum shear strain value is calculated; Deformation anomaly area identification based on strain field and vector field analysis: based on maximum shear strain distribution and horizontal displacement vector field , set the shear strain threshold value based on historical data , all pixel points and regions that meet are preliminarily identified as strain anomaly areas, and constitute a candidate feature point set of potential linear deformation features Each candidate point is attached with its position , shear strain value and divergence value; Linear feature clustering and spatial curve fitting: Using the Euclidean distance as a metric, candidate points that are spatially close are grouped into the same cluster. Each cluster Represents an independent, continuous transformation, for each cluster obtained from clustering. , and the points As data points, the least squares method is used to fit the geometric polynomial curve of the linear deformation feature. Based on the fitted curve and the original data, the attributes of the linear feature are calculated, including the geographic coordinate sequence and total length. Mean shear strain Average displacement Construct a list of linear features from all the attributes of the curve features. Each item in the list contains all the geometric and attribute information of a linear deformation feature; The application display layer is used for dynamically displaying linear deformation characteristic attribute information, geometric shape polynomial curves and early warning information generated by the cloud platform and data analysis layer.

2. The loess tunnel portal side slope linear deformation precision monitoring system according to claim 1, characterized in that, The reference subsystem is composed of a base station array arranged at stable reference points, and a reference prism and a GNSS receiver are installed on the base station array as absolute references, and are used as absolute coordinate references and deformation reference systems of the entire monitoring system. The monitoring subsystem is composed of a plurality of intelligent targets arranged on a high slope surface, and is used to represent deformation of a slope body.

3. The loess tunnel portal side slope linear deformation precision monitoring system according to claim 2, characterized in that, Each intelligent target of the monitoring subsystem is internally integrated with: a prism for automatic aiming of a total station; an RFID tag with a unique ID code for identification and rapid inventory of the target; a Bluetooth module for short-range wireless wake-up and communication of the target; a battery as a power supply component for providing continuous power supply for the RFID tag and the Bluetooth module.

4. The loess tunnel portal side slope linear deformation precision monitoring system according to claim 1, characterized in that, The data acquisition and transmission layer comprises: a measurement robot network composed of an automatic total station, the total station communicates with a system host through a wireless network bridge, cyclically measures angles and distances of a base station array of the reference subsystem and intelligent targets of the monitoring subsystem, and acquires three-dimensional coordinate data thereof; a close-range photogrammetry module for acquiring three-dimensional coordinates of the intelligent targets through close-range photogrammetry; an environmental parameter sensing module for acquiring environmental parameters of the intelligent targets; and an intelligent edge gateway for transmitting the three-dimensional coordinate data, the three-dimensional displacement vector sequence, the environmental parameters and the three-dimensional displacement vector sequence of the intelligent targets to the cloud platform and data analysis layer. Near-view photogrammetry module: install industrial cameras coaxially on the measurement robot station, collect high-definition images of the slope regularly, and use the images to shoot the slope in extreme weather. The two-dimensional displacement of each intelligent target is calculated from the continuous image sequence; Environmental parameter perception module: real-time monitoring of environmental parameters such as precipitation, soil moisture, temperature, and humidity of the slope through a sensor array; Intelligent edge gateway: responsible for collecting data from total stations, industrial cameras, and sensor arrays, and transmitting the encrypted data to the cloud platform and data analysis layer through wireless networks.

5. The loess tunnel portal edge batter slope linear deformation precision monitoring system according to claim 1, characterized in that, The data fusion module in the cloud platform and data analysis layer is configured to perform the following data fusion process: Data alignment and input: receive three-dimensional coordinate data from each intelligent target of the measurement robot and two-dimensional displacement of each intelligent target from the near-view photogrammetry module, and align the two types of data on the timestamp; Constructing a state space model: use the state vector of the previous time as the system state and the measurement data of the current time as the observation value to construct a state space model for Kalman filtering; Adaptive filtering: in the filtering process, the observation residual covariance of each measurement sensor is calculated in real time, and the observation noise matrix of the filter is adjusted accordingly; Three-dimensional estimated output: through the prediction and update cycle of Kalman filtering, the three-dimensional displacement vector sequence of each intelligent target after fusion processing is output.

6. The loess tunnel portal edge batter slope linear deformation precision monitoring system according to claim 1, characterized in that, The AI intelligent early warning module is configured as a time series prediction and decision engine based on a long short-term memory network. This module uses linear deformation feature attribute information and real-time environmental data as the driving force to perform the following processes: Receive the attribute information of each linear feature identified, the three-dimensional displacement vector sequence of the data fusion module, and the environmental parameter sequence in the environmental parameter perception module; The received data is aligned and fused to construct a unified multi-dimensional input feature vector for predicting the time ​ The multi-dimensional input feature vector is input into a long short-term memory network model, the long short-term memory network is composed of an input layer, multiple LSTM layers and a fully connected output layer, and for the input feature vector, the fully connected output layer is mapped to a prediction output, that is The displacement amount of the monitoring point after the time , displacement rate .

7. The loess tunnel portal side slope linear deformation precision monitoring system according to claim 6, characterized in that, The AI ​​intelligent early warning module has multiple preset early warning thresholds, including displacement thresholds. , and displacement rate threshold , The predicted values ​​output by the Long Short-Term Memory network model and Real-time comparison with threshold: When or a L1 level warning is triggered; When or a L2 level warning is triggered; Once the warning is triggered, the system automatically generates a warning report and pushes the warning level, predicted value, and affected area to the application display layer through SMS, email, and the platform's built-in message center.

Images