Abnormal behavior early warning method and device based on foundation pit construction and storage medium

Abstract

The invention discloses an abnormal behavior early warning method and device based on foundation pit construction and a storage medium, and the method comprises the steps: obtaining foundation pit BIM data and foundation pit three-dimensional geological data, carrying out the layout of monitoring points, and obtaining the monitoring data of each monitoring point; controlling the unmanned aerial vehicle to carry out aerial patrol and shoot on-site videos to obtain surrounding environment three-dimensional data; trend prediction is conducted based on the monitoring data and the surrounding environment three-dimensional data, and the foundation pit pipeline deformation trend, the foundation pit dewatering water level change trend and the foundation pit long plate support internal force change trend are obtained; according to the foundation pit pipeline deformation trend, the foundation pit dewatering water level change trend and the foundation pit long plate support internal force change trend, foundation pit safety risk assessment is conducted, and the foundation pit safety risk level is obtained; and when the safety risk level of the foundation pit reaches the preset early warning level, early warning of abnormal behaviors of foundation pit construction is carried out, the safety risk level of the foundation pit is accurately evaluated through multi-dimensional data prediction, then safety early warning is carried out in time, and the construction safety is effectively improved.

Description

Technical Field

[0001] This application relates to the field of safety early warning technology, and in particular to a method, device and storage medium for early warning of abnormal behavior based on foundation pit construction. Background Art

[0002] With the rapid development of urban infrastructure construction, deep foundation pit projects are increasingly being used in subway, underground utility tunnel, and high-rise building projects. Due to the complex construction environment, variable geological conditions, and dense surrounding buildings, the construction safety risks of deep foundation pits are becoming increasingly prominent. Once an instability, collapse, or pipeline damage accident occurs, it will not only cause significant economic losses but may also endanger human lives.

[0003] Currently, monitoring during foundation pit construction mainly relies on traditional fixed sensor deployment methods, such as GNSS, inclinometers, piezometers, and earth pressure cells. While these methods can reflect foundation pit deformation and the stress state of the support structure to some extent, their monitoring range is limited, and data analysis and cause tracing are often only possible after an accident occurs. This makes it difficult to achieve comprehensive, real-time monitoring and early warning of the construction process, resulting in a lack of assurance for construction safety. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device and storage medium for early warning of abnormal behavior in foundation pit construction, which aims to solve the technical problem that existing foundation pit construction monitoring relies on traditional fixed sensor deployment methods, which makes it difficult to achieve comprehensive and real-time monitoring and early warning of the construction process, resulting in poor construction safety.

[0005] To achieve the above objectives, this application proposes an early warning method for abnormal behavior during foundation pit construction, the method comprising: Acquire BIM data and 3D geological data of the foundation pit; Based on the BIM data and three-dimensional geological data of the foundation pit, monitoring points are set up, and monitoring data of each monitoring point is obtained. Control drones to conduct aerial surveys of the foundation pit construction site and capture on-site videos to obtain three-dimensional data of the surrounding environment; Based on the monitoring data and the three-dimensional data of the surrounding environment, trend prediction is performed to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support. Based on the deformation trend of the pipeline in the foundation pit, the water level change trend of the foundation pit dewatering, and the internal force change trend of the long plate bracing in the foundation pit, a safety risk assessment of the foundation pit is conducted to obtain the safety risk level of the foundation pit. When the safety risk level of the foundation pit reaches the preset warning level, an early warning of abnormal construction behavior in the foundation pit will be issued.

[0006] In one embodiment, the step of deploying monitoring points based on the foundation pit BIM data and the foundation pit 3D geological data, and acquiring monitoring data from each monitoring point, includes: A digital twin model of the foundation pit is constructed based on the BIM data and the three-dimensional geological data of the foundation pit. Obtain the current construction stage and structural load distribution; Based on the three-dimensional geological data of the foundation pit, the current construction stage, and the structural load distribution, potential risk areas are predicted using a joint model based on reinforcement learning and finite element analysis. Based on the digital twin foundation pit model and the potential risk area, a simulation of the monitoring point layout was conducted to obtain an initial monitoring point layout scheme. The initial monitoring point layout scheme was optimized to obtain the optimal monitoring point layout scheme; Monitoring points are set up at the foundation pit construction site according to the optimal monitoring point layout scheme, and monitoring data of each monitoring point are acquired in real time.

[0007] In one embodiment, the controlled drone conducts aerial surveys of the foundation pit construction site and captures on-site video to obtain three-dimensional data of the surrounding environment, including: Based on the location of each monitoring point, the UAV flight path is planned to obtain the UAV flight path; The drone is controlled to conduct aerial inspections of the foundation pit construction site according to the drone's flight path. During the aerial inspection, the drone's high-definition camera captures video of the site, and temperature and humidity data of the site environment are collected by temperature and humidity sensors. Keyframes were extracted from the captured video footage, and 3D reconstruction was performed based on the extracted keyframes to obtain the distribution of terrain, buildings, and underground pipelines around the foundation pit. The average temperature and surface humidity around the foundation pit are determined based on the temperature and humidity data of the site environment. Three-dimensional data of the surrounding environment are obtained based on the topography, distribution of buildings and underground pipelines around the foundation pit, average temperature and surface humidity around the foundation pit.

[0008] In one embodiment, the step of performing trend prediction based on the monitoring data and the three-dimensional data of the surrounding environment to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace includes: Based on the monitoring data, the displacement data of the foundation pit pipeline, the rise and fall data of the foundation pit dewatering water level, and the change data of the internal force of the foundation pit long plate support are determined. Based on the three-dimensional data of the surrounding environment, the distribution of the terrain, buildings and underground pipelines around the foundation pit, the average temperature and surface humidity around the foundation pit are determined. Based on the displacement data of the foundation pit pipeline, the terrain around the foundation pit, and the distribution of the buildings and underground pipelines, the deformation of the foundation pit pipeline is predicted, and the deformation trend of the foundation pit pipeline is obtained. Based on the rise and fall data of the water level in the foundation pit, the average temperature around the foundation pit and the surface humidity, the water level in the foundation pit is predicted, and the trend of water level change in the foundation pit is obtained. Based on the variation data of the internal force of the long plate bracing in the foundation pit and the average temperature around the foundation pit, the internal force of the long plate bracing in the foundation pit is predicted, and the variation trend of the internal force of the long plate bracing in the foundation pit is obtained.

[0009] In one embodiment, the step of predicting the deformation trend of the foundation pit pipeline based on the displacement data of the pipeline in the foundation pit, the surrounding terrain of the foundation pit, and the distribution of the buildings and underground pipelines includes: The displacement data of the foundation pit pipeline is preprocessed to obtain preprocessed displacement data, wherein the preprocessing includes the removal of outlier data points and the imputation of missing data. Spatial feature extraction is performed on the preprocessed displacement data to obtain a spatial feature sequence; Based on the spatial feature sequence, sequence analysis was performed to obtain the deformation of the foundation pit pipeline at different time periods; Based on the deformation of the foundation pit pipeline at different time periods, a deformation prediction model for the foundation pit pipeline is constructed. The spatial feature sequence is input into the foundation pit pipeline deformation prediction model to obtain the foundation pit pipeline deformation trend.

[0010] In one embodiment, the step of predicting the foundation pit's precipitation level based on the rise and fall data of the foundation pit's precipitation level, the average temperature around the foundation pit, and the surface humidity, to obtain the trend of the foundation pit's precipitation level change, includes: Obtain the initial hyperparameter combination of the foundation pit dewatering water level prediction model; The initial hyperparameter combination is input into the improved Pelican optimization algorithm for iterative optimization to obtain the optimal hyperparameter combination. The improved Pelican optimization algorithm is obtained by introducing Logistic chaotic mapping, adaptive weight factor and firefly perturbation strategy into the Pelican optimization algorithm. The optimal hyperparameter combination is configured into the foundation pit dewatering level prediction model to obtain the optimized foundation pit dewatering level prediction model. The rise and fall data of the foundation pit water level, the average temperature around the foundation pit, and the surface humidity are input into the optimized foundation pit water level prediction model to predict the foundation pit water level and obtain the trend of the foundation pit water level change.

[0011] In one embodiment, the step of predicting the internal force of the long brace of the foundation pit based on the variation data of the internal force of the long brace and the average temperature around the foundation pit, and obtaining the variation trend of the internal force of the long brace, includes: The data on the variation of internal forces of the long plate brace in the foundation pit are preprocessed to obtain preprocessed internal force data. The preprocessing steps include smoothing abnormal fluctuation data and filtering noise data. The time features of the preprocessed internal force data are extracted to obtain a time feature sequence; Based on the time feature sequence and the average temperature around the foundation pit, a correlation analysis was performed to determine the correlation between the change in the internal force of the long plate bracing in the foundation pit and the temperature. Based on the aforementioned correlation, a prediction model for the internal forces of the long slab bracing in the foundation pit is constructed. The time feature sequence and the average temperature around the foundation pit are input into the foundation pit long plate brace internal force prediction model to predict the internal force of the foundation pit long plate brace and obtain the changing trend of the internal force of the foundation pit long plate brace.

[0012] In one embodiment, the step of conducting a foundation pit safety risk assessment based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace to obtain the foundation pit safety risk level includes: A multi-dimensional risk feature vector is constructed based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace. The empirical Copula function is determined based on the empirical cumulative distribution of the multi-dimensional risk feature vectors. The joint distribution of the multi-dimensional risk feature vectors is determined based on the empirical Copula function. The tail probabilities of the joint distribution across all dimensions are determined using the empirical Copula function. Outlier scores are generated based on the tail probability, and the safety risk of the foundation pit construction is assessed based on the outlier scores to obtain the foundation pit safety risk level.

[0013] Furthermore, to achieve the above objectives, this application also proposes an early warning device for abnormal behavior during foundation pit construction, the device comprising: The acquisition module is used to acquire BIM data and 3D geological data of the foundation pit. The deployment module is used to deploy monitoring points based on the foundation pit BIM data and the foundation pit three-dimensional geological data, and to acquire monitoring data of each monitoring point. The control module is used to control the drone to conduct aerial inspections of the foundation pit construction site and take on-site videos to obtain three-dimensional data of the surrounding environment; The prediction module is used to perform trend prediction based on the monitoring data and the three-dimensional data of the surrounding environment to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support. The assessment module is used to conduct a safety risk assessment of the foundation pit based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace, and to obtain the foundation pit safety risk level. The early warning module is used to issue an early warning of abnormal construction behavior in the foundation pit when the safety risk level of the foundation pit reaches a preset early warning level.

[0014] In addition, to achieve the above objectives, this application also proposes an abnormal behavior early warning device based on foundation pit construction. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the abnormal behavior early warning method based on foundation pit construction as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the abnormal behavior early warning method based on foundation pit construction described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the abnormal behavior early warning method based on foundation pit construction described above.

[0017] This application proposes one or more technical solutions to acquire BIM data and 3D geological data of the foundation pit; deploy monitoring points based on the BIM data and 3D geological data, and acquire monitoring data from each monitoring point; control a drone to conduct aerial inspections of the foundation pit construction site and capture on-site videos to obtain 3D data of the surrounding environment; perform trend prediction based on the monitoring data and the 3D data of the surrounding environment to obtain the deformation trend of foundation pit pipelines, the water level change trend of foundation pit dewatering, and the internal force change trend of foundation pit long plate supports; conduct a foundation pit safety risk assessment based on the deformation trend of foundation pit pipelines, the water level change trend of foundation pit dewatering, and the internal force change trend of foundation pit long plate supports to obtain the foundation pit safety risk level; and issue an early warning for abnormal construction behavior when the foundation pit safety risk level reaches a preset warning level. Through the above methods, by performing multi-dimensional data prediction, the foundation pit safety risk level is accurately assessed, and timely safety warnings are issued, effectively improving construction safety. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the abnormal behavior early warning method for foundation pit construction provided in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the abnormal behavior early warning method based on foundation pit construction in this application. Figure 3 This is a schematic diagram of the module structure of the abnormal behavior early warning device based on foundation pit construction in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware operating environment of the abnormal behavior early warning device based on foundation pit construction in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is as follows: acquiring BIM data and three-dimensional geological data of the foundation pit; deploying monitoring points based on the BIM data and three-dimensional geological data of the foundation pit, and acquiring monitoring data from each monitoring point; controlling a drone to conduct aerial inspections of the foundation pit construction site and capture on-site videos to obtain three-dimensional data of the surrounding environment; performing trend prediction based on the monitoring data and the three-dimensional data of the surrounding environment to obtain the deformation trend of the foundation pit pipelines, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate supports; conducting a foundation pit safety risk assessment based on the deformation trend of the foundation pit pipelines, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate supports to obtain the foundation pit safety risk level; and issuing an early warning for abnormal construction behavior of the foundation pit when the foundation pit safety risk level reaches a preset warning level.

[0025] Currently, monitoring during foundation pit construction mainly relies on traditional fixed sensor deployment methods, such as GNSS, inclinometers, piezometers, and earth pressure cells. While these methods can reflect foundation pit deformation and the stress state of the support structure to some extent, their monitoring range is limited, and data analysis and cause tracing are often only possible after an accident occurs. This makes it difficult to achieve comprehensive, real-time monitoring and early warning of the construction process, resulting in a lack of assurance for construction safety.

[0026] This application provides a solution that accurately assesses the safety risk level of a foundation pit through multi-dimensional data prediction, thereby providing timely safety warnings and effectively improving construction safety.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an abnormal behavior early warning device based on foundation pit construction. The following description uses an abnormal behavior early warning device based on foundation pit construction as an example to illustrate this embodiment and the subsequent embodiments.

[0028] Based on this, the embodiments of this application provide a method for early warning of abnormal behavior during foundation pit construction, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the abnormal behavior early warning method based on foundation pit construction in this application.

[0029] In this embodiment, the abnormal behavior early warning method based on foundation pit construction includes steps S10~S60: Step S10: Obtain BIM data and 3D geological data of the foundation pit.

[0030] It should be noted that BIM data for foundation pits refers to Building Information Modeling (BIM) data, which contains detailed three-dimensional digital information such as the geometry, structural information, and material properties of the foundation pit. Meanwhile, three-dimensional geological data for foundation pits is geological information obtained through geological exploration, geophysical exploration, and other methods, including geological structure, soil layer distribution, and groundwater level in the area where the foundation pit is located. This data is also presented in three-dimensional form.

[0031] Step S20: Based on the BIM data of the foundation pit and the three-dimensional geological data of the foundation pit, set up monitoring points and obtain monitoring data of each monitoring point.

[0032] It should be noted that the location and number of monitoring points are determined based on the BIM data and 3D geological data of the foundation pit to ensure comprehensive and accurate capture of various deformations and stress states during the construction process. The layout of monitoring points must consider factors such as the shape and size of the foundation pit, geological conditions, and construction plan to ensure the accuracy and reliability of the monitoring data.

[0033] Understandably, monitoring points can include displacement monitoring points, stress monitoring points, settlement monitoring points, etc., used to monitor the deformation of the foundation pit, the stress on the support structure, and changes in the groundwater level.

[0034] It is worth noting that after the monitoring points are set up, various sensors and equipment are needed to monitor the points in real time and obtain monitoring data. This data can include displacement, stress values, settlement, etc., which can reflect the construction status and safety condition of the foundation pit in real time.

[0035] In one feasible implementation, step S20 may include: constructing a digital twin foundation pit model based on the foundation pit BIM data and the foundation pit three-dimensional geological data; obtaining the current construction stage and structural load distribution; predicting potential risk areas using a joint model based on reinforcement learning and finite element analysis based on the foundation pit three-dimensional geological data, the current construction stage, and the structural load distribution; simulating the layout of monitoring points based on the digital twin foundation pit model and the potential risk areas to obtain an initial monitoring point layout scheme; optimizing the initial monitoring point layout scheme to obtain an optimal monitoring point layout scheme; and deploying monitoring points at the foundation pit construction site according to the optimal monitoring point layout scheme, and acquiring monitoring data from each monitoring point in real time.

[0036] It should be noted that the digital twin foundation pit model is a virtual model built based on actual foundation pit BIM data and 3D geological data. It can reflect the construction status and geological conditions of the foundation pit in real time. By constructing a digital twin foundation pit model, the construction process and potential risk areas of the foundation pit can be understood more intuitively.

[0037] Understandably, the current construction stage refers to the current progress and status of the foundation pit construction process, while the structural load distribution refers to the distribution of various loads borne by the foundation pit and its surrounding buildings, equipment, etc. After obtaining the current construction stage and structural load distribution, a joint model based on reinforcement learning and finite element analysis is used to predict potential risk areas. The reinforcement learning model can make optimal decisions based on historical data and the current state, while finite element analysis can accurately simulate the stress state of the foundation pit. Combining the two allows for more accurate prediction of potential risk areas in the foundation pit.

[0038] It is worth noting that by simulating the layout of monitoring points based on the digital twin foundation pit model and potential risk areas, a preliminary monitoring point layout plan can be obtained, including the number and location of monitoring points. That is, based on the digital twin foundation pit model, the deformation and stress state of the foundation pit under different construction stages and geological conditions are simulated. By comparing and analyzing the simulation results, potential risk areas are identified. These areas are likely to be the areas with the most complex deformation and stress state of the foundation pit and are also the focus of monitoring. Then, within the potential risk areas, the number and location of monitoring points are initially determined according to the simulation results and actual needs, forming an initial monitoring point layout plan.

[0039] However, this scheme may not be optimal and therefore needs further optimization. The optimization process can consider factors such as the number and location of monitoring points, as well as the accuracy and reliability of the monitoring data, to ensure that the final monitoring point layout can comprehensively and accurately capture various deformations and stress states during the foundation pit construction process. After setting up monitoring points at the foundation pit construction site according to the optimal layout scheme, various sensors and equipment can be used to monitor the points in real time and acquire monitoring data.

[0040] Step S30: Control the drone to conduct aerial inspection of the foundation pit construction site and take on-site videos to obtain three-dimensional data of the surrounding environment.

[0041] It should be noted that drones, as an efficient means of aerial monitoring, can conduct comprehensive and real-time aerial inspections of the foundation pit construction site. Through the video captured by the drone, real-time image information of the foundation pit and its surrounding environment can be obtained. Image processing technology can be used to convert this two-dimensional image information into three-dimensional data. Combined with data from various sensors on the drone, more comprehensive and accurate three-dimensional data of the surrounding environment can be obtained.

[0042] In one feasible implementation, step S30 may include: planning the UAV flight path based on the location of each monitoring point to obtain the UAV flight path; controlling the UAV to conduct aerial inspection of the foundation pit construction site according to the UAV flight path, and capturing on-site video through the high-definition camera on the UAV during the aerial inspection, and collecting temperature and humidity data of the on-site environment through temperature and humidity sensors; extracting key frames from the captured on-site video, and performing three-dimensional reconstruction based on the extracted key frames to obtain the distribution of terrain, buildings and underground pipelines around the foundation pit; determining the average temperature and surface humidity around the foundation pit based on the temperature and humidity data of the on-site environment; and obtaining three-dimensional data of the surrounding environment based on the distribution of terrain, buildings and underground pipelines around the foundation pit, the average temperature and surface humidity around the foundation pit.

[0043] It should be noted that determining the relative location and importance of each monitoring point is crucial for optimizing the efficiency of drone patrols. Utilizing path planning algorithms, considering parameters such as the drone's flight speed, altitude, and turning angle, a drone flight path is generated that covers all key monitoring points while ensuring flight safety and efficiency. Controlling the drone to conduct aerial patrols of the foundation pit construction site along this planned flight path ensures that the drone can efficiently capture real-time image information of the foundation pit and its surrounding environment. During the aerial patrol, the drone's onboard high-definition camera captures clear video footage, while temperature and humidity sensors collect real-time temperature and humidity data of the site.

[0044] Understandably, extracting keyframes from the captured video footage can eliminate redundant information and retain the most crucial images reflecting changes in the foundation pit and its surrounding environment. Based on these keyframes, 3D reconstruction can provide a precise picture of the terrain, buildings, and underground pipelines around the foundation pit. Furthermore, temperature and humidity data from the site are also vital environmental parameters. These data determine the average temperature and surface humidity around the foundation pit, reflecting the climatic conditions and surface state at the construction site, providing valuable reference for subsequent data analysis and safety warnings. Integrating information such as the distribution of terrain, buildings, and underground pipelines around the foundation pit, along with the average temperature and surface humidity, yields comprehensive and accurate 3D data of the surrounding environment.

[0045] Step S40: Based on the monitoring data and the three-dimensional data of the surrounding environment, perform trend prediction to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support.

[0046] It should be noted that, based on monitoring data and 3D data of the surrounding environment, advanced data analysis techniques and algorithms can be used to deeply mine and process this data to predict the deformation trends of pipelines in the foundation pit, the changing trends of groundwater levels in the foundation pit, and the changing trends of internal forces in the long bracing of the foundation pit. The deformation trend of pipelines refers to the deformation and development direction of underground pipelines around the foundation pit, which is crucial for assessing the impact of foundation pit construction on the surrounding environment. The changing trend of groundwater levels in the foundation pit reflects the dynamic changes in groundwater levels during construction, which is of great significance for ensuring the stability of the foundation pit and construction safety. The changing trend of internal forces in the long bracing of the foundation pit is an important indicator of the stress state of the foundation pit support structure, reflecting its stability and safety. Through trend prediction, abnormal behaviors during foundation pit construction can be detected in a timely manner, providing strong support for safety early warning.

[0047] Step S50: Conduct a safety risk assessment of the foundation pit based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support, and obtain the foundation pit safety risk level.

[0048] It should be noted that after obtaining the deformation trends of the foundation pit pipelines, the water level changes in the foundation pit dewatering, and the internal force changes of the foundation pit long plate supports, these trends can be analyzed and calculated using a risk assessment model to determine the safety risk level of the foundation pit. In this embodiment, the risk assessment model is constructed using the COPOD algorithm, an anomaly detection algorithm based on data distribution characteristics. It can effectively detect abnormal data even without knowing the specific distribution of normal data. By inputting the deformation trends of the foundation pit pipelines, the water level changes in the foundation pit dewatering, and the internal force changes of the foundation pit long plate supports into the risk assessment model based on the COPOD algorithm, the safety risk level of the foundation pit can be calculated. In this embodiment, the safety risk level of the foundation pit can be divided into different levels, such as low risk, medium risk, and high risk, so that the construction unit can take corresponding safety measures for early warning and response.

[0049] In one feasible implementation, step S50 may include: constructing a multi-dimensional risk feature vector based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate bracing; determining an empirical Copula function based on the empirical cumulative distribution of the multi-dimensional risk feature vector; determining the joint distribution of the multi-dimensional risk feature vector according to the empirical Copula function; determining the tail probability of the joint distribution in all dimensions through the empirical Copula function; generating outlier scores based on the tail probabilities, and assessing the foundation pit construction safety risk based on the outlier scores to obtain the foundation pit safety risk level.

[0050] It should be noted that the multi-dimensional risk feature vector is composed of multiple risk indicators, such as the deformation trend of pipelines in the foundation pit, the trend of water level changes in the foundation pit, and the trend of internal force changes in the long plate bracing in the foundation pit. These indicators can comprehensively reflect various safety risks during the foundation pit construction process. By constructing a multi-dimensional risk feature vector, these risk indicators can be integrated to form a comprehensive risk feature representation. Assume there are n monitoring points, recording data such as the deformation trend of pipelines in the foundation pit, the trend of water level changes in the foundation pit, and the trend of internal force changes in the long plate bracing. For each time step t, these data are combined into a multi-dimensional risk feature vector X(t). For each risk feature X... i For the sample data of (t), its empirical cumulative distribution function can be calculated as follows: in, Risk characteristic X iThe empirical cumulative distribution function of (t), where n is the total number of samples. For indicator functions, when hour, =1, otherwise 0.

[0051] Copula functions describe the dependencies between multiple random variables. To construct the joint distribution of a multidimensional risk feature vector, the empirical Copula function can be used, which combines the marginal distributions of multiple random variables with their dependencies. Empirical Copula function It can be derived from the empirical distribution function. The calculation yields the following formula: in, For empirical Copula functions, It is a vector composed of the marginal distribution values ​​of each variable. , , This represents three risk characteristics of the i-th data point (e.g., pipeline deformation, rainfall level, internal force of long plate bracing, etc.), each... The values ​​corresponding to the i-th sample in the j-th dimension (risk feature) are respectively: , , , , , It is the cumulative distribution function corresponding to risk characteristics X1, X2, and X3. It is the standardized variable of the i-th dimension.

[0052] The joint distribution is the joint probability distribution among multiple risk feature vectors. It is determined through the empirical Copula function. The joint distribution of multi-dimensional risk feature vectors can be obtained. As shown in the following formula: in, , , Risk characteristics are defined in three dimensions.

[0053] Then, the tail probabilities of the joint distribution across all dimensions are determined using an empirical Copula function. Tail probabilities refer to the probability that, in extreme cases, the value of the risk eigenvector falls within a certain region. This can be achieved by calculating the joint distribution. The risk is assessed using the tail probability, as shown in the following formula: in, This represents the probability that the value of X lies at the tail of the probability distribution. Is the cumulative distribution function H in The value at that location, The threshold value is the value at the tail end.

[0054] Outlier score is an important indicator for assessing whether data points are outliers. The outlier score O(X) is generated based on the tail probability and joint distribution. The outlier score can be calculated using the following formula: The safety risk level of foundation pit construction can be determined by the outlier score O(X). Assuming that the risk level of foundation pit construction is divided into several levels (e.g., low risk, medium risk, high risk), different thresholds can be set according to the outlier score to assess the safety risk. For example, low risk: when O(X) < τ1; medium risk: when τ1 ≤ O(X) < τ2; high risk: when O(X) ≥ τ2, where τ1 and τ2 are the thresholds for the outlier score.

[0055] Step S60: When the safety risk level of the foundation pit reaches the preset warning level, issue an early warning for abnormal construction behavior in the foundation pit.

[0056] It should be noted that the system will automatically trigger an early warning mechanism when the safety risk level of the foundation pit reaches the preset warning level. This early warning mechanism can be implemented in various ways, such as sending SMS or email notifications, or displaying warning information on the monitoring screen at the construction site. The warning information will clearly indicate the current safety risk level of the foundation pit and the potential safety hazards, providing timely risk alerts to the construction unit. Simultaneously, it can also provide corresponding countermeasure suggestions to help the construction unit quickly take effective action to reduce safety risks and ensure the safe progress of foundation pit construction. Through such an early warning mechanism, dynamic monitoring and risk management of the foundation pit construction process can be achieved, providing strong protection for construction safety.

[0057] This embodiment provides a method for early warning of abnormal behavior during foundation pit construction. The method involves acquiring BIM data and 3D geological data of the foundation pit; deploying monitoring points based on the BIM and 3D geological data, and acquiring monitoring data from each point; controlling a drone to conduct aerial surveys of the foundation pit construction site and capture video footage to obtain 3D data of the surrounding environment; performing trend prediction based on the monitoring data and the 3D environmental data to obtain trends in pipeline deformation, water level changes, and internal force changes of the long support beams; conducting a foundation pit safety risk assessment based on these trends to determine the foundation pit safety risk level; and issuing an early warning for abnormal construction behavior when the foundation pit safety risk level reaches a preset warning level. By employing this method, multi-dimensional data prediction accurately assesses the foundation pit safety risk level, enabling timely safety warnings and effectively improving construction safety.

[0058] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S40 includes steps S401 to S404: Step S401: Based on the monitoring data, determine the displacement data of the foundation pit pipeline, the rise and fall data of the foundation pit dewatering water level, and the change data of the internal force of the foundation pit long plate support. Based on the three-dimensional data of the surrounding environment, determine the distribution of the terrain, buildings and underground pipelines around the foundation pit, the average temperature and surface humidity around the foundation pit.

[0059] It should be noted that, in this embodiment, the monitoring data includes displacement data of the foundation pit pipelines, rise and fall data of the foundation pit dewatering water level, and change data of the internal force of the foundation pit long plate support. The three-dimensional data of the surrounding environment includes the topography around the foundation pit, the distribution of buildings and underground pipelines, the average temperature around the foundation pit, and the surface humidity.

[0060] Understandably, displacement data of pipelines in a foundation pit reflects their stability. By monitoring changes in pipeline displacement, abnormal deformation can be detected promptly, thus determining the stability of the foundation pit. If displacement data exceeds the normal range, it may indicate a risk of collapse or deformation of the foundation pit, requiring immediate intervention.

[0061] The rise and fall of the water level in the foundation pit is also crucial to the safety of foundation pit construction. Changes in the water level directly affect the stability and bearing capacity of the foundation pit soil. If the water level rises too quickly or too high, it may cause the soil around the foundation pit to soften, increasing the risk of collapse. Conversely, if the water level falls too quickly or too low, it may cause soil consolidation, leading to heave at the bottom of the foundation pit or settlement of the surrounding ground.

[0062] The variation data of internal forces in the long braces of the foundation pit is an important basis for assessing the stability of the foundation pit support structure. As a key component of the foundation pit support system, the changes in the internal forces of the long braces directly reflect the stress state of the foundation pit support structure. If the internal forces of the long braces increase abnormally, it may mean that the support structure is at risk of overload or failure, requiring immediate reinforcement or other strengthening measures.

[0063] Step S402: Based on the displacement data of the foundation pit pipeline, the terrain around the foundation pit, and the distribution of the buildings and underground pipelines, predict the deformation trend of the foundation pit pipeline.

[0064] It should be noted that the prediction of pipeline deformation in foundation pits is achieved by analyzing and modeling historical displacement data to predict the deformation of pipelines in the future over a certain period. Spatiotemporal correlation analysis can be used for prediction. The accuracy of the prediction results depends on the complexity of the selected model, the completeness and accuracy of the historical data, and the length of the prediction period. To improve prediction accuracy, the influence of external factors such as the surrounding terrain, the distribution of buildings and underground pipelines on the deformation of the foundation pit pipelines can be considered. For example, the presence of buildings and underground pipelines may limit the displacement space of the foundation pit pipelines, while changes in terrain may affect the stability and deformation pattern of the soil.

[0065] In one feasible implementation, step S402 may include: preprocessing the displacement data of the foundation pit pipeline to obtain preprocessed displacement data, wherein the preprocessing includes removing outlier data points and imputing missing data; extracting spatial features from the preprocessed displacement data to obtain a spatial feature sequence; performing sequence analysis based on the spatial feature sequence to obtain the deformation of the foundation pit pipeline in different time periods; constructing a foundation pit pipeline deformation prediction model based on the deformation of the foundation pit pipeline in different time periods; and inputting the spatial feature sequence into the foundation pit pipeline deformation prediction model to obtain the deformation trend of the foundation pit pipeline.

[0066] It should be noted that preprocessing the displacement data of the foundation pit pipeline is to improve data accuracy. Outlier data points may be caused by measurement errors or equipment malfunctions, and these data points will negatively affect the training of the prediction model, so they need to be removed. At the same time, imputation of missing data can ensure data integrity and avoid data gaps during the prediction process.

[0067] Specifically, outlier data point removal includes: inputting the displacement data set to be processed, A = {a1, a2, a3, ..., a...} n}, where n represents the total amount of displacement data; the natural nearest neighbor search algorithm is used to find the natural neighborhood feature values ​​of the original data, denoted as B; the displacement data is then obtained. The three nearest neighbors are identified, including the k-nearest neighbor, the reverse nearest neighbor, and the shared nearest neighbor; displacement data is created based on these three nearest neighbors. The neighborhood space; determine the displacement data The average distance and relative average distance to all points in the neighborhood space; based on displacement data. Displacement data is determined by the average distance to all points in the neighborhood space. Local density; based on displacement data The average density of nearest neighbors is determined by the relative average distance to all points in the neighborhood space; the outlier degree of the displacement data is determined based on the local density and the average density of nearest neighbors; displacement data with an outlier degree greater than a preset outlier degree threshold are considered abnormal outlier data, and deleting abnormal outlier data completes the removal of abnormal outlier data points.

[0068] The formula for calculating the eigenvalue B of the natural neighborhood is: Where B is the feature value of the natural neighborhood. The displacement data at the s-th iteration The number of anti-nearest neighbors.

[0069] The formula for calculating the relative average distance is: in, For displacement data To neighboring space The relative average distance between all points within the area. For displacement data To neighboring space The average distance between all points within the neighborhood, where B is the natural neighborhood feature value and m is the number of data points in the neighborhood space. It is a constant, taking values ​​of [0.05, 0.2].

[0070] Specifically, missing data imputation includes: clustering the displacement data to determine the cluster centers; determining the correlation between the cluster centers and the current displacement data; when the correlation is greater than a preset correlation threshold, using the cluster centers as missing values ​​to fill in the missing values; when the correlation is less than or equal to the preset correlation threshold, using the sum of the standard deviations of the cluster centers and the displacement data as missing values ​​to fill in the missing values.

[0071] Spatial feature extraction involves extracting spatially correlated features from the preprocessed displacement data. These features reflect the deformation patterns and trends of the pipelines in the foundation pit. Sequence analysis further reveals the deformation of the pipelines at different time points, providing strong support for building a prediction model. Finally, inputting the spatial feature sequence into the foundation pit pipeline deformation prediction model yields the deformation trend of the pipelines. Step S403: Based on the rise and fall data of the foundation pit water level, the average temperature around the foundation pit and the surface humidity, predict the foundation pit water level and obtain the trend of the foundation pit water level change.

[0072] It should be noted that the prediction of dewatering levels in foundation pits involves analyzing historical precipitation data and combining it with environmental factors such as average temperature and surface humidity around the pit to predict changes in the dewatering level over a future period. This prediction process also relies on accurate model selection and data analysis. Average temperature and surface humidity are important factors affecting soil moisture evaporation and infiltration; their changes directly influence the rise and fall of the foundation pit dewatering level. Therefore, incorporating these factors into the prediction model can improve the accuracy of the prediction.

[0073] In practical implementation, support vector machines, random forests, convolutional neural networks, bidirectional gated recurrent units, and other methods can be used to construct precipitation level prediction models for foundation pits. These algorithms can learn the patterns of precipitation level changes from a large amount of historical data and take into account the influence of various environmental factors. By training and optimizing the model, more accurate prediction results can be obtained.

[0074] In one feasible implementation, step S403 may include: obtaining an initial hyperparameter combination of the foundation pit dewatering level prediction model; inputting the initial hyperparameter combination into an improved pelican optimization algorithm for iterative optimization to obtain an optimal hyperparameter combination, wherein the improved pelican optimization algorithm is obtained by introducing Logistic chaotic mapping, adaptive weighting factor and firefly perturbation strategy into the pelican optimization algorithm; configuring the optimal hyperparameter combination into the foundation pit dewatering level prediction model to obtain an optimized foundation pit dewatering level prediction model; inputting the rise and fall data of the foundation pit dewatering level, the average temperature around the foundation pit and the surface humidity into the optimized foundation pit dewatering level prediction model to predict the foundation pit dewatering level and obtain the trend of foundation pit dewatering level change.

[0075] It should be noted that, in this embodiment, the foundation pit dewatering water level prediction model is a CNN-BiGRU model that considers spatiotemporal correlation. The CNN-BiGRU model combines the advantages of convolutional neural networks (CNN) and bidirectional gated recurrent units (BiGRU), enabling it to simultaneously capture the spatial features and temporal dependencies of the data. The CNN layer extracts the spatial features of the foundation pit dewatering water level data, such as local patterns and trends in water level changes. The BiGRU layer, on the other hand, captures the temporal dependencies of water level changes, considering the influence of historical data on the current water level.

[0076] Understandably, introducing the improved Pelican Optimization algorithm to optimize the model's hyperparameters can further improve prediction accuracy. This algorithm enhances search diversity through Logistic chaotic mapping, avoiding getting trapped in local optima; the adaptive weighting factor balances global and local search capabilities; and the firefly perturbation strategy helps the algorithm escape local optima and accelerates the convergence process. Through iterative optimization, the optimal hyperparameter combination can be obtained, thereby constructing a higher-performance pit dewatering level prediction model.

[0077] In the specific implementation, a pelican population is initialized, with each pelican representing a hyperparameter combination. Initial pelican positions are generated based on a Logistic chaotic mapping to increase population diversity. The fitness value of each pelican is determined based on the prediction results of the foundation pit precipitation level prediction model. The pelican positions are updated according to the fitness values, and an adaptive weighting factor is used to balance the global and local searches. A firefly perturbation strategy is introduced to fine-tune the positions of some pelicans to avoid getting trapped in local optima. The above steps are repeated until a preset number of iterations is reached or the fitness value converges. The individual with the best fitness value is selected from the final pelican population, and its corresponding hyperparameter combination is the optimal hyperparameter combination. Configuring the optimal hyperparameter combination into the foundation pit precipitation level prediction model can significantly improve the model's prediction performance. By inputting the rise and fall data of foundation pit precipitation levels, the average temperature around the foundation pit, and surface humidity into the optimized model, a more accurate trend of foundation pit precipitation level changes can be obtained.

[0078] Step S404: Based on the change data of the internal force of the long plate brace of the foundation pit and the average temperature around the foundation pit, predict the internal force of the long plate brace of the foundation pit to obtain the change trend of the internal force of the long plate brace of the foundation pit.

[0079] It should be noted that the prediction of internal forces in the long bracing of the foundation pit is achieved by analyzing historical data on the changes in internal forces of the long bracing and combining this with environmental factors such as the average temperature around the foundation pit to predict the future trend of the internal forces in the long bracing. This prediction process is crucial for assessing the stability and safety of the foundation pit support structure. Average temperature is one of the important factors affecting soil stress and deformation, and its changes may indirectly affect the distribution of internal forces in the long bracing of the foundation pit. Therefore, incorporating average temperature into the prediction model helps to more comprehensively consider the impact of temperature effects and improve the accuracy of the prediction.

[0080] In practical implementation, similar machine learning algorithms, such as support vector regression, gradient boosting trees, or long short-term memory networks, can be used to construct prediction models for the internal forces of long bracing in foundation pits. These algorithms can learn the patterns of internal force changes in long bracing from historical data and consider the influence of various environmental factors. By training and optimizing the model, more accurate prediction results can be obtained, providing strong support for the safety management of foundation pit construction.

[0081] In one feasible implementation, step S404 may include: preprocessing the variation data of the internal forces of the long slab brace in the foundation pit to obtain preprocessed internal force data, wherein the preprocessing step includes smoothing abnormal fluctuation data and filtering noise data; extracting time features from the preprocessed internal force data to obtain a time feature sequence; performing correlation analysis based on the time feature sequence and the average temperature around the foundation pit to determine the correlation between the variation of the internal forces of the long slab brace in the foundation pit and the temperature; constructing a prediction model for the internal forces of the long slab brace in the foundation pit based on the correlation; and inputting the time feature sequence and the average temperature around the foundation pit into the prediction model for the internal forces of the long slab brace in the foundation pit to predict the internal forces of the long slab brace in the foundation pit, thereby obtaining the trend of the variation of the internal forces of the long slab brace in the foundation pit.

[0082] It should be noted that smoothing abnormal fluctuation data and filtering noisy data can ensure that the data input into the prediction model is more stable and reliable, reducing prediction errors caused by data quality issues. The time feature extraction step can extract time-related features from the preprocessed internal force data, such as daily, weekly, or seasonal variations. These features can reflect the pattern of internal force changes of the long plate bracing in the foundation pit over time.

[0083] It is worth noting that when constructing the prediction model for the internal forces of long slab supports in foundation pits, the correlation between the time feature series and the average temperature can be fully considered. Through correlation analysis, the correlation between the changes in the internal forces of the long slab supports and temperature can be determined, and this correlation can provide the model with more accurate input features. During the model training process, methods such as cross-validation can be used to evaluate the model's performance and ensure that the model has good generalization ability. Finally, by inputting the preprocessed time feature series and average temperature into the optimized prediction model for the internal forces of long slab supports in foundation pits, the changing trend of the internal forces of the long slab supports in deep foundation pits can be obtained.

[0084] In this embodiment, by predicting the changing trends in multiple dimensions based on monitoring data and three-dimensional data of the surrounding environment, the richness of the data is effectively improved, thereby enhancing the accuracy and reliability of early warning of abnormal behavior in foundation pit construction.

[0085] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the abnormal behavior early warning method based on foundation pit construction. Any simple modifications based on this technical concept are within the protection scope of this application.

[0086] This application also provides an early warning device for abnormal behavior during foundation pit construction; please refer to [reference needed]. Figure 3 The abnormal behavior early warning device based on foundation pit construction includes: The acquisition module 10 is used to acquire BIM data and three-dimensional geological data of the foundation pit.

[0087] The deployment module 20 is used to deploy monitoring points based on the foundation pit BIM data and the foundation pit three-dimensional geological data, and to acquire monitoring data of each monitoring point.

[0088] The control module 30 is used to control the drone to conduct aerial inspections of the foundation pit construction site and take on-site videos to obtain three-dimensional data of the surrounding environment.

[0089] The prediction module 40 is used to perform trend prediction based on the monitoring data and the three-dimensional data of the surrounding environment to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support.

[0090] The assessment module 50 is used to conduct a safety risk assessment of the foundation pit based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support, and to obtain the foundation pit safety risk level.

[0091] The early warning module 60 is used to issue an early warning of abnormal construction behavior in the foundation pit when the safety risk level of the foundation pit reaches a preset early warning level.

[0092] The abnormal behavior early warning device for foundation pit construction provided in this application adopts the abnormal behavior early warning method for foundation pit construction in the above embodiments. It can solve the technical problem that existing foundation pit construction monitoring relies on traditional fixed sensor deployment methods, which makes it difficult to achieve comprehensive and real-time monitoring and early warning of the construction process, resulting in poor construction safety. Compared with the prior art, the beneficial effects of the abnormal behavior early warning device for foundation pit construction provided in this application are the same as those of the abnormal behavior early warning method for foundation pit construction provided in the above embodiments, and other technical features of the abnormal behavior early warning device for foundation pit construction are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0093] This application provides an abnormal behavior early warning device based on foundation pit construction. The abnormal behavior early warning device based on foundation pit construction includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the abnormal behavior early warning method based on foundation pit construction in the above embodiment 1.

[0094] The following is for reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing an abnormal behavior early warning device based on foundation pit construction in the embodiments of this application. The abnormal behavior early warning device based on foundation pit construction in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The abnormal behavior early warning device based on foundation pit construction shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0095] like Figure 4As shown, the early warning device for abnormal behavior during foundation pit construction may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the early warning device for abnormal behavior during foundation pit construction. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the abnormal behavior early warning device based on foundation pit construction to exchange data with other devices wirelessly or via wired communication. Although the figure shows an abnormal behavior early warning device based on foundation pit construction with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0096] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0097] The abnormal behavior early warning device for foundation pit construction provided in this application adopts the abnormal behavior early warning method for foundation pit construction in the above embodiments. It can solve the technical problem that existing foundation pit construction monitoring relies on traditional fixed sensor deployment methods, which makes it difficult to achieve comprehensive and real-time monitoring and early warning of the construction process, resulting in poor construction safety. Compared with the prior art, the beneficial effects of the abnormal behavior early warning device for foundation pit construction provided in this application are the same as those of the abnormal behavior early warning method for foundation pit construction provided in the above embodiments, and other technical features of the abnormal behavior early warning device for foundation pit construction are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0098] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0099] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0100] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the abnormal behavior early warning method based on foundation pit construction in the above embodiments.

[0101] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0102] The aforementioned computer-readable storage medium may be included in an early warning device for abnormal behavior during foundation pit construction; or it may exist independently and not be assembled into an early warning device for abnormal behavior during foundation pit construction.

[0103] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by an abnormal behavior early warning device for foundation pit construction, the device causes the following actions: acquires foundation pit BIM data and foundation pit 3D geological data; deploys monitoring points based on the foundation pit BIM data and the foundation pit 3D geological data, and acquires monitoring data from each monitoring point; controls a drone to conduct aerial inspections of the foundation pit construction site and capture on-site videos to obtain 3D data of the surrounding environment; performs trend prediction based on the monitoring data and the surrounding environment 3D data to obtain trends in foundation pit pipeline deformation, foundation pit dewatering level changes, and foundation pit long plate support internal force changes; conducts foundation pit safety risk assessment based on the foundation pit pipeline deformation trends, foundation pit dewatering level changes, and foundation pit long plate support internal force changes to obtain a foundation pit safety risk level; and issues an early warning for abnormal behavior in foundation pit construction when the foundation pit safety risk level reaches a preset warning level.

[0104] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0106] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0107] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for early warning of abnormal behavior in foundation pit construction. This solves the technical problem that existing foundation pit construction monitoring relies on traditional fixed sensor deployment methods, making it difficult to achieve comprehensive, real-time monitoring and early warning of the construction process, resulting in poor construction safety. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the abnormal behavior early warning method for foundation pit construction provided in the above embodiments, and will not be repeated here.

[0108] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for early warning of abnormal behavior in foundation pit construction.

[0109] The computer program product provided in this application can solve the technical problem that existing foundation pit construction monitoring relies on traditional fixed sensor deployment methods, making it difficult to achieve comprehensive and real-time monitoring and early warning of the construction process, resulting in poor construction safety. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the abnormal behavior early warning method based on foundation pit construction provided in the above embodiments, and will not be repeated here.

[0110] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for early warning of abnormal behavior during foundation pit construction, characterized in that, The method includes: Acquire BIM data and 3D geological data of the foundation pit; Based on the BIM data and three-dimensional geological data of the foundation pit, monitoring points are set up, and monitoring data of each monitoring point is obtained. Control drones to conduct aerial surveys of the foundation pit construction site and capture on-site videos to obtain three-dimensional data of the surrounding environment; Based on the monitoring data and the three-dimensional data of the surrounding environment, trend prediction is performed to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support. Based on the deformation trend of the pipeline in the foundation pit, the water level change trend of the foundation pit dewatering, and the internal force change trend of the long plate bracing in the foundation pit, a safety risk assessment of the foundation pit is conducted to obtain the safety risk level of the foundation pit. When the safety risk level of the foundation pit reaches the preset warning level, an early warning of abnormal construction behavior in the foundation pit will be issued.

2. The method as described in claim 1, characterized in that, The step of setting up monitoring points based on the foundation pit BIM data and the foundation pit 3D geological data, and acquiring monitoring data from each monitoring point, includes: A digital twin model of the foundation pit is constructed based on the BIM data and the three-dimensional geological data of the foundation pit. Obtain the current construction stage and structural load distribution; Based on the three-dimensional geological data of the foundation pit, the current construction stage, and the structural load distribution, potential risk areas are predicted using a joint model based on reinforcement learning and finite element analysis. Based on the digital twin foundation pit model and the potential risk area, a simulation of the monitoring point layout was conducted to obtain an initial monitoring point layout scheme. The initial monitoring point layout scheme was optimized to obtain the optimal monitoring point layout scheme; Monitoring points are set up at the foundation pit construction site according to the optimal monitoring point layout scheme, and monitoring data of each monitoring point are acquired in real time.

3. The method as described in claim 1, characterized in that, The controlled drone conducts aerial surveys of the foundation pit construction site and captures on-site video, obtaining three-dimensional data of the surrounding environment, including: Based on the location of each monitoring point, the UAV flight path is planned to obtain the UAV flight path; The drone is controlled to conduct aerial inspections of the foundation pit construction site according to the drone's flight path. During the aerial inspection, the drone's high-definition camera captures video of the site, and temperature and humidity data of the site environment are collected by temperature and humidity sensors. Keyframes were extracted from the captured video footage, and 3D reconstruction was performed based on the extracted keyframes to obtain the distribution of terrain, buildings, and underground pipelines around the foundation pit. The average temperature and surface humidity around the foundation pit are determined based on the temperature and humidity data of the site environment. Three-dimensional data of the surrounding environment are obtained based on the topography, distribution of buildings and underground pipelines around the foundation pit, average temperature and surface humidity around the foundation pit.

4. The method as described in claim 1, characterized in that, The trend prediction based on the monitoring data and the surrounding three-dimensional environmental data yields the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate bracing, including: Based on the monitoring data, the displacement data of the foundation pit pipeline, the rise and fall data of the foundation pit dewatering water level, and the change data of the internal force of the foundation pit long plate support are determined. Based on the three-dimensional data of the surrounding environment, the distribution of the terrain, buildings and underground pipelines around the foundation pit, the average temperature and surface humidity around the foundation pit are determined. Based on the displacement data of the foundation pit pipeline, the terrain around the foundation pit, and the distribution of the buildings and underground pipelines, the deformation of the foundation pit pipeline is predicted, and the deformation trend of the foundation pit pipeline is obtained. Based on the rise and fall data of the water level in the foundation pit, the average temperature around the foundation pit and the surface humidity, the water level in the foundation pit is predicted, and the trend of water level change in the foundation pit is obtained. Based on the variation data of the internal force of the long plate bracing in the foundation pit and the average temperature around the foundation pit, the internal force of the long plate bracing in the foundation pit is predicted, and the variation trend of the internal force of the long plate bracing in the foundation pit is obtained.

5. The method as described in claim 4, characterized in that, The method of predicting the deformation trend of the foundation pit pipelines based on the displacement data of the pipelines in the foundation pit, the surrounding terrain of the foundation pit, and the distribution of the buildings and underground pipelines includes: The displacement data of the foundation pit pipeline is preprocessed to obtain preprocessed displacement data, wherein the preprocessing includes the removal of outlier data points and the imputation of missing data. Spatial feature extraction is performed on the preprocessed displacement data to obtain a spatial feature sequence; Based on the spatial feature sequence, sequence analysis was performed to obtain the deformation of the foundation pit pipeline at different time periods; Based on the deformation of the foundation pit pipeline at different time periods, a deformation prediction model for the foundation pit pipeline is constructed. The spatial feature sequence is input into the foundation pit pipeline deformation prediction model to obtain the foundation pit pipeline deformation trend.

6. The method as described in claim 4, characterized in that, The method of predicting the foundation pit's precipitation level based on the rise and fall data of the foundation pit's precipitation level, the average temperature around the foundation pit, and the surface humidity, to obtain the trend of the foundation pit's precipitation level change, includes: Obtain the initial hyperparameter combination of the foundation pit dewatering water level prediction model; The initial hyperparameter combination is input into the improved Pelican optimization algorithm for iterative optimization to obtain the optimal hyperparameter combination. The improved Pelican optimization algorithm is obtained by introducing Logistic chaotic mapping, adaptive weight factor and firefly perturbation strategy into the Pelican optimization algorithm. The optimal hyperparameter combination is configured into the foundation pit dewatering level prediction model to obtain the optimized foundation pit dewatering level prediction model. The rise and fall data of the foundation pit water level, the average temperature around the foundation pit, and the surface humidity are input into the optimized foundation pit water level prediction model to predict the foundation pit water level and obtain the trend of the foundation pit water level change.

7. The method as described in claim 4, characterized in that, The method of predicting the internal force of the long brace in the foundation pit based on the variation data of the internal force of the long brace and the average temperature around the foundation pit, and obtaining the variation trend of the internal force of the long brace, includes: The data on the variation of internal forces of the long plate brace in the foundation pit are preprocessed to obtain preprocessed internal force data. The preprocessing steps include smoothing abnormal fluctuation data and filtering noise data. The time features of the preprocessed internal force data are extracted to obtain a time feature sequence; Based on the time feature sequence and the average temperature around the foundation pit, a correlation analysis was performed to determine the correlation between the change in the internal force of the long plate bracing in the foundation pit and the temperature. Based on the aforementioned correlation, a prediction model for the internal forces of the long slab bracing in the foundation pit is constructed. The time feature sequence and the average temperature around the foundation pit are input into the foundation pit long plate brace internal force prediction model to predict the internal force of the foundation pit long plate brace and obtain the changing trend of the internal force of the foundation pit long plate brace.

8. The method as described in claim 1, characterized in that, The foundation pit safety risk assessment is conducted based on the deformation trend of the pipelines in the foundation pit, the water level change trend of the foundation pit dewatering, and the internal force change trend of the long plate bracing in the foundation pit, to obtain the foundation pit safety risk level, including: A multi-dimensional risk feature vector is constructed based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace. The empirical Copula function is determined based on the empirical cumulative distribution of the multi-dimensional risk feature vectors. The joint distribution of the multi-dimensional risk feature vectors is determined based on the empirical Copula function. The tail probabilities of the joint distribution across all dimensions are determined using the empirical Copula function. Outlier scores are generated based on the tail probability, and the safety risk of the foundation pit construction is assessed based on the outlier scores to obtain the foundation pit safety risk level.

9. An early warning device for abnormal behavior during foundation pit construction, characterized in that, The abnormal behavior early warning device based on foundation pit construction includes: The acquisition module is used to acquire BIM data and 3D geological data of the foundation pit. The deployment module is used to deploy monitoring points based on the foundation pit BIM data and the foundation pit three-dimensional geological data, and to acquire monitoring data of each monitoring point. The control module is used to control the drone to conduct aerial inspections of the foundation pit construction site and take on-site videos to obtain three-dimensional data of the surrounding environment; The prediction module is used to perform trend prediction based on the monitoring data and the three-dimensional data of the surrounding environment to obtain the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate support. The assessment module is used to conduct a safety risk assessment of the foundation pit based on the deformation trend of the foundation pit pipeline, the water level change trend of the foundation pit dewatering, and the internal force change trend of the foundation pit long plate brace, and to obtain the foundation pit safety risk level. The early warning module is used to issue an early warning of abnormal construction behavior in the foundation pit when the safety risk level of the foundation pit reaches a preset early warning level.

10. A storage medium, characterized in that, The storage medium stores an abnormal behavior early warning program based on foundation pit construction. When the processor executes the abnormal behavior early warning program based on foundation pit construction, it implements the abnormal behavior early warning method based on foundation pit construction as described in any one of claims 1 to 8.

Images