Method and system for evaluating positions of construction fences in expressway construction area

Abstract

The invention discloses a method and system for evaluating the position of a construction fence of a highway construction area, and relates to the technical field of safety evaluation, and the method comprises the steps: obtaining real-time traffic flow data, construction area three-dimensional point cloud data and fence structure parameters corresponding to the highway construction area; constructing a fence structure stability analysis model according to the three-dimensional point cloud data of the construction area to obtain fence structure stress distribution data, and constructing a traffic flow disturbance model based on the real-time traffic flow data to obtain a vehicle running track disturbance coefficient; performing multi-dimensional coupling analysis on the fence structure stress distribution data and the vehicle running track disturbance coefficient to obtain fence collision risk probability data; constructing a safety evaluation index system according to the fence collision risk probability data; and inputting the safety evaluation index system into the deep learning evaluation model, outputting a fence position comprehensive evaluation grade, and when the comprehensive evaluation grade exceeds a preset threshold value, triggering an early warning signal. The method has the effect of improving the evaluation efficiency.

Description

Technical Field

[0001] This application relates to the technical field of safety evaluation, and in particular, to a method and system for evaluating the position of construction enclosures in highway construction areas. Background Art

[0002] Construction enclosures are common traffic safety facilities in road construction areas. Reasonably setting the position of construction enclosures in the construction area plays an important role in ensuring traffic safety in the construction area and saving land resources in the construction area. With the continuous and rapid development of China's economy, a large number of early-built expressways mainly with two-way four lanes can no longer meet the current increasing traffic volume. China will enter the heyday of the reconstruction and expansion of expressways. The sudden change of the traffic environment brought by the road construction area will have a greater impact on the operation of traffic flow and traffic safety, and even cause traffic accidents to occur from time to time. Considering the operation of traffic flow on the original road, generally, construction is carried out by closing some lanes or occupying the road shoulder. Setting construction enclosures on the roadside of the road construction area to make the construction site a relatively isolated space is of great significance for reducing traffic accidents.

[0003] In related technologies, the current safety evaluation of enclosures in highway construction areas mainly relies on manual inspections and static mechanical model analysis. The safety assessment is carried out by regularly checking the apparent damage of the enclosure structure and measuring the foundation settlement. The above technologies are mostly limited to single physical field analysis, and fail to effectively integrate the spatio-temporal coupling effect of structural mechanical response and dynamic traffic flow, lacking the risk evolution mechanism under the synergistic action of multiple factors, thus effectively reducing the evaluation efficiency and there are areas for improvement. Summary of the Invention

[0004] In view of the deficiencies of the prior art, this application provides a method and system for evaluating the position of construction enclosures in highway construction areas.

[0005] In a first aspect, this application provides a method for evaluating the position of construction enclosures in highway construction areas, including the following steps:

[0006] Step S1: Obtain real-time traffic flow data, three-dimensional point cloud data of the construction area, and enclosure structure parameters corresponding to the highway construction area. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include the strength of the enclosure material, the shear strength of the connecting piece, and the foundation anchorage depth;

[0007] Step S2: Construct an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area, perform finite element stress field simulation in combination with the enclosure structure parameters to obtain enclosure structure stress distribution data, and construct a traffic flow perturbation model based on the real-time traffic flow data to obtain a vehicle operation trajectory perturbation coefficient;

[0008] Step S3: Conduct multi-dimensional coupling analysis on the stress distribution data of the enclosure structure and the vehicle operation trajectory disturbance coefficient, and then obtain the enclosure collision risk probability data;

[0009] Step S4: Construct a safety evaluation index system based on the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic disturbance index, and an emergency response index;

[0010] Step S5: Input the structural safety index, the traffic disturbance index, and the emergency response index into a preset deep learning evaluation model, output the comprehensive evaluation grade of the enclosure location, and when the comprehensive evaluation grade exceeds the preset threshold, generate an enclosure location optimization suggestion and trigger an early warning signal;

[0011] Step S6: Push the comprehensive evaluation grade and the early warning signal to the construction management terminal and the in-vehicle navigation system in real time, and synchronously update the warning range of the electronic fence.

[0012] Preferably, step 1 includes the following steps:

[0013] Step S11: Collect real-time traffic flow data corresponding to the highway construction area through a roadside millimeter-wave radar array, and use a multi-target tracking algorithm to extract vehicle trajectory data, vehicle speed data, and vehicle type distribution data corresponding to the lane;

[0014] Step S12: Use a three-dimensional laser scanner carried by a drone to obtain point cloud data of the construction area, and generate three-dimensional point cloud data of the construction area through a point cloud registration algorithm;

[0015] Step S13: Use a stress wave detector and an Internet of Things sensor to conduct real-time detection on the enclosure structure, and then obtain the enclosure material strength, the shear strength of the connecting piece, and the foundation anchorage depth corresponding to the enclosure structure.

[0016] Preferably, the specific steps for constructing an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area in step S2 are as follows:

[0017] Step S21: Convert the three-dimensional point cloud data of the construction area into a finite element mesh model, and set the material constitutive relationship and boundary conditions;

[0018] Step S22: Apply the multi-physical field coupling action of wind load, vehicle aerodynamic load, and temperature load;

[0019] Step S23: Calculate the stress-strain distribution nephogram of the enclosure structure according to the material constitutive relationship, boundary conditions, and multi-physical field coupling action and using a non-linear solver;

[0020] Step S24: Extract the maximum principal stress value and the critical buckling coefficient from the stress-strain distribution contour map of the enclosure structure as the structural stability indicators, and construct a stability analysis model of the enclosure structure based on the structural stability indicators.

[0021] Preferably, step S3 includes the following steps:

[0022] Step S31: Establish a vehicle deviation probability distribution model based on vehicle trajectory data, and calculate the probability density function of vehicles deviating from the construction area in each lane;

[0023] Step S32: Establish a kinetic energy impact model based on vehicle type distribution data and vehicle speed data, and calculate the impact kinetic energy of different types of vehicles at different speeds;

[0024] Step S33: Perform spatio-temporal matching on the stress distribution data of the enclosure structure and the impact kinetic energy of different types of vehicles at different speeds to obtain the dynamic load-bearing capacity margin of each section of the enclosure;

[0025] Step S34: Perform Monte Carlo simulation based on the dynamic load-bearing capacity margin of each section of the enclosure and the probability density function of vehicles deviating from the construction area in each lane to obtain the enclosure collision risk probability data.

[0026] Preferably, the Monte Carlo simulation in step S34 specifically includes:

[0027] Establish a two-dimensional probability distribution function of the event of vehicles deviating from the construction area in each lane and the load-bearing capacity of the enclosure, set multiple random samplings, and generate the vehicle deviation position and impact kinetic energy parameters simultaneously for each random sampling. When the impact kinetic energy parameter corresponding to the random sampling exceeds the load-bearing capacity of the enclosure, it is recorded as a failure event, and then calculate the occurrence frequency corresponding to the failure event, and set the occurrence frequency as the enclosure collision risk probability data.

[0028] Preferably, step S4 includes the following steps:

[0029] Step S41: Normalize the stress distribution data of the enclosure structure, and confirm the structural safety index according to the normalized stress distribution data of the enclosure structure;

[0030] Step S42: Confirm the traffic disturbance index based on the vehicle operation trajectory disturbance coefficient and the dynamic weight distribution in peak hours and off-peak hours;

[0031] Step S43: Confirm the emergency response index according to the emergency access setting parameters in the construction area and the rescue response time.

[0032] Preferably, updating the warning range of the electronic fence in step S6 specifically includes:

[0033] Calculate the dynamic warning radius according to the comprehensive evaluation level, and use the variable message sign to display the real-time warning range according to the dynamic warning radius, and send a graded warning signal to the vehicles approaching the construction area enclosure structure through V2X communication.

[0034] Preferably, the graded warning signal includes:

[0035] When the comprehensive evaluation level is between the first preset threshold and the second preset threshold, output a first-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning lights in yellow, and reduce the volume of the in-vehicle navigation system and display a prompt message;

[0036] When the comprehensive evaluation level is between the second preset threshold and the third preset threshold, output a second-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning lights in orange, and activate the in-vehicle HUD head-up display warning sign;

[0037] When the comprehensive evaluation level exceeds the third preset threshold, output a third-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning lights in red, and trigger the vehicle's active braking system and link with the road management department.

[0038] In a second aspect, the present application provides an evaluation system for the construction enclosure position in a highway construction area, including:

[0039] A data acquisition module for acquiring real-time traffic flow data, three-dimensional point cloud data of the construction area, and enclosure structure parameters corresponding to the highway construction area. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include the strength of the enclosure material, the shear strength of the connecting piece, and the foundation anchorage depth;

[0040] A data analysis module for constructing an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area, performing a finite element stress field simulation in combination with the enclosure structure parameters to obtain enclosure structure stress distribution data, and constructing a traffic flow perturbation model based on the real-time traffic flow data to obtain a vehicle operation trajectory perturbation coefficient;

[0041] An enclosure collision risk probability confirmation module for performing multi-dimensional coupling analysis on the enclosure structure stress distribution data and the vehicle operation trajectory perturbation coefficient to obtain enclosure collision risk probability data;

[0042] A safety evaluation index system construction module for constructing a safety evaluation index system according to the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic perturbation index, and an emergency response index;

[0043] A comprehensive evaluation grade generation module is used to input the structural safety index, traffic disturbance index and emergency response index into a preset deep learning evaluation model, output the comprehensive evaluation grade of the enclosure position, and generate optimization suggestions for the enclosure position and trigger an early warning signal when the comprehensive evaluation grade exceeds a preset threshold;

[0044] The early warning module is used to push the comprehensive evaluation level and early warning signal to the construction management terminal and the vehicle navigation system in real time, and simultaneously update the electronic fence warning range.

[0045] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-described methods for evaluating the location of construction fences in a highway construction area.

[0046] In summary, this application includes the following beneficial technical effects:

[0047] The present application provides an evaluation method for the position of construction fences in a highway construction area. The method obtains real-time traffic flow data, three-dimensional point cloud data of the construction area and fence structure parameters corresponding to the highway construction area, constructs a fence structure stability analysis model according to the three-dimensional point cloud data of the construction area, performs finite element stress field simulation in combination with the fence structure parameters, obtains fence structure stress distribution data, and constructs a traffic flow disturbance model based on real-time traffic flow data to obtain a vehicle running trajectory disturbance coefficient. A multi-dimensional coupling analysis is performed on the fence structure stress distribution data and the vehicle running trajectory disturbance coefficient to obtain fence collision risk probability data, thereby effectively integrating the spatiotemporal coupling effect of the structural mechanics response and the dynamic traffic flow, increasing the risk evolution mechanism under the synergistic effect of multiple factors, and constructs a safety evaluation index system according to the fence collision risk probability data to output a comprehensive evaluation level of the fence position. When the comprehensive evaluation level exceeds a preset threshold, a fence position optimization suggestion is generated and a warning signal is triggered, thereby effectively evaluating the position of the construction fence in the highway construction area, thereby effectively improving the evaluation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 It is a flow chart of the evaluation method for the location of construction fences in a highway construction area according to an embodiment of the present application.

[0050] Figure 2It is a schematic diagram of an evaluation system for the construction enclosure position in the highway construction area of the embodiment of the present application. Specific embodiments

[0051] The following will Figure 1-2 further elaborate on the present application in conjunction with the attached drawings.

[0052] Embodiment 1

[0053] The embodiment of the present application discloses an evaluation method for the construction enclosure position in the highway construction area.

[0054] Referring to Figure 1 , an evaluation method for the construction enclosure position in the highway construction area includes the following steps:

[0055] Step S1: Obtain the real-time traffic flow data corresponding to the highway construction area, the three-dimensional point cloud data of the construction area, and the enclosure structure parameters. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include the strength of the enclosure material, the shear strength of the connecting parts, and the foundation anchorage depth;

[0056] Step S2: Construct an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area, perform a finite element stress field simulation in combination with the enclosure structure parameters to obtain the enclosure structure stress distribution data, and construct a traffic flow disturbance model based on the real-time traffic flow data to obtain the vehicle operation trajectory disturbance coefficient;

[0057] Step S3: Perform a multi-dimensional coupling analysis on the enclosure structure stress distribution data and the vehicle operation trajectory disturbance coefficient to obtain the enclosure collision risk probability data;

[0058] Step S4: Construct a safety evaluation index system according to the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic disturbance index, and an emergency response index;

[0059] Step S5: Input the structural safety index, the traffic disturbance index, and the emergency response index into a preset deep learning evaluation model, output the comprehensive evaluation grade of the enclosure position, and when the comprehensive evaluation grade exceeds the preset threshold, generate an enclosure position optimization suggestion and trigger a warning signal;

[0060] Step S6: Push the comprehensive evaluation grade and the warning signal to the construction management terminal and the in-vehicle navigation system in real time, and synchronously update the warning range of the electronic fence.

[0061] It should be noted that Step 1 includes the following steps:

[0062] Step S11: Collect real-time traffic flow data corresponding to the highway construction area through a roadside millimeter-wave radar array, and use a multi-target tracking algorithm to extract vehicle trajectory data, vehicle speed data, and vehicle type distribution data corresponding to the lanes.

[0063] Step S12: Use a 3D laser scanner carried by a drone to obtain point cloud data of the construction area, and generate 3D point cloud data of the construction area through a point cloud registration algorithm.

[0064] Step S13: Use a stress wave detector and Internet of Things sensors to perform real-time detection on the enclosure structure, and then obtain the strength of the enclosure material, the shear strength of the connecting parts, and the foundation anchorage depth corresponding to the enclosure structure.

[0065] Specifically, in step S11, real-time traffic flow data corresponding to the highway construction area is collected through a roadside millimeter-wave radar array. The millimeter-wave radar uses electromagnetic waves in the millimeter-wave band to detect targets, and has the characteristics of high precision and high resolution. A millimeter-wave radar array is installed on the roadside of the highway construction area. The radar continuously emits millimeter-wave signals and receives the signals reflected back by targets such as vehicles. By analyzing and processing the echo signals, the traffic flow data of the construction area can be obtained in real time, and a multi-target tracking algorithm is used to simultaneously track multiple vehicle targets, and extract the vehicle trajectory data, vehicle speed data, and vehicle type distribution data corresponding to the lanes from the complex radar echo data. Exemplarily, the multi-target tracking algorithm can calculate the driving trajectory according to the position information of the vehicle at different times; obtain the vehicle speed data by measuring the position change of the vehicle at adjacent times; and judge the vehicle type distribution data according to the characteristic information such as the size and shape of the vehicle, such as distinguishing different types of vehicles such as cars and large trucks.

[0066] Step S12 uses a 3D laser scanner carried by a drone to obtain point cloud data of the construction area. The drone has flexible flight capabilities and can fly over the construction area according to a predetermined flight path. The 3D laser scanner calculates the distance from the target point to the scanner by emitting a laser beam and measuring the time from the emission to the reflection of the laser, so as to obtain the three-dimensional coordinate information of the target point. During the flight of the drone, the 3D laser scanner continuously scans the construction area and collects a large amount of point cloud data. The point cloud data is a collection of discrete three-dimensional coordinate points, representing the shape and position information of the surface of the objects in the construction area. Through the point cloud registration algorithm, the point cloud data collected from different perspectives is aligned and fused to generate 3D point cloud data of the construction area, thereby constructing a 3D model of the construction area and providing intuitive spatial information for subsequent analysis and decision-making.

[0067] In step S13, a stress wave detector and Internet of Things sensors are used to perform real-time detection on the enclosure structure. The stress wave detector emits stress waves towards the enclosure structure, receives the stress wave signals reflected by the structure, analyzes the internal condition of the enclosure structure based on the characteristics of the signals, and thereby obtains the strength of the enclosure material. The Internet of Things sensors can monitor parameters such as the shear strength of the connectors of the enclosure structure and the foundation anchorage depth in real time. For example, pressure sensors are installed at the connectors of the enclosure to measure the shear force borne by the connectors in real time, so as to obtain the shear strength data of the connectors; displacement sensors are installed at the foundation part of the enclosure to monitor the change in the foundation anchorage depth. Through real-time detection, potential safety hazards in the enclosure structure can be discovered in a timely manner, providing strong data support for the safety management of the construction area.

[0068] It should be noted that the specific steps for constructing the enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area in step S2 are as follows:

[0069] Step S21: Convert the three-dimensional point cloud data of the construction area into a finite element mesh model, and set the material constitutive relationship and boundary conditions;

[0070] Step S22: Apply the multi-physical field coupling effects of wind load, vehicle aerodynamic load, and temperature load;

[0071] Step S23: Calculate the stress-strain distribution cloud diagram of the enclosure structure according to the material constitutive relationship, boundary conditions, and multi-physical field coupling effects and by using a non-linear solver;

[0072] Step S24: Extract the maximum principal stress value and the critical buckling coefficient as the structure stability indicators based on the stress-strain distribution cloud diagram of the enclosure structure, and construct the enclosure structure stability analysis model based on the structure stability indicators.

[0073] Specifically, in step S21, the three-dimensional point cloud data of the construction area is converted into a finite element mesh model, and the material constitutive relationship and boundary conditions are set. The three-dimensional point cloud data of the construction area is a set of discrete points collected by a three-dimensional laser scanner carried by a drone. Through specific software algorithms, the point cloud data is converted into a finite element mesh model. The finite element mesh model divides the enclosure structure into many small units, facilitating mechanical analysis. Then, the material constitutive relationship is set. The material constitutive relationship describes the stress-strain relationship of the enclosure material when it is stressed. For example, for a steel enclosure, its material constitutive relationship may follow Hooke's law, etc. At the same time, the boundary conditions are set according to the actual installation situation of the enclosure. For example, the connection method between the bottom of the enclosure and the foundation can be set as a fixed constraint to simulate the situation where the bottom of the enclosure cannot move or rotate.

[0074] Step S22 applies the multi-physics field coupling of wind load, vehicle aerodynamic load and temperature load. Wind load refers to the pressure generated by wind acting on the enclosure. According to local meteorological data and wind speed model, the wind load size under different working conditions is calculated and applied to the finite element model. Vehicle aerodynamic load is the aerodynamic effect on the enclosure when the vehicle is driving. Its size and direction are determined by fluid mechanics principles and vehicle driving parameters. The temperature load takes into account the impact of ambient temperature changes on the enclosure structure. For example, when the temperature rises, the material will expand and generate thermal stress. The above three loads are applied to the finite element model at the same time to simulate the multi-physics field coupling effect that the enclosure is subjected to in the actual working environment.

[0075] Step S23 calculates the stress-strain distribution cloud map of the enclosure structure according to the material constitutive relationship, boundary conditions and multi-physics field coupling, and uses a nonlinear solver. The nonlinear solver is a computing tool specifically used to deal with nonlinear problems. The finite element model is solved by taking into account the nonlinear characteristics of the material (such as the plastic deformation of the material) and the multi-physics field coupling. Through iterative calculation, the stress and strain distribution of the enclosure structure under various loads is obtained and displayed intuitively in the form of a cloud map. For example, in the stress-strain distribution cloud map, the darker color area indicates that the stress or strain is larger, which may be the weak part of the enclosure structure.

[0076] Step S24 extracts the maximum principal stress value and the critical buckling coefficient as structural stability indicators based on the stress-strain distribution cloud map of the enclosure structure, and constructs a stability analysis model of the enclosure structure based on the structural stability indicators. From the stress-strain distribution cloud map, find the maximum principal stress value, which reflects the maximum stress that the enclosure structure is subjected to when it is under force. The critical buckling coefficient is used to evaluate whether the enclosure structure will buckle and become unstable when under pressure. By analyzing the above two indicators, the stability of the enclosure structure is judged. Based on the structural stability index, a mathematical model is constructed to predict and evaluate the stability of the enclosure structure under different working conditions, providing a scientific basis for the design, maintenance and safety assessment of the enclosure structure.

[0077] Finite element stress field simulation is performed in combination with the enclosure structure parameters to obtain the enclosure structure stress distribution data. The process of obtaining the enclosure structure stress distribution data is as follows:

[0078] Import the enclosure structure stability analysis model constructed based on the 3D point cloud data of the construction area into the finite element analysis software. Combine the enclosure structure parameters and set the material constitutive relationship and boundary conditions in the finite element analysis software. For example, if the bottom of the enclosure is rigidly connected to the foundation, it can be set as a fixed constraint. According to the actual working conditions, apply multi-physical field coupling effects such as wind load (determine the wind speed and direction based on local meteorological data and then calculate the wind load), vehicle aerodynamic load (calculate through parameters such as vehicle driving speed and vehicle type), and temperature load (consider the environmental temperature change range). Use the non-linear solver in the software to solve and calculate the model. Through iterative operations, the software will generate the stress-strain distribution of the enclosure structure, presented in the form of a cloud diagram. The stress distribution data of the enclosure structure can be extracted from it to intuitively understand the stress magnitude of each part of the enclosure.

[0079] Construct a traffic flow perturbation model based on real-time traffic flow data. The process of obtaining the vehicle operation trajectory perturbation coefficient is as follows:

[0080] Continuously collect the real-time traffic flow data of the highway construction area through the roadside millimeter-wave radar array. Use the multi-target tracking algorithm to process these data, and accurately extract the vehicle trajectory data, vehicle speed data, and vehicle type distribution data corresponding to the lanes from them. Based on the above extracted data, construct a traffic flow perturbation model. For example, consider that different vehicle types (sedans, large trucks, etc.) produce different perturbations to the surrounding air when driving at different speeds, and thus have different impacts on the enclosure structure. Establish a mathematical model, take factors such as vehicle trajectory, vehicle speed, and vehicle type as variables, and analyze the relationship with the perturbation received by the enclosure structure. Through simulation and calculation, quantify the perturbation degree of vehicle operation on the enclosure structure to obtain the vehicle operation trajectory perturbation coefficient. For example, when a large truck approaches the enclosure at a high speed, the calculated perturbation coefficient will be relatively large, indicating that the interference of vehicle operation on the enclosure structure stability is more obvious at this time.

[0081] It should be noted that step S3 includes the following steps:

[0082] Step S31: Establish a vehicle deviation probability distribution model based on the vehicle trajectory data and calculate the probability density function of vehicles deviating from the construction area in each lane;

[0083] Step S32: Establish a kinetic energy impact model based on the vehicle type distribution data and vehicle speed data and calculate the impact kinetic energy of different types of vehicles at different speeds;

[0084] Step S33: Perform spatio-temporal matching on the enclosure structure stress distribution data and the impact kinetic energy of different types of vehicles at different speeds to obtain the dynamic load-bearing capacity margin of each section of the enclosure;

[0085] Step S34: Conduct Monte Carlo simulation based on the dynamic bearing capacity margin of each section of the enclosure and the probability density function of vehicle deviation from the construction area in each lane to obtain the data of the enclosure collision risk probability.

[0086] Specifically, in step S31, a vehicle deviation probability distribution model is established based on vehicle trajectory data. The vehicle trajectory data collected by the roadside millimeter-wave radar array contains the driving path information of vehicles in each lane. Using statistical analysis methods, a large number of vehicle trajectories are processed to establish a vehicle deviation probability distribution model. For example, the frequency and amplitude of vehicles deviating from the normal trajectory when driving in different lanes are statistically analyzed, so as to calculate the probability density function of vehicle deviation from the construction area in each lane. The probability density function of vehicle deviation from the construction area in each lane can describe the likelihood of a vehicle deviating from the construction area at a certain position.

[0087] Step S32 establishes a kinetic energy impact model based on vehicle type distribution data and vehicle speed data. Different types of vehicles have different masses and driving speeds, resulting in different impact kinetic energies. According to the vehicle type distribution data, the mass parameters of different vehicle types are determined. Combining with the vehicle speed data, the impact kinetic energies of different types of vehicles at different speeds are calculated according to the kinetic energy formula. For example, large trucks have a large mass, and if they drive at a relatively high speed, their impact kinetic energy will be much greater than that of small cars.

[0088] Step S33 performs spatio-temporal matching between the enclosure structure stress distribution data and the impact kinetic energies of different types of vehicles at different speeds. The enclosure structure stress distribution data reflects the stress conditions of each part of the enclosure at different times, while the vehicle impact kinetic energy reflects the possible impact caused by vehicle collision. Performing spatio-temporal matching between the two means determining the relationship between the stress borne by the enclosure and the possible vehicle impact kinetic energy at a certain moment and a certain position, so as to obtain the dynamic bearing capacity margin of each section of the enclosure. For example, at a specific position, if the stress of the enclosure is small and the possible vehicle impact kinetic energy is also small, then the dynamic bearing capacity margin of this section is relatively large.

[0089] Step S34 conducts Monte Carlo simulation based on the dynamic bearing capacity margin of each section of the enclosure and the probability density function of vehicle deviation from the construction area in each lane. Monte Carlo simulation is a method of estimating results through random sampling. Using a computer program to perform a large number of random samplings to simulate the situation where vehicles deviate from the construction area and collide with the enclosure. Combining with the dynamic bearing capacity margin of each section of the enclosure, calculate the possibility of the enclosure colliding in each simulation. After multiple simulations, the data of the enclosure collision risk probability is statistically obtained.

[0090] Furthermore, the Monte Carlo simulation in step S34 specifically includes:

[0091] Establish a two-dimensional probability distribution function for the vehicle deviation from the construction area events in each lane and the bearing capacity of the enclosure, set multiple random samplings, and generate the vehicle offset position and the impact kinetic energy parameters simultaneously for each random sampling. When the impact kinetic energy parameter corresponding to the random sampling exceeds the bearing capacity of the enclosure, it is recorded as a failure event. Then, calculate the occurrence frequency corresponding to the failure event, and set the occurrence frequency as the enclosure collision risk probability data.

[0092] It should be noted that step S4 includes the following steps:

[0093] Step S41: Normalize the enclosure structure stress distribution data, and confirm the structural safety index according to the normalized enclosure structure stress distribution data;

[0094] Step S42: Based on the vehicle operation trajectory perturbation coefficient and combined with the dynamic weight distribution in the peak period and off-peak period, confirm the traffic perturbation index;

[0095] Step S43: Confirm the emergency response index according to the construction area emergency passage setting parameters and the rescue response time.

[0096] Specifically, in step S41, the enclosure structure stress distribution data is processed to determine the structural safety index, and the enclosure structure stress distribution data is normalized. Normalization is to scale the data proportionally so that it falls into a specific interval, usually [0, 1]. For example, if the original range of the enclosure structure stress distribution data is from 10 MPa to 100 MPa, through the normalization formula, all stress data is converted into the [0, 1] interval, eliminating the influence of the data dimension, which is convenient for subsequent analysis and comparison. After the normalization process, the structural safety index is confirmed according to the processed data. Certain rules can be set. For example, if most of the normalized stress data is in a lower interval (such as less than 0.5), it is considered that the structural safety index is higher, indicating that the enclosure structure is in a relatively safe state; on the contrary, if most of the data is close to 1, the structural safety index is lower, and there may be potential safety hazards.

[0097] Step S42 determines the traffic disturbance index based on the vehicle operation trajectory disturbance coefficient, while considering the dynamic weight allocation during peak hours and off-peak hours. The vehicle operation trajectory disturbance coefficient is obtained from the traffic flow disturbance model constructed based on real-time traffic flow data before, which reflects the degree of interference of vehicle operation on the stability of the enclosure structure. Since the traffic flow and vehicle operation characteristics during peak hours and off-peak hours are different, the impacts on the enclosure also vary. Therefore, different weights need to be assigned to peak hours and off-peak hours. For example, assume the weight for peak hours is 0.7 and the weight for off-peak hours is 0.3. If the vehicle operation trajectory disturbance coefficient obtained during peak hours is large, after multiplying by 0.7, its contribution to the traffic disturbance index is large; even if the disturbance coefficient during off-peak hours is relatively small, but after multiplying by 0.3, it will also have a certain impact on the traffic disturbance index. Through the above method, considering the situations of different periods comprehensively, the traffic disturbance index is confirmed, which can more comprehensively reflect the impact of traffic conditions on the enclosure structure.

[0098] Step S43 determines the emergency response index based on the emergency access setting parameters in the construction area and the rescue response time. The emergency access setting parameters in the construction area include information such as the number, width, and location of the emergency access. For example, the more the number of emergency accesses, the wider the width, and the more reasonable the location, the more conducive it is to the development of rescue work. The rescue response time refers to the time from the occurrence of an accident to the arrival of rescue forces at the scene and the start of rescue. An evaluation model is established to quantitatively process the emergency access setting parameters and the rescue response time. For example, each additional emergency access can increase a certain score, and the shorter the rescue response time, the corresponding score can also be increased. By combining the above scores, the emergency response index is obtained. If the emergency access is set reasonably and the rescue response time is short, the emergency response index is high, indicating that the construction area has strong emergency response capabilities in dealing with emergencies; otherwise, the emergency response index is low.

[0099] The steps of inputting the structural safety index, traffic disturbance index, and emergency response index into a preset deep learning evaluation model, outputting the comprehensive evaluation level of the enclosure location, and generating an enclosure location optimization suggestion and triggering a warning signal when the comprehensive evaluation level exceeds the preset threshold specifically include:

[0100] Taking the structural safety index, traffic disturbance index, and emergency response index as input data, input them into a preset deep learning evaluation model. The deep learning evaluation model is trained with a large amount of data and can learn the complex relationship between the above indexes and the comprehensive evaluation level of the enclosure location. For example, the model may find that when the structural safety index is high, the traffic disturbance index is low, and the emergency response index is high, the comprehensive evaluation level of the enclosure location will be high, indicating that the location is relatively optimal.

[0101] The deep learning evaluation model calculates and analyzes the input exponential data, outputs the comprehensive evaluation level of the enclosure location, and compares the output comprehensive evaluation level with a preset threshold. If the comprehensive evaluation level exceeds the preset threshold, it indicates that there are certain problems with the enclosure location. At this time, optimization suggestions for the enclosure location will be generated. For example, if the traffic disturbance index is too high, resulting in an unsatisfactory comprehensive evaluation level, the optimization suggestion may be to adjust the enclosure location to reduce the impact on traffic. At the same time, a warning signal is triggered to remind relevant personnel to pay attention to the potential risks of the enclosure location and take timely measures to handle them.

[0102] It should be noted that the specific update of the electronic fence warning range in step S6 includes:

[0103] Calculate the dynamic warning radius according to the comprehensive evaluation level, and use the variable message sign to display the real-time warning range according to the dynamic warning radius, and send a graded warning signal to the vehicles approaching the enclosure structure in the construction area through V2X communication.

[0104] Specifically, establish a correspondence model between the comprehensive evaluation level and the dynamic warning radius. Exemplarily, the comprehensive evaluation level is divided into five levels. The first level indicates that the safety of the enclosure location is extremely high, and the corresponding dynamic warning radius may be set to 10 meters; the fifth level indicates that there are relatively large risks at the enclosure location, and the dynamic warning radius is set to 50 meters. As the comprehensive evaluation level increases, the dynamic warning radius increases accordingly. After obtaining the specific comprehensive evaluation level of the enclosure location, calculate the dynamic warning radius of the enclosure location according to the above correspondence model. For example, if the comprehensive evaluation level of a certain enclosure location is the third level, according to the pre-set correspondence, determine its dynamic warning radius to be 30 meters. According to the calculated dynamic warning radius, use the variable message sign to display the real-time warning range. The variable message sign is installed at a suitable location near the construction area and obtains the dynamic warning radius information through a data connection with the system. Convert the dynamic warning radius into a visual warning range and display it on the variable message sign. For example, the variable message sign can clearly mark the area with a radius of 30 meters centered on the enclosure as the warning range in the form of graphics, text, etc., to remind passing vehicles and pedestrians to pay attention to safety and make preparations in advance. Furthermore, by dynamically adjusting the warning radius and real-time displaying the warning range, the safety of the construction area and its surrounding areas can be more effectively guaranteed.

[0105] Furthermore, the graded warning signal includes:

[0106] When the comprehensive evaluation level is between the first preset threshold and the second preset threshold, then output a first-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning lights as yellow, and reduce the volume of the in-vehicle navigation system and display a prompt message;

[0107] When the comprehensive evaluation level is between the second preset threshold and the third preset threshold, a secondary warning signal is output, the warning light system of the anti-collision barrels outside the construction area is activated, the warning lights are displayed in orange, and the in-vehicle HUD head-up display warning sign is activated.

[0108] When the comprehensive evaluation level exceeds the third preset threshold, a tertiary warning signal is output, the warning light system of the anti-collision barrels outside the construction area is activated, the warning lights are displayed in red, and the vehicle active braking system is triggered and the road management department is linked.

[0109] Embodiment 2

[0110] The embodiment of the present application also discloses an evaluation system for the position of the construction enclosure in the highway construction area.

[0111] Refer to Figure 2 , an evaluation system for the position of the construction enclosure in the highway construction area, includes:

[0112] A data acquisition module for acquiring real-time traffic flow data, three-dimensional point cloud data of the construction area, and enclosure structure parameters corresponding to the highway construction area. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include enclosure material strength, shear strength of connectors, and foundation anchorage depth;

[0113] A data analysis module for constructing an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area, performing finite element stress field simulation in combination with the enclosure structure parameters to obtain enclosure structure stress distribution data, and constructing a traffic flow perturbation model based on the real-time traffic flow data to obtain a vehicle operation trajectory perturbation coefficient;

[0114] An enclosure collision risk probability confirmation module for performing multi-dimensional coupling analysis on the enclosure structure stress distribution data and the vehicle operation trajectory perturbation coefficient to obtain enclosure collision risk probability data;

[0115] A safety evaluation index system construction module for constructing a safety evaluation index system based on the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic perturbation index, and an emergency response index;

[0116] A comprehensive evaluation level generation module for inputting the structural safety index, the traffic perturbation index, and the emergency response index into a preset deep learning evaluation model, outputting a comprehensive evaluation level of the enclosure position, and generating an enclosure position optimization suggestion and triggering a warning signal when the comprehensive evaluation level exceeds the preset threshold;

[0117] A warning module for pushing the comprehensive evaluation level and the warning signal to the construction management terminal and the in-vehicle navigation system in real time, and synchronously updating the warning range of the electronic fence.

[0118] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution. As long as they do not deviate from the concept of the invention, they shall fall within the protection scope of the present invention.

[0119] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0120] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments in order to better explain the principle and practical application of the present invention, so that those skilled in the art of the present technology can understand and utilize the present invention well.

Claims

1. An evaluation method for the construction enclosure position in a highway construction area, characterized in that, It includes the following steps: Step S1: Obtain the real-time traffic flow data corresponding to the highway construction area, the three-dimensional point cloud data of the construction area, and the enclosure structure parameters. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include the strength of the enclosure material, the shear strength of the connecting parts, and the foundation anchorage depth; Step S2: Construct an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area, perform a finite element stress field simulation in combination with the enclosure structure parameters to obtain the enclosure structure stress distribution data, and construct a traffic flow disturbance model based on the real-time traffic flow data to obtain the vehicle operation trajectory disturbance coefficient; Step S3: Conduct a multi-dimensional coupling analysis on the enclosure structure stress distribution data and the vehicle operation trajectory disturbance coefficient to obtain the enclosure collision risk probability data; Step S4: Construct a safety evaluation index system based on the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic disturbance index, and an emergency response index; Step S5: Input the structural safety index, the traffic disturbance index, and the emergency response index into a preset deep learning evaluation model, output the comprehensive evaluation grade of the enclosure position, and when the comprehensive evaluation grade exceeds the preset threshold, generate an enclosure position optimization suggestion and trigger a warning signal; Step S6: Push the comprehensive evaluation grade and the warning signal to the construction management terminal and the in-vehicle navigation system in real time, and synchronously update the warning range of the electronic fence.

2. The evaluation method for the construction enclosure position in a highway construction area according to claim 1, characterized in that, Step 1 includes the following steps: Step S11: Collect the real-time traffic flow data corresponding to the highway construction area through a roadside millimeter-wave radar array, and use a multi-target tracking algorithm to extract the vehicle trajectory data, vehicle speed data, and vehicle type distribution data corresponding to the lanes; Step S12: Use a three-dimensional laser scanner carried by a drone to obtain the point cloud data of the construction area, and generate the three-dimensional point cloud data of the construction area through a point cloud registration algorithm; Step S13: Use a stress wave detector and an Internet of Things sensor to perform real-time detection on the enclosure structure, and then obtain the strength of the enclosure material, the shear strength of the connecting parts, and the foundation anchorage depth corresponding to the enclosure structure.

3. The evaluation method for the construction enclosure position in a highway construction area according to claim 1, characterized in that, The specific steps for constructing an enclosure structure stability analysis model based on the three-dimensional point cloud data of the construction area in Step S2 are as follows: Step S21: Convert the three-dimensional point cloud data of the construction area into a finite element mesh model, and set the material constitutive relationship and boundary conditions; Step S22: Apply the multi-physical field coupling effects of wind load, vehicle aerodynamic load, and temperature load; Step S23: Calculate the stress-strain distribution nephogram of the enclosure structure according to the material constitutive relationship, boundary conditions, and multi-physical field coupling effects and using a non-linear solver; Step S24: Extract the maximum principal stress value and the critical buckling coefficient as the structural stability indicators based on the stress-strain distribution nephogram of the enclosure structure, and construct an enclosure structure stability analysis model based on the structural stability indicators.

4. The evaluation method for the construction enclosure position in a highway construction area according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Establish a vehicle offset probability distribution model based on the vehicle trajectory data, and calculate the probability density function of vehicles deviating from the construction area in each lane; Step S32: Establish a kinetic energy impact model based on the vehicle type distribution data and vehicle speed data, and calculate the impact kinetic energy of different types of vehicles at different speeds; Step S33: Perform spatio-temporal matching on the enclosure structure stress distribution data and the impact kinetic energy of different types of vehicles at different speeds to obtain the dynamic bearing capacity margin of each section of the enclosure; Step S34: Conduct Monte Carlo simulation based on the dynamic bearing capacity margin of each section of the enclosure and the probability density function of vehicle deviation from the construction area in each lane to obtain the enclosure collision risk probability data.

5. The evaluation method for the construction enclosure position in a highway construction area according to claim 4, characterized in that, The Monte Carlo simulation in Step S34 specifically includes: Establish a two-dimensional probability distribution function of the event of vehicle deviation from the construction area in each lane and the bearing capacity of the enclosure, set multiple random samplings, and generate vehicle offset positions and impact kinetic energy parameters simultaneously for each random sampling. When the impact kinetic energy parameter corresponding to the random sampling exceeds the bearing capacity of the enclosure, it is recorded as a failure event. Then calculate the occurrence frequency corresponding to the failure event, and set the occurrence frequency as the enclosure collision risk probability data.

6. The evaluation method for the construction enclosure position in a highway construction area according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Normalize the enclosure structure stress distribution data, and confirm the structural safety index based on the normalized enclosure structure stress distribution data; Step S42: Confirm the traffic disturbance index based on the vehicle operation trajectory disturbance coefficient and combined with the dynamic weight distribution during peak hours and off-peak hours; Step S43: Confirm the emergency response index according to the emergency access setting parameters in the construction area and the rescue response time.

7. The evaluation method for the construction enclosure position in a highway construction area according to claim 1, characterized in that, The specific update of the electronic fence warning range in Step S6 includes: Calculate the dynamic warning radius according to the comprehensive evaluation level, use a variable message sign to display the real-time warning range according to the dynamic warning radius, and send a graded warning signal to the vehicles approaching the enclosure structure in the construction area through V2X communication.

8. The evaluation method for the construction enclosure position in a highway construction area according to claim 7, characterized in that, The graded warning signal includes: When the comprehensive evaluation level is between the first preset threshold and the second preset threshold, output a first-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning light as yellow, and reduce the volume of the in-vehicle navigation system and display a prompt message; When the comprehensive evaluation level is between the second preset threshold and the third preset threshold, output a second-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning light as orange, and activate the in-vehicle HUD head-up display warning sign; When the comprehensive evaluation level exceeds the third preset threshold, output a third-level warning signal, activate the warning light system of the anti-collision barrels outside the construction area, display the warning light as red, and trigger the vehicle active braking system and link with the road management department.

9. An evaluation system for the construction enclosure position in a highway construction area, which is applied to the evaluation method for the construction enclosure position in a highway construction area described in any one of the above claims 1-8, characterized in that, Including: A data acquisition module for acquiring real-time traffic flow data, three-dimensional point cloud data of the construction area, and enclosure structure parameters corresponding to the highway construction area. The real-time traffic flow data includes vehicle trajectory data, vehicle speed data, and vehicle type distribution data. The enclosure structure parameters include the strength of the enclosure material, the shear strength of the connecting parts, and the foundation anchorage depth; The data analysis module is used to construct a stability analysis model of the enclosure structure based on the three-dimensional point cloud data of the construction area, perform finite element stress field simulation in combination with the enclosure structure parameters to obtain the stress distribution data of the enclosure structure, and construct a traffic flow disturbance model based on the real-time traffic flow data to obtain the vehicle operation trajectory disturbance coefficient; The enclosure collision risk probability confirmation module is used to perform multi-dimensional coupling analysis on the stress distribution data of the enclosure structure and the vehicle operation trajectory disturbance coefficient, and then obtain the enclosure collision risk probability data; The safety evaluation index system construction module is used to construct a safety evaluation index system according to the enclosure collision risk probability data. The safety evaluation index system includes a structural safety index, a traffic disturbance index, and an emergency response index; The comprehensive evaluation grade generation module is used to input the structural safety index, the traffic disturbance index, and the emergency response index into a preset deep learning evaluation model, output the comprehensive evaluation grade of the enclosure position, and generate an enclosure position optimization suggestion and trigger a warning signal when the comprehensive evaluation grade exceeds the preset threshold; The warning module is used to push the comprehensive evaluation grade and the warning signal to the construction management terminal and the in-vehicle navigation system in real time, and synchronously update the warning range of the electronic fence.

10. A computer-readable storage medium, characterized in that: Stored with instructions, when the instructions are run on a computer, the computer is caused to execute a method for evaluating the position of a construction enclosure in a highway construction area according to any one of claims 1 to 8.

Images