Post-accident residual performance evaluation method of traffic protection facilities based on digital twin

Abstract

The present application provides a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins, which relates to the field of electronic digital data processing. The method includes: obtaining accident video data and vehicle parameter information uploaded by the accident vehicle; extracting collision characteristic parameters of the collision process in the accident video data; establishing a digital twin model under the accident working condition based on the vehicle parameter information and collision characteristic parameters, and simulating the collision process to obtain stress distribution data and plastic deformation data of the protection facilities; and establishing a residual performance evaluation index system in combination with the performance requirements in the protection facility design specifications; calculating the residual performance index of the traffic protection facilities based on the residual performance evaluation index system, and matching the corresponding maintenance and reinforcement suggestions. The implementation of this method avoids the subjectivity and time delay of traditional manual detection, and can quickly and accurately evaluate the residual performance status of the protection facilities after the accident, thereby improving the evaluation efficiency and accuracy.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing, and in particular to a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins. Background Art

[0002] With the rapid development of my country's transportation industry, the construction scale of important transportation infrastructure such as expressways and urban freeways continues to expand. As crucial infrastructure for ensuring road traffic safety, the integrity and reliability of traffic protection facilities are directly related to the safety of life and property of road users. During road operations, traffic protection facilities are inevitably subject to accidents such as vehicle collisions, posing a significant challenge to the maintenance and repair work of road operators.

[0003] In related technologies, the performance evaluation of traffic protection facilities after a vehicle collision primarily relies on manual on-site inspections. Inspectors visually inspect the protective facilities for visible damage, such as deformation and cracking, and, based on experience, determine whether they require repair or replacement. Furthermore, some road operators use portable testing instruments to quantitatively measure individual parameters of the protective facilities, such as geometric dimensional deviations and steel strength, as a supplementary basis for evaluation.

[0004] However, the traditional assessment process is time-consuming. Inspectors need to observe and measure damaged protective equipment section by section. Furthermore, because the inspection data is primarily focused on visible damaged areas, changes in stress distribution within the protective equipment and potential structural damage can be easily missed. Frequent on-site inspections, especially on accident-prone roads, not only increase traffic pressure but also create the risk of secondary accidents. This shows that with increasingly congested road traffic and the increasing demand for rapid response after accidents, the efficiency and accuracy of this traditional assessment method are no longer sufficient to meet actual needs. Summary of the Invention

[0005] This application provides a method for evaluating the remaining performance of traffic protection facilities after an accident based on digital twins, which is used to address the problem of how to quickly and accurately evaluate the remaining performance status of damaged traffic protection facilities after a collision accident occurs in the traffic protection facilities.

[0006] In a first aspect, the present application provides a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins, which is applied to a traffic protection facility performance evaluation system. The method includes:

[0007] Obtaining accident video data and vehicle parameter information uploaded by the accident vehicle, wherein the accident video data includes a complete video of the process before, during, and after the accident, and the vehicle parameter information includes vehicle mass, vehicle size, and vehicle stiffness;

[0008] Extracting collision characteristic parameters of the collision process from the accident video data using a computer vision algorithm, wherein the collision characteristic parameters include collision speed, collision angle, collision position, and deformation of protective facilities;

[0009] Establishing a digital twin model under an accident condition based on the vehicle parameter information and the collision characteristic parameters, the digital twin model including a vehicle kinematic model and a protective facility finite element model;

[0010] Simulating the collision process in the digital twin model to obtain stress distribution data and plastic deformation data of the protective facilities;

[0011] Based on the stress distribution data and plastic deformation data, combined with the performance requirements in the protective facility design specifications, a residual performance evaluation index system is established, wherein the residual performance evaluation index system includes structural strength, geometric dimensions and functional integrity;

[0012] According to the residual performance evaluation index system, the residual performance index of the traffic protection facilities is calculated, and the corresponding maintenance and reinforcement suggestions are matched according to the residual performance index.

[0013] Through the above-mentioned embodiment, the system obtains accident video data and vehicle parameters, combines computer vision to extract collision features, and establishes a digital twin model for simulation analysis. This can quickly obtain stress distribution and deformation data of protective facilities without the need for on-site manual inspection. Based on this data, a residual performance evaluation index system is established to comprehensively evaluate the structural strength, geometric dimensions, and functional integrity of protective facilities, and provide corresponding maintenance recommendations. This method avoids the subjectivity and time delay of traditional manual inspection, and can quickly and accurately evaluate the residual performance status of protective facilities after an accident, thereby improving evaluation efficiency and accuracy.

[0014] In some embodiments, the step of extracting collision characteristic parameters of the collision process in the accident video data using a computer vision algorithm specifically includes:

[0015] Extracting a video frame sequence from the accident video data and performing image enhancement and target segmentation processing to obtain an image of the protective facility area;

[0016] Performing feature point detection and tracking on the protective facility area image to obtain feature point motion data;

[0017] Based on the feature point motion data, a kinematic analysis method is used to calculate the collision speed and collision angle, and a three-dimensional reconstruction method is used to determine the collision position and the deformation of the protective facility.

[0018] Through the above-described embodiment, the system uses computer vision technologies such as video frame sequence processing, feature point detection and tracking, and 3D reconstruction to accurately acquire key parameters such as velocity, angle, position, and deformation during a collision. This method replaces traditional methods that require manual measurement and estimation, improving not only the efficiency of data acquisition but also the accuracy of parameter measurement. These highly accurate collision characteristic parameters provide reliable input data for subsequent digital twin models.

[0019] In some embodiments, after the step of detecting and tracking feature points on the protective facility area image and acquiring feature point motion data, the method further includes:

[0020] Extracting audio data from the accident video data and performing noise reduction and segmentation processing to obtain a collision acoustic signal;

[0021] Performing time-frequency analysis on the collision acoustic signal to obtain a spectrum characteristic graph, and then extracting acoustic characteristic parameters from the spectrum characteristic graph, wherein the acoustic characteristic parameters include the peak frequency and energy distribution of the collision sound wave;

[0022] The feature point motion data is filtered and optimized based on the acoustic feature parameters to obtain optimized feature point motion data.

[0023] Through the above-mentioned embodiments, the system optimizes the motion data of visual feature points by incorporating collision acoustic signal analysis, effectively improving the accuracy of collision feature parameters. Acoustic features can capture collision details that are difficult to capture visually, such as internal structural deformation and damage. This multimodal data fusion method can more comprehensively reflect the physical phenomena during a collision, improving the reliability and accuracy of residual performance assessments of protective equipment.

[0024] In some embodiments, after the step of extracting collision characteristic parameters of the collision process in the accident video data using a computer vision algorithm, the method further includes:

[0025] When the accident video data is blocked or has an angle restriction, identifying missing parameters in the collision feature parameters according to a preset collision parameter integrity detection mechanism;

[0026] Constructing a set of physical constraint equations that conform to the dynamic relationship of the collision process based on the collision characteristic parameters and the final deformation state;

[0027] Establishing a parameter sensitivity matrix based on the physical constraint equations, wherein the parameter sensitivity matrix is ​​used to quantify the influence of each collision characteristic parameter on the deformation result of the protective facility;

[0028] Determining the key missing parameters having the greatest impact on the digital twin model from the missing parameters according to the parameter sensitivity matrix;

[0029] The key missing parameters are randomly generated according to collision scenario constraints, wherein the collision scenario constraints include scene environment, road regulations and vehicle parameter information.

[0030] Through the above-described embodiments, the system addresses common real-world scenarios involving video data occlusion or angle restrictions. By establishing a parameter sensitivity matrix and a set of physical constraint equations, it can identify and supplement key missing parameters. This physics-based parameter correction method ensures reliable performance evaluation even with incomplete data, improving the practicality and adaptability of the evaluation method and enabling it to address a variety of complex accident scenarios.

[0031] In some embodiments, the step of randomly generating the key missing parameters according to the collision scenario constraints specifically includes:

[0032] A Monte Carlo method is used to generate multiple sets of parameter sampling values, wherein the parameter sampling values ​​meet the collision scenario constraint conditions;

[0033] Substituting each set of parameter sampling values ​​into the digital twin model to perform collision simulation and obtain corresponding simulated deformation results;

[0034] The optimal parameter combination corresponding to the simulated deformation result with the highest similarity to the actual deformation state is screened out through the similarity evaluation function;

[0035] The key missing parameter is determined according to the optimal parameter combination.

[0036] Through the above-mentioned embodiment, the system uses the Monte Carlo method to generate multiple sets of parameter sampling values ​​and screens the optimal parameter combination through similarity evaluation, achieving accurate estimation of missing parameters. This intelligent parameter optimization method not only ensures the rationality of physical constraints but also achieves the best match with the actual deformation state, improving the accuracy of assessment in the absence of data and providing reliable guarantees for rapid assessment.

[0037] In some embodiments, after the step of obtaining the accident video data and vehicle parameter information uploaded by the accident vehicle, the method further includes:

[0038] Acquiring multi-source video data, including full-angle video of post-accident protective facilities captured by on-site management personnel, video recorded by surrounding surveillance equipment during the accident, and video uploaded by dashcams of passing vehicles;

[0039] Based on the spatiotemporal alignment algorithm, the multi-source video data is matched and fused with the accident video data uploaded by the accident vehicle to obtain updated accident video data.

[0040] Through the above-mentioned implementation, the system significantly improves the integrity and reliability of accident data by integrating multi-source video data, including footage captured by on-site management, surrounding surveillance equipment, and passing vehicles, and performing spatiotemporal alignment and fusion. This comprehensive data collection approach overcomes the limitations of a single perspective, providing more comprehensive information support for protective facility performance evaluation and improving the accuracy of evaluation results.

[0041] In some embodiments, before simulating the collision process in the digital twin model and obtaining stress distribution data and plastic deformation data of the protective facilities, the method further includes:

[0042] Acquiring historical collision data corresponding to the collision location, wherein the historical collision data includes a timestamp of the historical collision event, collision characteristic parameters, and historical stress distribution data;

[0043] Analyze the historical stress distribution data based on the material cumulative damage model and calculate the material fatigue of each key part;

[0044] The material parameters of the finite element model of the protective facility are modified based on the material fatigue.

[0045] Through the above-described embodiment, the system analyzes historical collision data and a material cumulative damage model to calculate material fatigue in key areas. Based on this information, the material parameters of the finite element model are modified, allowing the assessment process to take into account the impact of the protective device's service history and cumulative damage. This historically factored assessment method is more consistent with the actual service status of the protective device and improves the accuracy and reliability of the residual performance assessment.

[0046] In a second aspect, the present application provides a traffic protection facility performance evaluation system, the traffic protection facility performance evaluation system comprising: one or more processors and a memory;

[0047] The memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions so that the traffic protection facility performance evaluation system can implement a post-accident residual performance evaluation method for traffic protection facilities based on digital twins provided in the above embodiment, which will not be repeated here.

[0048] On the third aspect, the present application provides a computer-readable storage medium comprising instructions. When the instructions are run on a traffic protection facility performance evaluation system, the traffic protection facility performance evaluation system can implement a post-accident residual performance evaluation method for traffic protection facilities based on digital twins provided in the above embodiment, which will not be repeated here.

[0049] Fourthly, the present application provides a computer program product. When the computer program product runs on a traffic protection facility performance evaluation system, the traffic protection facility performance evaluation system can implement a post-accident residual performance evaluation method for traffic protection facilities based on digital twins provided in the above embodiment, which will not be repeated here.

[0050] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0051] 1. By acquiring accident video data and combining it with computer vision technology to automatically extract collision characteristic parameters, a digital twin model was established for simulation analysis, enabling rapid, automated assessment of the remaining performance of protective equipment. This approach overcomes the limitations of traditional manual on-site testing, not only rapidly acquiring stress distribution and deformation data but also enabling in-depth analysis of the internal structural state of protective equipment, improving assessment efficiency and accuracy.

[0052] 2. The system fuses visual data, acoustic signals, and multi-source video for analysis, and addresses data loss through parameter sensitivity matrices and physical constraint equations. This multimodal data fusion approach, combined with physical model constraints, not only improves the robustness of the assessment but also enables intelligent algorithms to accurately infer key parameters under adverse conditions such as occlusion or limited viewing angles, ensuring the reliability of the assessment results.

[0053] 3. By analyzing historical collision data and combining it with a material cumulative damage model, we quantitatively assess the fatigue level of protective equipment and dynamically adjust the material parameters of the digital twin model accordingly. This dynamic assessment method, for the first time, incorporates the service history and cumulative damage of protective equipment into the assessment system, making the assessment results more consistent with actual service conditions and significantly improving the accuracy of residual performance assessments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a flow chart of a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins in an embodiment of the present application;

[0055] Figure 2 This is another flow chart of a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins in an embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of the structure of a physical device of the traffic protection facility performance evaluation system in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0058] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0059] It should be noted that, for the sake of convenience, the "traffic protection facility performance evaluation system" in this application may also be referred to as "system" in the following embodiments, and this abbreviation should not be a limitation of this application.

[0060] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins in an embodiment of the present application.

[0061] S101. Obtain accident video data and vehicle parameter information uploaded by the accident vehicle.

[0062] The accident vehicle refers to the vehicle that collides with road traffic protection equipment. Accident video data refers to the video data uploaded by the accident vehicle's onboard monitoring system (such as a dashcam), covering the entire process before, during, and after the accident. Vehicle parameter information represents parameters related to the accident vehicle, including but not limited to vehicle mass, dimensions, and rigidity.

[0063] Specifically, when a traffic protection facility is involved in a collision, the vehicle involved uploads video data recording the entire accident process, along with its own vehicle parameters. The traffic protection facility performance evaluation system receives this data, providing foundational data support for subsequent analysis of collision characteristics and the creation of digital twin models.

[0064] Optionally, a data upload module is pre-installed on vehicles at the factory. This module connects to the vehicle's dashcam and sensors. When an accident occurs, the dashcam automatically stores the accident video data and uses the vehicle's sensors to obtain information about vehicle parameters such as mass, dimensions, and stiffness. The data upload module uses the vehicle's onboard network, such as 4G or 5G, to upload this data to a server address specified by the traffic protection facility performance evaluation system. The system then retrieves the data from the server through a pre-set interface.

[0065] S102. Extracting collision feature parameters of the collision process from the accident video data using a computer vision algorithm.

[0066] Specifically, the traffic protection facility performance evaluation system uses computer vision algorithms to process captured accident video data. The algorithm analyzes the motion and relative position of the vehicle and protective facilities in the video, accurately extracting key parameters such as collision speed, collision angle, collision location, and deformation of the protective facilities.

[0067] Optionally, the system first extracts a sequence of video frames from the accident video data and processes each frame using an image enhancement algorithm to improve image clarity and contrast. Next, an object segmentation algorithm is used to separate the protective equipment and vehicle from the background, generating an image of the protective equipment area. Feature point detection and tracking are then performed on the protective equipment area image to obtain feature point motion data. Finally, based on this feature point motion data, kinematic analysis methods are used to calculate the collision velocity and angle, and 3D reconstruction methods are used to determine the collision location and deformation of the protective equipment.

[0068] Optionally, the system can preprocess the accident video data to remove noise and interference. It then uses deep learning object detection models, such as YOLO and Faster R-CNN, to identify vehicles and protective equipment in the video and determine their positions and outlines. By analyzing the positional changes of the vehicles and protective equipment in consecutive video frames, it calculates the collision speed and angle. Using stereo vision technology and combining video data from multiple cameras, it locates the collision location in three dimensions, while simultaneously calculating the deformation of the protective equipment using image deformation analysis algorithms.

[0069] S103. Establish a digital twin model under accident conditions based on vehicle parameter information and collision characteristic parameters.

[0070] Specifically, the traffic protection facility performance evaluation system constructs a vehicle kinematic model and a protective facility finite element model based on the acquired vehicle parameter information and collision characteristic parameters, and then combines them to form a digital twin model under accident conditions. When constructing the vehicle kinematic model, parameters such as vehicle mass, collision speed, and collision angle are used as input to determine the vehicle's motion trajectory and state changes during the collision. For the protective facility finite element model, the protective facility is meshed and mechanical parameters are set based on the structural design, material properties, collision position, deformation and other parameters of the protective facility to simulate its mechanical behavior under the action of collision force. This digital twin model can truly reflect the interaction between the vehicle and the protective facility under accident conditions, and provide a basis for subsequent simulation of the collision process and acquisition of stress distribution and plastic deformation data.

[0071] It should be noted that the digital twin model is a virtual model corresponding to a real physical entity or system, and is used in this step to simulate the collision process between the vehicle and the traffic protection facility under accident conditions. It includes a vehicle kinematic model and a finite element model of the protection facility. Among them, the vehicle kinematic model is used to describe the motion state of the vehicle during the collision process, such as the change law of speed, acceleration, displacement, etc. over time, and is constructed based on vehicle parameter information and the speed, angle, etc. in the collision characteristic parameters; the finite element model of the protection facility discretizes the protection facility into a finite number of units, and simulates its mechanical response during the collision process through numerical calculation methods, including stress, strain distribution and deformation. It is constructed according to the structural characteristics, material properties and collision position, deformation, etc. in the collision characteristic parameters of the protection facility.

[0072] S104. Simulate the collision process in the digital twin model to obtain stress distribution data and plastic deformation data of the protective facilities.

[0073] Specifically, the traffic protection facility performance evaluation system inputs previously acquired vehicle parameter information, collision characteristic parameters, etc. into the digital twin model. In the model, the vehicle kinematic model simulates the motion trajectory and state changes of the vehicle during a collision based on the set parameters, and the collision force generated is transmitted to the finite element model of the protective facility. The finite element model of the protective facility simulates the mechanical response of each unit during the collision through numerical calculation methods based on its own structure, material properties, and the collision force it receives. During the simulation process, the system records the stress changes in various parts of the protective facility to form stress distribution data; at the same time, it tracks information such as the area where plastic deformation of the protective facility occurs and the amount of deformation to obtain plastic deformation data.

[0074] Optionally, the system can utilize professional engineering simulation software, such as ANSYS. First, import the digital twin model that has been constructed in step S103 into the software, including the vehicle kinematic model and the finite element model of the protective facility. Set the relevant parameters of the collision simulation based on the accident video data, such as collision duration, time step, etc. Then start the simulation calculation, and the software will perform collision simulation according to the set parameters and the mechanical principles of the model. After the simulation is completed, the stress distribution cloud map and plastic deformation data of the protective facility are extracted through the post-processing module of the software. The stress magnitude and plastic deformation degree of different parts can be visually viewed, and the relevant data files can be exported for subsequent analysis.

[0075] Furthermore, when the traffic protection facility performance evaluation system prepares to conduct a new collision simulation, it can obtain historical collision data corresponding to the collision location before the collision simulation in order to account for the damage accumulated by the protection facilities in past collisions. This can be retrieved from a database storing historical data. The database stores historical collision event records corresponding to each collision location. The system selects the historical collision data corresponding to that location by accurately matching the coordinates or identification information of the collision location. This data is stored in a structured format and includes timestamps, collision characteristic parameters, and historical stress distribution data.

[0076] The system inputs historical stress distribution data into a pre-defined material cumulative damage model (such as one from professional finite element analysis software like ANSYS). This model analyzes the stress history of each critical component based on factors such as stress amplitude and number of loading cycles. For each critical component, the model calculates the damage generated by each stress loading cycle and accumulates this damage. For example, the model uses Miner's linear cumulative damage theory, which states that fatigue damage to a material is the sum of the damage generated by each stress cycle. When the cumulative damage reaches 1, fatigue failure occurs. Based on this theory, the system substitutes the number of stress cycles and corresponding stress amplitudes from each critical component in the historical collision into the model to calculate the material fatigue level for each critical component. The system then adjusts the material parameters in the protective equipment finite element model based on the calculated material fatigue level for each critical component. For example, for critical components with high fatigue levels, the elastic modulus is reduced by a certain percentage, which reduces the yield strength accordingly. This ensures that the finite element model better reflects the actual mechanical properties of the protective equipment after multiple collisions.

[0077] S105. Based on stress distribution data and plastic deformation data, combined with the performance requirements in the protective facility design specifications, establish a residual performance evaluation index system.

[0078] Among them, the protective facility design specifications refer to a series of standards and specifications followed in the design and construction process of protective facilities, which stipulate the various performance indicators and technical requirements that protective facilities should have; the residual performance evaluation index system is a set of indicators used to evaluate the residual performance status of traffic protection facilities after experiencing a collision accident, including structural strength, geometric dimensions and functional integrity.

[0079] Specifically, the traffic protection facility performance evaluation system first determines, based on stress distribution data, whether the stress in various parts of the protection facility exceeds the allowable stress range specified in the design specifications, thereby assessing the damage to the structural strength. Next, based on the plastic deformation data, the deformed geometric dimensions of the protection facility are measured and compared with the original dimensions specified in the design specifications to determine the extent of the geometric change. At the same time, considering the impact of stress distribution and plastic deformation on the function of the protection facility, its functional integrity is judged, such as whether the protection facility can still effectively block vehicles and guide traffic. These evaluation results are integrated to form a residual performance evaluation index system that includes structural strength, geometric dimensions, and functional integrity.

[0080] Optionally, the system can adopt the analytic hierarchy process (AHP). First, the target layer of the residual performance evaluation index system is determined to be the residual performance evaluation of protective facilities, and the criterion layer is determined to be structural strength, geometric dimensions, and functional integrity. Then, for each criterion layer indicator, a judgment matrix is ​​constructed based on the stress distribution data, plastic deformation data, and design specification requirements. For example, for structural strength, the relative size of the impact of stress exceeding the allowable stress at different locations on the overall structural strength is compared. The weight of each indicator is determined by calculating the eigenvector of the judgment matrix and performing a consistency test. Finally, the evaluation value of each indicator is comprehensively calculated according to the weight to obtain the preliminary results of the residual performance evaluation of protective facilities, thereby improving the residual performance evaluation index system.

[0081] S106. Calculate the residual performance index of the traffic protection facilities based on the residual performance evaluation index system, and match corresponding maintenance and reinforcement suggestions based on the residual performance index.

[0082] Specifically, the traffic protection facility performance evaluation system calculates the residual performance index (I) of traffic protection facilities based on the weights and corresponding evaluation values ​​of each indicator in the residual performance evaluation index system, using a specific calculation method (such as the weighted average method). For example, if the structural strength indicator has a weight of w1 and an evaluation value of x1; the geometric dimension indicator has a weight of w2 and an evaluation value of x2; and the functional integrity indicator has a weight of w3 and an evaluation value of x3, then the residual performance index (I) is calculated as w1*x1+w2*x2+w3*x3.

[0083] After obtaining the remaining performance index, the system compares it with a preset threshold range. If the remaining performance index is above the threshold range, it indicates that the protective facilities are slightly damaged and may only require simple local repairs. If the remaining performance index is within the threshold range, it is determined that moderate repair and reinforcement may be necessary. If the remaining performance index is below the threshold range, it is determined that the protective facilities may need to be completely replaced. Based on these comparison results, the system matches corresponding repair and reinforcement recommendations.

[0084] In the above-mentioned embodiment, the system acquires accident video data and vehicle parameters, combines them with computer vision to extract collision features, and establishes a digital twin model for simulation analysis. This allows rapid acquisition of stress distribution and deformation data for protective equipment, eliminating the need for on-site manual inspection. A residual performance evaluation index system is established based on this data, which comprehensively assesses the structural strength, geometric dimensions, and functional integrity of protective equipment and provides corresponding maintenance recommendations. This approach avoids the subjectivity and time delays of traditional manual inspections, enabling rapid and accurate assessment of the residual performance status of protective equipment after an accident, improving evaluation efficiency and accuracy.

[0085] For ease of understanding, the following is a further description of the process of extracting collision feature parameters of the collision process from accident video data using computer vision algorithms in this implementation. Figure 2 , which is another flow chart of a method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins in an embodiment of the present application.

[0086] S201. Extract a video frame sequence from the accident video data and perform image enhancement and target segmentation processing to obtain an image of the protective facility area.

[0087] Optionally, the system can utilize OpenCV's video reading functions to read accident video data at a fixed frame rate, decomposing the video into a series of image frames to generate a video frame sequence. OpenCV's image enhancement functions, such as CLAHE (Contrast Limited Adaptive Histogram Equalization), are then called to enhance each frame, improving contrast and clarity. Finally, a contour detection-based object segmentation method is employed. Edge detection algorithms (such as Canny Edge Detection) are used to locate edge information in the image. The outline of the protective facility is then filtered based on its shape and location, segmenting it from the background to produce an image of the protective facility area.

[0088] S202: Detect and track feature points on the protective facility area image to obtain feature point motion data.

[0089] Specifically, the traffic protection facility performance evaluation system uses a specific feature point detection algorithm, such as the SIFT (Scale-Invariant Feature Transform) algorithm, to identify points with unique characteristics within the protective facility area image. These points can represent the local features of the protective facility. It then uses a feature point tracking algorithm, such as the KLT (Kanade-Lucas-Tomasi) tracking algorithm, to track the detected feature points in successive image frames. By continuously updating the position of the feature points in each frame and recording their motion trajectories, it obtains feature point motion data.

[0090] S203: extract audio data from the accident video data and perform noise reduction and segmentation processing to obtain a collision acoustic signal.

[0091] Specifically, the traffic protection facility performance evaluation system uses video processing tools to extract audio data from accident video data. It then applies noise reduction algorithms, such as those based on wavelet transforms, to the audio data, removing noise components and enhancing audio clarity. The de-noised audio is then segmented based on the time of the collision and the characteristics of the audio signal. For example, audio segments of a certain length, centered on the moment of collision, are captured forward and backward, generating the collision acoustic signal.

[0092] Optionally, the system can use professional audio processing software, such as Audacity. First, import the accident video data into the Audacity software, and the software will automatically separate the audio track. Next, use the noise reduction plug-in that comes with Audacity to perform noise reduction on the audio by sampling noise samples and setting appropriate noise reduction parameters. Then, based on the analysis of the video image, determine the time range of the collision, use the marking and cutting tools in Audacity to segment the noise-reduced audio according to the collision time range, and export the collision acoustic signal. It is understandable that other methods can also be used to achieve this, such as using MATLAB's audio processing toolbox, etc., which are not limited here.

[0093] S204 , performing time-frequency analysis on the collision acoustic signal to obtain a spectrum feature graph, and then extracting acoustic feature parameters from the spectrum feature graph.

[0094] Specifically, the traffic protection facility performance evaluation system uses time-frequency analysis algorithms, such as the short-time Fourier transform (STFT), to process collision acoustic signals. The STFT divides the audio signal into multiple short time segments and performs a Fourier transform on each segment to obtain the frequency components of the signal at different time points, generating a spectrum feature map. From this generated spectrum feature map, specific algorithms are then used to extract acoustic characteristic parameters. For example, the peak frequency of the collision sound wave is determined by finding the frequency corresponding to the energy peak in the spectrum map. The energy distribution is then determined by integrating the energy across different frequency bands in the spectrum map. These acoustic characteristic parameters are then used to optimize the collision characteristic parameters.

[0095] S205 : Filter and optimize the feature point motion data based on the acoustic feature parameters to obtain optimized feature point motion data.

[0096] Specifically, the traffic protection facility performance evaluation system analyzes feature point motion data based on collision information reflected by acoustic characteristic parameters. For example, if the peak frequency of the collision sound wave is high, indicating a more intense collision, this may cause significant fluctuations in the feature point motion data. In this case, the fluctuating data points can be smoothed based on parameters such as energy distribution. By establishing a mathematical model that combines the acoustic characteristic parameters with the feature point motion data, the feature point motion data is filtered to remove outliers and noise interference, resulting in more accurate and optimized feature point motion data.

[0097] Optionally, the system can employ a Kalman filter algorithm. First, the acoustic feature parameters are used as auxiliary observation data, combined with the initial state of the feature point motion data (such as initial position and velocity), to establish a Kalman filter model. Within the model, parameters such as the noise covariance matrix are adjusted during the prediction and update processes based on the acoustic feature parameters. For example, when the energy distribution of the collision sound wave indicates a complex collision, the measurement noise covariance is appropriately increased to more rationally integrate the observation data. Then, through the prediction and update steps of the Kalman filter, the feature point motion data is iteratively optimized to obtain the optimized feature point motion data.

[0098] S206. Based on the feature point motion data, a kinematic analysis method is used to calculate the collision speed and collision angle, and a three-dimensional reconstruction method is used to determine the collision position and deformation of the protective facility.

[0099] Specifically, the traffic protection facility performance evaluation system first calculates the collision velocity and angle based on feature point motion data using kinematic analysis methods. By analyzing the displacement changes and time intervals of feature points in consecutive image frames, the velocity of the feature points is calculated based on the definition of velocity (speed equals displacement divided by time). The collision velocity of the accident vehicle is then inferred based on the geometric relationship between the vehicle and the protection facility, as well as the location of the feature points on the vehicle or protection facility. The collision angle is calculated using trigonometric functions and other mathematical methods by analyzing the directional changes in the feature point's motion trajectory and the initial orientation of the protection facility.

[0100] To determine the collision location and deformation of protective equipment, the system uses 3D reconstruction. If multiple video sources are available (such as footage captured by on-site management, footage recorded by surrounding surveillance equipment, and footage uploaded by dashcams from passing vehicles), the system can leverage feature points from different perspectives within these videos and, through principles such as triangulation, construct 3D models of the protective equipment and vehicle, thereby accurately pinpointing the collision location. Deformation of the protective equipment is calculated by comparing the shape differences of the 3D models before and after the collision.

[0101] If only monocular video data is available, the system can also first extract video frames from the accident video, and after image enhancement processing, use feature point detection and tracking algorithms to obtain the motion trajectory of the feature points. Based on the assumption that the initial shape of the protective facility is known and the vehicle movement is within a plane, an improved structured light 3D reconstruction algorithm is used to estimate the depth of the feature points based on image texture, edge and other information, and calculate their 3D coordinates in combination with camera parameters. By screening and analyzing feature points related to the collision, the collision position is determined in combination with the 3D model of the protective facility. The reconstructed 3D model of the protective facility is compared with the initial model, and the deformation is obtained by calculating the distance difference between the corresponding points through point cloud registration. Finally, the results are verified by comparing with physical laws and actual conditions, and the assumptions and algorithms are adjusted and optimized, thereby completing the inference of 3D information from the 2D video image and determining the collision position and deformation of the protective facility.

[0102] In the above-mentioned embodiment, the system optimizes the motion data of visual feature points by incorporating collision acoustic signal analysis, effectively improving the accuracy of collision feature parameters. Acoustic features can capture collision details that are difficult to capture visually, such as internal structural deformation and damage. This multimodal data fusion method can more comprehensively reflect the physical phenomena during the collision process, improving the reliability and accuracy of the residual performance assessment of protective equipment.

[0103] S207: When the accident video data is blocked or has an angle limitation, identify missing parameters in the collision feature parameters according to a preset collision parameter integrity detection mechanism.

[0104] Specifically, the traffic protection facility performance evaluation system conducts a comprehensive inspection of the accident video data to determine whether there are any obstructions or angle restrictions. If so, the system activates the preset collision parameter integrity detection mechanism. This mechanism analyzes the extracted collision feature parameters according to pre-set rules. For example, by comparing the movement of feature points in different video frames, if the feature points disappear or the motion trajectory is abnormal in certain key frames, combined with the logical judgment of the collision process, it is determined which collision feature parameters may be missing. For example, if the contact position of the vehicle and the protective facility at the moment of collision cannot be clearly seen, then the collision position parameters may be missing; if the vehicle is partially obscured and its motion trajectory cannot be accurately tracked, the collision speed and collision angle parameters may be inaccurate or missing.

[0105] S208. Construct a set of physical constraint equations that conform to the dynamic relationship of the collision process based on the collision characteristic parameters and the final deformation state.

[0106] Specifically, the traffic protection facility performance evaluation system builds a set of physical constraint equations based on existing collision characteristic parameters, combined with the final deformation state of the protection facility, and in accordance with dynamic principles such as Newton's laws of motion and the law of conservation of momentum. For example, the law of conservation of momentum is used to establish equations for the motion state of the vehicle and protection facility after the collision, based on parameters such as collision velocity, vehicle mass, and the stiffness of the protection facility. Based on the deformation and material properties of the protection facility, the principles of elasticity are used to establish equations describing the stress-strain relationship within the protection facility.

[0107] Optionally, the system can also be automatically generated with the help of professional mechanical analysis software. The collision characteristic parameters and the final deformation state data of the protective facilities are input into professional mechanical analysis software such as ANSYS. The software automatically generates a set of physical constraint equations that conform to the dynamic relationship of the collision process based on its own mechanical algorithms and models according to the input data. The software will consider factors such as material properties and geometric shapes to ensure the accuracy and completeness of the set of equations. It is understandable that other methods can also be used to achieve this, such as using an open source mechanical calculation library and inputting data to generate a set of equations in accordance with its prescribed method and format, which is not limited here.

[0108] S209. Establish a parameter sensitivity matrix based on the physical constraint equations and then determine the key missing parameters that have the greatest impact on the digital twin model from the missing parameters.

[0109] Specifically, the traffic protection facility performance evaluation system mathematically analyzes a set of physical constraint equations to calculate the degree to which a small change in each collision characteristic parameter affects the resulting deformation of the protection facility. For example, by taking partial derivatives of the physical constraint equations, the rate of change of the protection facility deformation for each parameter change is obtained. These rates of change are converted into a matrix form to obtain the parameter sensitivity matrix. Then, based on the parameter sensitivity matrix, the degree of influence of each missing parameter on the resulting deformation of the protection facility is compared. The greater the impact of the missing parameter, the greater the impact on the digital twin model's simulation of the collision process and the evaluation of the protection facility's residual performance, thereby identifying the key missing parameters that have the greatest impact on the digital twin model.

[0110] S210. Generate multiple sets of parameter sampling values ​​using the Monte Carlo method, and substitute them into the digital twin model for collision simulation to obtain corresponding simulated deformation results.

[0111] Specifically, the traffic protection facility performance evaluation system uses the Monte Carlo method to randomly generate multiple sets of parameter sampling values ​​within the allowable parameter value range based on the collision scenario constraints. For example, for the missing collision speed parameter, a reasonable value range is determined based on factors such as vehicle type, road speed limit, and on-site environment, and then multiple speed values ​​are randomly generated within this range. These parameter groups containing the key missing parameter sampling values ​​are sequentially substituted into the digital twin model. The vehicle kinematic model in the model simulates the vehicle's motion trajectory and collision process based on the parameters, and the protective facility finite element model simulates the mechanical response of the protective facility under the action of the collision force, thereby obtaining the simulated deformation results of the protective facility corresponding to each set of parameters.

[0112] S211. Filter out the optimal parameter combination corresponding to the simulated deformation result that has the highest similarity to the actual deformation state through the similarity evaluation function, and determine the key missing parameters.

[0113] Specifically, the traffic protection facility performance evaluation system inputs each set of simulated deformation results and the actual deformation state into a similarity evaluation function for calculation. This similarity evaluation function calculates the degree of similarity between the simulated deformation results and the actual deformation state in terms of shape, size, position, and other aspects based on a preset algorithm (such as Euclidean distance or cosine similarity), generating a similarity value. The system compares the similarity values ​​corresponding to all simulated deformation results and identifies the set of simulated deformation results with the highest value. The corresponding parameter sampling value combination is then considered the optimal parameter combination. From this optimal parameter combination, the values ​​of the key missing parameters are extracted, and this value is determined by the system as the most reasonable value to supplement the missing parameters.

[0114] In the above-mentioned embodiment, the system addresses the common issues of occlusion or angle restrictions in video data found in real-world scenarios. By establishing a parameter sensitivity matrix and a set of physical constraint equations, it can identify and supplement key missing parameters. Monte Carlo methods are then used to generate multiple sets of parameter samples, and the optimal parameter combination is screened through similarity evaluation, achieving precise estimation of missing parameters. This intelligent parameter optimization method not only ensures the rationality of physical constraints but also achieves optimal matching with the actual deformation state, improving the accuracy of assessments in the absence of data.

[0115] The traffic protection facility performance evaluation system of the embodiment of the present invention is applied to electronic equipment. Figure 3 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0116] It should be noted that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0117] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions (computer programs) or by instructions (computer programs) controlling related hardware. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein the storage medium stores multiple instructions that can be loaded by the processor to execute any step of the method provided in the embodiments of the present invention.

[0118] Specifically, the storage medium and the processor are electrically connected, directly or indirectly, to enable data transmission or interaction. For example, these elements may be electrically connected to each other via one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software functional module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The storage medium is used to store programs, and the processor executes the programs after receiving execution instructions.

[0119] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0120] Since the instructions stored in the storage medium can execute the steps of any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0121] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for evaluating the residual performance of traffic protection facilities after an accident based on digital twins, applied to a traffic protection facility performance evaluation system, characterized in that: The method comprises: Obtaining accident video data and vehicle parameter information uploaded by the accident vehicle, wherein the accident video data includes a complete video of the process before, during, and after the accident, and the vehicle parameter information includes vehicle mass, vehicle size, and vehicle stiffness; Extracting collision characteristic parameters of the collision process from the accident video data using a computer vision algorithm, wherein the collision characteristic parameters include collision speed, collision angle, collision position, and deformation of protective facilities; The step of extracting collision characteristic parameters of the collision process in the accident video data by using a computer vision algorithm includes: Extracting a video frame sequence from the accident video data and performing image enhancement and target segmentation processing to obtain an image of the protective facility area; Performing feature point detection and tracking on the protective facility area image to obtain feature point motion data; Extracting audio data from the accident video data and performing noise reduction and segmentation processing to obtain a collision acoustic signal; Performing time-frequency analysis on the collision acoustic signal to obtain a spectrum characteristic graph, and then extracting acoustic characteristic parameters from the spectrum characteristic graph, wherein the acoustic characteristic parameters include the peak frequency and energy distribution of the collision sound wave; performing filtering optimization on the feature point motion data based on the acoustic feature parameters to obtain optimized feature point motion data; Based on the optimized motion data of the feature points, a kinematic analysis method is used to calculate the collision speed and collision angle, and a three-dimensional reconstruction method is used to determine the collision position and deformation of the protective device; Establishing a digital twin model under an accident condition based on the vehicle parameter information and the collision characteristic parameters, the digital twin model including a vehicle kinematic model and a protective facility finite element model; Simulating the collision process in the digital twin model to obtain stress distribution data and plastic deformation data of the protective facilities; Based on the stress distribution data and plastic deformation data, combined with the performance requirements in the protective facility design specifications, a residual performance evaluation index system is established, wherein the residual performance evaluation index system includes structural strength, geometric dimensions and functional integrity; According to the residual performance evaluation index system, the residual performance index of the traffic protection facilities is calculated, and the corresponding maintenance and reinforcement suggestions are matched according to the residual performance index.

2. The method according to claim 1, characterized in that After the step of extracting the collision characteristic parameters of the collision process in the accident video data by a computer vision algorithm, the method further includes: When the accident video data is blocked or has an angle restriction, identifying missing parameters in the collision feature parameters according to a preset collision parameter integrity detection mechanism; Constructing a set of physical constraint equations that conform to the dynamic relationship of the collision process based on the collision characteristic parameters and the final deformation state; Establishing a parameter sensitivity matrix based on the physical constraint equations, wherein the parameter sensitivity matrix is ​​used to quantify the influence of each collision characteristic parameter on the deformation result of the protective facility; Determining the key missing parameters having the greatest impact on the digital twin model from the missing parameters according to the parameter sensitivity matrix; The key missing parameters are randomly generated according to collision scenario constraints, which include scene environment, road regulations and vehicle parameter information.

3. The method according to claim 2, characterized in that The step of randomly generating the key missing parameters according to the collision scene constraints specifically includes: A Monte Carlo method is used to generate multiple sets of parameter sampling values, wherein the parameter sampling values ​​meet the collision scenario constraint conditions; Substituting each set of parameter sampling values ​​into the digital twin model to perform collision simulation and obtain corresponding simulated deformation results; The optimal parameter combination corresponding to the simulated deformation result with the highest similarity to the actual deformation state is screened out through the similarity evaluation function; The key missing parameter is determined according to the optimal parameter combination.

4. The method according to claim 1, wherein After the step of obtaining the accident video data and vehicle parameter information uploaded by the accident vehicle, the method further includes: Acquiring multi-source video data, including full-angle video of post-accident protective facilities captured by on-site management personnel, video recorded by surrounding surveillance equipment during the accident, and video uploaded by dashcams of passing vehicles; Based on the spatiotemporal alignment algorithm, the multi-source video data is matched and fused with the accident video data uploaded by the accident vehicle to obtain updated accident video data.

5. The method according to claim 1, wherein Before simulating the collision process in the digital twin model and obtaining stress distribution data and plastic deformation data of the protective facilities, the method further includes: Acquiring historical collision data corresponding to the collision location, wherein the historical collision data includes a timestamp of the historical collision event, collision characteristic parameters, and historical stress distribution data; Analyze the historical stress distribution data based on the material cumulative damage model and calculate the material fatigue of each key part; The material parameters of the finite element model of the protective facility are modified based on the material fatigue.

6. A traffic protection facility performance evaluation system, characterized in that: The traffic protection facility performance evaluation system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the traffic protection facility performance evaluation system to execute the method described in any one of claims 1 to 5.

7. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a traffic protection facility performance evaluation system, the traffic protection facility performance evaluation system is caused to execute the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product is run on a traffic protection facility performance evaluation system, the traffic protection facility performance evaluation system is enabled to execute the method according to any one of claims 1 to 5.

Images