Safety assessment intelligent analysis system for vehicle passing highway bridge

Abstract

The invention discloses a safety assessment intelligent analysis system for a vehicle passing highway bridge, and relates to the field of data analysis, and the system comprises a bridge operation and maintenance management platform which comprises a bridge monitoring module, a vehicle collection module, a driving analysis module, a risk assessment module and a passing operation and maintenance module; the bridge monitoring module is used for acquiring vehicle driving state data, environment monitoring data and bridge diagnosis data on a bridge, and setting a running state evaluation three-dimensional virtual image according to the acquired data; the vehicle acquisition module is used for acquiring vehicle basic data and vehicle driving data; the driving analysis module obtains a vehicle basic type; the risk assessment module is used for acquiring corresponding vehicle risk assessment prediction data; the traffic operation and maintenance module performs comprehensive analysis according to the running state assessment three-dimensional virtual image, the prediction state assessment model and the vehicle risk assessment prediction data to generate traffic operation and maintenance data; according to the invention, the safety of vehicles in the process of passing through the highway bridge is improved to a certain extent.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an intelligent analysis system for safety assessment of vehicles passing through highway bridges. Background Art

[0002] As a key component of transportation infrastructure, highway bridges undertake the task of a large number of vehicle passages. Their safety conditions are directly related to the smoothness of transportation and the safety of public life and property. With the development of the economy and the continuous increase in traffic flow, highway bridges are facing increasingly severe safety challenges. Once a bridge has a safety problem, it may lead to serious consequences such as traffic interruption and vehicle accidents, bringing huge economic losses and adverse effects to society.

[0003] After retrieval, the invention patent with the Chinese patent number CN116415507A discloses an intelligent assessment system for large-piece transportation bridges based on big data and cloud computing, which relates to the field of safe passage of bridges, including: a bridge information parameter collection module, a bridge passability assessment module, a cloud remote human-computer interaction module, and a convolutional neural network data learning module. Both the bridge information parameter collection module and the bridge passability assessment module are three-segment type with three data integration points. In the present invention, by providing a bridge passability assessment module, the bridge passability assessment module is used to formulate passability standards for the vehicle and large-piece object parameter data of each passing vehicle collected by the bridge information parameter collection module at the three data integration points.

[0004] Compared with the prior art, the invention patent with the Chinese patent number CN116415507A can evaluate the driving state of passing vehicles on the bridge through three data integration points, and judge whether there is an abnormality on the corresponding bridge according to the real-time evaluation results, thereby improving the safety of vehicles and bridges.

[0005] However, in the actual use process of the above system, when monitoring the vehicle driving data on the bridge through the data integration point, when an abnormality is detected, it may have already caused a certain degree of impact on the bridge safety. Therefore, how to predict the risk abnormality before the vehicle enters the bridge and avoid the impact on the highway bridge caused by abnormal situations is a problem that we need to solve. Summary of the Invention

[0006] The purpose of the present invention is to solve the drawback of the lag in safety assessment in the prior art, and to propose an intelligent analysis system for safety assessment of vehicles passing through highway bridges.

[0007] In order to achieve the above purpose, the present invention adopts the following technical solutions: An intelligent analysis system for the safety assessment of highway bridges for vehicle passage, including a bridge operation and maintenance management platform, wherein a bridge monitoring module, a vehicle acquisition module, a driving analysis module, a risk assessment module, and a passage operation and maintenance module are arranged in the bridge operation and maintenance management platform; The bridge monitoring module is used to monitor in real time the vehicle driving state data, environmental monitoring data, and bridge diagnosis data corresponding to the highway bridge, analyze and process the obtained data, obtain a three-dimensional virtual image of the operation state assessment corresponding to the current highway bridge, and construct a corresponding predicted state assessment model according to the historical monitoring data; The vehicle acquisition module is used to collect the driving process of vehicles that have not entered the highway bridge, and obtain vehicle basic data and vehicle driving data; The driving analysis module is used to classify vehicles according to the vehicle basic data, and obtain the corresponding vehicle basic types; The risk assessment module is used to perform risk early warning assessment according to the predicted state assessment model based on the vehicle basic types of vehicles that have not entered the highway bridge, and obtain the corresponding vehicle risk assessment prediction data; The passage operation and maintenance module is used to comprehensively analyze the vehicle risk assessment prediction data corresponding to vehicles that have not entered the highway bridge according to the three-dimensional virtual image of the operation state assessment corresponding to the current situation, judge whether the corresponding vehicles are allowed to enter the corresponding highway bridge, and generate passage operation and maintenance data.

[0008] The above technical solution further includes: The process of monitoring in real time the vehicle driving state data, environmental monitoring data, and bridge diagnosis data corresponding to the highway bridge includes: Set up a bridge driving monitoring unit, a bridge environmental monitoring unit, and a bridge diagnosis monitoring unit; The bridge driving monitoring unit, the bridge environmental monitoring unit, and the bridge diagnosis monitoring unit are respectively connected to a plurality of vehicle driving monitoring devices, environmental monitoring devices, and bridge diagnosis monitoring devices arranged at corresponding positions on the highway bridge; Obtain the corresponding vehicle driving state data through the vehicle driving monitoring device; Obtain the corresponding environmental monitoring data through the environmental monitoring device; Obtain the corresponding bridge diagnosis data through the bridge diagnosis monitoring device.

[0009] Furthermore, the process of obtaining the three-dimensional virtual image of the operation state assessment corresponding to the current highway bridge includes: Perform bridge segmentation processing according to the position information of the vehicle driving monitoring device, the environmental monitoring device, and the bridge diagnosis monitoring device on the highway bridge, and obtain the corresponding bridge monitoring nodes according to the segmentation processing results; Obtain the bridge diagnosis data corresponding to the corresponding bridge monitoring nodes, and construct the bridge diagnosis data set corresponding to the corresponding bridge monitoring nodes according to the data types corresponding to the bridge diagnosis data; perform feature extraction on the obtained bridge diagnosis data set to obtain the evaluation feature data corresponding to the bridge diagnosis data set; Preset the evaluation index system at the bridge monitoring nodes corresponding to the corresponding highway bridges, compare and analyze the obtained evaluation feature data with the corresponding evaluation index system, and obtain the corresponding index safety status evaluation data; Perform comprehensive processing on the obtained index safety status evaluation data to obtain the safety status evaluation data corresponding to the corresponding bridge monitoring nodes, perform visualization processing on the safety status evaluation data corresponding to each bridge monitoring node, and construct a three-dimensional virtual image of the operation status evaluation.

[0010] Further, the process of constructing the corresponding prediction status evaluation model includes: Obtain the historical vehicle driving status data, historical environmental monitoring data, and historical bridge diagnosis data corresponding to the corresponding bridge monitoring nodes, set the historical vehicle driving status data and historical environmental monitoring data as independent variable data, and set the historical bridge diagnosis data as dependent variable data. Perform single variable extraction on the data information corresponding to the independent variable data in sequence to obtain the corresponding single variable evaluation data set. According to the different data types corresponding to the independent variable data, set the corresponding independent variable elements and set the single variable evaluation data subset; Based on the Pearson correlation coefficient algorithm, obtain the correlation coefficient between the independent variable elements corresponding to the corresponding single variable evaluation data subset and the corresponding dependent variable data, perform normalization processing on the obtained correlation coefficient, and obtain the weight coefficient corresponding to the corresponding independent variable elements; Set the initial evaluation status model according to the historical environmental monitoring data, the corresponding correlation coefficient, the weight coefficient, and the corresponding historical bridge diagnosis data. Based on the output result of the initial evaluation status model and the corresponding historical vehicle driving status data, set the historical evaluation data set, and perform analysis and training on the historical evaluation data set based on the deep learning algorithm to construct the corresponding prediction status evaluation model for the corresponding bridge monitoring nodes.

[0011] Further, the process of obtaining vehicle basic data and vehicle driving data includes: Set corresponding ordinary monitoring sections on both sides of the highway bridge, and set corresponding vehicle driving acquisition terminals in the ordinary monitoring sections; Obtain the vehicle basic data and vehicle driving data of the corresponding vehicles through the corresponding vehicle driving acquisition terminals. The vehicle basic data is license plate number, vehicle type, vehicle size, approved load mass, and vehicle weight monitoring data, and the vehicle driving data is the driving feature data corresponding to the corresponding vehicle during the driving process.

[0012] Further, the process of obtaining the vehicle basic type corresponding to the corresponding vehicle includes: Obtain the vehicle basic data and vehicle driving data corresponding to the corresponding license plate number; Set the corresponding vehicle basic classification evaluation criteria according to the currently obtained environmental monitoring data. The vehicle basic classification evaluation criteria include the size evaluation data and weight evaluation data corresponding to ordinary vehicles and large vehicles respectively. If the evaluation results corresponding to the vehicle basic classification evaluation criteria are consistent, obtain the corresponding vehicle basic type; otherwise, dynamically refine and adjust the vehicle basic classification evaluation criteria to obtain the corresponding vehicle basic type.

[0013] Further, the process of obtaining the corresponding vehicle risk assessment prediction data includes: Obtain the vehicle basic type of the corresponding vehicle and the corresponding environmental monitoring data obtained in the ordinary monitoring section, input the obtained environmental monitoring data into the initial evaluation state model corresponding to the corresponding bridge monitoring node, and output the correlation coefficient and corresponding weight coefficient corresponding to the current environmental monitoring data and the corresponding bridge diagnosis data; Dynamically adjust according to the correlation coefficient and weight coefficient of the independent variable factors corresponding to the environmental monitoring data corresponding to the vehicle basic type corresponding to the corresponding vehicle; According to the corresponding dynamic adjustment result, input the obtained correlation coefficient, weight coefficient and corresponding vehicle driving data into the prediction state evaluation model, output the vehicle risk assessment prediction data of the corresponding vehicle at the bridge monitoring node corresponding to the highway bridge, and send it to the traffic operation and maintenance module.

[0014] Further, the process of generating traffic operation and maintenance data includes: Obtain the vehicle driving data corresponding to the corresponding vehicle and the corresponding three-dimensional virtual image of the operation state evaluation, and combine the corresponding vehicle driving data to obtain the predicted time interval when the vehicle enters the corresponding bridge monitoring node of the highway bridge; Integrate and analyze the safety state evaluation data of the corresponding bridge monitoring node in the three-dimensional virtual image of the operation state evaluation and the predicted time interval when the vehicle that has not entered the highway bridge passes through the corresponding bridge monitoring node, and obtain the maximum risk value of the vehicle risk assessment prediction data corresponding to each bridge monitoring node; Preset the risk assessment threshold corresponding to each bridge monitoring node, compare and analyze the corresponding maximum risk value with the corresponding risk assessment threshold, judge whether the corresponding vehicle is allowed to pass through the highway bridge, and generate traffic operation and maintenance data according to the judgment result.

[0015] The present invention has the following beneficial effects: 1. In the present invention, by analyzing and processing the vehicle driving state data, environmental monitoring data, and bridge diagnosis data within the bridge at the current moment, a corresponding three-dimensional operation state evaluation image is obtained. Based on the three-dimensional operation state evaluation image and the vehicle driving data corresponding to the corresponding vehicle, passage operation and maintenance processing are carried out, ensuring the safety of highway bridges to the greatest extent, avoiding safety accidents that occur after vehicles enter the highway bridges, thereby improving the safety of vehicles passing through highway bridges. Moreover, by conducting risk assessment in advance, unnecessary losses caused by the lag of safety assessment are avoided.

[0016] 2. In the present invention, by setting multiple bridge monitoring nodes, due to the different influencing effects of the environmental monitoring data and vehicle driving data corresponding to different bridge monitoring nodes on the bridge safety data, a dynamically adjustable data evaluation process is set up. Combining the data types of vehicles and vehicle driving data, the maximum risk data when vehicles pass through highway bridges is predicted and evaluated to determine whether the corresponding vehicles are allowed to pass through the corresponding highway bridges, ensuring the safety of highway bridges to the greatest extent while also improving the safety of vehicles during the driving process on highway bridges. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic structural diagram of a safety assessment intelligent analysis system for vehicle passage on highway bridges proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment 1 As Figure 1 shown, a safety assessment intelligent analysis system for vehicle passage on highway bridges proposed by the present invention includes a bridge operation and maintenance management platform, and a bridge monitoring module, a vehicle acquisition module, a driving analysis module, a risk assessment module, and a passage operation and maintenance module are arranged in the bridge operation and maintenance management platform.

[0020] In this embodiment, the bridge operation and maintenance management platform is used to perform evaluation processing based on the driving state data of corresponding vehicles in the highway bridge, obtain the safety state evaluation data corresponding to the corresponding highway bridge, predict and analyze the risk evaluation data corresponding to the entry of vehicles that have not entered the highway bridge into the current highway bridge according to the corresponding safety state evaluation data, and determine whether to allow the corresponding vehicles to enter the corresponding highway bridge according to the prediction and analysis results, so as to conduct a safety evaluation of the highway bridge. The specific implementation process includes: The bridge monitoring module is used to monitor the vehicle driving state data, environmental monitoring data, and bridge diagnosis data corresponding to the highway bridge in real time, analyze and process the obtained data, obtain the three-dimensional virtual image of the operation state evaluation corresponding to the current highway bridge, and construct the corresponding prediction state evaluation model according to the historical monitoring data. The specific implementation process includes: Set up a bridge driving monitoring unit, a bridge environment monitoring unit, a bridge diagnosis monitoring unit, and a bridge state evaluation unit; The bridge driving monitoring unit is used to monitor the vehicle driving state data corresponding to the highway bridge in real time; Set up multiple vehicle driving monitoring devices on the corresponding highway bridge, obtain the vehicle driving video data corresponding to the corresponding positions in the highway bridge through each vehicle driving monitoring device, analyze and process the obtained vehicle driving video data, and perform marking processing on the vehicle driving video data according to the position information of the corresponding vehicle driving monitoring device; Set the corresponding driving evaluation nodes in sequence according to the position information of the corresponding highway bridge to which the vehicle driving monitoring device belongs, and set the driving analysis link for the set driving evaluation nodes; Set the corresponding forward evaluation sub-link and reverse evaluation sub-link according to the driving analysis link; The forward evaluation sub-link and the reverse evaluation sub-link are respectively used to monitor the vehicles in the opposite driving directions on the highway bridge. The process includes: Collect vehicle characteristics from the vehicle driving video data at the driving evaluation nodes corresponding to the head and tail in the driving analysis link, obtain the vehicle driving video data corresponding to the corresponding driving evaluation nodes, decompose the vehicle driving video data, obtain the corresponding image sequence, and perform enhancement processing on the video image frames corresponding to the obtained image sequence; Randomly obtain the video image frames corresponding to the image sequence, analyze and process the video image frames based on the object detection algorithm, detect the position information and bounding box of the corresponding vehicle, and obtain the vehicle image data; Extract vehicle features from the obtained vehicle image data, preprocess the obtained vehicle image data according to the corresponding pixel values to obtain the corresponding grayscale image, extract texture features from the grayscale image, calculate the occurrence frequencies corresponding to pixels with different grayscale values in the grayscale image in the corresponding directions and distances, construct a gray-level co-occurrence matrix based on the corresponding occurrence frequencies, and extract the corresponding texture features based on the gray-level co-occurrence matrix; Mark the corresponding vehicles according to the corresponding texture features in the vehicle image data; The corresponding driving evaluation nodes in the driving analysis link analyze and process the corresponding vehicles according to the marked vehicles. The specific implementation process includes: When the driving evaluation nodes corresponding to the head and tail in the corresponding driving analysis link obtain the marks of the corresponding vehicles, set the corresponding vehicle storage files according to the corresponding vehicle marking results, sequentially transmit the corresponding vehicle storage files by the corresponding driving evaluation nodes according to the vehicle driving paths, and input the corresponding vehicle driving results into the corresponding vehicle storage files; The corresponding driving evaluation nodes obtain the vehicle driving video data of the vehicles marked by the corresponding vehicle storage files, analyze and process the image sequences corresponding to the corresponding driving evaluation nodes in the vehicle driving video data, and extract the corresponding evaluation index data according to the change relationships between the image elements in the image sequences. The evaluation index data includes but is not limited to driving speed indexes, driving behavior indexes, driving environment indexes, etc. Among them: The driving speed indexes include average vehicle speed and overspeed frequency data; The driving behavior indexes include emergency braking frequency, lane change frequency, and sharp turn frequency; The driving environment indexes include road condition information and climate impact data corresponding to the corresponding highway bridges; Comprehensively analyze the obtained evaluation index data, obtain the node vehicle driving state data corresponding to the marked vehicles in the corresponding driving evaluation nodes, store the obtained node vehicle driving state data in the corresponding vehicle storage files, and perform identification marking; Obtain the vehicle driving video data corresponding to the next driving evaluation node in the driving analysis link, use the node vehicle driving state data corresponding to the corresponding driving evaluation node in the vehicle storage file as the evaluation basis, and perform evaluation and analysis on the node vehicle driving state data corresponding to the next driving evaluation node according to the corresponding evaluation basis; Mark the time information corresponding to the node vehicle driving state data corresponding to each driving evaluation node in the corresponding vehicle storage file; Perform visualization processing on the corresponding highway bridges according to the analysis results in each vehicle storage file in the driving analysis link to obtain the vehicle driving state data corresponding to each position on the current highway bridge; The bridge environment monitoring unit is used to monitor the corresponding environmental monitoring data on the highway bridge in real time, and the process includes: Corresponding environmental monitoring devices are set in the corresponding highway bridge and in the highway connected to the highway bridge. The environmental monitoring devices include meteorological monitoring devices and hydrological monitoring devices, where: The meteorological monitoring device is used to collect the corresponding meteorological monitoring data at the corresponding location. The meteorological monitoring data includes wind speed data, rainfall data, temperature data, humidity data, and sunshine data; The hydrological monitoring device is used to collect the corresponding hydrological monitoring data of the corresponding highway bridge. The hydrological monitoring data includes water level data and water flow velocity data; The meteorological monitoring data and hydrological monitoring data obtained at the corresponding environmental monitoring device are marked according to the corresponding location information, and the meteorological monitoring data and hydrological monitoring data are uniformly marked as the corresponding environmental monitoring data according to the marking result; The bridge diagnosis monitoring unit is used to monitor the corresponding bridge diagnosis data on the highway bridge in real time, and the process includes: Bridge diagnosis monitoring devices are set at corresponding positions in the corresponding highway bridge. The bridge diagnosis monitoring devices include strain monitoring devices, displacement monitoring devices, and crack monitoring devices, where: The strain monitoring device is used to obtain the corresponding stress change data at the corresponding position of the highway bridge; The displacement monitoring device is used to obtain the corresponding displacement change data at the corresponding position of the highway bridge; The crack monitoring device is used to obtain the corresponding crack signal data at the corresponding position of the highway bridge; The stress change data, displacement change data, and crack signal data corresponding to the corresponding position of the highway bridge are marked according to the corresponding position information, and the corresponding bridge diagnosis data at the corresponding position of the highway bridge is generated according to the marking result; The bridge condition assessment unit is used to analyze and process the vehicle driving state data, environmental monitoring data, and bridge diagnosis data obtained on the current highway bridge, obtain the three-dimensional virtual image of the operation state assessment corresponding to the current highway bridge, and construct the corresponding prediction state assessment model according to the historical monitoring data. The process includes: Construct a virtual bridge image corresponding to the corresponding highway bridge according to the position information of the corresponding monitoring device in the highway bridge and the construction image of the highway bridge, and perform mapping processing in the virtual bridge image according to the position information of the corresponding highway bridge of the corresponding monitoring device to obtain the three-dimensional virtual visualization image of the operation; Perform bridge segmentation based on the position information of the corresponding monitoring devices in the running three-dimensional virtual visualization image, obtain the corresponding bridge monitoring nodes in the running three-dimensional virtual visualization image, and perform marking processing on the corresponding bridge monitoring nodes according to the driving sequence of the highway bridge; Perform bridge safety assessment based on the marking results corresponding to the corresponding bridge monitoring nodes and the data information corresponding to the corresponding monitoring devices. The process includes: Obtain the bridge diagnosis data corresponding to the position of the corresponding bridge monitoring node, evaluate the bridge diagnosis data, integrate the corresponding bridge diagnosis data, construct the corresponding bridge diagnosis data set, and perform data cleaning and data standardization processing on the bridge diagnosis data set; Extract features from the bridge diagnosis data set that has completed data cleaning and data standardization processing, obtain the data information collected for different data types in the bridge diagnosis data set, and mark the data information subsets corresponding to the corresponding data types as x i (t), where i is the corresponding data type and t is the collection time of the corresponding data information; Perform data signal decomposition processing on the corresponding bridge diagnosis data set based on wavelet transform to obtain the corresponding decomposition level J; In the j-th layer of decomposition, analyze and process through the low-pass filter and the high-pass filter g(n) to obtain the corresponding approximation coefficients sim j (m) and detail coefficients det j (m); Analyze and process the corresponding data information subsets based on the corresponding approximation coefficients and detail coefficients to obtain the corresponding mean data, variance data, and energy data; Obtain the corresponding time-domain characteristics, frequency-domain characteristics, and frequency characteristics respectively based on the mean data, variance data, and energy data of the corresponding data information subsets; The time-domain characteristics, frequency-domain characteristics, and frequency characteristics corresponding to the corresponding data information subsets; Perform correlation analysis on the obtained time-domain characteristics, frequency-domain characteristics, and frequency characteristics with the preset bridge condition assessment indicators to obtain the assessment characteristic data corresponding to the bridge diagnosis data set; Establish an assessment index system for the corresponding highway bridge according to the expert experience and relevant specification standards in the field of bridge engineering; Perform comparative analysis on the obtained assessment characteristic data with the corresponding assessment index system to obtain the index safety status assessment data corresponding to the corresponding bridge monitoring node; Comprehensively process the obtained index safety status evaluation data, obtain the safety status evaluation data corresponding to the corresponding bridge monitoring nodes, and perform visualization processing on the corresponding running three-dimensional virtual image according to the safety status evaluation data corresponding to the corresponding bridge monitoring nodes to obtain the running status evaluation three-dimensional virtual image corresponding to the highway bridge at the current moment; Obtain the historical vehicle driving status data, historical environmental monitoring data, and historical bridge diagnosis data obtained by the corresponding bridge monitoring nodes. Sequentially extract single variables according to the historical environmental monitoring data, historical vehicle driving status data, and historical bridge diagnosis data to construct corresponding single variable evaluation data sets. The corresponding historical environmental monitoring data and historical vehicle driving status data in the single variable evaluation data set are respectively the corresponding independent variable data, and the historical bridge diagnosis data is the corresponding dependent variable data; Analyze and process the obtained single variable evaluation data sets. Set the variable type corresponding to the independent variable data in the single variable evaluation data set as the corresponding independent variable element, and set the corresponding single variable evaluation data subset according to the corresponding independent variable element. The historical bridge diagnosis data corresponding to the corresponding dependent variable data is obtained within the single variable evaluation data subset according to the change situation of the corresponding independent variable element and the situation where other independent variable elements remain unchanged; Obtain the correlation coefficient between the independent variable element corresponding to the corresponding single variable evaluation data subset and the corresponding dependent variable data based on the Pearson correlation coefficient algorithm : , where n is the number of corresponding data points in the single variable evaluation data subset, X and Y respectively correspond to the corresponding independent variable data and dependent variable data, and are respectively the i-th data points of the corresponding independent variable data and dependent variable data in the single variable evaluation data subset, and are respectively the corresponding means, and k is the corresponding independent variable element; Integrate the correlation coefficient corresponding to the corresponding single variable evaluation data subset, and perform normalization processing on the integration result to obtain the weight coefficient corresponding to the corresponding independent variable element , where: , where K is the number of independent variable elements, k is the corresponding identification mark, M is the data volume corresponding to the independent variable element with the corresponding identification mark k, j is the identification mark of the corresponding independent variable element, is the basic deviation coefficient corresponding to the corresponding independent variable element; Construct a state evaluation model based on the correlation data and weight coefficients corresponding to the historical bridge diagnosis data respectively from the historical environmental monitoring data and historical vehicle driving state data; Set an initial evaluation state model according to the historical environmental monitoring data, and set a predicted state evaluation model corresponding to the historical bridge diagnosis data based on the output result of the initial evaluation state model according to the corresponding historical vehicle driving state data; And sequentially connect the constructed initial evaluation state model and the corresponding predicted state evaluation model, and store according to the sequential connection result.

[0021] The vehicle acquisition module is used to acquire the driving process of vehicles that have not entered the highway bridge, and obtain vehicle basic data and vehicle driving data. Its specific implementation process includes: Corresponding ordinary monitoring sections are respectively set on both sides of the highway bridge, and corresponding vehicle driving acquisition terminals are set in the ordinary monitoring sections; The vehicle driving acquisition terminals respectively include RFID reading and writing terminals, dynamic weighing sensors and vehicle driving video monitoring devices, among which: The RFID reading and writing terminal is used to identify data such as the corresponding license plate number, vehicle type, body color, vehicle size and approved load mass, and the vehicle type includes various types such as cars, trucks, buses, etc.; The dynamic weighing sensor is used to obtain the vehicle weight monitoring data corresponding to the corresponding vehicle; Mark the data information obtained by the RFID reading and writing terminal and the dynamic weighing sensor as the vehicle basic data corresponding to the vehicle with the corresponding license plate number; The vehicle driving video monitoring device is used to obtain vehicle driving video data, analyze and process the vehicle driving video data, and obtain the vehicle driving data corresponding to the corresponding vehicle; Obtain the corresponding vehicle driving data, extract features from the corresponding vehicle driving data, including average speed data, maximum acceleration data, braking frequency data, etc.; Preset a driving evaluation model, set the corresponding feature extraction result as the driving data input set corresponding to the corresponding type of vehicle, input the obtained driving data input set into the driving evaluation model, and the corresponding driving evaluation model evaluates the driving state of the corresponding vehicle driving data, and outputs the corresponding state evaluation type. The state evaluation type includes safe driving type, abnormal driving type and dangerous driving type, and the vehicles of the safe driving type are sent to the driving analysis module.

[0022] The driving analysis module is used to classify vehicles according to the vehicle basic data, and obtain the vehicle basic type corresponding to the corresponding vehicle. Its specific implementation process includes: Obtain the vehicle basic data and vehicle driving data corresponding to the corresponding license plate number, and analyze and process the vehicle basic data and vehicle driving data obtained in the ordinary monitoring section at the current moment. The process includes: Obtain the corresponding vehicle size data, approved load mass data, and vehicle weight monitoring data in the vehicle basic data; Set the corresponding vehicle basic classification evaluation criteria according to the currently obtained environmental monitoring data. The vehicle basic classification evaluation criteria include the size evaluation data and weight evaluation data corresponding to ordinary vehicles and large-piece vehicles respectively; Compare and analyze the vehicle size data and vehicle weight monitoring data with the corresponding vehicle basic classification evaluation criteria respectively, and obtain the vehicle basic type according to the corresponding comparison and analysis results. The vehicle basic type is two types: ordinary vehicles and large-piece vehicles; If the vehicle basic types corresponding to the size evaluation data and the weight evaluation data are the same, mark the obtained vehicle basic type as the corresponding vehicle basic type; If the vehicle basic types corresponding to the size evaluation data and the weight evaluation data are different, dynamically adjust the corresponding vehicle basic classification evaluation criteria according to the corresponding vehicle type, and obtain the vehicle basic type corresponding to the corresponding size evaluation data and weight evaluation data according to the dynamic adjustment result of the vehicle basic classification evaluation criteria; If the vehicle basic types corresponding to the corresponding size evaluation data and the weight evaluation data are the same, mark the obtained vehicle basic type as the corresponding vehicle type; If the vehicle basic types corresponding to the size evaluation data and the weight evaluation data are still different, mark the obtained vehicle basic type as the corresponding abnormality; Mark the vehicles with abnormalities, store the classification results corresponding to other vehicle types, and send the classification results to the risk assessment module.

[0023] The risk assessment module is used to perform risk early warning assessment according to the vehicle basic type of the vehicle that has not entered the highway bridge according to the prediction status assessment model, and obtain the corresponding vehicle risk assessment prediction data. The specific implementation process includes: Obtain the classification results of the corresponding vehicles obtained in the ordinary monitoring section, and perform risk assessment prediction according to the classification results of the corresponding vehicles. The process includes: Obtain the environmental monitoring data corresponding to the current highway bridge, input the obtained environmental monitoring data into the corresponding initial assessment status model, output the correlation coefficient and the corresponding weight coefficient corresponding to the current environmental monitoring data and the corresponding bridge diagnosis data, and perform dynamic adjustment according to the correlation coefficient and weight coefficient of the independent variable factors corresponding to the environmental monitoring data corresponding to the vehicle basic type corresponding to the corresponding vehicle; Obtain the corresponding vehicle mass data F, and mark the effect coefficients corresponding to large vehicles and ordinary vehicles as and respectively. Mark the correlation coefficient and weight coefficient of the corresponding independent variable factors after dynamic adjustment as and respectively, where: ; ; Input the obtained correlation coefficient, weight coefficient, and the corresponding vehicle driving data into the prediction status evaluation model according to the corresponding dynamic adjustment results, and output the vehicle risk assessment prediction data corresponding to the vehicle at the bridge monitoring node corresponding to the highway bridge; Send the vehicle risk assessment prediction data of the vehicles that have not entered each bridge monitoring node of the highway bridge to the traffic operation and maintenance module.

[0024] The traffic operation and maintenance module is used to comprehensively analyze the vehicle risk assessment prediction data of the vehicles that have not entered the highway bridge according to the current corresponding operation status evaluation three-dimensional virtual image, determine whether the corresponding vehicle is allowed to enter the corresponding highway bridge, and generate traffic operation and maintenance data. The specific implementation process includes: Obtain the current operation status evaluation three-dimensional virtual image corresponding to the highway bridge and the vehicle risk assessment prediction data of the vehicles at each bridge monitoring node that have not entered the highway bridge; Obtain the vehicle driving data corresponding to the corresponding vehicle, and combine the vehicle driving data to obtain the predicted time interval corresponding to the vehicle entering the corresponding bridge monitoring node of the highway bridge; Integrate and analyze in combination with the current operation status evaluation three-dimensional virtual image corresponding to each bridge monitoring node and the predicted time interval for the vehicles that have not entered the highway bridge to pass through the bridge monitoring node; Obtain the maximum risk value of the vehicle risk assessment prediction data corresponding to each bridge monitoring node; Preset the risk assessment threshold corresponding to each bridge monitoring node, and compare and analyze the corresponding maximum risk value with the corresponding risk assessment threshold: If the maximum risk value is less than the risk assessment threshold, the corresponding bridge monitoring node is allowed to pass; If the maximum risk value is greater than or equal to the risk assessment threshold, the corresponding bridge monitoring node is not allowed to pass; Statistically analyze the allowable passing conditions of each bridge monitoring node in the highway bridge: If all bridge monitoring nodes in the highway bridge allow passing, the corresponding vehicle is allowed to enter the highway bridge. If there is a bridge monitoring node that does not allow passing, the corresponding vehicle is not allowed to enter the highway bridge. The traffic operation and maintenance data is generated according to the judgment result, and the traffic operation and maintenance data includes the analysis result of whether the corresponding vehicle is allowed to enter the highway bridge; According to the traffic operation and maintenance data, the corresponding vehicle entering the highway bridge process is fed back to the bridge monitoring module, and the corresponding operation status evaluation three-dimensional virtual image is updated in real time; It should be further explained that, in the specific implementation process, vehicles whose vehicle types are judged to be abnormal need to be marked and sent to corresponding management personnel based on the marking results, and the corresponding management personnel will manage the corresponding vehicles.

[0025] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent analysis system for the safety assessment of highway bridges for vehicle passage, including a bridge operation and maintenance management platform, characterized in that, The bridge operation and maintenance management platform is provided with a bridge monitoring module, a vehicle data collection module, a driving analysis module, a risk assessment module, and a passage operation and maintenance module; The bridge monitoring module is used to monitor in real time the vehicle driving state data, environmental monitoring data, and bridge diagnosis data corresponding to a highway bridge, analyze and process the obtained data, obtain a three-dimensional virtual image of the operation state assessment corresponding to the current highway bridge, and construct a corresponding predicted state assessment model based on historical monitoring data; The vehicle data collection module is used to collect the driving process of vehicles that have not entered the highway bridge, and obtain vehicle basic data and vehicle driving data; The driving analysis module is used to classify vehicles according to vehicle basic data, and obtain the corresponding vehicle basic types; The risk assessment module is used to perform risk warning assessment according to the predicted state assessment model based on the vehicle basic types of vehicles that have not entered the highway bridge, and obtain the corresponding vehicle risk assessment prediction data; The passage operation and maintenance module is used to comprehensively analyze the vehicle risk assessment prediction data corresponding to vehicles that have not entered the highway bridge according to the three-dimensional virtual image of the operation state assessment corresponding to the current situation, determine whether the corresponding vehicles are allowed to enter the corresponding highway bridge, and generate passage operation and maintenance data.

2. The intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 1, wherein, The process of monitoring in real time the vehicle driving state data, environmental monitoring data, and bridge diagnosis data corresponding to a highway bridge includes: Setting up a bridge driving monitoring unit, a bridge environmental monitoring unit, and a bridge diagnosis monitoring unit; The bridge driving monitoring unit, the bridge environmental monitoring unit, and the bridge diagnosis monitoring unit are respectively connected to a plurality of vehicle driving monitoring devices, environmental monitoring devices, and bridge diagnosis monitoring devices arranged at corresponding positions on the highway bridge; Obtaining the corresponding vehicle driving state data through the vehicle driving monitoring devices; Obtaining the corresponding environmental monitoring data through the environmental monitoring devices; Obtaining the corresponding bridge diagnosis data through the bridge diagnosis monitoring devices.

3. The intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 2, characterized in that, The process of obtaining the three-dimensional virtual image of the operation state assessment corresponding to the current highway bridge includes: Performing bridge segmentation processing according to the position information of the vehicle driving monitoring devices, environmental monitoring devices, and bridge diagnosis monitoring devices on the highway bridge, and obtaining the corresponding bridge monitoring nodes according to the segmentation processing results; Obtaining the bridge diagnosis data corresponding to the corresponding bridge monitoring nodes, constructing a bridge diagnosis data set corresponding to the corresponding bridge monitoring nodes according to the data types corresponding to the bridge diagnosis data; extracting features from the obtained bridge diagnosis data set to obtain the evaluation feature data corresponding to the bridge diagnosis data set; Presetting an evaluation index system at the bridge monitoring nodes corresponding to the corresponding highway bridge, comparing and analyzing the obtained evaluation feature data with the corresponding evaluation index system, and obtaining the corresponding index safety state evaluation data; Performing comprehensive processing on the obtained index safety state evaluation data, obtaining the safety state evaluation data corresponding to the corresponding bridge monitoring nodes, performing visualization processing on the safety state evaluation data corresponding to each bridge monitoring node, and constructing a three-dimensional virtual image of the operation state assessment.

4. The intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 3, wherein, The process of constructing the corresponding predicted state assessment model includes: Obtain the historical vehicle driving state data, historical environmental monitoring data, and historical bridge diagnosis data corresponding to the corresponding bridge monitoring nodes. Set the historical vehicle driving state data and historical environmental monitoring data as independent variable data, and the historical bridge diagnosis data as dependent variable data. Sequentially extract single variables from the data information corresponding to the independent variable data to obtain the corresponding single variable evaluation data set. According to the different data types corresponding to the independent variable data, set the corresponding independent variable elements and set the single variable evaluation data subset; Based on the Pearson correlation coefficient algorithm, obtain the correlation coefficient between the independent variable elements corresponding to the corresponding single variable evaluation data subset and the corresponding dependent variable data. Normalize the obtained correlation coefficient to obtain the weight coefficient corresponding to the corresponding independent variable element; Set the initial evaluation state model according to the historical environmental monitoring data, the corresponding correlation coefficient, the weight coefficient, and the corresponding historical bridge diagnosis data. Based on the output result of the initial evaluation state model and the corresponding historical vehicle driving state data, set the historical evaluation data set. Analyze and train the historical evaluation data set based on the deep learning algorithm to construct the prediction state evaluation model corresponding to the corresponding bridge monitoring node.

5. The intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 4, characterized in that, The process of obtaining vehicle basic data and vehicle driving data includes: Corresponding ordinary monitoring sections are respectively set on both sides of the highway bridge, and corresponding vehicle driving acquisition terminals are set in the ordinary monitoring sections; Obtain the vehicle basic data and vehicle driving data of the corresponding vehicle through the corresponding vehicle driving acquisition terminal. The vehicle basic data is license plate number, vehicle type, vehicle size, approved load mass, and vehicle weight monitoring data, and the vehicle driving data is the driving characteristic data corresponding to the corresponding vehicle driving process.

6. The intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 5, wherein, The process of obtaining the corresponding vehicle basic type includes: Obtain the vehicle basic data and vehicle driving data corresponding to the corresponding license plate number; Set the corresponding vehicle basic classification evaluation criteria according to the currently obtained environmental monitoring data. The vehicle basic classification evaluation criteria include the size evaluation data and weight evaluation data corresponding to ordinary vehicles and large-piece vehicles respectively. If the evaluation results corresponding to the vehicle basic classification evaluation criteria are consistent, obtain the corresponding vehicle basic type. Otherwise, dynamically refine and adjust the vehicle basic classification evaluation criteria to obtain the corresponding vehicle basic type.

7. An intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 6, characterized in that, The process of obtaining the corresponding vehicle risk assessment prediction data includes: Obtain the vehicle basic type of the corresponding vehicle obtained in the ordinary monitoring section and the corresponding environmental monitoring data. Input the obtained environmental monitoring data into the initial evaluation state model corresponding to the corresponding bridge monitoring node, and output the correlation coefficient and the corresponding weight coefficient between the current environmental monitoring data and the corresponding bridge diagnosis data; Dynamically adjust according to the correlation coefficient and weight coefficient of the independent variable factors corresponding to the environmental monitoring data corresponding to the corresponding vehicle basic type of the corresponding vehicle; Input the obtained correlation coefficient, weight coefficient, and corresponding vehicle driving data into the prediction status evaluation model according to the corresponding dynamic adjustment results, output the vehicle risk assessment prediction data corresponding to the vehicle at the bridge monitoring node corresponding to the highway bridge, and send it to the traffic operation and maintenance module.

8. An intelligent analysis system for safety assessment of highway bridges for vehicle passage according to claim 7, characterized in that, The process of generating traffic operation and maintenance data includes: Obtain the vehicle driving data corresponding to the corresponding vehicle and the corresponding three-dimensional virtual image of the operation status evaluation, and combine the corresponding vehicle driving data to obtain the predicted time interval corresponding to the vehicle driving into the bridge monitoring node of the highway bridge; Integrate and analyze the safety status evaluation data of the corresponding bridge monitoring node in the three-dimensional virtual image of the operation status evaluation and the predicted time interval of the vehicle not driving into the highway bridge passing through the corresponding bridge monitoring node to obtain the maximum risk of the vehicle risk assessment prediction data corresponding to each bridge monitoring node; Preset the risk assessment threshold corresponding to each bridge monitoring node, compare and analyze the corresponding maximum risk with the corresponding risk assessment threshold, judge whether the corresponding vehicle is allowed to pass through the highway bridge, and generate traffic operation and maintenance data according to the judgment result.

Images