A method, device and computer equipment for detecting abnormality of road and bridge parameters

Abstract

The present application relates to a method, device and computer equipment for detecting anomalies of road and bridge parameters. The method comprises: performing anomaly analysis according to the real-time road and bridge detection data and real-time road and bridge environmental data corresponding to the target detected road and bridge, obtaining preliminary road and bridge warning information and preliminary road and bridge diagnosis report; performing feature analysis on the real-time road and bridge detection data according to the preliminary road and bridge warning information, obtaining warning data processing decision information; performing scenario simulation according to the warning data processing decision information and the preliminary road and bridge diagnosis report, obtaining a road and bridge abnormality analysis report; adjusting system parameters according to the road and bridge abnormality analysis report, real-time road and bridge detection data and real-time road and bridge environmental data; detecting the target detected road and bridge using the adjusted parameters, and generating a road and bridge repair instruction according to the road and bridge abnormality analysis report when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold, so as to accurately discover the hidden internal structural damage of the road and bridge.

Description

Technical Field

[0001] The present application relates to the field of intelligent detection technology, and in particular to a method, device and computer equipment for detecting abnormalities of road and bridge parameters. Background Art

[0002] With the development of road and bridge technology, road and bridge parameter detection technology has emerged. This technology uses various instruments and equipment to evaluate and detect the structural performance, material condition and service life of roads and bridges. Its purpose is to timely discover and diagnose potential problems and damages of roads and bridges, so as to provide a scientific basis for maintenance and repair, and ensure the safety and long-term reliable operation of transportation infrastructure.

[0003] Traditional road and bridge parameter detection technology mainly relies on manual detection combined with instruments and equipment. Inspectors use visual inspection, auditory tapping, and measuring tools such as distance meters and crack gauges to identify and evaluate obvious structural parameter problems such as cracks, peeling, deformation, and corrosion on the surface of roads and bridges. Although traditional road and bridge parameter detection methods are simple and direct, they are easily affected by subjective judgment and environmental conditions. The detection accuracy and efficiency are prone to deviations, making it difficult to discover hidden internal structural damage of roads and bridges. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for detecting anomalies of road and bridge parameters that can accurately detect damage hidden in the internal structure of the road and bridge in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting anomalies of road and bridge parameters, comprising:

[0006] Analyze abnormal conditions of roads and bridges based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis reports;

[0007] In the case where the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network;

[0008] Perform virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0009] According to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted;

[0010] The target detected road and bridge are detected using the road and bridge detection system after adjusting parameters. When the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0011] In a second aspect, the present application also provides a device for detecting anomalies of road and bridge parameters, including:

[0012] The road and bridge situation analysis module is used to analyze the abnormal situation of the road and bridge according to the real-time road and bridge detection data corresponding to the target detection road and bridge and the real-time road and bridge environment data, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis report;

[0013] A data processing decision module is used to perform real-time data feature analysis on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information when the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network;

[0014] A data processing execution module, used to perform a virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0015] A system parameter adjustment module, used to adjust the system parameters of the road and bridge detection system corresponding to the target detection road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data;

[0016] A repair instruction generation module is used to detect the target detected road and bridge using the road and bridge detection system after adjusting parameters, and generate a road and bridge repair instruction according to the road and bridge abnormality analysis report when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0017] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0018] Analyze abnormal conditions of roads and bridges based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis reports;

[0019] In the case where the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network;

[0020] Perform virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0021] According to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted;

[0022] The target detected road and bridge are detected using the road and bridge detection system after adjusting parameters. When the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0024] Analyze abnormal conditions of roads and bridges based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis reports;

[0025] In the case where the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network;

[0026] Perform virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0027] According to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted;

[0028] The target detected road and bridge are detected using the road and bridge detection system after adjusting parameters. When the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0029] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0030] Analyze abnormal conditions of roads and bridges based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis reports;

[0031] In the case where the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network;

[0032] Perform virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0033] According to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted;

[0034] The target detected road and bridge are detected using the road and bridge detection system after adjusting parameters. When the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than a difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0035] The above-mentioned method, device, computer equipment, storage medium and computer program product for abnormal detection of road and bridge parameters analyze the abnormal situation of the road and bridge according to the real-time road and bridge detection data and real-time road and bridge environmental data corresponding to the target detection road and bridge, so as to obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis report; when the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is realized through a primary and secondary multi-level computing network; a virtual-real combined fault scenario simulation is performed according to the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormal analysis report; according to the road and bridge abnormal analysis report, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted; the road and bridge detection system after adjusting the parameters detects the target detection road and bridge, and when the difference between the road and bridge abnormal analysis report and the adjusted road and bridge abnormal analysis report is less than the difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormal analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detection road and bridge.

[0036] By comprehensively utilizing real-time detection data and environmental data, multi-level, real-time analysis and early warning of abnormal conditions of roads and bridges were realized for the first time. By using the primary and secondary multi-level computing network, the abnormal events triggered by the preliminary diagnosis were deeply analyzed to generate early warning data processing decision information, and a detailed abnormal analysis report of the road and bridge was generated through the virtual-real fault scenario simulation. According to the report, the parameters of the detection system are dynamically adjusted to improve the responsiveness and data accuracy of the detection system. Finally, when the difference between the real-time detection data and the adjusted data is less than the threshold, the system generates accurate repair instructions to ensure the timeliness and effectiveness of the repair. This method significantly improves the accuracy and efficiency of road and bridge detection, can accurately detect hidden internal structural damage of roads and bridges, reduce potential risks, extend the service life of roads and bridges, and ensure the safety and smoothness of public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A diagram of an application environment of a method for detecting anomalies of road and bridge parameters in an embodiment;

[0039] Figure 2A schematic diagram of a flow chart of a method for detecting abnormality of road and bridge parameters in an embodiment;

[0040] Figure 3 A flowchart of a method for obtaining early warning data processing decision information in one embodiment;

[0041] Figure 4 A schematic diagram of a flow chart of a method for determining preliminary data processing strategy information in one embodiment;

[0042] Figure 5 A schematic flow chart of a method for obtaining early warning data processing decision information in another embodiment;

[0043] Figure 6 A schematic diagram of a flow chart of a method for obtaining a road and bridge abnormality analysis report in one embodiment;

[0044] Figure 7 A schematic flow chart of a method for obtaining a road and bridge abnormality analysis report in another embodiment;

[0045] Figure 8 A schematic diagram of a flow chart of a method for adjusting system parameters in one embodiment;

[0046] Fig. 9 A schematic diagram of a flow chart of a method for generating a road and bridge repair instruction in one embodiment;

[0047] Fig.10 It is a structural block diagram of a device for detecting abnormality of road and bridge parameters in one embodiment;

[0048] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The method for detecting abnormality of road and bridge parameters provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 performs an abnormal situation analysis of the bridge according to the real-time bridge detection data and the real-time bridge environment data corresponding to the target detected bridge, and obtains preliminary bridge warning information and a preliminary bridge diagnosis report; when the preliminary bridge diagnosis report triggers bridge abnormality event trigger information, the real-time data feature analysis is performed on the real-time bridge detection data according to the preliminary bridge warning information to obtain warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network; a virtual-real combined fault scenario simulation is performed according to the warning data processing decision information and the preliminary bridge diagnosis report to obtain a bridge abnormality analysis report; the system parameters of the bridge detection system corresponding to the target detected bridge are adjusted according to the bridge abnormality analysis report, the real-time bridge detection data and the real-time bridge environment data; the bridge detection system detects the target detected bridge using the adjusted parameters, and when the difference between the bridge abnormality analysis report and the adjusted bridge abnormality analysis report is less than the difference threshold, a bridge repair instruction is generated according to the bridge abnormality analysis report; the bridge repair instruction is used to control the repair unit to repair the target detected bridge. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0051] In an exemplary embodiment, Figure 2 As shown in FIG. 1 , a method for detecting anomalies of road and bridge parameters is provided. The method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them:

[0052] Step 202: analyzing abnormal conditions of the road and bridge based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detected road and bridge, and obtaining preliminary road and bridge warning information and a preliminary road and bridge diagnosis report.

[0053] Among them, real-time road and bridge detection data can be dynamic data reflecting the structure and status of the road and bridge collected in real time through various sensors and detection equipment, including physical parameters such as vibration, stress, displacement, and temperature of the bridge.

[0054] Among them, real-time road and bridge environmental data can be dynamic data reflecting the environmental conditions around roads and bridges, which are obtained and recorded in real time through various environmental detection equipment, including meteorological conditions (such as temperature, humidity, rainfall, wind speed and direction), traffic flow, geological activities (such as earthquakes, ground subsidence) and other factors.

[0055] Among them, preliminary road and bridge warning information can be early warning information of potential abnormal conditions and safety hazards identified through analysis and processing, including possible structural problems, excessive stress, abnormal vibrations and other prompts.

[0056] Among them, the preliminary road and bridge diagnosis report can be preliminary assessment information generated through detailed analysis and evaluation. The report includes identified abnormal conditions, possible causes, scope of impact and preliminary risk assessment.

[0057] Specifically, the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge are collected, and the real-time road and bridge detection data and real-time road and bridge environment data are preprocessed, wherein the preprocessing includes data cleaning, noise filtering and missing value filling, and then the data from different sources are integrated together by using data fusion technology to construct a comprehensive data set. The comprehensive data set is input into the shallow collaborative learning model, and the input data is preliminarily screened by the shallow collaborative learning model, and a simple statistical analysis and machine learning model are used for rapid warning, and the preliminarily screened abnormal data is passed to the deep collaborative learning model. The deep collaborative learning model performs a detailed analysis of the abnormal data screened by the shallow collaborative learning model, uses a complex deep learning model for in-depth diagnosis, compares the diagnosis results with historical data, and identifies potential problems; finally, the preliminary road and bridge warning information and the preliminary road and bridge diagnosis report are output.

[0058] Step 204, when the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information.

[0059] The bridge abnormal event trigger information may be a specific abnormal condition identified in the past, including clear abnormal type (such as structural damage, abnormal vibration, etc.), occurrence location, severity, time and other details.

[0060] Among them, real-time data feature analysis can be achieved through advanced data processing algorithms and analysis techniques, using primary and secondary multi-level computing networks to extract and analyze features of real-time road and bridge inspection data, including identifying and extracting key indicators, such as physical characteristics such as stress, vibration, displacement, and variables such as temperature and humidity in environmental data.

[0061] Among them, the early warning data processing decision information can be guiding information generated after feature analysis of real-time road and bridge detection data, including specific data processing steps and strategies.

[0062] Specifically, if the information in the preliminary road and bridge diagnosis report can trigger the trigger information of the road and bridge abnormal event, that is, the information in the preliminary road and bridge diagnosis report contains the information of the road and bridge abnormal event, then according to the preliminary warning information, combined with the event-driven architecture and intelligent data routing, the primary and secondary multi-level computing network is used to realize the real-time deep data feature analysis of the real-time road and bridge detection data, that is, the real-time road and bridge detection data is segmented and input into the cloud and edge devices for calculation, and key abnormal features such as abnormal stress, vibration mode, etc. are identified. Then the system uses advanced data analysis algorithms and machine learning models to further process and classify these features and generate warning data processing decision information. The warning data processing decision information includes specific data processing methods and steps, such as noise filtering methods, abnormal data identification and isolation technology, feature priority sorting, and any combination of response strategy recommendations.

[0063] Step 206, performing a virtual-real fault scenario simulation based on the early warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report.

[0064] Among them, the virtual-reality combined fault scenario simulation can be achieved by combining virtual simulation technology and actual detection data to simulate and analyze potential faults of roads and bridges in different scenarios.

[0065] Among them, the road and bridge abnormality analysis report can be a detailed file generated after comprehensive analysis of real-time detection data, environmental data, preliminary diagnosis reports, and virtual and real fault scenario simulation results. The report includes a detailed description of the road and bridge abnormality, cause analysis, impact assessment, and potential risk analysis, and provides targeted repair suggestions and countermeasures.

[0066] Specifically, a virtual fault scenario is constructed based on the historical road and bridge inspection data and historical road and bridge environmental data of the target inspection road and bridge, and different types of road and bridge abnormalities are simulated by the simulation software in the twin model to generate simulation data, such as simulated structural damage, material fatigue, etc. Then, the simulation data generated by these virtual scenarios are combined with the actual detected abnormal data to deeply analyze the abnormal characteristics and possible causes, and generate a road and bridge abnormality analysis report.

[0067] Step 208: adjusting the system parameters of the road and bridge detection system corresponding to the target detection road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data, and the real-time road and bridge environment data.

[0068] Among them, the system parameters include system physical parameters about the system physical characteristics and model parameters about the primary and secondary multi-level computing networks, structural health twin models and scenario simulation twin models.

[0069] Specifically, according to the road and bridge anomaly analysis report, real-time road and bridge detection data and real-time road and bridge environmental data, the key parameters affecting the detection accuracy are deeply analyzed, including sensor position, sensitivity, data sampling frequency, filtering algorithm, etc. Then, according to the problems found, the installation position and angle of the sensor are adjusted to optimize its coverage and sensitivity; at the same time, the data sampling frequency and filtering algorithm are adjusted to ensure that the collected data are more accurate and representative. Subsequently, the system is recalibrated, and the second parameter adjustment is carried out by introducing known standard signals to verify the adjusted system parameters, and the parameters of the primary and secondary multi-level computing networks, structural health twin models and scenario simulation twin models are adjusted to ensure that the system can accurately reflect the actual conditions of the road and bridge. Finally, multiple field tests and verifications are carried out to gradually optimize and confirm the stability and reliability of the adjusted detection system.

[0070] Step 210, using the road and bridge detection system after adjusting parameters to detect the target detection road and bridge, when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than the difference threshold, generating a road and bridge repair instruction according to the road and bridge abnormality analysis report.

[0071] The difference threshold may be an allowable range set for evaluating the abnormal analysis report of the road and bridge before and after the adjustment, and is used to judge whether the system is consistent before and after the adjustment and determine the validity of the system processing data.

[0072] The road and bridge repair instructions may be specific operation guidelines generated based on the road and bridge abnormality analysis report, and are used to guide the repair unit to perform the road and bridge repair work.

[0073] Specifically, after adjusting the system parameters of the road and bridge detection system, the improved road and bridge detection system is used to re-test the target road and bridge comprehensively, and an adjusted road and bridge abnormality analysis report is generated. The road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report are compared and analyzed in detail, focusing on key parameters such as stress, vibration, and displacement, and the differences between them are calculated. If the differences are less than the preset difference threshold, it indicates that the system has achieved the expected effect before and after the adjustment, and the detection accuracy is guaranteed. Therefore, according to the road and bridge abnormality analysis report, specific repair instructions are formulated, which include precise repair locations, required materials, repair methods, and safety measures. The repair instructions are sent to the repair unit to control it to accurately repair the target road and bridge.

[0074] In the above-mentioned method for detecting abnormality of road and bridge parameters, the abnormality of the road and bridge is analyzed according to the real-time road and bridge detection data and the real-time road and bridge environmental data corresponding to the target detected road and bridge, so as to obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis report; when the preliminary road and bridge diagnosis report triggers the trigger information of the road and bridge abnormality event, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain the warning data processing decision information; the real-time data feature analysis is realized through a primary and secondary multi-level computing network; the virtual and real combined fault scenario simulation is performed according to the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain the road and bridge abnormality analysis report; according to the road and bridge abnormality analysis report, the system parameters of the road and bridge detection system corresponding to the target detected road and bridge are adjusted; the road and bridge detection system after adjusting the parameters is used to detect the target detected road and bridge, and when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than the difference threshold, a road and bridge repair instruction is generated according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0075] By comprehensively utilizing real-time detection data and environmental data, multi-level, real-time analysis and early warning of abnormal conditions of roads and bridges were realized for the first time. By using the primary and secondary multi-level computing network, the abnormal events triggered by the preliminary diagnosis were deeply analyzed to generate early warning data processing decision information, and a detailed abnormal analysis report of the road and bridge was generated through the virtual-real fault scenario simulation. According to the report, the parameters of the detection system are dynamically adjusted to improve the responsiveness and data accuracy of the detection system. Finally, when the difference between the real-time detection data and the adjusted data is less than the threshold, the system generates accurate repair instructions to ensure the timeliness and effectiveness of the repair. This method significantly improves the accuracy and efficiency of road and bridge detection, can accurately detect hidden internal structural damage of roads and bridges, reduce potential risks, extend the service life of roads and bridges, and ensure the safety and smoothness of public transportation.

[0076] In an exemplary embodiment, Figure 3 As shown, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain the warning data processing decision information, including steps 302 to 304. Among them:

[0077] Step 302, determining preliminary data processing strategy information based on preliminary road and bridge warning information and real-time road and bridge detection data.

[0078] The preliminary data processing strategy information can be a guiding information generated based on the preliminary road and bridge warning information and real-time detection data, which is used to preliminarily determine how to process and analyze these data. It includes any one or more of data cleaning methods, noise filtering techniques, feature extraction and pattern recognition steps, and any combination of the priority sorting and processing order of abnormal situations.

[0079] Specifically, the preliminary road and bridge warning information and the real-time road and bridge detection data are input into the algorithm based on the event-driven architecture (EDA). The event-driven architecture (EDA) identifies the data type and importance of each data of the real-time road and bridge detection data according to the preliminary road and bridge warning information and the real-time road and bridge detection data, and then dynamically adjusts the data processing strategy constructed by the historical road and bridge detection data and the historical road and bridge environmental data to obtain the dynamically adjusted data processing strategy; further, according to the preliminary road and bridge warning information, the processing priority and method of the dynamically adjusted data processing strategy are optimized to obtain the optimized dynamically adjusted data processing strategy; finally, according to the change information of the real-time road and bridge detection data, the optimized dynamically adjusted data processing strategy is adjusted for the third time to obtain preliminary data processing strategy information.

[0080] Step 304, according to the data feature information of the real-time road and bridge detection data, the real-time road and bridge detection data is sent to the primary and secondary multi-level computing network for splitting calculation, and the early warning data processing decision information is returned.

[0081] The data feature information may be the features of key parameters and indicators extracted from real-time road and bridge detection data, and these features can describe and reflect the structural state and operating conditions of the road and bridge.

[0082] Among them, split computing can refer to decomposing a complex data processing task into multiple smaller subtasks, and processing these subtasks separately through hierarchical and parallel computing methods to improve computing efficiency and processing speed.

[0083] Specifically, intelligent data routing is used to extract the key features of real-time road and bridge inspection data to obtain data feature information, such as stress feature information, vibration feature information, temperature feature information, etc. The above-mentioned feature information is sent to the primary and secondary multi-level computing network, and split and parallelized in the network. Each level processes data of different types and priorities, or processes data that requires different computing power. The primary level is responsible for in-depth analysis and anomaly detection of key features (or data that requires higher computing power), while the secondary level is responsible for screening and verification of auxiliary data (or data that requires lower computing power). Finally, the calculation results of each level are summarized to generate warning data processing decision information.

[0084] In this embodiment, by combining preliminary road and bridge warning information and real-time road and bridge detection data, effective preliminary data processing strategy information is formulated to ensure the pertinence and efficiency of data processing. The feature information of real-time detection data is sent to the primary and secondary multi-level computing network for split calculation, which can make full use of computing resources and accurately analyze different types of data. In this way, the returned warning data processing decision information is more accurate and real-time, which improves the recognition ability and response speed of abnormal road and bridge conditions, thereby greatly improving the overall efficiency of road and bridge safety detection and maintenance.

[0085] In an exemplary embodiment, Figure 4 As shown, according to the preliminary road and bridge warning information and the real-time road and bridge detection data, the preliminary data processing strategy information is determined, including steps 402 to 406. Among them:

[0086] Step 402: Determine the dynamic processing method of each detection data according to the data type and importance corresponding to each sub-data in the real-time road and bridge detection data.

[0087] The dynamic processing method of detection data may refer to flexibly adjusting the data processing strategy according to the different types and importance of real-time road and bridge detection data to optimize detection efficiency and resource utilization.

[0088] Specifically, in the event-driven architecture, based on the preliminary road and bridge warning information and real-time road and bridge detection data, the real-time road and bridge detection data are classified to identify various data types, such as stress, vibration, displacement, temperature, etc. Then, the importance of each data type in the overall detection is evaluated and its priority is determined. For high-importance data (such as stress and vibration), high-frequency sampling and real-time analysis methods are used to ensure rapid identification and response to abnormal situations; for medium-importance data (such as displacement), medium-frequency sampling and regular analysis are used; for low-importance data (such as temperature), low-frequency sampling and batch processing are used; the processing strategies of these data are dynamically adjusted to ensure that key data are prioritized and accurately analyzed, while optimizing resource allocation to obtain dynamic processing methods for each detection data.

[0089] Step 404, based on the preliminary road and bridge warning information, the abnormality elimination scheme logic is constructed for each detection data dynamic processing method to obtain the detection data dynamic processing strategy.

[0090] Among them, the logic construction of the abnormality elimination plan can be to integrate the dynamic processing methods of detection data of different types and importance according to the preliminary road and bridge warning information to form a systematic processing strategy.

[0091] Among them, the dynamic processing strategy of detection data can be a set of flexible processing methods formulated according to the type and importance of real-time road and bridge detection data, as well as preliminary warning information.

[0092] Specifically, based on the preliminary road and bridge warning information, (1) define the anomaly detection rules and trigger conditions for each type of data, (2) set up a comprehensive processing flow to combine the processing methods of different data, (3) set up alarm and priority processing mechanisms for abnormal situations, (4) record and analyze abnormal data to determine its possible causes and impact range, and (5) formulate and implement corresponding response and repair measures as the construction conditions of the abnormal elimination plan logic. Further, according to the above construction conditions, the dynamic processing methods of various detection data are integrated so that the dynamic processing methods of various detection data can be arbitrarily combined to form an abnormal elimination plan as the dynamic processing strategy of detection data.

[0093] Step 406, adjusting the correlation between the detection data dynamic processing strategies in the detection data dynamic processing strategy to obtain preliminary data processing strategy information.

[0094] Specifically, the interaction between the dynamic processing strategies of the detection data is analyzed, such as the impact of stress changes on vibration, the impact of temperature on displacement, etc. Then, the coordination mechanism of the dynamic processing strategies of the detection data is optimized to ensure that the processing of high-priority data does not interfere with the detection of other data, and to establish real-time correlation analysis between key data. For example, when the stress data is abnormal, the processing of vibration and displacement data is strengthened at the same time. Through these adjustments, a comprehensive and coordinated preliminary data processing strategy information is formed.

[0095] In this embodiment, by analyzing the data type and importance of each sub-data in the real-time road and bridge detection data, a corresponding dynamic processing method is formulated to ensure that each type of data is optimally processed. Using the preliminary road and bridge warning information, the abnormality elimination scheme logic is constructed to form a dynamic processing strategy for detection data, which can effectively identify and eliminate abnormal situations. The interrelationships of these dynamic processing strategies are further adjusted, the overall processing flow is optimized, and preliminary data processing strategy information is finally generated. This process improves the accuracy and efficiency of data processing, enhances the ability to quickly identify and respond to road and bridge anomalies, and thus significantly improves the safety monitoring and maintenance effects of roads and bridges.

[0096] In an exemplary embodiment, Figure 5 As shown, according to the data feature information of the real-time road and bridge detection data, the real-time road and bridge detection data is sent to the primary and secondary multi-level computing network for splitting calculation, and the early warning data processing decision information is returned, including steps 502 to 506. Among them:

[0097] Step 502: segment the real-time road and bridge detection data according to the data feature information of the real-time road and bridge detection data to obtain segmented road and bridge detection data.

[0098] The segmented road and bridge detection data may be data obtained by classifying and segmenting the road and bridge detection data collected in real time according to its characteristic information.

[0099] Specifically, the data feature information of the real-time road and bridge detection data is used to segment the real-time road and bridge detection data, including one or more of the following: (1) segmentation by time period, dividing the data into continuous time windows along the time axis; (2) segmentation by spatial position, classifying the data according to different sensor locations or road and bridge parts; (3) segmentation by feature type, grouping data with similar features, such as grouping all stress data into one group, grouping all vibration data into one group, etc., to obtain segmented road and bridge detection data.

[0100] Step 504: Use a data operation computing power algorithm to calculate the detection data computing power information corresponding to each segmented road and bridge detection data.

[0101] Among them, the data operation computing power algorithm can be an algorithm for calculating the resources required for segmenting road and bridge detection data for analysis.

[0102] Among them, the detection data computing power information can be data on resources required to split the road and bridge detection data for analysis.

[0103] Specifically, the data operation computing power algorithm is used to calculate the computing power required for analyzing each segmented road and bridge inspection data, and the required computing power data for the first time is obtained. For example, for vibration data, fast Fourier transform (FFT) is applied for frequency domain analysis; for stress data, regression analysis is used to calculate its change trend; for temperature data, time series analysis is used to predict its fluctuation. Then, parallel computing and optimization algorithms are considered to improve the computing efficiency and adjust the computing power data required for the first time to obtain the computing power information of the segmented data corresponding to each segmented road and bridge inspection data, including computing resource requirements, processing time, accuracy and performance indicators.

[0104] Step 506, according to the computing power information of each detection data, each segmented road and bridge detection data is sent to the cloud and each edge device of the primary and secondary multi-level computing network for analysis to obtain each detection data analysis result.

[0105] Among them, the inspection data analysis results can be the specific output obtained by processing and analyzing the segmented road and bridge inspection data, including the identification and quantification of key features, such as changes in stress, vibration, displacement and temperature, as well as the detection and evaluation of potential anomalies.

[0106] Specifically, the computing requirements and priorities of each group of segmented road and bridge inspection data are evaluated based on the computing power information of each inspection data. Then, data with high computing power requirements and high priority are sent to the cloud main-level computing network for in-depth analysis, such as complex model training and large-scale data processing; data with low computing power requirements and low priority are sent to edge devices for real-time processing and preliminary analysis, such as simple threshold detection and rapid response analysis. This allocation ensures efficient use of computing resources and timely data processing. Finally, the analysis results of the cloud and edge devices are integrated to obtain the comprehensive analysis results of each inspection data.

[0107] Step 508, integrating the analysis results of each detection data to obtain early warning data processing decision information.

[0108] Specifically, the comprehensive analysis results of different types of detection data are summarized, such as changes in stress, vibration, displacement and temperature and abnormal detection information, and the comprehensive analysis results of various detection data are comprehensively processed using data fusion technology. The relationship and influence between the results are analyzed, key features and trends are extracted, and unified early warning data processing decision information is generated, including specific risk assessments, warning levels, priority processing recommendations and response measures.

[0109] In this embodiment, by segmenting the data according to the data feature information of the real-time road and bridge detection data, it is ensured that each group of data is consistent and comparable, and the data is further used to run the computing power algorithm to calculate the computing power information of each segmented data, and optimize the allocation of computing resources. These data are distributed to the cloud and edge devices of the primary and secondary multi-level computing network for analysis, making full use of computing resources and improving the analysis speed and efficiency. Finally, the analysis results of each detection data are integrated to generate warning data processing decision information. This method significantly improves the accuracy and real-time performance of data processing, improves the effectiveness of anomaly detection and early warning, and ensures the timeliness and reliability of road and bridge monitoring and maintenance.

[0110] In an exemplary embodiment, Figure 6 As shown, a virtual-real fault scenario simulation is performed based on the early warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report, including steps 602 to 608. Among them:

[0111] Step 602: construct a structural health twin model and a scenario simulation twin model of the target detection road and bridge based on the historical road and bridge detection data and historical road and bridge environment data corresponding to the target detection road and bridge.

[0112] Among them, historical road and bridge inspection data can refer to detailed data on the structure and status of road and bridges collected regularly or continuously by various sensors and inspection equipment over a period of time in the past. These data include physical parameters such as stress, vibration, displacement, temperature, and environmental factors such as meteorological conditions and traffic flow.

[0113] Among them, historical road and bridge environmental data can refer to detailed data related to the environmental conditions around roads and bridges collected by environmental detection equipment over a period of time in the past. These data include meteorological conditions (such as temperature, humidity, rainfall, wind speed and direction), traffic flow, geological activities (such as earthquakes, ground subsidence), etc.

[0114] Among them, the structural health twin model can be a virtual digital model used to express the status of the road and bridge structure, which is constructed by using historical data through physical modeling, machine learning and other technologies.

[0115] Among them, the scenario simulation twin model can be a virtual digital model constructed by using historical data through simulation and modeling technology to simulate the abnormal performance of roads and bridges under different environmental conditions and scenarios and different response measures.

[0116] Specifically, the historical road and bridge inspection data and historical road and bridge environmental data corresponding to the target detection road and bridge are preprocessed and feature extracted, and the health status of the road and bridge is simulated through machine learning and physical modeling methods to construct a structural health twin model of the target detection road and bridge. At the same time, the abnormal relationship between the historical road and bridge environmental data and the historical road and bridge inspection data is used to simulate the abnormal performance of roads and bridges in different scenarios and different response measures, and to construct a scenario simulation twin model.

[0117] Step 604, according to the early warning data processing decision information and the real-time road and bridge environmental data, the model parameters and calculation logic of the structural health twin model and the scenario simulation twin model are adjusted to obtain the adjusted structural health twin model and the adjusted scenario simulation twin model.

[0118] Specifically, the existing parameters and calculation logic of the structural health twin model and the scenario simulation twin model are evaluated to identify the parts that need to be adjusted. The parameters of the structural health twin model and the scenario simulation twin model are calibrated to adapt to the key features and real-time road and bridge environmental data identified in the warning data processing decision information that need to be processed, such as adjusting the thresholds and response mechanisms of parameters such as stress, vibration, and temperature. At the same time, the calculation logic is updated to ensure that the model can more accurately simulate the actual situation and predict potential risks, and obtain the adjusted structural health twin model and the adjusted scenario simulation twin model.

[0119] Step 606 , input the real-time road and bridge inspection data into the adjusted structural health twin model to obtain real-time structural health status analysis information.

[0120] Among them, the real-time structural health status analysis information can be a detailed assessment result on the current health status of the road and bridge obtained by inputting real-time road and bridge detection data into the structural health twin model.

[0121] Specifically, the real-time road and bridge inspection data is input into the adjusted structural health twin model, and the input data is analyzed using the calculation logic of the adjusted model to simulate the health status of the road and bridge under the current inspection data. Through model calculation and comparison with historical data, the structural health status is identified and evaluated, including the changing trends and abnormal conditions of key indicators such as stress, vibration, and displacement, and real-time structural health status analysis information is generated.

[0122] Step 608 , input the real-time structural health status analysis information and the historical fault analysis data corresponding to the target detected road and bridge into the adjusted scenario simulation twin model to obtain a road and bridge abnormality analysis report.

[0123] Specifically, the real-time structural health status analysis information and the historical fault analysis data corresponding to the target detected road and bridge are input into the adjusted scenario simulation twin model, and the calculation logic of the adjusted twin model is used to simulate the abnormal performance of the road and bridge in different environments and scenarios and different response measures. By comparing and analyzing the real-time status and historical fault data, abnormal situations and risk points are identified, and their possible impact scope and severity are evaluated, and a detailed road and bridge abnormality analysis report is generated, including specific abnormality descriptions, cause analysis, impact assessments, and recommended repair measures.

[0124] In this embodiment, by utilizing the historical detection data and environmental data of the target detection road and bridge, a structural health twin model and a scenario simulation twin model are constructed to achieve accurate simulation and prediction of the road and bridge status. Combined with the early warning data processing decision information and real-time environmental data, the model parameters and calculation logic are adjusted to ensure the accuracy and real-time performance of the model. The real-time detection data is input into the adjusted structural health twin model to generate real-time structural health status analysis information, providing a detailed assessment of the current status of the road and bridge. This information is further input into the adjusted scenario simulation twin model with historical fault analysis data to generate a road and bridge abnormality analysis report. This process significantly improves the accuracy of road and bridge abnormality identification and prediction, provides a scientific basis for timely maintenance and repair, and thus enhances the safety and reliability of roads and bridges.

[0125] In an exemplary embodiment, Figure 7As shown, the real-time structural health status analysis information and the historical fault analysis data corresponding to the target detected road and bridge are input into the adjusted scene simulation twin model to obtain the road and bridge abnormality analysis report, including steps 702 to 706. Among them:

[0126] Step 702 , performing multi-scenario simulation on the real-time structural health status analysis information to obtain simulation data for each fault scenario.

[0127] Among them, the fault scenario simulation data can be the response data or fault data of the road and bridge under different fault conditions (such as earthquake, overload, temperature sudden change, etc.).

[0128] Specifically, the real-time structural health status analysis information is input into the multi-scenario simulation system of the adjusted scenario simulation twin model, and different fault simulation scenarios are set under the real-time structural health status analysis information, including various possible fault conditions such as earthquake, overload, temperature change, etc. Then, the adjusted structural health twin model is re-run under each fault simulation scenario to analyze the real-time and continuous response of the road and bridge under different stress, vibration and environmental conditions, optimize the real-time structural health status analysis information, and generate fault scenario simulation data under each fault simulation scenario.

[0129] Step 704 , based on the historical fault analysis data, the simulation data of each fault scenario is converted into reality to obtain the reality data of each fault scenario.

[0130] Among them, the fault scenario realization data can be data obtained by comparing the simulated fault scenario data with the historical fault analysis data, and applying a realization conversion algorithm to correct and optimize.

[0131] Specifically, a comparative analysis is performed on the simulation data of each fault scenario based on the historical fault analysis data to identify the actual features and patterns in the historical fault data. Combined with the reality conversion algorithm (an algorithm that adjusts the simulation data to be closer to the actual situation), the key indicators (such as stress, displacement, vibration, etc.) in the simulation data of each fault scenario are adjusted to values ​​that are closer to the actual situation. The actual distribution and changing trends of the historical data are further used to correct and optimize the adjusted fault scenario simulation data to obtain the reality data of each fault scenario.

[0132] Step 706: Generate a road and bridge abnormality analysis report based on the actualized data of each fault scenario.

[0133] Specifically, based on the actual data of each fault scenario, a comprehensive analysis is conducted on the actual data of the fault scenario under different fault scenarios to identify and evaluate various potential structural anomalies and risks. Then, the key indicator changes and impact range of the actual data of each fault scenario are summarized to determine the possible causes of the fault and their severity. Finally, these analysis results are summarized to form a detailed road and bridge anomaly analysis report.

[0134] In this embodiment, by performing multi-scenario simulation on real-time structural health status analysis information and converting the simulated data into reality, more realistic fault scenario data is generated, thereby forming a detailed road and bridge abnormality analysis report. This method helps to comprehensively and accurately predict the failure risks of roads and bridges under different environments and load conditions, and provide targeted early warning and response plans. This not only improves the efficiency and pertinence of road and bridge maintenance work, reduces blind maintenance and waste of resources, but also greatly improves the safety and reliability of road and bridge operation, ensuring the stability and smoothness of public transportation.

[0135] In an exemplary embodiment, Figure 8 As shown, according to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted, including steps 802 to 806. Among them:

[0136] Step 802, using the detection system self-healing algorithm, according to the road and bridge abnormality analysis report and the real-time road and bridge detection data, determine the system physical parameter adjustment information and the system algorithm parameter adjustment information.

[0137] Among them, the detection system self-healing algorithm can be an algorithm that analyzes real-time detection data and abnormal analysis reports, identifies system physical parameters and algorithm parameters that need to be adjusted, and automatically calculates and applies these adjustments to optimize system performance.

[0138] The system physical parameter adjustment information may be specific information of the physical parameters that need to be adjusted, determined and calculated according to real-time detection data and abnormality analysis reports during the self-healing process of the detection system.

[0139] The system algorithm parameter adjustment information may be specific information of the algorithm parameters that need to be adjusted, determined and calculated according to real-time detection data and anomaly analysis reports during the self-healing process of the detection system.

[0140] Specifically, the physical parameters and algorithm parameters of the current system are identified based on the abnormal analysis report of the road and bridge and the real-time road and bridge detection data; the key abnormal indicators in the abnormal analysis report of the road and bridge and the change trends in the real-time road and bridge detection data are compared, and the physical parameters (such as sensor position, sensitivity, etc.) and algorithm parameters (such as data processing algorithm, threshold setting, etc.) that need to be adjusted are analyzed and determined from the physical parameters and algorithm parameters of the current system. By simulating and optimizing the self-healing algorithm of the detection system, the specific parameter adjustment values ​​and adjustment methods are calculated, and the system physical parameter adjustment information and system algorithm parameter adjustment information are generated.

[0141] Step 804: Adjust the parameters related to the physical characteristics of the system in the system parameters according to the system physical parameter adjustment information.

[0142] Specifically, according to the system physical parameter adjustment information, the system physical characteristic parameters that need to be adjusted in the system parameters are identified, such as sensor position, sensitivity, and calibration value. Then, the setting interface or control module of the detection system is accessed, and the physical parameter adjustment information is input to adjust the parameters of the specific system physical characteristics, for example, repositioning the sensor to optimize its coverage, adjusting the sensitivity to improve data collection accuracy, or recalibrating the device to ensure accuracy.

[0143] Step 806, and, according to the system algorithm parameter adjustment information, adjust the parameters of the primary and secondary multi-level computing networks, the structural health twin model, and the scenario simulation twin model in the system parameters.

[0144] Specifically, according to the system algorithm parameter adjustment information, the algorithm parameters that need to be adjusted in the system parameters include the specific parameters of the primary and secondary multi-level computing networks, the structural health twin model, and the scenario simulation twin model. Then access the system configuration interface or the algorithm control module, enter the system algorithm parameter adjustment information to adjust the parameters of the specific model. For example, adjust the threshold and weight parameters of the multi-level computing network, optimize the stress and vibration analysis algorithm of the structural health twin model, or update the environmental variables and response mechanism of the scenario simulation twin model.

[0145] In this embodiment, by adopting the self-healing algorithm of the detection system, the adjustment information of the system physical parameters and algorithm parameters is determined according to the abnormal analysis report of the road and bridge and the real-time road and bridge detection data, and the physical characteristic parameters of the system and the parameters of the computing network and twin model are adjusted respectively. This process ensures that the detection system can be adaptively adjusted and optimized in actual operation, significantly improving the detection accuracy and response speed of the system. Through continuous automatic correction and optimization, the system can more accurately identify and warn of potential failures of roads and bridges, improve the efficiency and effectiveness of maintenance work, thereby extending the service life of roads and bridges and ensuring the safety and smoothness of public transportation.

[0146] In an exemplary embodiment, Fig. 9 As shown, generating a road and bridge repair instruction according to the road and bridge abnormality analysis report includes steps 902 to 914. Among them:

[0147] Step 902, identifying the road and bridge fault type and road and bridge fault level of the target detected road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data, and the historical road and bridge abnormality analysis report corresponding to the target detected road and bridge.

[0148] Among them, the road and bridge failure types can be the classification of various specific problems and defects that occur in the structure and function of the road and bridge. These failure types can include structural damage (such as cracks and fractures), material fatigue (such as corrosion and aging), mechanical failure (such as failure of bridge expansion joints), and environmental impacts (such as damage caused by earthquakes and floods).

[0149] Among them, the road and bridge fault level can be used to classify the problems of the road and bridge according to the severity of the fault to assess its impact on the structural safety and function. The fault level is usually divided into three levels: minor, moderate and severe. Minor faults may require regular inspection and small-scale repairs, moderate faults require timely maintenance and repairs, and severe faults may pose a major threat to the safety of the road and bridge, requiring immediate emergency measures.

[0150] Specifically, the abnormal analysis report of the road and bridge, the real-time road and bridge detection data and the historical abnormal analysis report of the road and bridge are comprehensively analyzed and compared to identify the key abnormal characteristics and change trends; the identified abnormalities are classified by combining the fault classification algorithm to determine the specific road and bridge fault type (such as structural damage, material fatigue, overload, etc.). At the same time, according to the key abnormal characteristics and the historical road and bridge abnormal analysis report, the severity of each road and bridge fault type is evaluated, and the road and bridge fault level is determined by classification (such as minor, moderate, and severe).

[0151] Step 904, determining the road and bridge repair method, road and bridge repair material and road and bridge repair process according to the road and bridge fault type, real-time road and bridge detection data and historical road and bridge abnormality analysis report.

[0152] Among them, road and bridge repair methods, road and bridge repair materials and road and bridge repair processes can be the specific methods, required materials and implementation technologies used in the road and bridge repair process. Repair methods include different repair and reinforcement methods, such as crack repair, structural reinforcement or replacement of damaged parts; repair materials refer to the specific materials used for repair, such as high-strength concrete, steel bars, polymers, etc.; repair processes refer to specific construction techniques and steps, such as grouting, welding, spraying, etc.

[0153] Specifically, according to the road and bridge fault type, real-time road and bridge detection data and historical road and bridge abnormal analysis reports, the specific fault type and severity are analyzed in detail. Combined with the analysis results and real-time detection data, the scope and impact of the current fault are evaluated, and the successful repair cases and methods in the historical abnormal analysis reports are further referred to to determine the most suitable road and bridge repair method (such as structural reinforcement, crack repair, material replacement, etc.). At the same time, on the basis of determining the road and bridge repair method, appropriate repair materials (such as high-strength concrete, steel bars, polymers, etc.) and specific repair processes (such as grouting, welding, spraying, etc.) are selected.

[0154] Step 906, simulate the road and bridge repair according to the road and bridge repair method, road and bridge repair material and road and bridge repair process to obtain road and bridge simulation repair data.

[0155] The road and bridge simulation repair data may be detailed data obtained by implementing predetermined repair methods, repair materials and repair processes in a simulation environment.

[0156] Specifically, according to the determined road and bridge repair method, road and bridge repair material and road and bridge repair process, the road and bridge model is constructed in the simulation environment and these repair parameters are applied to simulate the repair. The specific steps include: selecting the road and bridge repair method (such as crack repair or structural reinforcement), applying the selected road and bridge repair material (such as high-strength concrete or steel bars), and performing simulated construction according to the established road and bridge repair process (such as grouting or welding), generating road and bridge simulation repair data, and recording the changes in key indicators during the repair process, such as stress distribution, displacement adjustment and structural stability.

[0157] Step 908: Use the real-time road and bridge environment data to adjust the road and bridge simulation repair data to obtain adjusted road and bridge simulation repair data.

[0158] Specifically, the real-time road and bridge environmental data is input into the constructed road and bridge model of the simulation system, and the simulated repair process is rerun to reflect the impact of the actual environment on the repair effect. The key indicators in the road and bridge simulation repair data (such as stress distribution and displacement adjustment) are adjusted to match the current environmental conditions to ensure the feasibility and effectiveness of the repair plan under actual conditions, and the adjusted road and bridge simulation repair data is generated.

[0159] Step 910, when the difference between the road and bridge simulation repair data and the adjusted road and bridge simulation repair data is greater than the repair limit threshold, the road and bridge repair method, road and bridge repair material and road and bridge repair process are adjusted according to the real-time road and bridge environmental data to obtain the adjusted road and bridge repair method, adjusted road and bridge repair material and adjusted road and bridge repair process.

[0160] The repair limit threshold may be a maximum allowable difference range set when evaluating a road or bridge repair plan, and is used to measure whether the difference between the simulated repair data and the adjusted simulated repair data is reasonable.

[0161] Specifically, when the difference between the simulated road and bridge repair data and the adjusted simulated road and bridge repair data is greater than the repair limit threshold, the factors that cause the road and bridge repair methods, road and bridge repair materials, and road and bridge repair processes to perform poorly under actual environmental conditions are identified. Then, based on the real-time road and bridge environmental data, the repair plan is adjusted: a repair method that is more suitable for the current environment is selected (such as changing the reinforcement method), the repair material is replaced or optimized (such as selecting a material with better weather resistance), and the repair process is improved (such as adjusting the construction steps or technology), and the adjusted road and bridge repair method, adjusted road and bridge repair material, and adjusted road and bridge repair process are obtained.

[0162] Step 912, simulating the road and bridge repair according to the adjusted road and bridge repair method, adjusted road and bridge repair material, and adjusted road and bridge repair process to obtain road and bridge application repair data.

[0163] Among them, the road and bridge application repair data can be detailed data that can be used in actual applications after simulated repair using adjusted repair methods, repair materials and repair processes in a simulation environment.

[0164] Specifically, according to the determined adjusted road and bridge repair method, adjusted road and bridge repair materials, and adjusted road and bridge repair process, a road and bridge model is constructed in a simulation environment and these repair parameters are applied to simulate the repair. The specific steps include: implementing the adjusted road and bridge repair method (such as a new reinforcement method), using adjusted road and bridge repair materials or optimized repair materials (such as improved weather-resistant materials), and performing simulated construction according to the adjusted road and bridge repair process (such as updated construction technology and steps), generating road and bridge application repair data, and recording changes in key indicators during the repair process, such as stress distribution, displacement adjustment, and structural stability.

[0165] Step 914: Generate a road and bridge repair instruction according to the road and bridge application repair data and the road and bridge fault level.

[0166] Specifically, according to the road and bridge application repair data and the road and bridge fault level, the key indicators in the repair data and the severity of the fault level, as well as the specific repair measures and steps, are comprehensively analyzed, including the selection of appropriate repair methods, repair materials and repair processes. The above information is integrated into detailed repair instructions, clarifying the repair location, required resources, construction methods and safety measures, and generating road and bridge repair instructions to guide the repair unit to carry out actual repair work, ensure that the repair process is carried out scientifically, orderly and efficiently, and restore the safety and function of the road and bridge.

[0167] In this embodiment, the process of identifying the type and level of road and bridge faults, determining the repair plan in a refined manner, conducting multiple simulations and optimization adjustments, and finally generating accurate repair instructions improves the scientific nature and effectiveness of the repair plan. This method can not only accurately identify and classify faults, ensuring that each repair decision is based on detailed data and model analysis, but also reduce uncertainty and errors in actual repairs through repeated verification and adjustment, thereby improving repair efficiency, reducing maintenance costs, extending the service life of roads and bridges, and significantly improving the safety and reliability of public transportation infrastructure.

[0168] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0169] Based on the same inventive concept, the embodiment of the present application also provides a device for detecting anomalies of road and bridge parameters for implementing the above-mentioned method for detecting anomalies of road and bridge parameters. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of the device for detecting anomalies of one or more road and bridge parameters provided below can refer to the limitations of the above-mentioned method for detecting anomalies of road and bridge parameters, and will not be repeated here.

[0170] In an exemplary embodiment, Fig.10 As shown, a device for detecting abnormalities of road and bridge parameters is provided, comprising: a road and bridge condition analysis module 1002, a data processing decision module 1004, a data processing execution module 1006, a system parameter adjustment module 1008 and a repair instruction generation module 1010, wherein:

[0171] The road and bridge condition analysis module 1002 is used to analyze the abnormal conditions of the road and bridge according to the real-time road and bridge detection data corresponding to the target detected road and bridge and the real-time road and bridge environment data, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis report;

[0172] The data processing decision module 1004 is used to perform real-time data feature analysis on the real-time road and bridge detection data according to the preliminary road and bridge warning information when the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, and obtain warning data processing decision information; the real-time data feature analysis is realized through a primary and secondary multi-level computing network;

[0173] The data processing execution module 1006 is used to perform virtual-real fault scenario simulation based on the early warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report;

[0174] The system parameter adjustment module 1008 is used to adjust the system parameters of the road and bridge detection system corresponding to the target detection road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data;

[0175] The repair instruction generation module 1010 is used to detect the target detected road and bridge using the road and bridge detection system after adjusting the parameters, and generate a road and bridge repair instruction according to the road and bridge abnormality analysis report when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than the difference threshold; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge.

[0176] In one embodiment, the data processing decision module 1004 is also used to determine preliminary data processing strategy information based on preliminary road and bridge warning information and real-time road and bridge detection data; based on the data feature information of the real-time road and bridge detection data, the real-time road and bridge detection data is sent to the primary and secondary multi-level computing network for split calculation, and the warning data processing decision information is returned.

[0177] In one embodiment, the data processing decision module 1004 is also used to determine the dynamic processing method of each detection data according to the data type and importance corresponding to each sub-data in the real-time road and bridge detection data; according to the preliminary road and bridge warning information, the abnormal elimination plan logic of each detection data dynamic processing method is constructed to obtain the detection data dynamic processing strategy; the mutual correlation relationship of each detection data dynamic processing strategy in the detection data dynamic processing strategy is adjusted to obtain the preliminary data processing strategy information.

[0178] In one embodiment, the data processing decision module 1004 is also used to segment the real-time road and bridge detection data according to the data feature information of the real-time road and bridge detection data to obtain each segmented road and bridge detection data; use the data operation computing power algorithm to calculate the detection data computing power information corresponding to each segmented road and bridge detection data; send each segmented road and bridge detection data to the cloud and each edge device of the primary and secondary multi-level computing network for analysis according to the computing power information of each detection data to obtain each detection data analysis result; integrate the analysis results of each detection data to obtain early warning data processing decision information.

[0179] In one embodiment, the data processing execution module 1006 is also used to construct a structural health twin model and a scenario simulation twin model of the target detection road and bridge based on the historical road and bridge detection data and historical road and bridge environmental data corresponding to the target detection road and bridge; adjust the model parameters and calculation logic of the structural health twin model and the scenario simulation twin model according to the early warning data processing decision information and the real-time road and bridge environmental data to obtain the adjusted structural health twin model and the adjusted scenario simulation twin model; input the real-time road and bridge detection data into the adjusted structural health twin model to obtain real-time structural health status analysis information; input the real-time structural health status analysis information and the historical fault analysis data corresponding to the target detection road and bridge into the adjusted scenario simulation twin model to obtain a road and bridge abnormality analysis report.

[0180] In one embodiment, the data processing execution module 1006 is also used to perform multi-scenario simulation on the real-time structural health status analysis information to obtain simulation data for each fault scenario; perform reality conversion on the simulation data for each fault scenario based on historical fault analysis data to obtain realized data for each fault scenario; and generate a road and bridge abnormality analysis report based on the realized data for each fault scenario.

[0181] In one embodiment, the data processing execution module 1006 is also used to adopt the detection system self-healing algorithm to determine the system physical parameter adjustment information and the system algorithm parameter adjustment information according to the road and bridge abnormality analysis report and the real-time road and bridge detection data; according to the system physical parameter adjustment information, adjust the parameters in the system parameters related to the physical characteristics of the system; and, according to the system algorithm parameter adjustment information, adjust the parameters in the system parameters related to the primary and secondary multi-level computing networks, the structural health twin model, and the scenario simulation twin model.

[0182] In one embodiment, the repair instruction generation module 1010 is further used to identify the road bridge fault type and road bridge fault level of the target detection road bridge according to the road bridge fault analysis report, the real-time road bridge detection data and the historical road bridge fault analysis report corresponding to the target detection road bridge; determine the road bridge repair method, road bridge repair material and road bridge repair process according to the road bridge fault type, the real-time road bridge detection data and the historical road bridge fault analysis report; simulate the road bridge repair according to the road bridge repair method, the road bridge repair material and the road bridge repair process to obtain the road bridge simulation repair data; use the real-time road bridge environment data to simulate the road bridge repair data. Adjust to obtain adjusted road and bridge simulation repair data; when the difference between the road and bridge simulation repair data and the adjusted road and bridge simulation repair data is greater than the repair limit threshold, according to the real-time road and bridge environmental data, adjust the road and bridge repair method, road and bridge repair materials and road and bridge repair process respectively to obtain the adjusted road and bridge repair method, adjusted road and bridge repair materials and adjusted road and bridge repair process; simulate the road and bridge repair according to the adjusted road and bridge repair method, adjusted road and bridge repair materials and adjusted road and bridge repair process to obtain road and bridge application repair data; generate road and bridge repair instructions according to the road and bridge application repair data and the road and bridge fault level.

[0183] Each module in the above-mentioned abnormality detection device for road and bridge parameters can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0184] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting abnormalities of road and bridge parameters is implemented.

[0185] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0186] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0187] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0188] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0189] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0190] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0191] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0192] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting anomalies of road and bridge parameters, characterized in that: The method comprises: Analyze abnormal conditions of roads and bridges based on the real-time road and bridge detection data and real-time road and bridge environment data corresponding to the target detection road and bridge, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis reports; In the case where the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information, the real-time data feature analysis is performed on the real-time road and bridge detection data according to the preliminary road and bridge early warning information to obtain early warning data processing decision information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network; Perform virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report; According to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data, the system parameters of the road and bridge detection system corresponding to the target detection road and bridge are adjusted; Using the road and bridge detection system after adjusting the parameters to detect the target detection road and bridge, when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than the difference threshold, generating a road and bridge repair instruction according to the road and bridge abnormality analysis report; the road and bridge repair instruction is used to control the repair unit to repair the target detection road and bridge; Wherein, generating a road and bridge repair instruction according to the road and bridge abnormality analysis report includes: Identify the road and bridge fault type and road and bridge fault level of the target detected road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data, and the historical road and bridge abnormality analysis report corresponding to the target detected road and bridge; Determine the road and bridge repair method, road and bridge repair material and road and bridge repair process according to the road and bridge fault type, the real-time road and bridge detection data and the historical road and bridge abnormality analysis report; Performing simulated road and bridge repair according to the road and bridge repair method, the road and bridge repair material, and the road and bridge repair process to obtain simulated road and bridge repair data; Using the real-time road and bridge environment data, adjusting the road and bridge simulation repair data to obtain adjusted road and bridge simulation repair data; When the difference between the road and bridge simulation repair data and the adjusted road and bridge simulation repair data is greater than the repair limit threshold, the road and bridge repair method, the road and bridge repair material, and the road and bridge repair process are adjusted according to the real-time road and bridge environmental data to obtain an adjusted road and bridge repair method, an adjusted road and bridge repair material, and an adjusted road and bridge repair process; Simulate the road and bridge repair according to the adjusted road and bridge repair method, the adjusted road and bridge repair material, and the adjusted road and bridge repair process to obtain road and bridge application repair data; The road and bridge repair instruction is generated according to the road and bridge application repair data and the road and bridge fault level.

2. The method according to claim 1, characterized in that The performing of real-time data feature analysis on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information includes: Determining preliminary data processing strategy information according to the preliminary road and bridge warning information and the real-time road and bridge detection data; According to the data feature information of the real-time road and bridge detection data, the real-time road and bridge detection data is sent to the primary and secondary multi-level computing network for splitting calculation, and the early warning data processing decision information is returned.

3. The method according to claim 2, characterized in that The determining of preliminary data processing strategy information according to the preliminary road and bridge warning information and the real-time road and bridge detection data includes: Determine the dynamic processing mode of each detection data according to the data type and importance corresponding to each sub-data in the real-time road and bridge detection data; According to the preliminary road and bridge warning information, each of the detection data dynamic processing methods is logically constructed to eliminate abnormalities, and a detection data dynamic processing strategy is obtained; The mutual correlation relationship between the detection data dynamic processing strategies in the detection data dynamic processing strategy is adjusted to obtain the preliminary data processing strategy information.

4. The method according to claim 2, characterized in that: The method of sending the real-time road and bridge detection data to the primary and secondary multi-level computing network for splitting and computing according to the data feature information of the real-time road and bridge detection data, and returning the early warning data processing decision information includes: According to the data feature information of the real-time road and bridge detection data, the real-time road and bridge detection data is segmented to obtain segmented road and bridge detection data; Using a data operation computing power algorithm to calculate the detection data computing power information corresponding to each of the segmented road and bridge detection data; According to the computing power information of each detection data, each of the segmented road and bridge detection data is sent to the cloud and each edge device of the primary and secondary multi-level computing network for analysis to obtain the analysis results of each detection data; The analysis results of each of the detection data are integrated to obtain the warning data processing decision information.

5. The method according to claim 1, characterized in that The method of performing virtual-real combined fault scenario simulation based on the early warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report includes: Constructing a structural health twin model and a scenario simulation twin model of the target detection road bridge according to the historical road bridge detection data and historical road bridge environment data corresponding to the target detection road bridge; According to the early warning data processing decision information and the real-time road and bridge environment data, the model parameters and calculation logic of the structural health twin model and the scenario simulation twin model are adjusted to obtain an adjusted structural health twin model and an adjusted scenario simulation twin model; Inputting the real-time road and bridge inspection data into the adjusted structural health twin model to obtain real-time structural health status analysis information; The real-time structural health status analysis information and the historical fault analysis data corresponding to the target detected road and bridge are input into the adjusted scenario simulation twin model to obtain the road and bridge abnormality analysis report.

6. The method according to claim 5, characterized in that The real-time structural health status analysis information and the historical fault analysis data corresponding to the target detected road and bridge are input into the adjusted scenario simulation twin model to obtain the abnormal analysis report of the road and bridge, including: Perform multi-scenario simulation on the real-time structural health status analysis information to obtain simulation data for each fault scenario; According to the historical fault analysis data, each of the fault scenario simulation data is converted into reality to obtain the reality data of each fault scenario; The road and bridge abnormality analysis report is generated based on the actualized data of each fault scenario.

7. The method according to claim 5, characterized in that The adjusting of the system parameters of the road and bridge detection system corresponding to the target detection road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data comprises: Adopting the detection system self-healing algorithm, according to the road and bridge abnormality analysis report and the real-time road and bridge detection data, determining the system physical parameter adjustment information and the system algorithm parameter adjustment information; According to the system physical parameter adjustment information, adjusting parameters related to system physical characteristics in the system parameters; And, according to the system algorithm parameter adjustment information, the parameters of the system parameters regarding the primary and secondary multi-level computing network, the structural health twin model, and the scenario simulation twin model are adjusted.

8. A device for detecting abnormalities of road and bridge parameters, characterized in that: The device comprises: The road and bridge situation analysis module is used to analyze the abnormal situation of the road and bridge according to the real-time road and bridge detection data corresponding to the target detection road and bridge and the real-time road and bridge environment data, and obtain preliminary road and bridge warning information and preliminary road and bridge diagnosis report; A data processing decision module is used to perform real-time data feature analysis on the real-time road and bridge detection data according to the preliminary road and bridge warning information to obtain warning data processing decision information when the preliminary road and bridge diagnosis report triggers the road and bridge abnormal event trigger information; the real-time data feature analysis is implemented through a primary and secondary multi-level computing network; A data processing execution module, used to perform a virtual-real fault scenario simulation based on the warning data processing decision information and the preliminary road and bridge diagnosis report to obtain a road and bridge abnormality analysis report; A system parameter adjustment module, used to adjust the system parameters of the road and bridge detection system corresponding to the target detection road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data and the real-time road and bridge environment data; A repair instruction generating module is used to detect the target detected road and bridge using the road and bridge detection system after adjusting the parameters, and generate a road and bridge repair instruction according to the road and bridge abnormality analysis report when the difference between the road and bridge abnormality analysis report and the adjusted road and bridge abnormality analysis report is less than the difference threshold; the road and bridge repair instruction is used to control the repair unit to repair the target detected road and bridge; Wherein, generating a road and bridge repair instruction according to the road and bridge abnormality analysis report includes: Identify the road and bridge fault type and road and bridge fault level of the target detected road and bridge according to the road and bridge abnormality analysis report, the real-time road and bridge detection data, and the historical road and bridge abnormality analysis report corresponding to the target detected road and bridge; Determine the road and bridge repair method, road and bridge repair material and road and bridge repair process according to the road and bridge fault type, the real-time road and bridge detection data and the historical road and bridge abnormality analysis report; Performing simulated road and bridge repair according to the road and bridge repair method, the road and bridge repair material, and the road and bridge repair process to obtain simulated road and bridge repair data; Using the real-time road and bridge environment data, adjusting the road and bridge simulation repair data to obtain adjusted road and bridge simulation repair data; When the difference between the road and bridge simulation repair data and the adjusted road and bridge simulation repair data is greater than the repair limit threshold, the road and bridge repair method, the road and bridge repair material, and the road and bridge repair process are adjusted according to the real-time road and bridge environmental data to obtain an adjusted road and bridge repair method, an adjusted road and bridge repair material, and an adjusted road and bridge repair process; Simulate the road and bridge repair according to the adjusted road and bridge repair method, the adjusted road and bridge repair material, and the adjusted road and bridge repair process to obtain road and bridge application repair data; The road and bridge repair instruction is generated according to the road and bridge application repair data and the road and bridge fault level.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images