Road and bridge disease analysis and early warning method and system based on big data

Abstract

The invention discloses a road and bridge disease analysis and early warning method and system based on big data, and relates to the technical field of smart cities. Multiple groups of sensors are deployed, acquired related transverse wind load information data are associated with related vertical traffic load information data, and an external force load influence coefficient Xhz is constructed; after comparison, a preliminary early warning signal is sent out, related surface state data information and related vibration state data information of the current road and bridge are further collected and associated with an external force load influence coefficient Xhz, a comprehensive disease degree index Zbh is calculated through fitting in combination with a disease evaluation model, and the comprehensive disease degree index Zbh is compared with an evaluation threshold value K; according to the method and the system, the multi-dimensional data is acquired to judge whether the road bridge has a disease risk, a disease early warning instruction of a corresponding grade is generated and executed, and accurate identification and real-time early warning of the road bridge disease are realized through dynamic association and intelligent analysis of the multi-dimensional data.

Description

Technical Field

[0001] The present invention relates to the field of smart city technology, and in particular to a road and bridge disease analysis and early warning method and system based on big data. Background Art

[0002] Driven by the rapid development of information and communication technology, smart city construction has become one of the important directions of modern urban governance. As an important part of smart city infrastructure, road and bridge management plays a key role in ensuring smooth and safe urban traffic. In road and bridge management, the road and bridge disease monitoring and early warning system based on big data has gradually replaced the traditional manual inspection method with its real-time and intelligent advantages, and has become an important technical means to improve the efficiency of road and bridge management.

[0003] At present, traditional road and bridge disease monitoring and early warning still rely on regular manual inspections. Due to the limitations in real-time performance, data fusion analysis capabilities, and intelligence levels, this method has several significant shortcomings. First, traditional manual inspection methods are difficult to capture the dynamic impact of external loads on roads and bridges and the continuous monitoring of the operating status of roads and bridges. They also lack the ability to link and analyze environmental factors and traffic factors. These shortcomings will lead to the failure to timely identify and deal with early road and bridge diseases, causing the diseases to gradually expand into structural risks. Secondly, the accuracy of crack and vibration detection is limited, making it difficult to accurately identify diseases. The lack of in-depth analysis of multi-dimensional load data leads to delayed early warning of disease risks, affecting the scientific nature of road and bridge maintenance decisions. Especially in harsh environments, these shortcomings will further aggravate the safety hazards of road and bridge operation. Once a road and bridge fails in structure during operation, it will cause serious traffic interruptions and even casualties, causing huge economic losses and social impacts. Therefore, it is urgent to build a road and bridge disease analysis and early warning method and system based on big data to provide a more efficient and reliable solution for the safety management of roads and bridges. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a road and bridge disease analysis and early warning method and system based on big data, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a road and bridge disease analysis and early warning method based on big data, comprising the following steps: S1. Use multiple sets of sensors deployed to collect environmental wind status information around roads and bridges, obtain relevant lateral wind load information data, and collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges, and construct relevant vertical traffic load information data; S2. Correlate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; S3. After receiving the preliminary warning signal, relevant surface state data information and relevant vibration state data information of the current road bridge are collected, and associated with the external load influence coefficient Xhz, combined with the disease assessment model, to fit and construct a comprehensive disease degree index Zbh; S4. Preset an assessment threshold K and compare and analyze it with the comprehensive disease severity index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute a corresponding level of disease warning instruction.

[0006] Preferably, the specific steps of S1 include: S11. Deploy ultrasonic anemometers in the central area of ​​the road and bridge where there is no obstacle, embed a dynamic weighing system on the entrance and exit surfaces of the road and bridge, and set up multiple groups of traffic cameras above the road surface. Combined with wireless communication technology, connect the ultrasonic anemometers, dynamic weighing system and multiple groups of traffic cameras to a cloud database, which is used to store relevant pre-processed data information; wherein the dynamic weighing system integrates piezoelectric sensors, strain gauges and force sensors; S12. Using the deployed ultrasonic anemometer, collect the environmental wind state information around the road and bridge to obtain relevant lateral wind load information data, which includes the actual wind speed Vfs and the wind direction angle Qfx; and according to the driving conditions of various types of vehicles on the road and bridge, combined with the wirelessly connected dynamic weighing system and multiple groups of traffic camera equipment, collect the traffic load state information of the road and bridge, and construct relevant vertical traffic load information data, which includes the total traffic flow Vxc of various types of vehicles and the single axle load Fhz of different axles of various types of vehicles; S13. Preprocess the relevant data information in the relevant lateral wind load information data and the relevant vertical traffic load information data, and send the preprocessed relevant data information to the cloud database for storage; the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling.

[0007] Preferably, the specific steps of S2 include: S21. Using the three-dimensional model of the road and bridge established by fluid dynamics software, simulate and analyze the wind resistance performance of the road and bridge in the windward state, and combine the simulation analysis test results to obtain the wind resistance design coefficient Xfz, which is associated with the relevant lateral wind load information data. After dimensionless processing, the lateral wind load coefficient Xfh is constructed. The lateral wind load coefficient Xfh is calculated and obtained by the following formula: ; In the formula, represents the wind direction angle, is the actual wind speed, Wind direction angle The squared cosine of .

[0008] Preferably, the specific step S2 also includes: S22. Based on fatigue tests of road and bridge materials and the actual effects and design specifications of vehicle loads, a standard axle load Fh is constructed. By extracting features from relevant vertical traffic load information data, the standard axle load Fh is associated with the single axle load Fhz of different axles of various types of vehicles to obtain the single-vehicle equivalent axle load coefficient Xfx of the corresponding type of vehicle. The single-vehicle equivalent axle load coefficient Xfx of the i-th type of vehicle is calculated. i For example, it is obtained in the following way: ; In the formula, It is represented as the single axle load of the jth axle of the i-th type of vehicle, j=1, 2, 3, ..., n, and n represents the number of axles; S22, based on obtaining the single vehicle equivalent axle load coefficient Xfx of the i-th category vehicle i In this way, the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles are obtained respectively, and the total traffic flow Vxc of various types of vehicles in the relevant vertical traffic load information data is associated with the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles by extracting features from the relevant vertical traffic load information data, and the vertical traffic load coefficient Xzx is constructed. The vertical traffic load coefficient Xzx is calculated and obtained by the following formula: ; In the formula, It is expressed as the total traffic flow of the i-th category of vehicles, It is expressed as the single vehicle equivalent axle load coefficient of the i-th category vehicle, i=1, 2, 3, ..., m, and m represents the number of vehicle categories.

[0009] Preferably, the specific step S2 also includes: S23. By associating the lateral wind load coefficient Xfh with the vertical traffic load coefficient Xzx, after linear normalization processing and machine deep learning calculation, an external load influence coefficient Xhz is constructed. The external load influence coefficient Xhz is calculated and obtained by the following formula: ; In the formula, and They are respectively expressed as the weight values ​​of the lateral wind load coefficient Xfh and the vertical traffic load coefficient Xzx; S24, comparing and analyzing the external load influence coefficient Xhz with a preset threshold value to preliminarily determine whether the current road bridge is adversely affected by the external load. The specific comparison content is as follows: If the external load influence coefficient Xhz exceeds the threshold, it is preliminarily determined that the current road bridge is adversely affected by the external load, and a preliminary warning signal will be issued for further analysis; If the external load influence coefficient Xhz does not exceed the threshold, it can be preliminarily determined that the current road bridge is not adversely affected by the external load.

[0010] Preferably, the specific steps of S3 include: S31. After receiving the preliminary warning signal, multiple sets of sensors are used to collect relevant surface state data information and relevant vibration state data information of the road and bridge, and send them to the cloud database for storage. The specific process is as follows: S311, using multiple groups of traffic cameras set above the road bridge to collect surface state information of the road bridge, and combining image processing technology and edge detection algorithm to obtain relevant surface state data information, wherein the relevant surface state data information includes the length Dcd, width Dkd and depth Lsd of each crack; S312, using a high-sensitivity acceleration sensor fixed at the center of the road bridge to monitor the vibration state of the road bridge in real time, and performing frequency domain analysis on the vibration signal at each monitoring time point within the monitoring period through Fourier transform, and constructing relevant vibration state data information after feature extraction, the relevant vibration state data information includes the maximum value of the vibration frequency within the monitoring period ; S313, sending the acquired relevant surface state data information and relevant vibration state data information to a cloud database for storage via wireless transmission.

[0011] Preferably, the specific step S3 also includes: S32, analyzing the relevant surface state data information in the cloud database, and obtaining the surface disease coefficient Xbm after dimensionless processing, wherein the surface disease coefficient Xbm is obtained by the following formula: ; In the formula, is the length of the ath crack, is the width of the ath crack, is the depth of the ath crack, , and They are all expressed as weight values, a=1, 2, 3, ..., k, and k represents the number of cracks.

[0012] The specific steps of S3 also include: S33, the surface damage coefficient Xbm and the external load influence coefficient Xhz are associated with the relevant vibration state data information, and after dimensionless processing, combined with the damage assessment model, a comprehensive damage degree index Zbh is constructed by fitting. The comprehensive damage degree index Zbh is obtained by the following formula: ; In the formula, Expressed as the maximum vibration frequency, , and Both are expressed as weight values, and A is expressed as a correction constant.

[0013] Preferably, the specific steps of S4 include: S41, pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively judge whether there is a disease risk for the current road bridge under the influence of external force load, so as to generate and execute the corresponding level of disease warning instructions. The specific process is as follows: If the comprehensive disease severity index Zbh ≥ the assessment threshold K, it means that the current road and bridge are at risk of disease under the influence of external loads, and a first-level disease warning instruction is generated. The execution content is: immediately publish a notice of road and bridge traffic restrictions through the public platform, control the traffic at the entrance and exit of the road and bridge, and restrict the passage of overloaded vehicles; organize road and bridge structure experts and inspection teams to conduct on-site inspections, focusing on crack expansion, structural deformation and abnormal vibration; initiate an emergency maintenance plan and temporarily reinforce the discovered diseased parts; If the comprehensive damage degree index Zbh is less than the assessment threshold K, it means that there is no damage risk for the current road and bridge under the influence of external loads, and a second-level damage warning instruction is generated. The execution content is: continue to monitor the vibration frequency, crack expansion, traffic load and wind load of the road and bridge, upload the monitoring data to the cloud database in real time, conduct further assessment in combination with the damage assessment model, dynamically update the comprehensive damage degree index Zbh, include the road and bridge in the recent maintenance plan, arrange inspection and local repair work, and implement some vehicle flow and load restrictions on the road and bridge.

[0014] A road bridge disease analysis and early warning system based on big data, including a data acquisition module, a load analysis module, a disease assessment module and a grade early warning module; The data acquisition module is used to collect environmental wind status information around roads and bridges using multiple sets of deployed sensors to obtain relevant lateral wind load information data, and to collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges to construct relevant vertical traffic load information data; The load analysis module is used to associate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external force load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; The damage assessment module is used to collect relevant surface state data information and relevant vibration state data information of the current road bridge after receiving the preliminary warning signal, and associate them with the external load influence coefficient Xhz, and combine them with the damage assessment model to fit and construct a comprehensive damage degree index Zbh; The grade warning module is used to pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute the corresponding grade disease warning instructions.

[0015] The present invention provides a road and bridge disease analysis and early warning method and system based on big data, which has the following beneficial effects: (1) By integrating sensor networks, cloud computing and big data analysis technology, real-time monitoring of the operating status of roads and bridges, multi-dimensional data analysis and intelligent disease assessment are achieved. Compared with traditional manual detection methods, it has achieved significant improvements in real-time performance, data processing capabilities and intelligence levels, effectively solving the technical bottlenecks of traditional methods that are difficult to dynamically capture the impact of external loads and lack multi-dimensional data comprehensive analysis capabilities. By deploying multiple sets of sensors, it can sense the key parameters of the wind state, traffic load state, road and bridge surface state and vibration state around roads and bridges, and upload the collected data to the cloud database through wireless communication technology. Based on fluid dynamics simulation and deep learning algorithms, a comprehensive disease severity index Zbh is constructed, which can accurately evaluate the road and bridge under complex external loads. risk level; through dimensionless processing, feature extraction and fitting modeling, an in-depth analysis of the combined effects of wind load and traffic load is achieved, the comprehensive disease risk of roads and bridges is dynamically evaluated, and graded early warning instructions are generated according to different degrees of disease; its significant advantages are: on the one hand, through real-time dynamic monitoring and data correlation analysis, early-stage diseases of roads and bridges can be identified in time, thereby avoiding the expansion of diseases into structural risks; on the other hand, graded early warning and scientific decision-making support provide a strong guarantee for the rational allocation of road and bridge maintenance resources, reducing social and economic losses such as traffic interruptions and casualties caused by road and bridge failures; it provides a more efficient, intelligent and reliable technical solution for the management of roads and bridges in smart cities, which is of great significance to improving the operational safety and management efficiency of urban transportation infrastructure.

[0016] (2) In view of the fact that traditional methods are difficult to capture the impact of dynamic loads on roads and bridges, multiple sets of sensors, including ultrasonic anemometers, dynamic weighing systems and high-sensitivity accelerometers, are deployed at key locations on roads and bridges to perceive the external loads and structural responses of roads and bridges. By combining the big data platform with the cloud database, it is possible to collect and store environmental wind status and traffic load status information in real time, forming a high-precision, multi-dimensional data foundation. In particular, by constructing the relationship between the lateral wind load coefficient Xfh and the vertical traffic load coefficient Xzx, and using dimensionless processing and machine learning algorithms, an in-depth analysis of the combined effects of wind load and traffic load is achieved, effectively making up for the defects of single load analysis in traditional methods. In addition, by using data fitting and deep learning technology, the external load influence coefficient Xhz is constructed, and by comparing it with the preset threshold, a preliminary warning signal can be issued in a timely manner. Compared with the traditional regular manual inspection method, continuous dynamic monitoring of the operating status of roads and bridges is achieved, which improves the timeliness and accuracy of early disease identification.

[0017] (3) By introducing high-resolution image processing technology, edge detection algorithm and frequency domain analysis method, the measurement accuracy and analysis ability of disease parameters are improved; the relevant surface state data information of the length Dcd, width Dkd and depth Lsd of each crack of the road bridge is obtained by using traffic cameras combined with image processing technology, and the maximum vibration frequency of the road bridge is extracted by combining acceleration sensors and Fourier transform technology. , providing comprehensive data support for disease assessment; in addition, by constructing a comprehensive disease severity index Zbh, the surface disease information, external load influence and vibration state data are organically combined to form an accurate and quantitative disease risk assessment model. Based on this model, it is possible to generate graded disease warning instructions according to the assessment results, and put forward scientific maintenance suggestions and emergency reinforcement plans for different risk levels, thereby effectively avoiding the risk of road and bridge structure failure caused by insufficient monitoring accuracy and delayed decision-making in traditional methods. This integrated and intelligent assessment method not only improves the accuracy of road and bridge disease monitoring, but also provides a scientific basis for the efficient allocation of maintenance resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of a process flow of a road and bridge disease analysis and early warning method based on big data of the present invention; Figure 2 This is a block diagram of a road and bridge disease analysis and early warning system based on big data in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1: Please refer to Figure 1 The present invention provides a road and bridge disease analysis and early warning method based on big data, comprising the following steps: S1. Use multiple sets of sensors deployed to collect environmental wind status information around roads and bridges, obtain relevant lateral wind load information data, and collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges, and construct relevant vertical traffic load information data; S2. Correlate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; S3. After receiving the preliminary warning signal, relevant surface state data information and relevant vibration state data information of the current road bridge are collected, and associated with the external load influence coefficient Xhz, combined with the disease assessment model, to fit and construct a comprehensive disease degree index Zbh; S4. Preset an assessment threshold K and compare and analyze it with the comprehensive disease severity index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute a corresponding level of disease warning instruction.

[0021] In this embodiment, multiple sets of sensors are deployed to collect multi-dimensional data of environmental wind load and traffic load in real time, and the monitoring data are dimensionlessly processed and correlated with big data technology to construct the external load influence coefficient Xhz. In combination with the collected relevant surface state data information and relevant vibration state data information, a comprehensive disease degree index Zbh is constructed, thereby realizing dynamic monitoring and intelligent evaluation of road and bridge diseases. Compared with the traditional regular manual detection method, this method effectively overcomes the limitations of insufficient real-time performance, one-sided monitoring data, and lack of multi-dimensional load linkage analysis, and can capture the state changes of roads and bridges under complex load environments, especially in early disease identification. It has significant advantages in identification and dynamic risk warning. In addition, through high-resolution image processing technology and frequency domain analysis methods, the detection accuracy of crack and vibration disease parameters has been improved, providing more reliable data support for road and bridge disease assessment. Through the precise division of risk levels and scientific graded warning instructions, it not only optimizes the maintenance resource allocation of roads and bridges, but also effectively avoids serious consequences such as traffic interruption and casualties caused by failure to deal with disease risks in a timely manner. This innovative method improves the efficiency, intelligence level and scientific decision-making of road and bridge disease monitoring, and provides an efficient and accurate solution for the long-term safety management of roads and bridges in smart cities.

[0022] Example 2: Please refer to Figure 1 , specifically: S1 specific steps include: S11. Deploy ultrasonic anemometers in the central area of ​​the road and bridge where there is no obstacle, embed a dynamic weighing system on the entrance and exit surfaces of the road and bridge, and set up multiple groups of traffic cameras above the road surface. Combined with wireless communication technology, connect the ultrasonic anemometers, dynamic weighing system and multiple groups of traffic cameras to a cloud database, which is used to store relevant pre-processed data information; wherein the dynamic weighing system integrates piezoelectric sensors, strain gauges and force sensors; S12. Using the deployed ultrasonic anemometer, collect the environmental wind state information around the road and bridge to obtain relevant lateral wind load information data, which includes the actual wind speed Vfs and the wind direction angle Qfx; and according to the driving conditions of various types of vehicles on the road and bridge, combined with the wirelessly connected dynamic weighing system and multiple groups of traffic camera equipment, collect the traffic load state information of the road and bridge, and construct relevant vertical traffic load information data, which includes the total traffic flow Vxc of various types of vehicles and the single axle load Fhz of different axles of various types of vehicles; It should be noted that the wind direction angle Qfx represents the angle between the wind direction and the longitudinal axis of the road bridge. It is an important parameter for calculating the lateral wind load and directly affects the directional component of the wind force on the road bridge. The wind speed and wind direction data collected by the ultrasonic anemometer are combined with the azimuth sensor to accurately calculate the angle, providing a basis for the calculation of the lateral wind load coefficient Xfh. The total traffic flow Vxc represents the total number of various types of vehicles passing through the road bridge in unit time. It is an important indicator for evaluating the impact of traffic loads and reflects the vertical pressure of traffic flow on the road bridge. The traffic flow is recorded in real time by traffic cameras deployed on the road bridge and is obtained by combining statistics with the vehicle classification algorithm. The uniaxial load Fhz represents the vertical load imposed by a single axle of the vehicle on the road bridge. It is the core parameter for the vertical load analysis of the road bridge and is obtained by real-time detection of the piezoelectric sensor, strain gauge and force sensor in the dynamic weighing system. These parameters act together on the road bridge load analysis, providing accurate data support for the comprehensive impact assessment of lateral wind load and vertical traffic load, and then used for disease warning and road bridge health management.

[0023] S13. Preprocess the relevant data information in the relevant lateral wind load information data and the relevant vertical traffic load information data, and send the preprocessed relevant data information to the cloud database for storage; the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling.

[0024] In this embodiment, by deploying ultrasonic anemometers, dynamic weighing systems and multiple groups of traffic cameras at key locations of roads and bridges, real-time data collection and monitoring of environmental wind status information and traffic load status information are achieved, providing a high-precision data basis for road and bridge disease analysis; combined with wireless communication technology and cloud database, the limitations of traditional manual detection in real-time and data fusion analysis capabilities are effectively solved, making dynamic monitoring of road and bridge operation status possible, especially in the data preprocessing stage, through denoising, filling missing values ​​and data smoothing operations, the data quality and reliability are further improved, thereby significantly improving the ability to capture early signs of road and bridge diseases. Compared with traditional detection methods, it can not only accurately quantify the changes in external force loads, but also efficiently process the correlation between multi-dimensional data, laying a solid foundation for building a scientific disease assessment model; this innovative collection and processing method effectively solves the problem of insufficient linkage analysis capabilities for road and bridge load states, provides important guarantees for timely identification and accurate early warning of disease risks, and improves the intelligent level and scientific decision-making capabilities of road and bridge management.

[0025] Example 3: Please refer to Figure 1 , specifically: S2 specific steps include: S21. Using the three-dimensional model of the road and bridge established by fluid dynamics software, simulate and analyze the wind resistance performance of the road and bridge in the windward state, and combine the simulation analysis test results to obtain the wind resistance design coefficient Xfz, which is associated with the relevant lateral wind load information data. After dimensionless processing, the lateral wind load coefficient Xfh is constructed. The lateral wind load coefficient Xfh is calculated and obtained by the following formula: ; In the formula, Indicates the wind direction angle, specifically the angle between the wind direction and the longitudinal axis of the road bridge. is the actual wind speed, Wind direction angle The squared cosine of .

[0026] It should be noted that the wind resistance design coefficient Xfz is an important parameter for measuring the wind resistance performance of road bridges under wind loads. It indicates the size of the air resistance that road bridges are subject to in the windward state. It is closely related to the geometric shape, structural characteristics, and ancillary facilities of guardrails and sound insulation screens of road bridges. The role of the wind resistance design coefficient Xfz is to provide basic data for the quantitative calculation of lateral wind loads, so as to accurately evaluate the impact of wind on the safety of road bridge structures, which is particularly important in complex wind environments. The acquisition method usually includes using fluid dynamics software to establish a three-dimensional model of the road bridge, simulating the distribution characteristics of wind flow on the surface of the road bridge, and calculating the wind pressure and wind force components of different parts of the road bridge to obtain the wind resistance coefficient; at the same time, the scaled model of the road bridge can also be tested through wind tunnel tests. By measuring the wind force and converting it into the resistance coefficient at the actual size, the wind resistance design coefficient Xfz is the key input for the calculation of lateral wind loads in the road bridge disease analysis, and provides a scientific basis for the safety assessment of road bridges under the combined action of multiple environmental loads.

[0027] Specifically, the specific steps of S2 also include: S22. Based on fatigue tests of road and bridge materials and the actual effects and design specifications of vehicle loads, a standard axle load Fh is constructed. By extracting features from relevant vertical traffic load information data, the standard axle load Fh is associated with the single axle load Fhz of different axles of various types of vehicles to obtain the single-vehicle equivalent axle load coefficient Xfx of the corresponding type of vehicle. The single-vehicle equivalent axle load coefficient Xfx of the i-th type of vehicle is calculated. i For example, it is obtained in the following way: ; In the formula, It is represented as the single axle load of the jth axle of the i-th type of vehicle, j=1, 2, 3, ..., n, and n represents the number of axles; S22, based on obtaining the single vehicle equivalent axle load coefficient Xfx of the i-th category vehicle i In this way, the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles are obtained respectively, and the total traffic flow Vxc of various types of vehicles in the relevant vertical traffic load information data is associated with the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles by extracting features from the relevant vertical traffic load information data, and the vertical traffic load coefficient Xzx is constructed. The vertical traffic load coefficient Xzx is calculated and obtained by the following formula: ; In the formula, It is expressed as the total traffic flow of the i-th category of vehicles, It is expressed as the single vehicle equivalent axle load coefficient of the i-th category vehicle, i=1, 2, 3, ..., m, and m represents the number of vehicle categories.

[0028] It should be noted that the standard axle load Fh is an important reference value used to measure the damage caused by vehicles to road bridge structures in road bridge design and disease assessment. It is usually expressed as a standardized single-axle load value, and the international standard value is 8.16 tons. Its role is to uniformly evaluate the cumulative damage effects of different vehicle types and axle load distributions on roads and bridges, making complex traffic load analysis more simplified and standardized. The acquisition method is based on fatigue experiments on road bridge materials. By observing the fatigue life of the structure through multiple loadings of different axle loads, and combining the actual distribution characteristics of vehicle loads and experimental research results, a reference value that can represent the design and assessment of roads and bridges is determined. In addition, the standard axle load Fh is also calibrated and revised according to relevant design specifications to ensure that it is consistent with actual traffic load conditions. The standard axle load Fh is widely used in equivalent axle load calculations and vertical traffic load analysis, providing an important basis for quantitative analysis of the operating status of roads and bridges and disease early warning.

[0029] Specifically, the specific steps of S2 also include: S23. By associating the lateral wind load coefficient Xfh with the vertical traffic load coefficient Xzx, after linear normalization processing and machine deep learning calculation, an external load influence coefficient Xhz is constructed. The external load influence coefficient Xhz is calculated and obtained by the following formula: ; In the formula, and They are respectively expressed as the weight values ​​of the lateral wind load coefficient Xfh and the vertical traffic load coefficient Xzx; S24, comparing and analyzing the external load influence coefficient Xhz with a preset threshold value to preliminarily determine whether the current road bridge is adversely affected by the external load. The specific comparison content is as follows: If the external load influence coefficient Xhz exceeds the threshold, it is preliminarily determined that the current road bridge is adversely affected by the external load, and a preliminary warning signal will be issued for further analysis; If the external load influence coefficient Xhz does not exceed the threshold, it can be preliminarily determined that the current road bridge is not adversely affected by the external load.

[0030] In this embodiment, based on fluid dynamics and multi-source data analysis technology, the dynamic effects of external force loads on roads and bridges are deeply modeled and analyzed, and accurate risk assessment and preliminary warning under the combined effects of lateral wind loads and vertical traffic loads are achieved; first, the three-dimensional model of the road and bridge constructed by fluid dynamics software is used to simulate and analyze the wind resistance performance of the road and bridge in the windward state, and the wind resistance design coefficient Xfz is obtained, and the lateral wind load coefficient Xfh is constructed in combination with the actual wind speed Vfs and wind direction angle Qfx data; this process effectively solves the one-sided and inaccurate wind load analysis in traditional methods. The lack of comprehensive calculation of dynamic wind components provides a scientific basis for the evaluation of wind load impact on roads and bridges in complex environments; secondly, based on material fatigue experiments, actual vehicle load effects and design specifications, a standard axle load FhF is constructed, and the single-axle load Fhz of different axles of various types of vehicles is extracted and calculated to obtain the single-vehicle equivalent axle load coefficient Xfx of the corresponding category of vehicles; further, by correlating with the total traffic flow Vxc of various categories of vehicles, a vertical traffic load coefficient Xzx is constructed, which accurately reflects the vertical load of roads and bridges under actual traffic loads. Loading conditions; finally, by normalizing the lateral wind load coefficient Xfh and the vertical traffic load coefficient Xzx, and introducing the machine deep learning algorithm, the external load influence coefficient Xhz was fitted and constructed. The external load influence coefficient Xhz integrates multi-dimensional load information, effectively making up for the lack of complex external force linkage analysis in the traditional monitoring method. By comparing the external load influence coefficient Xhz with the preset threshold, it can timely determine whether the current road and bridge are adversely affected by the external load, and issue a preliminary warning signal; this early warning mechanism improves the real-time and intelligent level of road and bridge disease monitoring, and effectively solves the problem that traditional methods are difficult to capture the dynamic load impact of roads and bridges and the early warning lag; especially when the operation status of roads and bridges is complex or the environmental conditions are harsh, it can quickly identify potential risks and provide scientific preliminary diagnosis basis for road and bridge management departments; Overall, the innovation of this process in load modeling, risk assessment and preliminary warning response not only effectively reduces the threat of road and bridge disease risks to traffic safety, but also significantly optimizes the resource allocation of road and bridge maintenance, and provides strong technical support for road and bridge management in smart cities.

[0031] Example 4: Please refer to Figure 1 , specifically: S3 specific steps include: S31. After receiving the preliminary warning signal, multiple sets of sensors are used to collect relevant surface state data information and relevant vibration state data information of the road and bridge, and send them to the cloud database for storage. The specific process is as follows: S311, using multiple groups of traffic cameras set above the road bridge to collect surface state information of the road bridge, and combining image processing technology and edge detection algorithm to obtain relevant surface state data information, wherein the relevant surface state data information includes the length Dcd, width Dkd and depth Lsd of each crack; It should be noted that the length Dcd, width Dkd and depth Lsd of each crack in the relevant surface status data information are important indicators for evaluating the degree of damage to road and bridge structures. Their role is to comprehensively quantify the surface diseases of roads and bridges, and provide data support for disease risk assessment and maintenance decisions. The specific acquisition method is to use traffic cameras to capture high-definition images in real time, and use image processing algorithms, including edge detection and morphological analysis, to identify crack areas and extract length and width information; the depth is acquired by combining texture analysis and optical measurement technology; this process realizes efficient and non-contact monitoring of road and bridge surface diseases, and improves detection accuracy and efficiency.

[0032] S312, using a high-sensitivity acceleration sensor fixed at the center of the road bridge to monitor the vibration state of the road bridge in real time, and performing frequency domain analysis on the vibration signal at each monitoring time point within the monitoring period through Fourier transform, and constructing relevant vibration state data information after feature extraction, the relevant vibration state data information includes the maximum value of the vibration frequency within the monitoring period ; It should be noted that the maximum vibration frequency during the monitoring period It indicates the highest frequency of the vibration response of the road bridge during the monitoring period. It is an important parameter for evaluating the dynamic characteristics and structural health of the road bridge. Its function is to reflect the dynamic stability of the road bridge under the action of external force loads. Abnormal vibration frequency indicates that there are structural defects and potential risks in the road bridge. It is obtained through high-sensitivity acceleration sensors deployed at the center of the road bridge. The sensors monitor the vibration signals of the road bridge in real time, and use Fourier transform to convert the time domain signals into frequency domain signals, from which the maximum vibration frequency is extracted. This indicator provides key data support for the vibration status analysis and disease assessment of road bridges, and helps to identify existing structural problems in a timely manner.

[0033] S313, sending the acquired relevant surface state data information and relevant vibration state data information to a cloud database for storage via wireless transmission.

[0034] In this embodiment, through the coordinated work of multiple groups of sensors, after receiving the preliminary warning signal, in-depth and accurate data collection and analysis are carried out on the surface state and vibration state of the road bridge; by using the traffic camera installed above the road bridge, combined with image processing technology and edge detection algorithm, the length Dcd, width Dkd and depth Lsd parameters of each crack on the surface of the road bridge can be efficiently and accurately extracted, realizing the automated and high-precision monitoring of the surface diseases of the road bridge, and effectively making up for the shortcomings of the traditional manual detection method in crack detection accuracy and efficiency. At the same time, through the high-sensitivity acceleration sensor fixed at the center of the road bridge, the vibration state of the road bridge is monitored in real time, and the vibration signal is analyzed in the frequency domain using Fourier transform technology to extract the maximum value of the vibration frequency The acquisition of this vibration state data effectively solves the problem of insufficient dynamic response monitoring of roads and bridges in traditional methods, and provides dynamic parameter support for road and bridge health assessment. In addition, by wirelessly transmitting the collected surface state and vibration state data to the cloud database for centralized storage and management, real-time and efficient integration of data is achieved. Compared with the traditional method that relies on manual recording, this method not only improves the efficiency and reliability of data collection, but also provides high-quality data support for subsequent disease assessment, thereby optimizing the scientific decision-making process of road and bridge maintenance.

[0035] Example 5: Please refer to Figure 1 , specifically: S3 specific steps also include: S32, analyzing the relevant surface state data information in the cloud database, and obtaining the surface disease coefficient Xbm after dimensionless processing, wherein the surface disease coefficient Xbm is obtained by the following formula: ; In the formula, is the length of the ath crack, is the width of the ath crack, is the depth of the ath crack, , and They are all expressed as weight values, a=1, 2, 3, ..., k, and k represents the number of cracks.

[0036] Specifically, the S3 specific steps also include: S33, the surface damage coefficient Xbm and the external load influence coefficient Xhz are associated with the relevant vibration state data information, and after dimensionless processing, combined with the damage assessment model, a comprehensive damage degree index Zbh is constructed by fitting. The comprehensive damage degree index Zbh is obtained by the following formula: ; In the formula, Expressed as the maximum vibration frequency, , and Both are expressed as weight values, and A is expressed as a correction constant.

[0037] In this embodiment, by comprehensively analyzing the surface state, external force load and vibration state stored in the cloud database, accurate quantification and risk assessment of the degree of road and bridge damage are achieved; using the surface damage coefficient Xbm, the length Dcd, width Dkd and depth Lsd parameters of each crack on the surface of the road and bridge are comprehensively evaluated according to the weights, and the severity of the surface damage is quantified, which effectively solves the problem of single analysis of damage parameters and lack of unified evaluation standards in traditional methods; at the same time, the surface damage coefficient Xbm, the external force load influence coefficient Xhz and the maximum vibration frequency Pzp max The comprehensive disease severity index Zbh was constructed through dimensionless processing and disease assessment model fitting. The comprehensive disease severity index Zbh can reflect the comprehensive disease risk of roads and bridges under multi-dimensional loads, and provides a scientific basis for the intelligent diagnosis and quantitative management of road and bridge diseases. Compared with the traditional method that only relies on manual detection or single parameter evaluation, it realizes the deep integration and comprehensive quantification of multi-source data, and provides a more accurate analysis method for the overall evaluation of the health status of roads and bridges. In addition, by scientifically adjusting the weight values ​​and correction constants in the model, it can flexibly adapt to different road and bridge structures and environmental conditions to ensure the efficiency and reliability of the evaluation results. This evaluation method based on the comprehensive disease severity index Zbh not only improves the timeliness and accuracy of road and bridge disease risk identification, but also optimizes the priority ranking of road and bridge maintenance, and provides strong decision-making support for road and bridge management departments to formulate scientific maintenance and reinforcement plans.

[0038] Example 6: Please refer to Figure 1 , specifically: S4 specific steps include: S41, pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively judge whether there is a disease risk for the current road bridge under the influence of external force load, so as to generate and execute the corresponding level of disease warning instructions. The specific process is as follows: If the comprehensive disease severity index Zbh ≥ the assessment threshold K, it means that the current road and bridge are at risk of disease under the influence of external loads, and a first-level disease warning instruction is generated. The execution content is: immediately publish a notice of road and bridge traffic restrictions through the public platform, control the traffic at the entrance and exit of the road and bridge, and restrict the passage of overloaded vehicles; organize road and bridge structure experts and inspection teams to conduct on-site inspections, focusing on crack expansion, structural deformation and abnormal vibration; initiate an emergency maintenance plan and temporarily reinforce the discovered diseased parts; If the comprehensive damage degree index Zbh is less than the assessment threshold K, it means that there is no damage risk for the current road and bridge under the influence of external loads, and a second-level damage warning instruction is generated. The execution content is: continue to monitor the vibration frequency, crack expansion, traffic load and wind load of the road and bridge, upload the monitoring data to the cloud database in real time, conduct further assessment in combination with the damage assessment model, dynamically update the comprehensive damage degree index Zbh, include the road and bridge in the recent maintenance plan, arrange inspection and local repair work, and implement some vehicle flow and load restrictions on the road and bridge.

[0039] In this embodiment, by setting the evaluation threshold K and comparing and analyzing it with the comprehensive disease degree index Zbh, a graded early warning and scientific response to the disease risk of roads and bridges is achieved; for different disease risk levels, corresponding first-level disease warning instructions and second-level disease warning instructions are generated and differentiated processing is implemented; for the first-level disease warning instructions, traffic restriction announcements can be quickly issued, vehicle load limit measures can be implemented, and road and bridge structure experts can be organized to conduct on-site inspections of crack expansion, structural deformation and vibration anomalies, and emergency maintenance plans can be immediately initiated to effectively curb the further deterioration of the disease; this response mechanism effectively solves the problems of risk warning lag and single response measures in traditional methods, ensuring the safe operation of roads and bridges under high-risk conditions; for the second-level disease warning instructions, the comprehensive disease degree is dynamically updated by continuously monitoring the vibration frequency, crack expansion, traffic load and wind load of roads and bridges. Index Zbh, and include roads and bridges in the recent maintenance plan, arrange routine inspections and local repairs, and implement flow or load restrictions on some vehicles; such a hierarchical management method not only improves the accuracy and scientificity of road and bridge maintenance, but also avoids excessive consumption of resources and accumulation of safety hazards; compared with traditional single assessment or static early warning methods, this hierarchical early warning mechanism combines big data technology and dynamic assessment models to achieve continuous tracking and intelligent response to disease risks, especially under environmental conditions with complex external force loads, and can quickly make accurate judgments, which not only ensures the safety of road and bridge operation, but also optimizes the efficiency of maintenance decisions; by scientifically dividing risk levels and implementing targeted response measures, it reduces the risks of traffic interruption, economic losses and casualties caused by road and bridge diseases, and provides a set of efficient, intelligent and reliable solutions for smart city road and bridge management.

[0040] Example 7: Please refer to Figure 1 and Figure 2 ,Specifically: A road and bridge disease analysis and early warning system based on big data, including a data acquisition module, a load analysis module, a disease assessment module and a grade early warning module; The data acquisition module is used to collect environmental wind status information around roads and bridges using multiple sets of deployed sensors to obtain relevant lateral wind load information data, and to collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges to construct relevant vertical traffic load information data; The load analysis module is used to associate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external force load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; The damage assessment module is used to collect relevant surface state data information and relevant vibration state data information of the current road bridge after receiving the preliminary warning signal, and associate them with the external load influence coefficient Xhz, and combine them with the damage assessment model to fit and construct a comprehensive damage degree index Zbh; The grade warning module is used to pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute the corresponding grade disease warning instructions.

[0041] In this embodiment, a full-process, intelligent road and bridge disease monitoring and early warning system is constructed through the collaborative work of the data acquisition module, the load analysis module, the disease assessment module and the grade warning module; multiple sets of sensors are used to collect environmental wind status and traffic load information in real time, effectively overcoming the limitations of traditional manual detection methods in real time and comprehensive data acquisition, especially in the comprehensive analysis of lateral wind loads and vertical traffic loads, improving the monitoring ability of dynamic changes of external loads, constructing the external load influence coefficient Xhz through dimensionless processing and data fitting technology, and realizing preliminary early warning based on preset thresholds, effectively solving the problem that it is difficult to capture the complex load linkage effect in traditional methods; the disease assessment module further combines relevant surface state data information and relevant vibration state data information, and uses the disease assessment model to fit and construct a comprehensive disease degree index Zbh, realizing The precise quantification and intelligent analysis of road and bridge disease risks effectively overcome the defects of single parameter evaluation and insufficient analysis accuracy in traditional methods; through the hierarchical response mechanism of the graded warning module, the system can intelligently generate differentiated warning instructions according to the degree of disease, and provide scientific decision-making support from emergency reinforcement to routine maintenance, which not only ensures the safety of road and bridge operation, but also optimizes the allocation efficiency of maintenance resources; compared with the traditional static detection and delayed warning mode, this system takes big data technology as the core, and builds a closed-loop system of real-time monitoring, comprehensive analysis and intelligent decision-making, which effectively fills many technical gaps in road and bridge monitoring and early warning; its innovative modular design not only improves the comprehensiveness and accuracy of road and bridge disease monitoring, but also significantly enhances the ability to cope with complex environments and sudden risks, providing efficient, accurate and sustainable technical solutions for smart city road and bridge management.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A road and bridge disease analysis and early warning method based on big data, characterized by: The following steps are involved: S1. Use multiple sets of sensors deployed to collect environmental wind status information around roads and bridges, obtain relevant lateral wind load information data, and collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges, and construct relevant vertical traffic load information data; S2. Correlate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; S3. After receiving the preliminary warning signal, relevant surface state data information and relevant vibration state data information of the current road bridge are collected, and associated with the external load influence coefficient Xhz, combined with the disease assessment model, to fit and construct a comprehensive disease degree index Zbh; S4. Preset an assessment threshold K and compare and analyze it with the comprehensive disease severity index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute a corresponding level of disease warning instruction.

2. The road and bridge disease analysis and early warning method based on big data according to claim 1 is characterized by: The specific steps of S1 include: S11. Deploy ultrasonic anemometers in the central area of ​​the road and bridge where there is no obstacle, embed a dynamic weighing system on the entrance and exit surfaces of the road and bridge, and set up multiple groups of traffic cameras above the road surface. Combined with wireless communication technology, connect the ultrasonic anemometers, dynamic weighing system and multiple groups of traffic cameras to a cloud database, which is used to store relevant pre-processed data information; wherein the dynamic weighing system integrates piezoelectric sensors, strain gauges and force sensors; S12. Using the deployed ultrasonic anemometer, collect the environmental wind state information around the road and bridge to obtain relevant lateral wind load information data, which includes the actual wind speed Vfs and the wind direction angle Qfx; and according to the driving conditions of various types of vehicles on the road and bridge, combined with the wirelessly connected dynamic weighing system and multiple groups of traffic camera equipment, collect the traffic load state information of the road and bridge, and construct relevant vertical traffic load information data, which includes the total traffic flow Vxc of various types of vehicles and the single axle load Fhz of different axles of various types of vehicles; S13. Preprocess the relevant data information in the relevant lateral wind load information data and the relevant vertical traffic load information data, and send the preprocessed relevant data information to the cloud database for storage; the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling.

3. The road and bridge disease analysis and early warning method based on big data according to claim 2 is characterized by: The specific steps of S2 include: S21. Using the three-dimensional model of the road and bridge established by fluid dynamics software, simulate and analyze the wind resistance performance of the road and bridge in the windward state, and combine the simulation analysis test results to obtain the wind resistance design coefficient Xfz, which is associated with the relevant lateral wind load information data. After dimensionless processing, the lateral wind load coefficient Xfh is constructed. The lateral wind load coefficient Xfh is calculated and obtained by the following formula: ； In the formula, represents the wind direction angle, is the actual wind speed, Wind direction angle The squared cosine of .

4. The road and bridge disease analysis and early warning method based on big data according to claim 2 is characterized by: The specific steps of S2 also include: S22. Based on fatigue tests of road and bridge materials and the actual effects and design specifications of vehicle loads, a standard axle load Fh is constructed. By extracting features from relevant vertical traffic load information data, the standard axle load Fh is associated with the single axle load Fhz of different axles of various types of vehicles to obtain the single-vehicle equivalent axle load coefficient Xfx of the corresponding type of vehicle. The single-vehicle equivalent axle load coefficient Xfx of the i-th type of vehicle is calculated. i For example, it is obtained in the following way: ； In the formula, It is represented as the single axle load of the jth axle of the i-th type of vehicle, j=1, 2, 3, ..., n, and n represents the number of axles; S22, based on obtaining the single vehicle equivalent axle load coefficient Xfx of the i-th category vehicle i In this way, the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles are obtained respectively, and the total traffic flow Vxc of various types of vehicles in the relevant vertical traffic load information data is associated with the single-vehicle equivalent axle load coefficients Xfx of several types of vehicles by extracting features from the relevant vertical traffic load information data, and the vertical traffic load coefficient Xzx is constructed. The vertical traffic load coefficient Xzx is calculated and obtained by the following formula: ； In the formula, It is expressed as the total traffic flow of the i-th category of vehicles, It is expressed as the single vehicle equivalent axle load coefficient of the i-th category vehicle, i=1, 2, 3, ..., m, and m represents the number of vehicle categories.

5. The road and bridge disease analysis and early warning method based on big data according to claim 4 is characterized by: The specific steps of S2 also include: S23. By associating the lateral wind load coefficient Xfh with the vertical traffic load coefficient Xzx, after linear normalization processing and machine deep learning calculation, an external load influence coefficient Xhz is constructed. The external load influence coefficient Xhz is calculated and obtained by the following formula: ； In the formula, and They are respectively expressed as the weight values ​​of the lateral wind load coefficient Xfh and the vertical traffic load coefficient Xzx; S24, comparing and analyzing the external load influence coefficient Xhz with a preset threshold value to preliminarily determine whether the current road bridge is adversely affected by the external load. The specific comparison content is as follows: If the external load influence coefficient Xhz exceeds the threshold, it is preliminarily determined that the current road bridge is adversely affected by the external load, and a preliminary warning signal will be issued for further analysis; If the external load influence coefficient Xhz does not exceed the threshold, it can be preliminarily determined that the current road bridge is not adversely affected by the external load.

6. The road and bridge disease analysis and early warning method based on big data according to claim 5 is characterized by: The specific steps of S3 include: S31. After receiving the preliminary warning signal, multiple sets of sensors are used to collect relevant surface state data information and relevant vibration state data information of the road and bridge, and send them to the cloud database for storage. The specific process is as follows: S311, using multiple groups of traffic cameras set above the road bridge to collect surface state information of the road bridge, and combining image processing technology and edge detection algorithm to obtain relevant surface state data information, wherein the relevant surface state data information includes the length Dcd, width Dkd and depth Lsd of each crack; S312, using a high-sensitivity acceleration sensor fixed at the center of the road bridge to monitor the vibration state of the road bridge in real time, and performing frequency domain analysis on the vibration signal at each monitoring time point within the monitoring period through Fourier transform, and constructing relevant vibration state data information after feature extraction, the relevant vibration state data information includes the maximum value of the vibration frequency within the monitoring period ; S313, sending the acquired relevant surface state data information and relevant vibration state data information to a cloud database for storage via wireless transmission.

7. The road and bridge disease analysis and early warning method based on big data according to claim 6 is characterized by: The specific steps of S3 also include: S32, analyzing the relevant surface state data information in the cloud database, and obtaining the surface disease coefficient Xbm after dimensionless processing, wherein the surface disease coefficient Xbm is obtained by the following formula: ； In the formula, is the length of the ath crack, is the width of the ath crack, is the depth of the ath crack, , and They are all expressed as weight values, a=1, 2, 3, ..., k, and k represents the number of cracks.

8. The road and bridge disease analysis and early warning method based on big data according to claim 7 is characterized by: The specific steps of S3 also include: S33, the surface damage coefficient Xbm and the external load influence coefficient Xhz are associated with the relevant vibration state data information, and after dimensionless processing, combined with the damage assessment model, a comprehensive damage degree index Zbh is constructed by fitting. The comprehensive damage degree index Zbh is obtained by the following formula: ； In the formula, Expressed as the maximum vibration frequency, , and Both are expressed as weight values, and A is expressed as a correction constant.

9. The road and bridge disease analysis and early warning method based on big data according to claim 8 is characterized by: The specific steps of S4 include: S41, pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively judge whether there is a disease risk for the current road bridge under the influence of external force load, so as to generate and execute the corresponding level of disease warning instructions. The specific process is as follows: If the comprehensive disease severity index Zbh ≥ the assessment threshold K, it means that the current road and bridge are at risk of disease under the influence of external loads, and a first-level disease warning instruction is generated. The execution content is: immediately publish a notice of road and bridge traffic restrictions through the public platform, control the traffic at the entrances and exits of roads and bridges, and restrict the passage of overloaded vehicles; organize road and bridge structure experts and inspection teams to conduct on-site inspections, focusing on crack expansion, structural deformation and abnormal vibration; Initiate emergency maintenance plans and conduct temporary reinforcement of the discovered damaged parts; If the comprehensive damage degree index Zbh is less than the assessment threshold K, it means that there is no damage risk for the current road and bridge under the influence of external loads, and a second-level damage warning instruction is generated. The execution content is: continue to monitor the vibration frequency, crack expansion, traffic load and wind load of the road and bridge, upload the monitoring data to the cloud database in real time, conduct further assessment in combination with the damage assessment model, dynamically update the comprehensive damage degree index Zbh, include the road and bridge in the recent maintenance plan, arrange inspection and local repair work, and implement some vehicle flow and load restrictions on the road and bridge.

10. A road and bridge disease analysis and early warning system based on big data, used to implement the road and bridge disease analysis and early warning method based on big data as described in any one of claims 1 to 9, characterized in that: Including data acquisition module, load analysis module, disease assessment module and grade warning module; The data acquisition module is used to collect environmental wind status information around roads and bridges using multiple sets of deployed sensors to obtain relevant lateral wind load information data, and to collect traffic load status information of roads and bridges according to the driving conditions of various types of vehicles on roads and bridges to construct relevant vertical traffic load information data; The load analysis module is used to associate the relevant lateral wind load information data with the relevant vertical traffic load information data, and after dimensionless processing, fit and construct the external force load influence coefficient Xhz, and compare it with the preset threshold value to issue a preliminary warning signal; The damage assessment module is used to collect relevant surface state data information and relevant vibration state data information of the current road bridge after receiving the preliminary warning signal, and associate them with the external load influence coefficient Xhz, and combine them with the damage assessment model to fit and construct a comprehensive damage degree index Zbh; The grade warning module is used to pre-set the evaluation threshold K, and compare and analyze it with the comprehensive disease degree index Zbh to comprehensively determine whether the current road bridge has a disease risk under the influence of external force loads, so as to generate and execute the corresponding grade disease warning instructions.

Images