A highway bridge water damage monitoring and early warning method and system

Abstract

The present invention relates to the technical field of intelligent bridge monitoring, specifically to a method and system for monitoring and warning of water damage of highway bridges, the method comprising the following steps: dividing the information collection time stage according to the bridge water damage process stage to obtain information data sets of different process stages; using the DBSCAN algorithm and the information data set to obtain the forecast information set and obtain the forecast analysis result; based on the DBSCAN algorithm and the information data set, the first warning layer information set is obtained, and a flood velocity prediction model and a cross-sectional flow analysis model are established at the same time, thereby obtaining the first warning result; based on the DBSCAN algorithm and the information data set, the second, third and fourth warning layer information sets are obtained, and the second, third and fourth warning results are obtained according to the multi-layer information set; combining the forecast analysis results and the four-layer warning results to realize the monitoring and warning of the water damage of highway bridges. Considering the influence and coupling of multiple factors on bridges provides support for scientific management and safety of bridges.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent bridge monitoring, and in particular to a method and system for monitoring and early warning of water damage to highway bridges. Background Art

[0002] As a key hub in the transportation network, the stability and safety of highway bridges are directly related to road traffic efficiency, smooth logistics, and the safety of life and property. However, with the continuous intensification of global climate change, especially in extreme weather conditions such as heavy rains and typhoons, the foundation and superstructure of bridges are extremely susceptible to water scouring, sediment erosion, and water pressure shock, which can lead to damage to the bridge structure, traffic interruption, economic losses, and other consequences.

[0003] Among the damaged bridges, small and medium span bridges account for a considerable proportion, among which the number of damaged beam bridges and masonry arch bridges is significant. Specifically, among the 221 small and medium span damaged bridges, there are as many as 110 beam bridges, accounting for 50%, and 50 masonry arch bridges, accounting for 23%. Through investigation and analysis of the damage of bridges, it can be found that small and medium span bridges show some common damage points in water damage disasters, including foundation damage, damage to the road-bridge connection position, and damage to the connection between the upper structure and the lower structure. For bridges of different structural types, the damage forms are different. The typical damage forms of beam bridges include support damage, horizontal lateral displacement of the upper beam body, tilt settlement, and lateral or longitudinal beam drop. In contrast, the damage forms of masonry arch bridges are mainly manifested in cracking of arch rings and arch ribs, displacement of arch angles, and lateral shear damage of arch rings.

[0004] In summary, the problem of water damage to highway bridges cannot be ignored. It is not only related to the smoothness and safety of transportation, but also closely related to property safety. Therefore, it is necessary to attach great importance to the disaster prevention and mitigation of bridges, strengthen monitoring, early warning and emergency response capabilities, so as to ensure the safety and stability of bridges under extreme weather conditions.

[0005] The current bridge monitoring system has significant imperfections in assessing bridge safety, especially the failure to fully integrate the comprehensive impact of meteorological, hydrological and hydraulic factors on bridges, which leads to the lack of effective water damage monitoring and early warning mechanisms to quickly and accurately determine the status of bridges in the face of natural disasters such as floods. In addition, the current bridge monitoring system has failed to fully consider the interaction between floods and bridges during flood disasters, such as the direct impact of floods on bridge structures, the scouring of bridge foundations, and the erosion of road-bridge connections. The existing monitoring system mainly focuses on the integrity monitoring of the bridge structure itself, while the in-depth analysis of monitoring data and the construction of early warning mechanisms are relatively simple and extensive. The above limitations make the early warning effect relatively one-sided, making it difficult to achieve a comprehensive and accurate prediction of bridge conditions, and thus cannot effectively guarantee the safety and stability of bridges under extreme weather conditions such as floods. Summary of the invention

[0006] In view of the defects of existing methods and the shortcomings of practical applications, in order to comprehensively evaluate the comprehensive impact of multiple factors such as meteorology, hydrology, and hydraulics on bridge safety, and analyze the interaction between floods and bridges, a scientific and reliable decision-making basis is provided for bridge monitoring and early warning, so as to take countermeasures quickly and effectively, thereby ensuring the safety and stability of bridges under extreme weather conditions. In a first aspect, the present invention provides a method for monitoring and early warning of water damage to a highway bridge. The method comprises the following steps: dividing information collection time stages according to the progress stage of bridge water damage, and obtaining information data sets of different progress stages according to the information collection time stages; establishing a DBSCAN algorithm, using the DBSCAN algorithm and the information data set to obtain a forecast information set, and obtaining a forecast analysis result according to the forecast information set; obtaining a first warning layer information set based on the DBSCAN algorithm and the information data set, establishing a flood flow velocity prediction model and a cross-sectional flow analysis model based on the first warning layer information set, and obtaining a first warning result based on the flood flow velocity prediction model, the cross-sectional flow analysis model and the first warning layer information set; obtaining a second warning layer information set, a third warning layer information set and a fourth warning layer information set based on the DBSCAN algorithm and the information data set, and obtaining a second warning result, a third warning result and a fourth warning result respectively according to the second warning layer information set, the third warning layer information set and the fourth warning layer information set; combining the forecast analysis result, the first warning result, the second warning result, the third warning result and the fourth warning result to achieve comprehensive monitoring and accurate early warning of water damage to highway bridges. The present invention divides the information collection time stages and collects information data sets, thereby realizing comprehensive monitoring of the progress of bridge water damage, helping to timely discover potential safety hazards, providing decision support for bridge management departments, and helping bridge management departments to quickly take response measures under extreme weather conditions such as floods, thereby ensuring the safety and stability of the bridge.

[0007] Optionally, the information collection time stage is divided according to the bridge water damage process stage, and the information data sets of different process stages are obtained according to the information collection time stage, including: dividing the information collection time stage into a no-rainfall stage, a watershed convergence stage, a tributary formation stage, a main stream formation stage, and a main stream action stage according to the bridge water damage process stage; obtaining information data sets of different process stages according to the no-rainfall stage, the watershed convergence stage, the tributary formation stage, the main stream formation stage, and the main stream action stage. The present invention subdivides the bridge water damage process stage, which helps to accurately capture water damage process data, achieve early warning and prevention, and at the same time improve emergency response capabilities, further ensure the safety and stability of bridges, and reduce disaster losses.

[0008] Optionally, the establishment of the DBSCAN algorithm includes: establishing the DBSCAN algorithm based on the density space clustering algorithm; performing data clustering processing on the information data set according to the DBSCAN algorithm, and obtaining abnormal data points of the information data set; optimizing the information data set according to the abnormal data points to obtain information sets at different process stages. The DBSCAN algorithm of the present invention can automatically determine the number of clusters according to the density distribution of data points, can identify and process noise points and abnormal values, and ensure the accuracy of the data set.

[0009] Optionally, the use of the DBSCAN algorithm and the information data set to obtain a forecast information set, and obtaining a forecast analysis result based on the forecast information set includes: filtering out a forecast information set according to the DBSCAN algorithm and the information data set, wherein the forecast information set includes meteorological monitoring information in a non-rainfall stage; analyzing the rainfall in the watershed based on the meteorological monitoring information, and obtaining a forecast analysis result based on the rainfall in the watershed. The present invention predicts the rainfall in the watershed based on the meteorological monitoring information in the non-rainfall stage to obtain a forecast analysis result, which is helpful for advance planning, optimizing resource allocation, and preventing disasters, and is of great significance for ensuring the safety and stability of bridges.

[0010] Optionally, the establishment of a flood velocity prediction model and a cross-sectional flow analysis model based on the first warning layer information set includes: introducing a Xie Cai operation model, obtaining a U-shaped cross-sectional hydraulic radius and a V-shaped cross-sectional hydraulic radius based on the Xie Cai operation model and the first warning layer information set; and establishing a flood velocity prediction model based on the U-shaped cross-sectional hydraulic radius and the V-shaped cross-sectional hydraulic radius. The present invention calculates the hydraulic radius using the Xie Cai model, and can more accurately determine the relevant parameters of the model, which helps to optimize the actual performance of the prediction model and the analysis model, and improve the accuracy of the bridge prediction results.

[0011] Optionally, the hydraulic radius of the U-shaped section satisfies the following relationship:

[0012]

[0013] in, represents the hydraulic radius of the U-shaped section, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. Indicates the width of the riverbed bottom;

[0014] The hydraulic radius of the V-shaped section satisfies the following relationship:

[0015]

[0016] in, represents the hydraulic radius of the V-section, It represents the angle between the riverbed side and the riverbed bottom plane. Indicates the average flood depth.

[0017] The present invention clarifies the mathematical relationship between the U-shaped section and the V-shaped section, which is convenient for calculation and design and helps to meet specific water flow conditions and water delivery requirements in practice.

[0018] Optionally, the establishing of the flood velocity prediction model according to the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section includes: constructing a U-shaped water flow section velocity prediction function according to the hydraulic radius of the U-shaped section;

[0019] The U-shaped water flow section velocity prediction function satisfies the following relationship:

[0020]

[0021] in, represents the average flow velocity of the U-shaped water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. represents the width of the riverbed bottom. The average flood depth. It indicates the flood gradient;

[0022] Constructing a flow velocity prediction function of a V-shaped water flow section according to the hydraulic radius of the V-shaped section;

[0023] The V-shaped water flow section velocity prediction function satisfies the following relationship:

[0024]

[0025] in, represents the average flow velocity of the water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. Represents the flood gradient; and obtains a flood velocity prediction model by combining the U-shaped water flow section velocity prediction function and the V-shaped water flow section velocity prediction function.

[0026] The present invention establishes a flood velocity prediction model based on the hydraulic radius of the section, takes into account the influence of different section shapes on the water velocity, improves the accuracy and applicability of the prediction results, and helps to build a more complete and efficient flood early warning and monitoring system.

[0027] Optionally, establishing a flood velocity prediction model and a cross-sectional flow analysis model according to the first warning layer information set includes: constructing a U-shaped cross-sectional flow analysis function according to the first warning layer information set;

[0028] The U-shaped cross-section flow analysis function satisfies the following relationship:

[0029]

[0030] in, Indicates the flow rate of the U-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. represents the width of the riverbed bottom. It indicates the flood gradient;

[0031] Constructing a V-section flow analysis function according to the first warning layer information set;

[0032] The V-shaped cross-section flow analysis function satisfies the following relationship:

[0033]

[0034] in, Indicates the flow rate of the V-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. Represents flood gradient; a cross-sectional flow analysis model is obtained by combining the U-shaped cross-sectional flow analysis function and the V-shaped cross-sectional flow analysis function.

[0035] The present invention establishes a cross-sectional flow analysis model based on information sets, improves the accuracy of flow prediction results, enhances the adaptability of the model, and helps management departments to formulate more reasonable and scientific management and early warning plans.

[0036] Optionally, the second warning layer information set, the third warning layer information set and the fourth warning layer information set are obtained based on the DBSCAN algorithm and the information data set, and the second warning result, the third warning result and the fourth warning result are obtained respectively according to the second warning layer information set, the third warning layer information set and the fourth warning layer information set, including: based on the DBSCAN algorithm and the information data set, the second warning layer information set is screened out, the second warning layer information set includes hydraulic collection information in the tributary formation stage; the second warning result is obtained according to the hydraulic collection information; based on the DBSCAN algorithm and the information data set, the third warning layer information set is screened out, the third warning layer information set includes hydraulic detection information in the main stream formation stage; the third warning result is obtained according to the hydraulic detection information; based on the DBSCAN algorithm and the information data set, the fourth warning layer information set is screened out, the fourth warning layer information set includes hydraulic and structural monitoring data in the main stream action stage; the fourth warning result is obtained according to the hydraulic and structural monitoring data.

[0037] The present invention combines multi-layer warning layer information sets to obtain the second warning result, the third warning result and the fourth warning result, improves the accuracy and timeliness of the warning, reduces the degree of data redundancy and optimizes the actual performance of the monitoring and early warning system.

[0038] In the second aspect, the present invention also provides a highway bridge water damage monitoring and early warning system, which can efficiently execute a highway bridge water damage monitoring and early warning method provided by the present invention, the above system includes an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are interconnected, the above memory includes a computer-readable storage medium as described in the first aspect of the present invention, the above memory is used to store a computer program, the above computer program includes program instructions, and the above processor is configured to call program instructions. The highway bridge water damage monitoring and early warning system provided by the present invention has a compact structure, strong applicability, and greatly improves the operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of the highway bridge water damage monitoring and early warning method of the present invention;

[0040] Figure 2 It is a schematic diagram of a U-shaped section in the highway bridge water damage monitoring and early warning method of the present invention;

[0041] Figure 3 It is a schematic diagram of a V-shaped section in the highway bridge water damage monitoring and early warning method of the present invention;

[0042] Figure 4 It is a schematic diagram of the DBSCAN process in the highway bridge water damage monitoring and early warning method of the present invention;

[0043] Figure 5 It is a schematic diagram of different tributaries and main streams in the highway bridge water damage monitoring and early warning method of the present invention;

[0044] Figure 6 It is a structural schematic diagram of the highway bridge water damage monitoring and early warning system of the present invention. DETAILED DESCRIPTION

[0045] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0046] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0047] See also Figure 1 In order to comprehensively and systematically analyze the impact of meteorological conditions, hydrological conditions, hydraulic characteristics and other factors on bridge safety performance, and deeply analyze the interaction mechanism between floods and bridges, the present invention monitors and warns highway bridge water damage based on information collection and prediction analysis models, which helps to quickly and efficiently take targeted protective measures under extreme climate conditions, thereby ensuring the safety and stability of bridges. The present invention provides a highway bridge water damage monitoring and early warning method, which includes the following steps:

[0048] S1. Divide the information collection time stages according to the bridge water damage process stage, and obtain the information data sets of different process stages according to the above information collection time stages. The implementation steps and specific contents are as follows:

[0049] According to the progress stage of bridge water damage, the information collection time stage is divided into no-rainfall stage, watershed convergence stage, tributary formation stage, main stream formation stage and main stream action stage; and according to the above-mentioned no-rainfall stage, watershed convergence stage, tributary formation stage, main stream formation stage and main stream action stage, the information data sets of different process stages are obtained.

[0050] In this embodiment, the complete process of bridge damage by water disasters is understood and analyzed. First, the information collection time stage of early warning monitoring is divided into five periods, which mainly include the non-rainfall stage, the basin convergence stage, the tributary formation stage, the main stream formation stage and the main stream action stage. Based on this, the turning point information and data of bridge water damage events from brewing to occurrence can be accurately captured, thereby ensuring the comprehensiveness, pertinence and timeliness of the system information data set.

[0051] Furthermore, the above information collection time period is explained:

[0052] Pre-rainfall stage: Information collection in this stage mainly focuses on routine monitoring of the bridge and its surrounding environment before rainfall, including but not limited to the structural condition of the bridge, daily records of river water levels, stability assessment of surrounding geological conditions, etc. Through continuous monitoring, baseline data of the bridge and its basin are established, providing a reference for information comparison and data analysis in subsequent time stages.

[0053] Basin convergence stage: As rainfall begins, water in the basin begins to converge. Information collected at this stage focuses on rainfall intensity, rainfall duration, changes in soil saturation in the basin, and the initial formation of small-scale water flows. The above information is crucial for predicting the development trend of floods and assessing their potential threats to bridges.

[0054] Tributary formation stage: As rainfall continues, multiple tributaries gradually form in the basin. Information collection at this stage should strengthen the timely monitoring of the water volume, flow rate, flow direction and possible intersection points of each tributary. At the same time, attention should also be paid to the scouring of bridge foundations, slope protection and other structures by tributaries, so as to take timely response measures and early warning plans in the future.

[0055] Mainstream formation stage: When multiple tributaries converge to form a mainstream, the scale and power of the flood will be significantly enhanced. Information collection at this stage should not only monitor key parameters such as the water level, flow velocity, and flow of the mainstream in real time, but also pay close attention to the direct impact of the mainstream on the bridge, such as the stress of the bridge piers and the degree of flooding on the bridge deck.

[0056] Mainstream stage: This stage is the most critical stage of the bridge damage process. At this stage, the strong water flow of the main stream will cause serious scouring and damage to the bridge structure. At this time, the focus of information collection should be on the real-time response of the bridge structure, including but not limited to the deformation of the bridge, the development of cracks, and the risk of possible collapse. At the same time, it is also necessary to record the damage condition of the bridge after the flood recedes, which is conducive to providing reliable data support and basis for bridge repair work.

[0057] Through the information collection and data accumulation in the above five time stages, a complete and continuous information chain of the bridge water damage process can be constructed, that is, a collection of information data at different process stages can be obtained to provide scientific basis and information support for bridge safety warning, risk assessment and post-disaster restoration.

[0058] Furthermore, in the present embodiment, the method for acquiring the highway bridge information data set is only an optional condition of the present invention. In one or some other embodiments, the method for acquiring the information data set can be adjusted according to the actual situation of the highway bridge and the monitoring and early warning requirements, thereby optimizing the data collection frequency, range and accuracy, avoiding unnecessary waste of resources, and ensuring the effective acquisition of key information, thereby further improving the response speed and accuracy of the highway bridge water damage monitoring and early warning method.

[0059] S2. Obtain a forecast information set using the DBSCAN algorithm and the information data set, and obtain a forecast analysis result based on the forecast information set. The specific steps and implementation contents are as follows:

[0060] In an optional embodiment, a forecast information set is screened out according to the DBSCAN algorithm and the information data set, and the forecast information set mainly includes meteorological monitoring information in the non-rainfall stage; at the same time, the rainfall situation in the basin is analyzed based on the meteorological monitoring information to obtain the forecast analysis result.

[0061] First, the DBSCAN algorithm is used to process the information data set to filter out the forecast information set. In the embodiment, the above-mentioned forecast information set mainly includes the meteorological monitoring information in the non-rainfall stage; then, the rainfall situation in the basin is inferred based on the meteorological monitoring information to obtain the forecast analysis result.

[0062] First, the DBSCAN algorithm is used to filter the forecast information set of highway bridge water damage monitoring from the information data set. This set mainly covers the meteorological monitoring information in the non-rainfall stage. Next, the above meteorological monitoring information is used to predict the rainfall trend in the highway bridge basin, that is, to obtain the rainfall situation in the basin, so as to obtain the forecast analysis results of the highway bridge water damage monitoring and early warning method.

[0063] In the embodiment, the non-rainfall stage specifically refers to the 15 days before the heavy rain hits. The meteorological data such as temperature change, precipitation, wind speed and direction in the highway bridge basin within half a month will be comprehensively collected. Through data analysis, the rainfall conditions in the highway bridge basin in the future period can be accurately estimated, that is, the forecast analysis results of the highway bridge water damage monitoring and early warning method are obtained.

[0064] In order to efficiently collect the above-mentioned meteorological data, the data collection system of the automated weather station is used in the embodiment. The above-mentioned system integrates sensors such as platinum resistance thermometers, cup anemometers and wind vanes, which can monitor and record various meteorological data in the non-raining stage in real time and accurately, such as temperature, humidity, wind speed, wind direction, etc., providing a reliable data basis for bridge water damage warning. On the other hand, the automated weather station network can collect and transmit the above-mentioned meteorological data in real time without manual intervention, which improves the efficiency and accuracy of data collection, and further realizes the remote transmission and accurate analysis of meteorological data, further improving the intelligent level of the highway bridge water damage monitoring and early warning method, and integrating the above-mentioned meteorological monitoring information in the non-raining stage. For specific information, please refer to Table 1.

[0065] Table 1 Meteorological monitoring information during the period without rainfall

[0066]

[0067] The meteorological monitoring information in the non-rainfall stage shown in Table 1 provides a solid information basis for bridge water damage warning. The above meteorological monitoring information provides a scientific decision-making basis for the bridge management department, helps to formulate reasonable response measures based on real-time meteorological data, and reduces the threat of floods to bridge safety. At the same time, the automated and intelligent meteorological monitoring system improves the working efficiency of the highway bridge water damage monitoring and early warning system, reduces manual intervention, and reduces the risk of false alarms and missed reports. S3. Based on the DBSCAN algorithm and the information data set, the first warning layer information set is obtained, and a flood flow velocity prediction model and a cross-sectional flow analysis model are established based on the above first warning layer information set. The first warning result is obtained based on the above flood flow velocity prediction model, the cross-sectional flow analysis model and the first warning layer information set. In an optional embodiment, the first warning layer information set is firstly screened based on the information data set, and the water flow convergence speed, convergence flow and flow velocity in the basin convergence stage are calculated based on the first warning layer information set; then, the first warning result is obtained in combination with the basin rainfall situation, water flow convergence speed, convergence flow and flow velocity. The specific contents are as follows:

[0068] In this embodiment, the first warning layer information set is obtained based on the DBSCAN algorithm and the information data set, and the above information set mainly includes the key data of the watershed convergence stage. Next, the first warning layer information is used to calculate the core parameters such as the convergence speed, convergence flow and flow rate of the water flow in the watershed convergence process. On this basis, it is also necessary to comprehensively consider the relevant rainfall conditions in the basin, as well as the historical water flow convergence speed, convergence flow and flow rate, conduct a comprehensive analysis of the first warning layer information set and obtain the first warning result.

[0069] In the basin convergence stage, that is, the period when heavy rain causes water to converge rapidly in the basin, it is observed that the entire process from the beginning of rainfall to the formation of floods takes about 8 hours. In order to carry out early warning of flood peaks, the hydrological monitoring equipment is used in the embodiment to collect rainfall data in real time, and key indicators such as the speed of water convergence, the converged flow rate and the flow rate are calculated at the same time. The above calculation results are helpful to more accurately evaluate the possible impact of floods, and thus obtain the first warning result of the highway bridge water damage monitoring and early warning method.

[0070] In order to more comprehensively display the information content of the watershed convergence stage, the above information is aggregated into an information table. Please refer to Table 2 for the information set of the watershed convergence stage.

[0071] Table 2 Information collection of watershed convergence stage

[0072]

[0073] Table 2 above lists the relevant information of the basin convergence stage, which provides comprehensive and accurate data support for monitoring and early warning by integrating information from a variety of hydrological and geological monitoring equipment.

[0074] Among them, the tipping bucket rain gauge can measure rainfall intensity in real time and monitor the rainfall convergence process in the basin. It can accurately understand the distribution and intensity of rainfall, thereby predicting changes in surface runoff and providing key data for flood warning.

[0075] Turbidimeters measure the concentration of sediment or suspended particles in the water, reflecting the solid matter carried by the water flow, which helps to determine the turbidity of the flood and possible erosion. At the same time, TDR probe soil moisture meters monitor soil moisture, and geological radar is used for in-depth analysis of soil structure and water content. The above information together provides an important basis for the monitoring and early warning methods of highway bridge water damage.

[0076] Combining data from tipping bucket rain gauges, turbidity meters, TDR probe soil moisture meters and geological radars can help to more comprehensively analyze rainfall, water flow and soil conditions in the basin, thereby more accurately predicting the possibility of floods, which is conducive to formulating response measures in advance and reducing the potential threat of floods to infrastructure such as bridges.

[0077] By integrating data from a variety of monitoring devices, we can more keenly capture early signs of floods, improve the accuracy and timeliness of early warning results, and at the same time ensure the scientificity and accuracy of the first warning results. This will enable us to better assess the risk of water damage to highway bridges, develop effective risk management strategies, and further ensure the safety and stability of key infrastructure such as bridges under extreme weather conditions.

[0078] In order to effectively analyze the water flow convergence speed, convergence flow and flow rate in the basin convergence stage, in the embodiment

[0079] Based on the information set of the first warning layer, a flood velocity prediction model and a cross-sectional flow analysis model were established.

[0080] The embodiment introduces the Xie Cai operation model. Based on the Xie Cai operation model and the first warning layer information set, the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section in the basin convergence stage are obtained. At the same time, a flood flow velocity prediction model is further established based on the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section.

[0081] In the embodiment, the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section are obtained by using the Xie Cai calculation model and the first warning layer information set.

[0082] The hydraulic radius of the U-shaped section and the V-shaped section is determined based on the Xie Cai operation model and the information set of the first warning layer. The above process is crucial for accurately calculating the flood flow rate, especially in areas where floods occur frequently and the river morphology is diverse, among which the V-shaped and U-shaped are mainly analyzed.

[0083] For the calculation of flood flow rate, the embodiment adopts a calculation method based on water depth changes, river cross-sectional dimensions and Xie Cai's formula. The above method mainly uses the hydraulic information collected by the second warning layer, such as tributary flow, flow velocity, water level, etc., and combines the actual cross-sectional shape of the river to calculate the average flow velocity of the water flow section.

[0084] In the embodiment, the river is divided into different section types according to the cross-sectional size and water depth changes of the river, and the corresponding flood velocity prediction models are applied respectively. For U-shaped and V-shaped sections, the hydraulic radius in Xie Cai's formula is used as the key parameter, and other hydraulic elements, such as cross-sectional area and wetted perimeter, are combined to estimate the water flow velocity of different river forms.

[0085] In summary, a prediction model is established through the Xie Cai operation model, the first warning layer information set, and the actual shape and hydraulic characteristics of the river section. The flow velocity of the flood in the U-shaped section and the V-shaped section is calculated and analyzed through the prediction model. The above prediction process not only improves the accuracy of the highway bridge water damage monitoring and early warning method, but also provides data support for subsequent early warning and disaster reduction work.

[0086] The average flow velocity of the water flow section in the embodiment needs to satisfy the following relationship:

[0087]

[0088] in, represents the average flow velocity of the water flow section, represents the roughness coefficient, represents the hydraulic radius, Indicates flood gradient.

[0089] For the problem of calculating the flow velocity of a compound section, that is, a complex river section composed of a main channel and a river beach, the cross-sectional average flow velocities of the river channel and the river beach need to be calculated separately, that is, the average flow velocities of the main channel and the river beach are calculated separately, where the main channel refers to the deeper part of the river channel with faster water flow, and the river beach is the shallower area on both sides of the river channel with slower water flow. By calculating the average flow velocity of these two parts separately, the water flow characteristics of the entire compound section can be understood more accurately. The flood flow velocity prediction model in the embodiment mainly includes the flow velocity prediction function of the U-shaped water flow section and the flow velocity prediction function of the V-shaped water flow section.

[0090] In an optional embodiment, a flood velocity prediction model is established based on the first warning layer information set. The flood velocity prediction model in the embodiment mainly includes a U-shaped water flow section velocity prediction function and a V-shaped water flow section velocity prediction function.

[0091] First, the hydraulic radius of the U-shaped section is calculated based on the first warning layer information set. The hydraulic radius of the U-shaped section is calculated mainly based on given geometric parameters such as the riverbed angle, water depth and bottom width. For a schematic diagram of the U-shaped section in the embodiment, please refer to Figure 2 .

[0092] The hydraulic radius of the above U-shaped section satisfies the following relationship:

[0093]

[0094] in, represents the hydraulic radius of the U-shaped section, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. Indicates the width of the riverbed.

[0095] The flow velocity prediction function of the U-shaped water flow section is constructed based on the hydraulic radius of the U-shaped section.

[0096] When constructing the velocity prediction function of the U-shaped water flow section, the hydraulic radius of the U-shaped section is substituted into the average velocity formula of the water flow section to obtain the average velocity prediction function of the U-shaped water flow section. The velocity prediction function of the U-shaped water flow section satisfies the following relationship:

[0097]

[0098] in, represents the average flow velocity of the U-shaped water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. represents the width of the riverbed bottom. The average flood depth. It indicates the flood gradient;

[0099] The roughness coefficient reflects the effect of the roughness of the riverbed surface on the water flow velocity.

[0100] Flood gradient refers to the height difference within a unit horizontal distance in the direction of flood flow.

[0101] In the embodiment, the average flow velocity of the U-shaped water flow section is predicted according to the riverbed geometric parameter angle, bottom width and water depth, roughness coefficient and flood gradient. The U-shaped water flow section flow velocity prediction function provides a practical tool for predicting flood flow velocity, which is beneficial to flood risk assessment and accurate flood detection.

[0102] The flow velocity prediction function of the V-shaped water flow section is constructed according to the hydraulic radius of the V-shaped section.

[0103] Similarly, the hydraulic radius of the V-shaped cross section is calculated based on the above-mentioned first warning layer information set and cross section schematic diagram information. For the V-shaped cross section schematic diagram in the embodiment, please refer to Figure 3 .

[0104] The hydraulic radius of the above V-shaped section satisfies the following relationship:

[0105]

[0106] in, represents the hydraulic radius of the V-section, It represents the angle between the riverbed side and the riverbed bottom plane. Indicates the average flood depth.

[0107] When constructing the velocity prediction model of the V-shaped water flow section, the hydraulic radius of the V-shaped section is integrated into the average velocity calculation formula of the water flow section, and then the average velocity prediction function of the V-shaped water flow section can be obtained. The velocity prediction function of the V-shaped water flow section satisfies the following relationship:

[0108]

[0109] in, represents the average flow velocity of the water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. It indicates the flood gradient;

[0110] In order to predict the average flow velocity of U-shaped and V-shaped water flow sections, a specific mathematical function is established in the embodiment. The above calculation function takes into account the geometric characteristics of the riverbed, the roughness of the water flowing through the riverbed, and the inclination of the flood in the river channel. By combining relevant factors to establish a prediction model, the average flow velocity of U-shaped and V-shaped water flow sections can be predicted more accurately, providing technical support for the risk assessment of highway bridge water damage monitoring and early warning methods.

[0111] In an optional embodiment, a cross-sectional flow analysis model is established based on the first warning layer information set. In the embodiment, the cross-sectional flow analysis model mainly includes a U-shaped cross-sectional flow analysis function and a V-shaped cross-sectional flow analysis function.

[0112] The flow rate of U-shaped and V-shaped sections is calculated using the average flow velocity of the section. When the area of ​​the riverbed bottom is very small relative to the area of ​​the entire V-shaped section, it can be approximately considered that this part of the area has no significant effect on the calculation of the flow rate, and therefore can be ignored in the calculation.

[0113] The flow rate of the corresponding section can be calculated by measuring or estimating the average flow velocity of the section, combined with the effective flow area of ​​the U-shaped or V-shaped section, that is, the approximate area after deducting the tiny area of ​​the riverbed bottom. The above-mentioned effective flow area mainly depends on the geometry of the section and the average water depth of the flood.

[0114] The above flow rate Q can be calculated by the following formula:

[0115]

[0116] in, Indicates the cross-sectional flow rate, represents the cross-sectional area of ​​the riverbed, Represents the average flow velocity in the riverbed.

[0117] A U-shaped section flow analysis function is constructed based on the first warning layer information set. The above U-shaped section flow analysis function satisfies the following relationship:

[0118]

[0119] in, Indicates the flow rate of the U-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. represents the width of the riverbed bottom. It indicates the flood gradient;

[0120] A V-shaped section flow analysis function is constructed based on the first warning layer information set. The V-shaped section flow analysis function satisfies the following relationship:

[0121]

[0122] in, Indicates the flow rate of the V-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. It indicates the flood gradient;

[0123] In the formation stage of flood tributaries converging, the first warning layer is mainly based on the hydraulic data integrated, the flood flow velocity prediction model (including the flow velocity prediction function of U-shaped and V-shaped water flow sections) and the section flow analysis model (including the flow analysis function of U-shaped and V-shaped sections). The above information sets and calculation models work together to accurately obtain the key parameters of water flow: flow, flow velocity and water level.

[0124] In an optional embodiment, the specific analysis process of the first warning layer result is as follows:

[0125] First, the flow state of each tributary is analyzed by using the above-mentioned flow velocity prediction model and cross-sectional flow analysis model, combined with real-time hydraulic data. The above steps can grasp the specific flow, flow velocity and water level of each tributary.

[0126] Subsequently, the flow parameters of the tributaries are summarized and the flow state of the mainstream is calculated based on this. The above calculation process fully considers the interaction between the tributaries and their combined contribution to the mainstream flow.

[0127] Finally, the second warning layer results were obtained based on the flow, velocity and water level parameters of the main stream, thus realizing the effective operation of the early warning mechanism. This not only improved the monitoring capabilities of flood dynamics, but also provided a decision-making basis for taking effective flood prevention measures.

[0128] Furthermore, in the present embodiment, the analysis method of the relevant warning results and the establishment method of the relevant model are merely an optional condition of the present invention. In one or some other embodiments, the result analysis method and the model establishment method can be optimized according to the needs of highway bridge water damage monitoring and model establishment. Different bridge structures and geographical locations face different flood risks. By optimizing the model, the highway bridge water damage monitoring and early warning method can adapt to the monitoring needs of different bridges and provide more accurate early warning information, which is of great significance to the safe operation of highway bridges.

[0129] S4. Based on the DBSCAN algorithm and the information data set, the second warning layer information set, the third warning layer information set and the fourth warning layer information set are obtained, and the second warning result, the third warning result and the fourth warning result are obtained respectively according to the second warning layer information set, the third warning layer information set and the fourth warning layer information set. The specific steps and related contents are as follows:

[0130] The second warning layer information set is screened out based on the DBSCAN algorithm and the information data set. In the embodiment, the second warning layer information set mainly includes the hydraulic collection information in the tributary formation stage: the second warning result can be obtained based on the hydraulic collection information.

[0131] First, the second warning layer information set is screened based on the DBSCAN algorithm and the information data set. In the embodiment, the second warning layer information set mainly includes the hydraulic collection information in the tributary formation stage. The tributary formation stage is crucial to understanding how floods gradually converge into the main stream from multiple tributaries, thereby triggering larger-scale flood events. In order to more comprehensively reflect the tributary formation stage and related complex processes, the second warning layer information set is screened and integrated based on the information data set in the embodiment, and the set mainly focuses on the hydraulic data in the tributary formation stage.

[0132] The hydraulic data measured in the embodiment not only directly reflects the hydrological conditions of the tributaries, but also provides basic analysis information on water flow conditions at different stages. By real-time monitoring and analysis of relevant hydraulic parameters, the dynamic changes of floods in the tributary formation stage can be more accurately grasped, thereby providing strong support for subsequent highway bridge water damage warning and response work.

[0133] In order to display the relevant information more intuitively, the hydraulic data of the tributary formation stage are sorted into Table 3. For the hydraulic collection information of the tributary formation stage in the embodiment, please refer to Table 3.

[0134] Table 3 Hydraulic collection information at the tributary formation stage

[0135]

[0136] In addition, in this embodiment, the hydraulic data set can be continuously expanded and improved to more comprehensively reflect the hydraulic characteristics of the tributary formation stage. More monitoring equipment and technical means can be introduced to obtain more accurate hydrological data; at the same time, the analysis and research of historical flood events can be strengthened to screen out more valuable early warning indicators and reference information, that is, the second early warning layer information set can be improved.

[0137] In the embodiment, a turbulence meter is used to monitor the convergence process of flood tributaries in real time, analyze the intensity and changes of turbulence in the water body, and provide data support for flood prediction; multi-beam sonar is used to perform underwater terrain scanning to analyze the riverbed morphology and its changes, providing a basis for flood path prediction.

[0138] The early warning mechanism can also be effectively improved based on the relevant set. Based on the collection of the above hydraulic data, the second-level early warning system can further calculate the flow, velocity and water level of the main stream, and build a second-level early warning mechanism. By comparing and analyzing the hydraulic characteristics of tributaries and main streams, valuable early warning indicators and reference information can be screened out to improve the accuracy and timeliness of flood warnings.

[0139] In addition, in order to more comprehensively reflect the hydraulic characteristics of the tributary formation stage, the hydraulic data set can be continuously expanded and improved, including but not limited to the introduction of more advanced monitoring equipment and technical means to improve the accuracy and comprehensiveness of hydrological data; at the same time, strengthen the analysis and research of historical flood events to provide a scientific basis for the continuous optimization of the early warning mechanism.

[0140] In order to fully grasp the development trend of the flood, the implementation example makes full use of the hydraulic data in the third warning layer information set. The above data mainly covers the key water flow parameters upstream of the main stream and under the bridge, such as flow, flow velocity and real-time changes in water level. By conducting in-depth analysis and calculation of the relevant data, the evolution characteristics and changes of the flood in the main stream formation stage can be depicted.

[0141] Based on the above analysis results and information, the third warning results are further derived, so as to track the water flow status upstream of the main stream and under the bridge in real time. It can not only capture the latest dynamics of the flood in time, but also accurately predict its possible impact, thereby providing decision-making support for relevant departments and providing data support for flood prevention and disaster reduction work.

[0142] The fourth warning layer information set is screened based on the information data set, wherein the fourth warning layer information set includes hydraulic and structural monitoring data of the mainstream stage; and the fourth warning result is obtained based on the hydraulic and structural monitoring data.

[0143] In the process of building a highway bridge water damage monitoring and early warning system, the fourth warning layer information set is screened out from the information data set. This set focuses on the hydraulic and structural monitoring data during the mainstream stage. The mainstream stage specifically refers to the period when the flood has an impact under the bridge.

[0144] In order to comprehensively assess the potential threat of floods to bridges, we mainly focus on the hydraulic and structural monitoring data in the fourth warning layer information set. The above data not only covers the hydraulic parameters such as flow, flow velocity, water level and other hydraulic parameters of the flood under the bridge, but also includes the real-time strain, displacement and other key parameter data of the bridge structure.

[0145] In-depth analysis of hydraulic and structural data can calculate the specific forces exerted by floods on bridges, and then conduct a comprehensive assessment of the bridge condition. The above process involves a comprehensive analysis of the bridge's ability to withstand the impact of floods and the effective identification of potential damage or risk factors.

[0146] The fourth warning result was obtained based on the above comprehensive analysis and evaluation. By real-time monitoring of the impact of floods on bridges during the mainstream stage, potential structural safety problems can be discovered and warned in a timely manner, thereby providing timely decision-making support for relevant departments and ensuring the safe operation of bridges under extreme weather conditions.

[0147] Furthermore, in this embodiment, the analysis method and implementation steps of the results of different warning layers are only an optional condition of the present invention. In one or some other embodiments, the analysis method and implementation steps of the warning results can be optimized according to the needs of the warning analysis and the information collection situation. By optimizing the analysis method and implementation steps, the warning information can be processed and analyzed more quickly, thereby improving the response speed of the warning system. At the same time, the optimized monitoring and early warning method can more accurately identify potential risks, reduce false alarms and missed alarms, and improve the credibility of the early warning monitoring results.

[0148] S5. By combining the forecast analysis results, the first warning results, the second warning results, the third warning results and the fourth warning results, comprehensive monitoring and accurate warning of the water damage of highway bridges can be achieved. The implementation steps and related contents are as follows:

[0149] In order to achieve comprehensive and accurate monitoring and early warning of water damage to highway bridges, the above-mentioned forecast analysis results, the first warning results, the second warning results, the third warning results and the fourth warning results are deeply integrated and comprehensively analyzed.

[0150] 1. Data integration and preprocessing

[0151] First, the warning analysis results of different warning layers are unified and integrated, including but not limited to forecast analysis results, hydraulic data of each warning layer, structural monitoring data, etc. During the integration process, the data are cleaned, denoised and standardized to ensure the accuracy and comparability of information and analysis data sets of different warning layers.

[0152] II. Comprehensive Analysis of Multi-level Early Warning Results

[0153] Preliminary warning analysis: Based on the information from the first warning layer, a preliminary judgment is made on the possibility and scale of the flood, providing a basis for subsequent warnings.

[0154] Analysis of the tributary convergence stage: Combined with the information from the second warning layer, the flow state of flood tributaries during their convergence process is deeply analyzed, and key parameters such as mainstream flow, flow velocity and water level are calculated to provide a basis for assessing the potential threat of floods to bridges.

[0155] Assessment during the mainstream phase: Use the data from the third warning layer to focus on analyzing the hydraulic and structural changes during the flood under the bridge, calculate the forces acting on the bridge, and comprehensively assess the actual condition of the bridge.

[0156] Final warning judgment: Based on the results of the fourth warning layer, a final judgment is made on the damage degree and potential risks of the bridge to form a comprehensive warning report.

[0157] III. Release and response of early warning information

[0158] Based on the comprehensive analysis, the risk level of highway bridge damage will be further divided, and early warning information will be issued in a timely manner according to the warning level and urgency, and relevant departments and personnel will be notified through various means such as SMS, email, APP push, etc. At the same time, a detailed emergency response plan will be formulated to ensure that prompt action can be taken after receiving the warning to reduce the impact of floods on highway bridges.

[0159] IV. Continuous Optimization of Monitoring and Early Warning Systems

[0160] In order to ensure the accuracy and effectiveness of the monitoring and early warning system, the embodiment will regularly evaluate and optimize the system performance, including but not limited to updating the early warning model, optimizing the algorithm, improving the data processing speed, etc. At the same time, the function and structure of the early warning system will be continuously adjusted and improved according to new monitoring data and early warning needs.

[0161] In summary, by integrating multi-level warning results, conducting comprehensive analysis and optimizing the warning system, we can achieve comprehensive monitoring and accurate warning of water damage to highway bridges, providing strong support for disaster prevention and mitigation.

[0162] Furthermore, a highway bridge water damage monitoring and early warning method in this embodiment also includes: an optimization processing flow of information data sets at different process stages, and the relevant steps and implementation contents are as follows.

[0163] In this embodiment, a DBSCAN algorithm is established, wherein the DBSCAN algorithm is mainly established based on a density space clustering algorithm. At the same time, data clustering processing is performed on information data sets at different time stages according to the DBSCAN algorithm, and abnormal data points of information data sets at different time stages are obtained. Then, the information data sets can be optimized based on the relevant abnormal data points to obtain information sets at different process stages.

[0164] A DBSCAN algorithm is constructed to perform data detection, identification and optimization processing on information data sets at different process stages to obtain the forecast information set, the first warning layer information set, the second warning layer information set, the third warning layer information set and the fourth warning layer information set in the embodiment.

[0165] DBSCAN, a density-based spatial clustering algorithm, has significant advantages in processing noisy application data. In the field of water depth and hydrological monitoring, this algorithm first removes extremely distorted water level collection points, which are often caused by equipment failure, environmental factors or data transmission errors; then, the DBSCAN algorithm further utilizes its density-based clustering characteristics to accurately identify abnormal points in hydrological data at different stages of the process.

[0166] By counting and sorting the abnormal points, the distribution of abnormal points in different process stages can be obtained. The above distribution information provides an intuitive and quantitative means for comprehensively evaluating the development degree and trend of floods. In the embodiment, the DBSCAN algorithm is used to more accurately grasp and analyze the dynamic changes of floods, providing a basis for subsequent decision support and monitoring and early warning systems.

[0167] For the specific operation flow of the DBSCAN algorithm, please refer to Figure 4 In an optional embodiment, the DBSCAN algorithm analyzes and identifies the monitoring data as follows:

[0168] In the monitoring and early warning system, a series of water level time series data from different tributaries and main stream locations are collected, that is, a collection of information data at different process stages.

[0169] Data input stage: Each set of input data subsets represents a specific water level measurement value. The above data subsets record in detail the measurement time node (timestamp), sensor location (sensor position), and the corresponding water level height (water level value). By integrating key information, a comprehensive and accurate information data set can be constructed, laying the foundation for the subsequent density clustering analysis of the DBSCAN algorithm.

[0170] The embodiment also draws a schematic diagram of the locations of different tributaries and main streams. For details, please refer to Figure 5 .

[0171] The relevant water level time series information is analyzed by taking tributary 1-1, tributary 2-1 and main stream 1 as examples. Please see Table 4 for details.

[0172] Table 4 Water level time series information of tributary 1-1, tributary 2-1, and main stream 1

[0173]

[0174] Data conversion and anomaly identification:

[0175] In the embodiment, a data point set in a two-dimensional space is constructed for each monitoring location based on the timestamp and water level data, where the time axis is the horizontal axis and the water level value is the vertical axis. Subsequently, the DBSCAN algorithm parameters are used to capture abnormal water level fluctuations. Specifically, each data point can be expressed as (tI, water level I), where tI represents the timestamp and water level I represents the water level measurement value at the corresponding time.

[0176] Spatial distance metrics:

[0177] In order to perform cluster analysis, it is necessary to convert the above time-water level data points into points in the spatial coordinate system and calculate the spatial distance between different points. The above steps are the basis for DBSCAN algorithm to perform density clustering.

[0178] DBSCAN parameter initialization:

[0179] When the DBSCAN algorithm is first applied, initial parameters need to be set based on reasonable assumptions about the rate of change of the water level. In an optional embodiment, a limit field radius is set and a limiting number of neighbors , you can choose is a relatively small value, such as a threshold representing a water level change, and is set to a small positive integer to ensure that a sufficiently dense data point group is identified. At the same time, in order to limit The value range can set an upper limit , the specific setting values ​​are as follows =1, .

[0180] First data clustering and exception handling:

[0181] Use the set DBSCAN parameters to cluster the water level data. In the above process, DBSCAN will cluster the water level data according to the limit area radius. The water level data points are divided into different clusters. If the distance between a water level data point and other data points exceeds If the water level changes beyond the normal range, or the water level changes drastically, that is, it does not conform to the normal water level change law, then the point is regarded as an extreme distortion error point. The above distortion points may be caused by sensor failure, environmental interference or errors in the data collection process. In order to maintain the integrity of the data, the relevant distortion points will be deleted and the value of the error point will be replaced by the mean of the adjacent data points before and after to ensure the continuity and accuracy of the data set.

[0182] The embodiment collects the relevant monitoring information of the time of 2024-12-01 and the location of tributary 1-1, please refer to Table 5 for details.

[0183] Table 5 Information table of branch 1-1 before replacement on 2024-12-01

[0184]

[0185] Based on the information in Table 5, it can be seen that the time 2024-12-01 00:04 is an extremely distorted error point, so its related water level information is deleted, and the mean value of the adjacent data points before and after 6.35m is replaced by the original 5.2m.

[0186] For relevant information about the replaced tributary 1-1 on 2024-12-01, please see Table 6.

[0187] Table 6 Information table of branch 1-1 after replacement on 2024-12-01

[0188]

[0189] Secondary setting of DBSCAN parameters:

[0190] When performing the second DBSCAN clustering analysis, the domain radius needs to be reset And the minimum number of neighbors Min1. In order to ensure the accuracy of clustering, a smaller upper limit of the domain radius can be set In the embodiment, Set to 0.2, and Min1 is used as the key threshold to determine whether a point can become a cluster core. The setting of Min1 will take into account the dimension of the data, and make appropriate adjustments and optimizations on this basis. In the embodiment, Min1 can be set to 3, considering that the data is two-dimensional, that is, time and water level, and plus 1 as a regular setting, and in the subsequent sensitivity analysis, Min1 can also be adjusted to 2 or 4 to observe the changes in the clustering effect.

[0191] Secondary Data Clustering and Anomaly Identification:

[0192] The water level data is clustered again using the re-set DBSCAN parameters. In this step, DBSCAN will cluster the water level data based on the domain radius. Divide the water level data points into finer clusters. If the distance between a water level data point and other data points exceeds If the water level of a point is out of the range of , or its water level change is more drastic than other points, that is, the water level change gradient is large, then the point is considered an outlier. The relevant outlier points represent special fluctuations or abnormal events in the water level data, which require further analysis and attention. The secondary clustering process can more accurately identify the abnormal features in the water level data and provide a basis for subsequent analysis and decision-making.

[0193] Then, the relevant monitoring information of the main stream 1, tributary 1-1 and tributary 2-1 is identified and analyzed. For relevant information, please see Table 7.

[0194] Table 7 Information table of main stream 1, tributary 1-1 and tributary 2-1

[0195]

[0196] Based on the identification information in Table 7, it can be seen that there is one abnormal point in tributary 1-1 and tributary 2-1 respectively, and the main stream 1 has three abnormal points.

[0197] Determine the extent of flood progress:

[0198] The flood-prone areas are analyzed by the number of abnormal points. The number of abnormal points in each segmented area is ranked and compared to determine the segmented area with the most concentrated abnormal points. The above area is where the flood is most severe. Then the most unfavorable water level data of the area is extracted for in-depth analysis, where the analysis conditions meet the following relationship:

[0199]

[0200] By comparing the flood conditions at the three locations, it can be found that the flood in the main stream 1 area is the most severe. Therefore, it can be judged that the current flood process mainly affects the vicinity of the main stream 1 area. On this basis, the most unfavorable water level in this area, i.e. 10.4 meters, is extracted for further analysis.

[0201] The process of hierarchical screening and processing of information data sets at different stages of the process is as follows;

[0202] In the forecast information stage, meteorological data in the non-rainfall stage are first collected and hydrological data are calculated based on them. Then, numerical simulation is performed using the EECRS hydraulic model to obtain the simulation results of FLOIF3D. The above results constitute the forecast information set, and finally the forecast information set is comprehensively analyzed to obtain the forecast analysis results.

[0203] Entering the first warning layer stage, the focus is on the collection of hydrological data at the convergence stage of the basin. After obtaining the relevant data, the HECRAS hydraulic model is used for simulation and hydraulic data is calculated at the same time. Subsequently, the information set of the first warning layer is obtained through FLOIT3D numerical simulation, and a comprehensive analysis is performed to produce the first warning result.

[0204] In the second warning layer stage, attention should be paid to the river hydraulic data in the tributary formation stage. Relevant data are obtained through measurement and processed using the DBSCAK algorithm to obtain more accurate hydraulic data. Then, FLOTV3D numerical simulation is carried out, and the second warning layer information set is constructed based on the obtained results, and a comprehensive analysis is performed to obtain the second warning result.

[0205] In the third warning layer, it is necessary to monitor under the bridge during the main stream formation stage, and obtain the hydraulic data of the main stream formation stage through the monitoring process. Subsequently, FLOIV3D is used for numerical simulation to obtain the information set of the third warning layer, and a comprehensive analysis is performed on it to finally obtain the third warning result.

[0206] Finally, in the fourth warning layer, structural monitoring of the bridges during the mainstream flow stage is carried out to obtain structural data. The above structural data constitute the information set of the fourth warning layer. A comprehensive analysis of this set can produce the final warning result.

[0207] The highway bridge water damage monitoring and early warning method proposed in this embodiment divides the time nodes for information collection according to the various stages of the bridge water damage process, so as to collect corresponding information data sets at different stages.

[0208] The specific implementation steps of the highway bridge water damage monitoring and early warning method will be unfolded in sequence:

[0209] First, based on the information data set, the forecast information set and the first warning layer information set are extracted. A comprehensive analysis of the two sets can produce forecast analysis results and first warning results, laying a preliminary foundation for subsequent warning work.

[0210] Secondly, the information data set is further used to construct the second warning layer information set. On this basis, a flood velocity prediction model and a cross-sectional flow analysis model are established. The above two models are combined with the second warning layer information set to quickly and accurately obtain the second warning results, which significantly improves the accuracy and pertinence of the warning.

[0211] Next, based on the information data set, the third warning layer information set and the fourth warning layer information set were screened out, and then the information of the two sets was carefully analyzed to obtain the third warning results and the fourth warning results respectively, further improving the warning analysis results and system integrity.

[0212] Finally, the forecast analysis results, the first warning results, the second warning results, the third warning results and the fourth warning results are integrated. The above process not only realizes the all-round monitoring of the water damage of highway bridges, but also ensures the accuracy and timeliness of the warning results, providing a strong guarantee for the safe operation of bridges.

[0213] In summary, the highway bridge water damage monitoring and early warning method of this embodiment achieves effective monitoring and accurate early warning of highway bridge water damage conditions through stage division, data collection and analysis, and multi-level early warning result fusion.

[0214] See also Figure 6 In an optional embodiment, the present invention further provides a highway bridge water damage monitoring and early warning system, the highway bridge water damage monitoring and early warning system comprises a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, the processor is configured to call the program instructions, and execute the specific steps of the highway bridge water damage monitoring and early warning method and related embodiments provided by the present invention. The highway bridge water damage monitoring and early warning system of the present invention has a complete structure and is objectively stable.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for monitoring and early warning of water damage to highway bridges, characterized in that: The steps include: Dividing the information collection time stages according to the bridge water damage process stage, and obtaining information data sets of different process stages according to the information collection time stages; Establishing a DBSCAN algorithm, using the DBSCAN algorithm and the information data set to obtain a forecast information set, and obtaining a forecast analysis result based on the forecast information set; Obtaining a first warning layer information set based on the DBSCAN algorithm and the information data set, establishing a flood velocity prediction model and a cross-sectional flow analysis model according to the first warning layer information set, and obtaining a first warning result based on the flood velocity prediction model, the cross-sectional flow analysis model and the first warning layer information set; Based on the DBSCAN algorithm and the information data set, a second warning layer information set, a third warning layer information set and a fourth warning layer information set are obtained, and a second warning result, a third warning result and a fourth warning result are obtained according to the second warning layer information set, the third warning layer information set and the fourth warning layer information set respectively; Combining the forecast analysis result, the first warning result, the second warning result, the third warning result and the fourth warning result to achieve comprehensive monitoring and accurate warning of the water damage of highway bridges; The establishment of a flood velocity prediction model and a cross-sectional flow analysis model based on the first warning layer information set includes: Introducing the Xiecai calculation model, and obtaining the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section according to the Xiecai calculation model and the first warning layer information set; Establishing a flood velocity prediction model according to the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section; The hydraulic radius of the U-shaped section satisfies the following relationship: ， in, represents the hydraulic radius of the U-shaped section, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. Indicates the width of the riverbed bottom; The hydraulic radius of the V-shaped section satisfies the following relationship: ， in, represents the hydraulic radius of the V-section, It represents the angle between the riverbed side and the riverbed bottom plane. It indicates the average depth of flood water; The method of establishing a flood velocity prediction model according to the hydraulic radius of the U-shaped section and the hydraulic radius of the V-shaped section includes: Constructing a flow velocity prediction function of a U-shaped water flow section according to the hydraulic radius of the U-shaped section; The U-shaped water flow section velocity prediction function satisfies the following relationship: ， in, represents the average flow velocity of the U-shaped water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. represents the width of the riverbed bottom. The average flood depth. It indicates the flood gradient; Constructing a flow velocity prediction function of a V-shaped water flow section according to the hydraulic radius of the V-shaped section; The V-shaped water flow section velocity prediction function satisfies the following relationship: ， in, represents the average flow velocity of the water flow section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. It indicates the flood gradient; Combining the U-shaped water flow section velocity prediction function and the V-shaped water flow section velocity prediction function to obtain a flood velocity prediction model; The establishment of a flood velocity prediction model and a cross-sectional flow analysis model based on the first warning layer information set includes: Constructing a U-shaped section flow analysis function according to the first warning layer information set; The U-shaped cross-section flow analysis function satisfies the following relationship: ， in, Indicates the flow rate of the U-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. represents the width of the riverbed bottom. It indicates the flood gradient; Constructing a V-section flow analysis function according to the first warning layer information set; The V-shaped cross-section flow analysis function satisfies the following relationship: ， in, Indicates the flow rate of the V-shaped section, represents the roughness coefficient, It represents the angle between the riverbed side and the riverbed bottom plane. The average flood depth. It indicates the flood gradient; Combining the U-shaped cross-section flow analysis function and the V-shaped cross-section flow analysis function to obtain a cross-section flow analysis model; The obtaining of a second warning layer information set, a third warning layer information set and a fourth warning layer information set based on the DBSCAN algorithm and the information data set, and obtaining a second warning result, a third warning result and a fourth warning result respectively according to the second warning layer information set, the third warning layer information set and the fourth warning layer information set include: Filtering out a second warning layer information set based on the DBSCAN algorithm and the information data set, wherein the second warning layer information set includes hydraulic collection information at a tributary formation stage; Obtaining a second early warning result according to the hydraulic collection information; Filtering out a third warning layer information set based on the DBSCAN algorithm and the information data set, wherein the third warning layer information set includes hydraulic detection information at a mainstream formation stage; Obtaining a third early warning result according to the hydraulic detection information; Filtering out a fourth warning layer information set based on the DBSCAN algorithm and the information data set, wherein the fourth warning layer information set includes hydraulic and structural monitoring data at the mainstream stage; A fourth early warning result is obtained based on the hydraulic and structural monitoring data.

2. The highway bridge water damage monitoring and early warning method according to claim 1 is characterized in that: The information collection time stages are divided according to the bridge water damage process stage, and the information data sets of different process stages are obtained according to the information collection time stages, including: According to the stage of bridge water damage process, the information collection time stage is divided into the pre-rainfall stage, basin convergence stage, tributary formation stage, main stream formation stage and main stream action stage; According to the no-rainfall stage, the watershed convergence stage, the tributary formation stage, the main stream formation stage and the main stream action stage, information data sets of different process stages are obtained.

3. The highway bridge water damage monitoring and early warning method according to claim 1 is characterized in that: The establishment of the DBSCAN algorithm includes: Establish the DBSCAN algorithm based on the density space clustering algorithm; Performing data clustering processing on the information data set according to the DBSCAN algorithm, and obtaining abnormal data points of the information data set; The information data set is optimized according to the abnormal data points to obtain information sets at different process stages.

4. The highway bridge water damage monitoring and early warning method according to claim 1 is characterized in that: The step of obtaining a forecast information set by using the DBSCAN algorithm and the information data set, and obtaining a forecast analysis result according to the forecast information set includes: Filtering out a forecast information set according to the DBSCAN algorithm and the information data set, wherein the forecast information set includes meteorological monitoring information in a non-rainfall stage; The rainfall situation in the watershed is analyzed based on the meteorological monitoring information, and a forecast analysis result is obtained based on the rainfall situation in the watershed.

5. A highway bridge water damage monitoring and early warning system, characterized in that: The system includes a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the highway bridge water damage monitoring and early warning method as described in any one of claims 1 to 4.

Images