Village and town dangerous bridge monitoring method and bridge monitoring device

Abstract

The invention discloses a town dangerous bridge monitoring method and a town dangerous bridge monitoring device, and relates to the technical field of bridge monitoring, and the detection method comprises the following specific steps: S100, data acquisition: regularly obtaining an image of an area where a bridge is located by using a high-resolution satellite remote sensing image, according to the invention, through comprehensive application of high-resolution satellite remote sensing images, geographic information acquisition equipment and a GIS spatial analysis model, comprehensive and real-time monitoring of the state of the town dangerous bridge is realized, and through regular acquisition of image data and geographic spatial data of the area where the bridge is located, tiny changes of the bridge and the surrounding environment thereof can be accurately captured, so that the safety of the town dangerous bridge is improved. Accurate data support is provided for subsequent safety condition analysis and intelligent early warning decision making, and in the data processing and integration stage, a bridge structure feature extraction algorithm and a multi-temporal image contrastive analysis technology are adopted to effectively identify bridge structure features and geological disaster hidden danger signs.

Description

Technical Field

[0001] This invention relates to the field of bridge monitoring technology, specifically to a method and device for monitoring dangerous bridges in rural areas. Background Technology

[0002] As vital infrastructure connecting urban and rural areas, the safety and stability of dangerous bridges in towns and villages directly impact the safety of people's lives and property. With the acceleration of urbanization and the increase in traffic flow, dangerous bridges in towns and villages face more and more safety challenges. In order to ensure the safe operation of bridges, it is crucial to promptly identify and address potential safety hazards. Therefore, developing an efficient and accurate monitoring method for dangerous bridges in towns and villages is of great significance.

[0003] Secondly, traditional technologies have many shortcomings in monitoring dangerous bridges in rural towns. Traditional monitoring methods often rely on manual inspections and periodic testing, which are not only inefficient but also make it difficult to comprehensively and accurately grasp the safety status of bridges. In addition, traditional monitoring methods often lack real-time monitoring and early warning mechanisms, making it impossible to detect and deal with potential safety hazards in a timely manner, thus leading to accidents. Furthermore, traditional technologies often lack comprehensiveness and accuracy in monitoring the surrounding environment of bridges, making it difficult to accurately assess the potential risks faced by bridges. Therefore, the application of traditional technologies in monitoring dangerous bridges in rural towns is greatly limited.

[0004] Therefore, developing a monitoring method and device for dangerous bridges in rural towns can not only ensure the safe operation of these bridges, but also improve the overall level of bridge management, providing strong protection for smooth urban and rural traffic and the safety of people's lives and property. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a method and device for monitoring dangerous bridges in rural areas. It acquires accurate data on the bridge and its surrounding environment through high-resolution satellite remote sensing images and geographic information acquisition equipment, and processes and integrates the data using advanced GIS spatial analysis models and bridge structural feature extraction algorithms, thereby realizing real-time monitoring and intelligent early warning of the bridge's safety status.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On the one hand, a method for monitoring dangerous bridges in rural towns, the specific steps of which are as follows:

[0007] S100, Data Acquisition: High-resolution satellite remote sensing images are used to periodically acquire images of the area where the bridge is located. At the same time, geographic information acquisition equipment is used to collect geospatial data on the bridge's geographical location, surrounding topography and hydrology.

[0008] S200, Data Processing and Integration: Radiometric and geometric corrections are performed on satellite image data. Bridge structural features are extracted from the images using bridge structural feature extraction algorithms. Geological hazard signs are identified by comparing and analyzing changes in the surrounding environment through multi-temporal images. The processed image data and geospatial data are coded and classified according to a unified standard, stored in the bridge geospatial database, and an index is established.

[0009] S300, Safety Status Analysis: Extract data from the bridge geospatial database, use the GIS spatial analysis model to analyze the potential risks faced by the bridge based on the influence of topography, hydrology and geology, and generate a safety status assessment report.

[0010] S400, Intelligent Early Warning Decision: Receives the transmitted assessment results and data from the bridge geospatial database, calculates early warning factors based on bridge status and environmental data, combined with the bridge's potential risk values, determines the early warning level based on the magnitude of the early warning factors, and automatically generates emergency response suggestions according to different risk levels.

[0011] S500, Decision Execution and Feedback: Receive emergency response suggestions, convey the suggestions to relevant management departments, and implement them; collect real-time feedback information on bridge status and surrounding areas; analyze the feedback information; and adjust and optimize emergency response suggestions.

[0012] Furthermore, in S100, the geographic information acquisition equipment in the data acquisition includes: a global positioning system receiver, a topographic surveying instrument, a lidar device, a hydrological monitoring station device, and a geological exploration device.

[0013] Furthermore, in step S200, the bridge structural features are extracted using a bridge structural feature extraction formula during data processing and integration. The formula is as follows: Among them, F bridge This represents the extracted bridge structural feature values, where I(x,y) is the pixel value of the satellite image at coordinates (x,y), and (x... i ,y i ) represents the coordinates of the key structural components of the bridge in the image, n represents the number of key structural components, and w represents the coordinates of the key structural components. i These are weighting coefficients set based on the importance of key components. and Let x and y represent the second derivatives of the satellite image in the horizontal and vertical directions at coordinates (x, y), respectively.

[0014] Furthermore, in step S200, the specific steps for determining signs of potential geological hazards by comparing and analyzing changes in the surrounding environment through multi-temporal images in data processing and integration are as follows: collect satellite image data from at least two different periods that cover the area where the bridge is located, and perform radiometric and geometric correction preprocessing; use image registration technology to extract and match features from images of different temporal periods, calculate image differences, subtract the corresponding pixel values ​​of the registered images to obtain the difference image, identify areas of change in the surrounding environment of the bridge by analyzing the changes in the pixel values ​​of the image, and for suspected areas of change, use a supervised classification algorithm to classify images of different temporal periods, and compare the classification results to identify signs of potential geological hazards.

[0015] Furthermore, in step S200, a supervised classification algorithm is used in the data processing and integration to classify images from different time phases. Assume there are n bands and m types of land features in the image. For the pixel to be classified, x = (x1, x2, ..., x...), ... n The probability P(k|x) that a feature belongs to the k-th type of land cover is calculated using the following formula: Where P(x) is a constant for all categories, P(k) is the prior probability of the k-th category of land cover, and P(x|k) is the probability of pixel x appearing under the condition of the k-th category of land cover. Assuming that the probability distribution of each band follows a normal distribution, the formula for calculating P(x|k) is: Where, μ k =(μ k1 ,μ k2 ,…,μ kn ) is the mean vector of the k-th land cover across all bands, Σ k It is the covariance matrix of the k-th land cover, |Σ k | is the determinant of the covariance matrix. It is the inverse of the covariance matrix, (x-μ) k ) T It is (x-μ) k The transpose of ) is used to calculate the probability P(k|x) of the pixel to be classified belonging to each land cover class, and the pixel is assigned to the class with the highest probability, i.e.: Class(x) = argm k axP(k|x).

[0016] Furthermore, in S300, the construction of the GIS spatial analysis model in the security status analysis is based on the formula: R total =α·R geo +β·R hydro +γ·R struct , where R total R is the potential risk value faced by the bridge. geo It is the geological hazard risk value, F bridge R represents the extracted bridge structural feature values.hydro It is the hydrological risk value, where α, β, and γ are weighting coefficients set according to the importance of different risk factors, and α+β+γ=1.

[0017] Furthermore, in the S300, the geological hazard risk value R in the safety status analysis... geo The calculation formula is: Where s j This is the probability score for the j-th type of geological disaster, d j It is the distance from the disaster source to the bridge, D j This is the threshold value for the impact range of the disaster, σ. j It is an indicator of the stability of the soil and rock mass in the area where the bridge is located, Σ max It is the maximum value of the stability index of the soil and rock mass; the hydrological risk value R hydro The calculation formula is: Q current This is the current flow rate value monitored by hydrological monitoring, Q. critical H is the critical flow rate that the bridge can withstand. rise This is the current water level rise, H. safe It is the threshold for the safe water level rise; the bridge structural risk value R struct The calculation formula is: Where ΔL is the actual deformation of the bridge structure, L0 is the maximum allowable deformation of the bridge structure, Δa is the actual stress change of the bridge structure, and a0 is the stress safety change threshold of the bridge structure.

[0018] Furthermore, in the S400 intelligent early warning decision-making process, the early warning level is divided as follows: bridge status data is B, environmental data is E, and the potential risk value faced by the bridge is R. total The warning level is L. The comprehensive status index S is calculated using the formula: S = w B ×B+w E ×E, where w B and w E It is the weight of the bridge status data and the environmental data, and w B +w E =1, calculate the early warning factor F, the formula is: F = α S ×S+β R ×R total Where F is the warning factor, α S and β R This is an adjustment coefficient used to adjust the influence of the comprehensive status index and comprehensive risk value on the early warning factor. The early warning level L is determined based on the value of the early warning factor F, using the following formula: Among them, T1, T2, and T3 are early warning thresholds, which are classification critical values obtained from historical bridge accident data, and T1 < T2 < T3. L = 1 represents low risk; L = 2 represents medium risk; L = 3 represents high risk; L = 4 represents extremely high risk.

[0019] Furthermore, in the S400, for intelligent early warning decision-making, emergency disposal suggestions are automatically generated for different risk levels:

[0020] Low risk level: Notify the maintenance personnel via text message, issue a gentle reminder warning, remind to pay attention to the bridge status, increase the inspection frequency from once a week to twice a week, and focus on checking the subtle changes in the bridge appearance and the operation status of the affiliated facilities according to the low-risk inspection list;

[0021] Medium risk level: Issue an obvious warning, generate emergency disposal suggestions such as setting up a sign at the bridge entrance to restrict specific vehicle types and one-way traffic on some lanes during peak hours, list the implementation steps, responsible departments, and expected effect evaluation criteria;

[0022] High risk level: Activate the advanced warning mechanism, send emergency information to the persons in charge of bridge management, transportation, and emergency rescue departments through multiple communication channels, and generate emergency disposal suggestions for closing some lanes and evacuating the surrounding personnel based on the data of bridge structure stress, risk diffusion, and population distribution;

[0023] Extremely high risk level: Trigger the highest warning response, remind to completely close the bridge and prohibit people and vehicles from passing,联动消防、医疗急救、交通管制周边部门迅速启动全方位应急预案,向各部门推送桥梁风险、事故类型及应对要点。

[0024] On the other hand, a monitoring device for dangerous bridges in rural areas, the device includes: a data acquisition module, a data processing and integration module, a safety condition analysis module, an intelligent early warning decision-making module, and a decision execution and feedback module;

[0025] The data acquisition module: uses high-resolution satellite remote sensing image equipment to regularly obtain image data of the bridge area. At the same time, with the help of global positioning system receivers, topographic surveying instruments, lidar equipment, hydrological monitoring station equipment, and geological exploration equipment (geographic information acquisition equipment), collect the geographical location of the bridge, geographical spatial data of the surrounding terrain and topography, and hydrology;

[0026] The data processing and integration module: receives data from the data acquisition module, performs radiometric correction and geometric correction processing on the satellite image data, uses a bridge structure feature extraction algorithm to extract the bridge structure features from the images, and at the same time determines the signs of geological disaster hazards by analyzing the changes in the surrounding environment through multi-temporal image comparison. Classify and encode the processed image data and geographical spatial data according to a unified standard, store them in the bridge geographical spatial database, and establish an index at the same time; It should be noted that there is an unclear part in the original text for item . The translation is done based on the existing text, but this part may need to be further clarified for a more accurate translation.

[0027] The safety status analysis module, based on data from the bridge geospatial database, uses a GIS spatial analysis model to comprehensively analyze the potential risks faced by the bridge in terms of topography, hydrology, and geology, generates a bridge safety status assessment report, and transmits it to the intelligent early warning decision module.

[0028] The intelligent early warning decision module receives the assessment results transmitted by the safety status analysis module and the data from the bridge geospatial database. Based on the bridge's status and environmental data, it calculates the early warning factor in conjunction with the potential risk value, determines the early warning level based on the magnitude of the early warning factor, and automatically generates emergency response suggestions based on the early warning level.

[0029] The decision execution and feedback module receives emergency response suggestions, conveys these suggestions to relevant management departments, and executes them. During execution, it collects real-time feedback information on the bridge's status and the surrounding environment, analyzes the feedback information, and feeds the analysis results back to the intelligent early warning decision module to adjust and optimize the emergency response suggestions.

[0030] Compared with existing technologies, this method and device for monitoring dangerous bridges in rural areas has the following advantages:

[0031] I. This invention achieves comprehensive and real-time monitoring of the condition of dangerous bridges in rural towns by comprehensively utilizing high-resolution satellite remote sensing imagery, geographic information acquisition equipment, and GIS spatial analysis models. By regularly collecting image and geospatial data of the area where the bridge is located, this invention can accurately capture subtle changes in the bridge and its surrounding environment, providing precise data support for subsequent safety status analysis and intelligent early warning decision-making. In the data processing and integration stage, the bridge structural feature extraction algorithm and multi-temporal image comparison analysis technology are used to effectively identify bridge structural features and signs of potential geological hazards, which not only improves the accuracy and efficiency of monitoring but also provides a scientific basis for bridge maintenance and management.

[0032] Second, this invention, by receiving data from a bridge geospatial database and combining it with bridge status and environmental data, can intelligently calculate early warning factors and determine early warning levels, thereby automatically generating emergency response suggestions. This not only realizes intelligent and automated early warning decision-making but also improves the speed and accuracy of emergency response. In particular, for different risk levels, this invention can automatically generate corresponding emergency response suggestions, including adjustments to inspection frequency, lane traffic restrictions, and evacuation measures for surrounding personnel. This provides bridge management departments with scientific and feasible emergency plans. This intelligent early warning decision-making mechanism not only reduces the workload of management personnel but also improves the overall level of bridge safety management, providing strong protection for the safe operation of dangerous bridges in rural areas.

[0033] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0035] Figure 1 A flowchart of a method for monitoring dangerous bridges in rural towns;

[0036] Figure 2 This is a flowchart illustrating the workflow of a monitoring device for dangerous bridges in rural towns. Detailed Implementation

[0037] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0038] Example 1:

[0039] Monitoring of dangerous bridges in a mountainous township

[0040] In a mountainous township, there is a bridge connecting two villages. Due to its early construction and long-term impact from the complex mountain environment, it has been listed as a dangerous bridge and is under key monitoring.

[0041] Data Acquisition: Monitoring personnel use high-resolution satellite remote sensing imagery equipment to acquire images of the bridge area every two weeks. Simultaneously, a GPS receiver is used to precisely measure the bridge's geographical location, determining its latitude and longitude coordinates with minimal error. A topographic surveying instrument is used to conduct detailed measurements of the terrain within a 500-meter radius of the bridge, recording information on terrain undulations and slope angles. LiDAR equipment scans the terrain from multiple angles to acquire high-precision three-dimensional terrain data, clearly showing the spatial relationship between the bridge and the surrounding terrain. Hydrological monitoring station equipment continuously monitors river flow, water level, and velocity data 24 hours a day. During heavy rain or other severe weather, the monitoring frequency is increased. Geological exploration equipment drills and samples the bridge foundation and surrounding geology to analyze the composition, density, and stability of the soil and rock.

[0042] Data Processing and Integration: The acquired satellite image data is imported into professional image processing software for radiometric and geometric correction, removing noise and distortion from the images. This ensures that the color and brightness parameters more accurately reflect the actual situation, and that the geometric shape better matches the real terrain. A bridge structural feature extraction algorithm is then used to identify key structural components of the bridge, including piers, bridge deck, and abutments. The formula is as follows: Among them, F bridge This represents the extracted bridge structural feature values, where I(x,y) is the pixel value of the satellite image at coordinates (x,y), and (x... i ,y i ) represents the coordinates of the key structural components of the bridge in the image, n represents the number of key structural components, and w represents the coordinates of the key structural components. i These are weighting coefficients set based on the importance of key components. and Let x and y represent the second derivatives of the satellite image in the horizontal and vertical directions at coordinates (x, y), respectively. Measure its size and location parameters. Compare satellite images from different periods over the past six months. It was found that vegetation on the mountainside upstream of the bridge has decreased locally, and there are slight cracks on the ground surface. A supervised classification algorithm was used to analyze this suspected area of ​​change. Assume there are n bands and m types of land features in the image. For the pixel to be classified, x = (x1, x2, ..., x...), ... n The probability P(k|x) that a feature belongs to the k-th type of land cover is calculated using the following formula: Where P(x) is a constant for all categories, P(k) is the prior probability of the k-th category of land cover, and P(x|k) is the probability of pixel x appearing under the condition of the k-th category of land cover. Assuming that the probability distribution of each band follows a normal distribution, the formula for calculating P(x|k) is: Where, μ k =(μ k1 ,μ k2 ,…,μ kn ) is the mean vector of the k-th land cover across all bands, Σ k It is the covariance matrix of the k-th land cover, |Σ k | is the determinant of the covariance matrix. It is the inverse of the covariance matrix, (x-μ) k ) T It is (x-μ) k The transpose of ) is used to calculate the probability P(k|x) of the pixel to be classified belonging to each type of land cover, and the pixel is assigned to the type with the highest probability, i.e.: After determining that the area has certain potential risks of geological disasters, the processed image data and geospatial data are stored in the bridge geospatial database according to a unified coding and classification standard, and a comprehensive index is established to facilitate quick querying and retrieval in the future.

[0043] Safety Status Analysis: Based on data from the bridge geospatial database, and utilizing a GIS spatial analysis model, this analysis comprehensively considers the complex mountainous terrain, significant variations in river flow, and potential geological hazards. The formula is: R total =α·R geo +β·R hydro +γ·R struct , where R total R is the potential risk value faced by the bridge. geo This is the geological hazard risk value, and the formula is: Where ΔL is the actual deformation of the bridge structure, L0 is the maximum allowable deformation of the bridge structure, Δa is the actual stress change of the bridge structure, a0 is the safe stress change threshold of the bridge structure, and F bridge The extracted bridge structural feature values ​​are calculated using the following formula: Q current This is the current flow rate value monitored by hydrological monitoring, Q. critical H is the critical flow rate that the bridge can withstand. rise This is the current water level rise, H. safe It is the threshold for the safe water level rise height, R hydro This is the hydrological risk value, calculated using the following formula: Where ΔL is the actual deformation of the bridge structure, L0 is the maximum allowable deformation of the bridge structure, Δa is the actual stress change of the bridge structure, a0 is the stress safety change threshold of the bridge structure, and α, β, and γ are weighting coefficients set according to the importance of different risk factors, and α+β+γ=1. The analysis found that the recent increase in rainfall in the mountainous area and the increase in river flow have generated a large scouring force on the bridge foundation. At the same time, the stability of the mountain has decreased, which may trigger landslide geological disasters that threaten the safety of the bridge. Based on the analysis results, a safety status assessment report was generated, which clearly pointed out the main risk points and the overall safety status level of the bridge.

[0044] Intelligent early warning and decision-making: The system receives data from the bridge geospatial database, combines the bridge's current status and environmental data with the bridge's potential risk value to calculate an early warning factor, and determines the early warning level based on the magnitude of the early warning factor. Let the bridge status data be B, the environmental data be E, and the potential risk value faced by the bridge be R. total The warning level is L. The comprehensive status index S is calculated using the formula: S = w B ×B+w E ×E, where w B and w E It is the weight of the bridge status data and the environmental data, and w B +w E =1, calculate the early warning factor F, the formula is: F = α S ×S+β R×R total , where F is the warning factor, α S and β R are adjustment coefficients used to adjust the influence degrees of the comprehensive status index and the comprehensive risk value on the warning factor. The warning level L is determined according to the value of the warning factor F. The formula is: where T1, T2, and T3 are warning thresholds set according to historical data, and T1 < T2 < T3. L is the warning level. L = 1 represents low risk; L = 2 represents medium risk; L = 3 represents high risk; L = 4 represents extremely high risk. When the calculated warning level is high risk, emergency disposal suggestions are automatically generated, including immediately closing some lanes and only allowing small vehicles and pedestrians to pass; evacuating the residents within 200 meters around the bridge and setting up temporary resettlement points; notifying the bridge management department, the traffic department, the emergency rescue department, and the local government to start the emergency plan and prepare to deal with possible disasters.

[0045] Decision execution and feedback: After receiving the emergency disposal suggestions, the relevant management departments act quickly. The traffic department sets up warning signs and roadblocks at the bridge entrance, closes some lanes, and arranges traffic police to direct traffic on the surrounding roads. The local government organizes community workers to notify the surrounding residents door to door for evacuation and helps the residents transfer important materials. During the execution process, special personnel are arranged to collect the feedback information of the bridge status and the surrounding environment in real time, such as whether there are new deformations in the bridge structure, whether the riverbank erosion situation has intensified, and whether the evacuation of residents is smooth. After analyzing this information again, it is fed back to the intelligent warning decision-making module to adjust and optimize the subsequent emergency disposal measures, such as Figure 1 , which clearly shows the complete process of dangerous bridge monitoring in mountainous rural areas from data collection to decision execution and feedback.

[0046] In summary, for the monitoring of the dangerous bridge in this mountainous rural area, data is collected through multi-device collaboration, covering various aspects of terrain, hydrology, and geology. After data processing and integration, potential hazards are accurately identified by comparing algorithms with images. The high risk is evaluated using the GIS spatial analysis model, and reasonable emergency disposal suggestions are generated accordingly. Each department responds and executes quickly, and real-time feedback and adjustment are carried out. This series of operations effectively guarantees the safety monitoring and management of the bridge in the complex mountainous environment, greatly reduces the disaster risk, builds a solid defense line for the safe travel of residents, and also provides a practical example for the monitoring of similar mountainous dangerous bridges, highlighting the remarkable effectiveness of this invention in ensuring the safety of rural traffic infrastructure.

[0047] Embodiment 2:

[0048] Monitoring of a dangerous bridge in a water town rural area.

[0049] In a water town, a bridge spans a river connecting the town's commercial and residential areas. Due to the large number of passing boats and complex water flow, the bridge poses certain safety hazards and requires comprehensive monitoring.

[0050] Data Acquisition: The monitoring team uses high-resolution satellite remote sensing imagery equipment to acquire images of the area where the bridge is located once a month. A GPS receiver is used to accurately measure the geographical location of the bridge to ensure positioning accuracy. Topographic surveying instruments measure the terrain around the bridge, including the slope of the riverbank and information on terrain changes. LiDAR equipment scans the bridge and surrounding terrain from different angles to obtain detailed three-dimensional terrain data. Hydrological monitoring station equipment monitors the river's flow, water level, flow velocity, and flow direction in real time, paying particular attention to the impact of vessel traffic on the water flow. Geological exploration equipment explores the geology of the bridge foundation and surrounding area to analyze the properties and stability of the soil and rock mass.

[0051] Data processing and integration: Radiometric and geometric corrections are performed on the acquired satellite images to improve image quality and accuracy. A bridge structural feature extraction algorithm is then used to accurately identify the various structural components of the bridge. The formula is as follows: For example, the dimensions and location parameters of bridge piers, bridge body, and railings were measured. Comparison with satellite images from different periods over the past year revealed localized erosion on the riverbank downstream of the bridge, and some small buildings were found near the bridge construction site. Multi-temporal image comparison analysis was used to further identify potential geological hazards. Satellite image data from several different periods covering the bridge area were collected, and radiometric and geometric corrections were performed. Image registration technology was used to extract and match features from different temporal images, and image difference calculations were performed. The difference image was obtained by subtracting the corresponding pixel values ​​of the registered images. By analyzing the changes in pixel values ​​in this image, areas of environmental change around the bridge were identified. For suspected areas of change, a supervised classification algorithm was used to classify the images from different temporal periods. Assuming there are n bands and m types of land features in the image, for the pixel to be classified, x = (x1, x2, ..., x...) n The probability P(k|x) that a feature belongs to the k-th type of land cover is calculated using the following formula: The probability of pixel x appearing, assuming the probability distribution of each band follows a normal distribution, is calculated using the formula: Calculate the probability P(k|x) of the pixel to be classified belonging to each type of land cover, and classify it into the type with the highest probability. Compare the classification results to identify signs of potential geological hazards, determine the scope and degree of riverbank erosion, and the potential impact of new buildings on bridge safety. Encode and classify the processed image data and geospatial data according to a unified standard, store them in the bridge geospatial database, and establish an index.

[0052] Safety Status Analysis: Utilizing a GIS spatial analysis model, and considering the complex water flow, frequent boat traffic, and riverbank erosion in the water town area, the potential risks faced by the bridge are assessed using the formula: R total =α·R geo +β·R hydro +γ·R struct Considering that riverbank erosion may lead to bridge foundation instability and a high risk of ship collisions, a safety status assessment report was generated, pointing out the safety hazards of the bridge and areas that require special attention.

[0053] Intelligent early warning decision-making: Based on data from the bridge geospatial database, current bridge status and environmental data, and the potential risk value of the bridge, an early warning factor is calculated. The early warning level is determined based on the magnitude of the early warning factor. Let the bridge status data be B, the environmental data be E, and the potential risk value faced by the bridge be R. total The warning level is L. The comprehensive status index S is calculated using the formula: S = w B ×B+w E ×E, calculate the early warning factor F, the formula is: F=α S ×S+β R ×R total The warning level L is determined based on the value of the warning factor F, using the following formula: L=1 indicates low risk; L=2 indicates medium risk; L=3 indicates high risk; L=4 indicates extremely high risk. The calculated warning level is medium risk. The system automatically generates emergency response suggestions, such as setting up obvious warning signs upstream and downstream of the bridge to remind passing ships to maintain a safe distance; arranging professional personnel to conduct regular inspections of the bridge, focusing on riverbank erosion areas and bridge structural connections; and strengthening traffic management around the bridge during peak traffic periods, restricting the passage of large and overloaded vehicles.

[0054] Decision Implementation and Feedback: Upon receiving emergency response recommendations, relevant management departments immediately implement them. The transportation department sets up warning buoys and signs upstream and downstream of the bridge to remind vessels to pay attention to safety. The bridge maintenance department arranges professional personnel to conduct detailed inspections of the bridge according to the prescribed frequency. After each inspection, detailed records are kept of the bridge's condition and riverbank erosion. During implementation, feedback information on the bridge's condition and the surrounding environment is collected in real time, such as whether vessels are complying with regulations and whether there are any abnormal changes in the bridge structure. This feedback information is fed back to the intelligent early warning decision-making module to promptly adjust and optimize emergency response measures, ensuring the safe operation of the bridge. Figure 2 This demonstrates the workflow relationships between the data acquisition module, data processing and integration module, safety status analysis module, intelligent early warning decision-making module, and decision execution and feedback module during the monitoring of dangerous bridges in water towns.

[0055] In summary, this invention, used in the monitoring of dangerous bridges in water towns, utilizes high-resolution satellite remote sensing imagery and various geographic information acquisition devices to obtain data. After processing and integration, the problem of riverbank erosion is clearly identified. The risk is assessed as medium risk using a GIS spatial analysis model, leading to targeted early warning decisions, including setting up warning signs, strengthening inspections, and traffic management. During the implementation of these decisions, various departments cooperate closely and provide timely feedback, achieving dynamic management of dangerous bridges. This embodiment fully demonstrates that the invention can effectively address the complex environmental factors in water towns, ensure the safe operation of dangerous bridges, and has significant demonstrative value for the monitoring of dangerous bridges in water towns, thereby improving the overall level of bridge management in townships.

[0056] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for monitoring dangerous bridges in rural towns, characterized in that, The specific steps of this monitoring method are as follows: S100, Data Acquisition: High-resolution satellite remote sensing images are used to periodically acquire images of the area where the bridge is located. At the same time, geographic information acquisition equipment is used to collect geospatial data on the bridge's geographical location, surrounding topography and hydrology. S200, Data Processing and Integration: Radiometric and geometric corrections are performed on satellite image data. Bridge structural features are extracted from the images using bridge structural feature extraction algorithms. Geological hazard signs are identified by comparing and analyzing changes in the surrounding environment through multi-temporal images. The processed image data and geospatial data are coded and classified according to a unified standard, stored in the bridge geospatial database, and an index is established. S300, Safety Status Analysis: Extract data from the bridge geospatial database, use the GIS spatial analysis model to analyze the potential risks faced by the bridge based on the influence of topography, hydrology and geology, and generate a safety status assessment report. S400, Intelligent Early Warning Decision: Receives the transmitted assessment results and data from the bridge geospatial database, calculates early warning factors based on bridge status and environmental data, combined with the bridge's potential risk values, determines the early warning level based on the magnitude of the early warning factors, and automatically generates emergency response suggestions according to different risk levels. S500, Decision Execution and Feedback: Receive emergency response suggestions, convey the suggestions to relevant management departments, and implement them; collect real-time feedback information on bridge status and surrounding areas; analyze the feedback information; and adjust and optimize emergency response suggestions.

2. The method for monitoring dangerous bridges in rural towns according to claim 1, characterized in that, In S100, the geographic information acquisition equipment for data acquisition includes: a global positioning system receiver, a topographic surveying instrument, a lidar device, hydrological monitoring station equipment, and geological exploration equipment.

3. The method for monitoring dangerous bridges in rural towns according to claim 1, characterized in that, In step S200, during data processing and integration, bridge structural features are extracted using a bridge structural feature extraction formula, which is: Among them, F bridge This represents the extracted bridge structural feature values, where I(x,y) is the pixel value of the satellite image at coordinates (x,y), and (x... i ,y i ) represents the coordinates of the key structural components of the bridge in the image, n represents the number of key structural components, and w represents the coordinates of the key structural components. i These are weighting coefficients set based on the importance of key components. and Let x and y represent the second derivatives of the satellite image in the horizontal and vertical directions at coordinates (x, y), respectively.

4. The method for monitoring dangerous bridges in rural towns according to claim 1, characterized in that, In step S200, the specific steps for determining signs of potential geological hazards by comparing and analyzing changes in the surrounding environment through multi-temporal images during data processing and integration are as follows: Collect satellite image data from at least two different periods covering the area where the bridge is located, perform radiometric and geometric correction preprocessing, and use image registration technology to extract features from the images from different temporal periods. The system matches and calculates the image difference. The corresponding pixel values ​​of the registered images are subtracted to obtain the difference image. By analyzing the changes in the pixel values ​​of this image, the system identifies areas of environmental change around the bridge. For suspected areas of change, a supervised classification algorithm is used to classify images from different time periods. The classification results are compared to identify signs of potential geological hazards.

5. A method for monitoring dangerous bridges in rural towns according to claim 4, characterized in that, In step S200, a supervised classification algorithm is used to classify images from different time phases during data processing and integration. Assume there are n bands and m types of ground features in the image. For the pixel to be classified, x = (x1, x2, ..., x...), ... n The probability P(k|x) that a feature belongs to the k-th type of land cover is calculated using the following formula: Where P(x) is a constant for all categories, P(k) is the prior probability of the k-th category of land cover, and P(x|k) is the probability of pixel x appearing under the condition of the k-th category of land cover. Assuming that the probability distribution of each band follows a normal distribution, the formula for calculating P(x|k) is: Where, μ k =(μ k1 ,μ k2 ,…,μ kn ) is the mean vector of the k-th land cover across all bands, Σ k It is the covariance matrix of the k-th land cover, |Σ k | is the determinant of the covariance matrix. It is the inverse of the covariance matrix, (x-μ) k ) T It is (x-μ) k The transpose of ) is used to calculate the probability P(k|x) of the pixel to be classified belonging to each type of land cover, and the pixel is assigned to the type with the highest probability, i.e.:

6. The method for monitoring dangerous bridges in rural towns according to claim 1, characterized in that, The S300 section describes the construction of the GIS spatial analysis model in the security status analysis, using the formula: R total =α·R geo +β·R hydro +γ·R struct , where R total R is the potential risk value faced by the bridge. geo It is the geological hazard risk value, F bridge R represents the extracted bridge structural feature values. hydro It is the hydrological risk value, where α, β, and γ are weighting coefficients set according to the importance of different risk factors, and α+β+γ=1.

7. The method for monitoring dangerous bridges in rural towns according to claim 3, characterized in that, In S300, the geological hazard risk value R in the safety status analysis... geo The calculation formula is: Where s j This is the probability score for the j-th type of geological disaster, d j It is the distance from the disaster source to the bridge, D j This is the threshold value for the impact range of the disaster, σ. j It is an indicator of the stability of the soil and rock mass in the area where the bridge is located, Σ max It is the maximum value of the stability index of the soil and rock mass; the hydrological risk value R hydro The calculation formula is: Q current This is the current flow rate value monitored by hydrological monitoring, Q. critical H is the critical flow rate that the bridge can withstand. rise This is the current water level rise, H. safe It is the threshold for the safe water level rise; the bridge structural risk value R struct The calculation formula is: Where ΔL is the actual deformation of the bridge structure, L0 is the maximum allowable deformation of the bridge structure, Δa is the actual stress change of the bridge structure, and a0 is the stress safety change threshold of the bridge structure.

8. A method for monitoring dangerous bridges in rural towns according to claim 6, characterized in that, For the S400, in the division of warning levels in intelligent warning decision-making, let the bridge status data be B, the environmental data be E, and the potential risk value faced by the bridge be R total , the warning level be L, calculate the comprehensive status index S, the formula is: S = w B ×B + w E ×E, where w B and w E are the weights of the bridge status data and environmental data, and w B + w E = 1, calculate the warning factor F, the formula is: F = α S ×S + β R ×R total , where F is the warning factor, α S and β R are adjustment coefficients, used to adjust the influence degree of the comprehensive status index and comprehensive risk value on the warning factor, and determine the warning level L according to the value of the warning factor F, the formula is: Where T1, T2, T3 are warning thresholds, the classification critical values obtained from historical bridge accident data, and T1 < T2 < T3, L = 1 is low risk; L = 2 is medium risk; L = 3 is high risk; L = 4 is extremely high risk.

9. A method for monitoring dangerous bridges in rural towns according to claim 8, characterized in that, The S400 system automatically generates emergency response suggestions for different risk levels during intelligent early warning decision-making. Low-risk level: Notify maintenance personnel via SMS, issue mild warnings, remind them to pay attention to the bridge's condition, increase the inspection frequency from once a week to twice a week, and focus on checking minor changes in the bridge's appearance and the operation of its ancillary facilities based on the low-risk inspection checklist; Medium risk level: Issue a clear warning and generate emergency response suggestions such as setting up signs at bridge entrances to restrict specific vehicle types and one-way traffic on some lanes during peak hours, and list the implementation steps, responsible departments and expected effect evaluation standards; High-risk level: The advanced early warning mechanism is activated, and emergency information is sent to the heads of bridge management, transportation and emergency rescue departments through multiple communication channels. Based on data on bridge structural stress and risk spread, as well as population distribution, emergency response suggestions for closing some lanes and evacuating surrounding personnel are generated. Extremely high risk level: Triggers the highest level of warning response, reminding people to completely close the bridge and prohibiting the passage of people and vehicles. It also prompts the fire department, medical emergency, traffic control and surrounding departments to quickly activate a comprehensive emergency plan and push the bridge risk, accident type and response points to all departments.

10. A monitoring device for dangerous bridges in rural towns, characterized in that, The device is applicable to a method for monitoring dangerous bridges in rural areas as described in any one of claims 1-9. The device includes: a data acquisition module, a data processing and integration module, a safety status analysis module, an intelligent early warning decision-making module, and a decision execution and feedback module. The data acquisition module uses high-resolution satellite remote sensing imagery equipment to periodically acquire image data of the area where the bridge is located. At the same time, it uses GPS receivers, topographic surveying instruments, lidar equipment, hydrological monitoring station equipment, and geological exploration equipment to collect geospatial data of the bridge's geographical location, surrounding topography, and hydrology. The data processing and integration module receives data from the data acquisition module, performs radiometric and geometric correction on the satellite image data, extracts the structural features of the bridge from the image using a bridge structural feature extraction algorithm, identifies signs of potential geological hazards by comparing and analyzing changes in the surrounding environment through multi-temporal images, encodes and classifies the processed image data and geospatial data according to a unified standard, and stores them in the bridge geospatial database, while also establishing an index. The safety status analysis module, based on data from the bridge geospatial database, uses a GIS spatial analysis model to comprehensively analyze the potential risks faced by the bridge in terms of topography, hydrology, and geology, generates a bridge safety status assessment report, and transmits it to the intelligent early warning decision module. The intelligent early warning decision module receives the assessment results transmitted by the safety status analysis module and the data from the bridge geospatial database. Based on the bridge's status and environmental data, it calculates the early warning factor in conjunction with the potential risk value, determines the early warning level based on the magnitude of the early warning factor, and automatically generates emergency response suggestions based on the early warning level. The decision execution and feedback module receives emergency response suggestions, conveys these suggestions to relevant management departments, and executes them. During execution, it collects real-time feedback information on the bridge's status and the surrounding environment, analyzes the feedback information, and feeds the analysis results back to the intelligent early warning decision module to adjust and optimize the emergency response suggestions.

Images