Inspection Data Monitoring Method and Server Applied to Road and Bridge Early Warning in Mountainous Areas

Abstract

The present invention provides a patrol data monitoring method and a server for mountain road and bridge early warning. First, road and bridge remote sensing monitoring data including current terrain distribution characteristics, road and bridge structure state parameters, and historical disaster records are obtained. Then, according to the current terrain distribution characteristics, a terrain feature extraction model is called to segment the target mountain road section, generating patrol sub-regions and terrain feature labels. Next, based on the terrain feature labels and road and bridge structure state parameters, a dynamic flight path including patrol nodes and flight parameters is generated for the unmanned aerial vehicle through a path planning model. Subsequently, the unmanned aerial vehicle is controlled to patrol according to this path, collecting multi-dimensional monitoring data such as surface deformation data, road and bridge crack images, and slope displacement trajectories. Finally, the multi-dimensional monitoring data and historical disaster records are input into a risk early warning model to generate a risk level signal and disposal suggestion information, realizing comprehensive intelligent monitoring and early warning of mountain roads and bridges and improving the monitoring accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and more particularly, to a method for monitoring inspection data and a server applied to mountain road and bridge early warning. Background Art

[0002] During the construction and operation of mountain roads and bridges, ensuring the safety and stability of roads and bridges is crucial for ensuring smooth transportation and the safety of people's lives and property. Due to the complex geographical environment in mountainous areas, with large terrain undulations, diverse geological conditions, and frequent impacts from natural disasters such as landslides, debris flows, and earthquakes, mountain roads and bridges face many potential risks. Therefore, effective monitoring and early warning of mountain roads and bridges are particularly critical.

[0003] Currently, there are various methods for monitoring mountain roads and bridges. The traditional manual inspection method relies on inspectors to physically check the condition of roads and bridges. However, due to the complex terrain in mountainous areas, manual inspection is not only inefficient but also difficult to reach some steep areas, easily resulting in inspection blind spots and unable to comprehensively and accurately grasp the overall condition of roads and bridges.

[0004] With the development of technology, some monitoring systems based on fixed sensors have been applied. These monitoring systems obtain partial data by installing fixed sensors at key positions of roads and bridges. For example, simple displacement sensors monitor the displacement changes of roads and bridges. However, such methods have obvious limitations. The installation positions of sensors are fixed and cannot flexibly adjust the monitoring range and focus according to the actual risk conditions of roads and bridges and terrain characteristics, and have insufficient monitoring capabilities for the complex terrain environment around roads and bridges and the dynamic changes of risks in different regions.

[0005] Meanwhile, in terms of inspection path planning, most existing technologies adopt the method of presetting fixed routes. Whether it is manual inspection or inspection using devices such as drones, fixed routes cannot adapt to the diversity of mountain terrains and the dynamic changes of the structural states of roads and bridges. This results in insufficient inspection frequencies in some high-risk areas, while excessive resources are invested in some low-risk areas, and the inspection forces cannot be allocated reasonably and efficiently. Summary of the Invention

[0006] In view of the above-mentioned problems, in combination with the first aspect of the present invention, embodiments of the present invention provide a method for monitoring inspection data applied to mountain road and bridge early warning, the method comprising:

[0007] Obtain remote sensing monitoring data of roads and bridges in a target mountainous section, the remote sensing monitoring data of roads and bridges including current terrain distribution characteristics, road and bridge structure state parameters, and historical disaster records;

[0008] Based on the current terrain distribution characteristics, call a terrain feature extraction model to perform regional segmentation on the target mountainous section, generating multiple inspection sub-regions and corresponding terrain feature labels;

[0009] According to the terrain feature tags and the road and bridge structure state parameters, a dynamic flight path of the unmanned aerial vehicle in the inspection sub-region is generated through a path planning model, and the dynamic flight path includes a plurality of inspection nodes and flight parameters between the inspection nodes;

[0010] Based on the dynamic flight path, the unmanned aerial vehicle is controlled to perform real-time inspection tasks, and multi-dimensional monitoring data in the inspection sub-region is collected, where the multi-dimensional monitoring data includes surface deformation data, road and bridge crack images, and slope displacement trajectories;

[0011] The multi-dimensional monitoring data and the historical disaster records are input into a risk warning model to generate a risk level signal for the target mountainous section of the road and corresponding disposal suggestion information.

[0012] On the other hand, an embodiment of the present invention further provides a server, including a processor and a machine-readable storage medium, the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0013] Based on the above aspects, in the embodiments of the present application, road and bridge remote sensing monitoring data including current terrain distribution characteristics, road and bridge structure state parameters, and historical disaster records is obtained. Regional segmentation is performed based on the current terrain distribution characteristics to generate terrain feature tags, and then a dynamic flight path for the unmanned aerial vehicle (UAV) is generated in combination with the road and bridge structure state parameters. By closely integrating terrain factors, road and bridge structures, and UAV inspection path planning, different from the traditional fixed-path inspection method, the dynamic flight path generated by this method can intelligently adjust the inspection route and nodes according to the variability of mountainous terrain and the differences in road and bridge structure states. It not only effectively covers all key areas, avoiding inspection blind spots, but also can reasonably allocate inspection resources according to the characteristics and risk levels of different regions, improving inspection efficiency and pertinence. At the same time, the flight parameter settings in the dynamic flight path ensure that the UAV can perform inspection tasks safely, stably, and efficiently in complex mountainous environments, further enhancing the reliability and practicality of the entire monitoring system. During real-time inspection tasks, multi-dimensional monitoring data is collected, including surface deformation data, road and bridge crack images, and slope displacement trajectories, etc., which can accurately capture the minute changes of road and bridges under the influence of various factors, providing rich and accurate basis for timely discovery of potential risks. Finally, the multi-dimensional monitoring data and historical disaster records are input into the risk early warning model to generate risk level signals and disposal suggestion information, realizing the intelligent assessment and early warning of risks for target mountain road sections. By fully considering the evolution law of mountain road and bridge disasters and the current actual situation, it can more accurately predict possible disaster risks and provide highly targeted and operable disposal suggestions. Compared with traditional early warning methods, it greatly improves the accuracy and timeliness of early warning, saves valuable time for taking effective preventive measures in a timely manner, effectively guarantees the safe operation of mountain roads and bridges, and reduces disaster losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic flowchart of the execution process of the inspection data monitoring method for mountain road and bridge early warning provided by an embodiment of the present invention.

[0015] Figure 2 It is a schematic diagram of the server hardware architecture provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The present invention will be specifically described below with reference to the accompanying drawings of the specification. Figure 1 It is a schematic flowchart of the inspection data monitoring method for mountain road and bridge early warning provided by an embodiment of the present invention. The inspection data monitoring method for mountain road and bridge early warning will be introduced in detail below.

[0017] Step S110: Obtain the road and bridge remote sensing monitoring data of the target mountain road section, where the road and bridge remote sensing monitoring data includes current terrain distribution characteristics, road and bridge structure state parameters, and historical disaster records.

[0018] For example, consider a section of a highway in a mountainous area. This highway section is located among mountains, and the surrounding terrain is complex and variable. Multispectral image data and three-dimensional point cloud data of this target mountainous area section are obtained through satellite remote sensing equipment. After the multispectral image data is processed by land cover classification, the sub-features of the current terrain distribution characteristics are obtained. For example, in a certain area, the vegetation is dense and the vegetation coverage density is high, while in other areas, there are more exposed rocks, and at the same time, hydrological distribution features such as rivers can be clearly seen. These constitute the current terrain distribution characteristics. For the three-dimensional point cloud data, after elevation difference processing, an accurate terrain slope matrix and surface undulation index are generated. For example, on the hillside on one side of a certain section of the road, the terrain slope matrix shows a large slope and a high surface undulation.

[0019] From the historical maintenance database of this highway section, the state parameters of the road and bridge structures are extracted. Among them, a certain pier has a certain degree of inclination, and its inclination angle is accurately recorded. There is settlement in some sections of the road surface, and the settlement rate is also measured and recorded. The integrity parameters of the slope support structure are also available in the database.

[0020] In addition, historical disaster records show that in the past few years, multiple disaster events have occurred in this mountainous area section. For example, a landslide event occurred at a certain specific location, resulting in damage to part of the roadbed; bridge crack expansion events were found on a certain bridge, and although they have been repaired, they still need to be closely monitored; there was also a roadbed collapse event in a certain section. These disaster events are classified by type, and their respective geographical coordinates and the timestamps of occurrence are all recorded in detail.

[0021] Step S120, based on the current terrain distribution characteristics, call the terrain feature extraction model to perform regional segmentation on the target mountainous area section, generating multiple inspection sub-regions and corresponding terrain feature labels.

[0022] Taking the previously mentioned mountainous highway section as an example, the terrain feature extraction model can segment the entire mountainous area section according to the current terrain distribution characteristics obtained previously, such as the vegetation coverage density in different regions, the exposed rock areas, and the hydrological distribution. For example, the area with dense vegetation, gentle slope, and close to the water source is divided into an inspection sub-region, and the terrain feature label of this region is "dense vegetation - low slope - near water". And for those sections with exposed rocks and large slopes, they are divided into another inspection sub-region, and its terrain feature label is "exposed rocks - high slope". In this way, the entire mountainous area section is divided into multiple inspection sub-regions, and each sub-region has its unique terrain feature label. These terrain feature labels accurately reflect the terrain characteristics of the sub-region, providing an important basis for the subsequent inspection path planning of the unmanned aerial vehicle.

[0023] Step S130: According to the terrain feature tags and the road and bridge structure state parameters, generate a dynamic flight path of the UAV in the inspection sub-region through a path planning model. The dynamic flight path includes multiple inspection nodes and flight parameters between the inspection nodes.

[0024] Still taking this mountainous highway section as an example, for the previously divided different inspection sub-regions and their corresponding terrain feature tags and road and bridge structure state parameters, the path planning model is used to plan the flight path of the UAV.

[0025] For example, in the inspection sub-region with dense vegetation - low slope - near water, due to the high vegetation coverage density and the low slope shown in the terrain slope matrix, according to relevant calculations, the minimum safe flight height of the UAV in this area is relatively low, and the obstacle avoidance buffer distance is also relatively small. At the same time, according to the road and bridge structure state parameters, if the inclination angle of a certain pier is small and the integrity of the slope support structure is good, then when determining the priority order of the inspection nodes, the priority of these nodes is relatively low, and the data collection duration of each inspection node is also shorter.

[0026] For example, for the inspection nodes of a certain bridge, due to its good structure state, the priority is low, and the data collection duration is set to a short time. Then, a path optimization algorithm is used to sort these inspection nodes spatially. First, assign a corresponding lower limit value of the flight height and an obstacle avoidance buffer boundary range to each inspection node. For example, for an inspection node near vegetation, the lower limit value of its flight height is set to be slightly higher than the vegetation height plus a certain safety margin, and the obstacle avoidance buffer boundary range takes into account the interference factors of the vegetation. Then, sort the inspection nodes from high to low according to the priority, and perform a secondary sort from short to long according to the data collection duration in the case of the same priority, forming a node access sequence with time weights. Then, generate multiple candidate flight paths between two adjacent inspection nodes. For example, from one end inspection node of the bridge to the other end inspection node, there are multiple different flight paths to choose from, and each candidate flight path must meet the requirements of the obstacle avoidance buffer boundary range and the flight height of the starting node and the ending node.

[0027] For each candidate flight path, the comprehensive cost value is calculated. For example, if a candidate flight path is close to an area where a landslide event has occurred, and the overlap ratio between the candidate flight path and the spatial distribution density of disaster points in the historical disaster records is high, then its safety risk cost is high, and the comprehensive cost value increases accordingly. The path with the lowest comprehensive cost value is selected from the candidate path set as the reference path. If there are nodes in the reference path where the data collection time exceeds the preset threshold, such as the pier of a complex structure, the optimized target path is generated by exchanging the node order or inserting an intermediate transition node. Finally, the flight speed of the drone and the sensor trigger frequency are dynamically matched according to the flight altitude lower limit value and the obstacle avoidance buffer boundary range of each path segment in the target path. For example, in the path segment with a higher flight altitude, the flight speed can be appropriately increased, while in the area with a smaller obstacle avoidance buffer boundary range, the sensor trigger frequency is increased to ensure the accuracy of data collection.

[0028] At the same time, the flight parameters are dynamically adjusted based on real-time meteorological data. If the real-time wind speed of the mountainous road section exceeds the first preset threshold during the inspection, the UAV reduces the flight speed according to the preset deceleration strategy, and increases the obstacle avoidance buffer distance according to the preset obstacle avoidance buffer strategy to ensure flight safety. If the rainfall intensity exceeds the second preset threshold, the anti-interference mode of the UAV is enabled, and the sensor trigger frequency is increased according to the first preset compensation parameter, because rainfall may affect the data collection accuracy, and increasing the sensor trigger frequency can compensate for this loss of accuracy. If the visibility is lower than the third preset threshold, the infrared imaging module of the UAV is activated to replace the visible light camera, and the data collection time of the corresponding inspection node is extended according to the second preset compensation parameter to obtain more comprehensive and accurate monitoring data. And predict the flight risk in the future time window based on the changing trend of meteorological data. If the predicted risk level exceeds the critical value, send a path replanning instruction to the navigation control unit of the UAV.

[0029] In the entire flight path planning, emergency avoidance nodes will also be inserted into the initial flight path. For example, according to historical disaster records, in areas where multiple landslides have occurred, the spatial distribution density is high. Emergency avoidance nodes are adaptively configured in these areas to generate an adjusted flight path. Finally, the adjusted flight path and flight parameters are integrated into a dynamic flight path and synchronized to the navigation control unit of the drone. A path deviation detection mechanism is preset in the navigation control unit. When the lateral offset between the actual flight trajectory of the drone and the dynamic flight path continues to exceed the preset ratio of the obstacle avoidance buffer boundary range, local path replanning is triggered, and only the remaining nodes that have not been visited are re-sorted in space, etc., to ensure that the drone can complete the inspection task according to the predetermined path.

[0030] Step S140: Based on the dynamic flight path, control the drone to perform real-time inspection tasks, and collect multi-dimensional monitoring data within the inspection sub-region. The multi-dimensional monitoring data includes surface deformation data, road and bridge crack images, and slope displacement trajectories.

[0031] In the above-mentioned mountain highway section, the drone starts to perform inspection tasks according to the dynamic flight path. When the drone flies to a certain area, it scans the surface deformation area through a lidar sensor. For example, in a section where there were signs of a minor landslide, the drone continuously emits laser pulses during flight, receives the reflected signals, and calculates the round-trip time difference of the pulses to generate an initial point cloud data set. Then, denoise the initial point cloud data, removing the abnormal points caused by surrounding vegetation occlusion or meteorological interference (such as scattering interference caused by foggy weather), to generate the denoised point cloud data. Next, based on the previously obtained terrain slope matrix, perform elevation correction on the denoised point cloud data to eliminate the error impact of terrain undulation on deformation calculation, and obtain the current point cloud data. Use the time series differential algorithm to compare the current point cloud data with the historical reference data, and calculate the three-dimensional displacement and displacement direction of each monitoring point. If the displacement of a certain area exceeds the warning threshold, mark this area as a risk area, and distinguish the risk level of the risk area with color gradients in the deformation displacement vector map, so as to obtain the surface deformation data.

[0032] At the same time, use an optical camera to take images of the road and bridge surface. During the inspection of a bridge, an image of the bridge surface is taken, and the crack length, width, and orientation features corresponding to the image are extracted through edge detection algorithms. For example, it is found that there is a crack in a certain support part of the bridge, the crack length is several centimeters, the width is gradually increasing, and the orientation is along a certain specific direction. These structured data constitute the road and bridge crack image.

[0033] Call the multi-band radar of the drone to continuously monitor the slope. In a certain slope area, the multi-band radar captures the slope displacement trajectory of the rock and soil mass inside the slope, including the displacement rate curve and the sliding direction index. For example, the displacement rate curve shows that the displacement rate gradually increases during a certain period of time, and the sliding direction is towards the highway subgrade.

[0034] In addition, the drone also synchronously collects environmental temperature and humidity, wind speed and direction, and vibration frequency parameters. For example, at a certain inspection moment, parameters such as the environmental temperature in degrees Celsius, humidity in percentage, wind speed and direction, and vibration frequency are accurately collected. These auxiliary verification information is aligned with the surface deformation data, road and bridge crack images, and slope displacement trajectories in time series, and stored in the distributed database after being bound to the corresponding geographical coordinates.

[0035] Step S150, inputting the multi-dimensional monitoring data and the historical disaster records into a risk warning model to generate a risk level signal and corresponding handling suggestion information for the target mountainous road section.

[0036] Continue to use the risk warning model for analysis based on the previously collected multi-dimensional monitoring data and the historical disaster records of this mountain road section.

[0037] For surface deformation data, if the displacement rate in a certain area continues to increase and the direction is consistent with the direction of historical landslides, for example, the surface displacement rate under a roadbed continues to increase over a period of time, and the displacement direction is the same as the direction of a previous landslide, then a first-level warning signal is triggered.

[0038] When analyzing the crack images of road bridges, if it is found that the extension direction of the cracks in a key part of the bridge coincides with the main stress direction of the bridge, and the width expansion rate exceeds the critical value, for example, the crack width grows rapidly in a short period of time and reaches a level that may affect the safety of the bridge structure, a secondary warning signal will be triggered.

[0039] The slope stability coefficient is calculated based on the sliding direction and speed of the slope displacement trajectory combined with real-time rainfall intensity data. For example, if the displacement trajectory of a certain slope shows that its sliding direction is toward the road, the displacement speed is fast, and the real-time rainfall intensity is large, the slope stability coefficient is lower than the safety threshold through calculation (such as vector decomposition of the sliding direction, comparison with historical disaster records, and searching the correlation mapping table between rainfall accumulation and displacement acceleration interval, etc.), and a level 3 warning signal is triggered.

[0040] Differentiated handling suggestions are generated based on the warning signal level. If a level 1 warning signal is triggered, emergency road closure measures may be taken; if a level 2 warning signal is triggered, speed limit measures may be taken; if a level 3 warning signal is triggered, a support structure reinforcement plan may be initiated.

[0041] Finally, the risk level signal and disposal suggestion information are pushed to the road and bridge management terminal, and the corresponding monitoring data traceability link is associated for manual review. For example, the road and bridge management department receives a risk level signal of a certain section of road as level 2 on the terminal, and the disposal suggestion is speed limit. At the same time, detailed monitoring data, such as bridge crack images, surface deformation data, etc., can be viewed through the traceability link for manual review to ensure the accuracy of the disposal decision.

[0042] In addition, during the whole process, a feedback closed-loop mechanism for multi-dimensional monitoring data and disposal suggestion information can be established. After the disposal suggestion information is adopted and implemented by the road and bridge management terminal, the structural response data of the corresponding area is continuously monitored. For example, after implementing a support structure reinforcement plan for a certain slope, the drone continues to monitor the deformation data of the reinforcement materials and the stress distribution data of the support structure in this area. By comparing the differences in the slope displacement trajectories before and after the disposal, the effective action radius and attenuation coefficient of the disposal measures corresponding to the disposal suggestion information are calculated. If the implemented attenuation coefficient exceeds the standard deviation of a preset multiple of the historical average value, it is determined that there are design defects in the current disposal plan. For example, if it is found that the displacement of the reinforced slope is still large and exceeds the expectation, optimization suggestions for material replacement or structural re-design are generated. The optimization suggestions are input into the path planning model to increase the monitoring frequency and sensor accuracy level of the defective area. And after the new disposal plan is implemented, the feedback closed-loop mechanism is restarted until the actual improvement rate reaches the standard, so as to continuously optimize the monitoring and disposal strategies and ensure the safe operation of the road and bridges in mountainous sections.

[0043] Based on the above steps, in the embodiment of the present application, by obtaining the road and bridge remote sensing monitoring data including the current terrain distribution characteristics, road and bridge structure state parameters, and historical disaster records, regional segmentation is performed based on the current terrain distribution characteristics to generate terrain feature tags, and then the dynamic flight path of the drone is generated in combination with the road and bridge structure state parameters. By closely integrating terrain factors, road and bridge structures, and the drone inspection path planning, different from the traditional fixed-path inspection method, the dynamic flight path generated by this method can intelligently adjust the inspection route and nodes according to the variability of the mountainous terrain and the differences in the road and bridge structure states. It not only effectively covers all key areas and avoids inspection blind spots, but also can reasonably allocate inspection resources according to the characteristics and risk levels of different areas, improving the inspection efficiency and pertinence. At the same time, the flight parameter settings in the dynamic flight path ensure that the drone can perform the inspection task safely, stably and efficiently in the complex mountainous environment, further enhancing the reliability and practicality of the entire monitoring system. In the real-time inspection task, multi-dimensional monitoring data is collected, including surface deformation data, road and bridge crack images, slope displacement trajectories, etc., which can accurately capture the minute changes of the road and bridge under the influence of various factors, providing rich and accurate basis for timely discovery of potential risks. Finally, the multi-dimensional monitoring data and historical disaster records are input into the risk early warning model to generate risk level signals and disposal suggestion information, realizing the intelligent evaluation and early warning of the risks of the target mountainous road section. Fully considering the evolution law of mountain road and bridge disasters and the current actual situation, it can more accurately predict the possible disaster risks and provide highly targeted and operable disposal suggestions. Compared with the traditional early warning method, it greatly improves the accuracy and timeliness of the early warning, saves valuable time for taking effective preventive measures in a timely manner, effectively guarantees the safe operation of mountain road and bridges, and reduces disaster losses.

[0044] In a possible implementation, step S110 includes:

[0045] Step S111, obtaining multispectral image data and three-dimensional point cloud data of the target mountainous section of the road through satellite remote sensing equipment.

[0046] Step S112, performing ground object classification processing on the multispectral image data, and extracting vegetation coverage density, rock exposure area, and hydrological distribution characteristics as sub-characteristics of the current terrain distribution characteristics.

[0047] For example, the satellite conducts all-round scanning imaging of the mountain highway section mentioned above from space, and the multispectral image data contains rich information. Then, ground object classification processing is performed on the multispectral image data to extract sub-characteristics such as vegetation coverage density, rock exposure area, and hydrological distribution characteristics. For example, in some sections of the mountainous section, the vegetation grows lushly, and through precise analysis and calculation, the vegetation coverage density value of this area is obtained. These vegetation may have potential impacts on the road and bridge structure. For example, the roots of the vegetation may damage the roadbed. While in other parts, there are rock exposure areas, which may imply that the geological structure stability of this area is poor and landslides and other disasters are likely to occur. At the same time, the hydrological distribution characteristics can also be clarified through analysis, such as the direction of the river and its relative position relationship with the road and bridge. If the river is too close to the road and bridge, it may cause hazards such as scouring of the road and bridge foundation.

[0048] Step S113, performing elevation difference processing on the three-dimensional point cloud data, generating a terrain slope matrix and a surface undulation index, and associating the terrain slope matrix and the surface undulation index to the corresponding inspection sub-region.

[0049] For the obtained three-dimensional point cloud data, elevation difference processing is required. During this process, a terrain slope matrix and a surface undulation index are generated. For example, in a certain section of the mountain highway, the terrain slope matrix shows that the slope is relatively large, which means greater challenges in driving or construction and maintenance in this section. The surface undulation index also reflects the terrain complexity of this area. For example, some hilly areas have a relatively large undulation. Then, associating the terrain slope matrix and the surface undulation index to the corresponding inspection sub-region helps to formulate targeted inspection plans according to different terrain characteristics in the follow-up.

[0050] Step S114, retrieving the historical maintenance database of the target mountainous section of the road, and extracting the pier inclination angle, pavement settlement rate, and slope support structure integrity parameters in the road and bridge structure state parameters.

[0051] In the historical maintenance database of the target mountainous road section, many parameters related to the state of the road and bridge structures are detailedly recorded. For example, for the piers under a certain bridge on the mountainous highway, data on the inclination angles of the piers are regularly measured by professional measuring instruments. The numerical values of the pier inclination angles reflect the structural stability of the piers. If the inclination angle is too large, it may affect the safety of the entire bridge. The road surface settlement rate is also an important parameter. In some sections, due to the influence of factors such as long-term vehicle loads and geological changes, the road surface will experience settlement. By analyzing historical data, the accurate road surface settlement rate can be obtained to evaluate the road surface condition. There are also parameters for the integrity of the slope support structure. On the slopes of mountainous road sections, slope support structures are set up to prevent disasters such as landslides from affecting the roads and bridges. The detection data of their integrity are recorded in the database. Poor integrity means that the protection ability of the slope may be reduced and there is a landslide risk.

[0052] Step S115, classify the historical disaster records according to the disaster types, where the disaster types include landslide events, bridge crack expansion events, and roadbed collapse events, and associate the geographical coordinates and occurrence timestamps corresponding to each event.

[0053] For example, various disaster types have occurred in this mountainous highway section, such as landslide events, bridge crack expansion events, and roadbed collapse events. For landslide events, clarify the geographical coordinates where they occur, such as on a hillside near a certain bend, accurate to the longitude and latitude values, and at the same time record the occurrence timestamp to analyze the reasons for the landslide in this area under specific time and geological conditions. For bridge crack expansion events, determine the specific location on the bridge and the corresponding geographical coordinates, and analyze the crack expansion rate and trend through the timestamp. For roadbed collapse events, also record the accurate location and time of occurrence.

[0054] In a possible implementation manner, step S130 includes:

[0055] Step S131, calculate the minimum safe flight height and obstacle avoidance buffer distance of the drone in the corresponding inspection sub-region according to the vegetation coverage density and terrain slope matrix in the terrain feature tags.

[0056] Step S132, determine the priority order of the inspection nodes and the data collection duration for each inspection node based on the pier inclination angle and slope support structure integrity parameter in the road and bridge structure state parameters.

[0057] Among them, the minimum safe flight height H_min = H_base + α×V + β×S̄

[0058] The obstacle avoidance buffer distance D_buffer = γ×(V / V_max) + δ×(ΔS / S_ref)

[0059] The priority P of the inspection node is P = θ×w1+(1 - I)×w2

[0060] The data acquisition duration T is T = T_base×(1 + P / P_max)

[0061] H_base is the reference safety height, α is the weight coefficient of the vegetation coverage density V, β is the correction coefficient of the average slope S̄ of the terrain slope matrix, γ is the vegetation density influence factor, V_max is the maximum vegetation coverage density in the area, δ is the adjustment coefficient of the slope change rate ΔS, S_ref is the slope reference threshold, θ is the pier inclination angle, I is the normalized value of the slope support structure integrity parameter, w1 and w2 are the weight coefficients of the inclination angle and integrity respectively, T_base is the basic acquisition duration, and P_max is the maximum priority value.

[0062] In this embodiment, taking a certain inspection sub - area in a mountainous highway section as an example, the vegetation coverage density in this area is at a relatively high level through previous analysis, and the terrain slope matrix shows that the average slope is also large. For the calculation of the minimum safe flight height, the reference safety height H_base is a basic set value, assumed to be a fixed value here, such as 100 meters. The vegetation coverage density V is high, and its weight coefficient α is set according to experience and relevant technical standards, assumed to be 0.5. The average slope S̄ of the terrain slope matrix is large, and its correction coefficient β is assumed to be 0.3. According to the formula for the minimum safe flight height H_min = H_base + α×V + β×S̄, due to the influence of the vegetation coverage density and the average slope, it is calculated that the minimum safe flight height in this area may reach 120 meters to ensure that the drone will not collide with vegetation or be in danger due to terrain undulation during flight.

[0063] For the obstacle - avoidance buffer distance, the maximum vegetation coverage density V_max in the area is assumed to be a specific value, such as 80%, the vegetation density influence factor γ is assumed to be 0.2, the slope change rate ΔS is obtained from the analysis of the terrain slope matrix, the slope reference threshold S_ref is a fixed reference standard value, assumed to be 15 degrees, and the adjustment coefficient δ of the slope change rate is assumed to be 0.1. According to the formula for the obstacle - avoidance buffer distance D_buffer = γ×(V / V_max)+δ×(ΔS / S_ref), due to the influence of the vegetation coverage density and the slope change rate, the obstacle - avoidance buffer distance in this area is calculated to be 5 meters, and this obstacle - avoidance buffer distance can provide enough safety buffer space for the drone to avoid obstacles.

[0064] Next, at a bridge on a mountain highway, the inclination angle θ of the bridge pier is measured to be 2 degrees, and the normalized value I of the integrity parameter of the slope support structure is 0.8 after evaluation. The weight coefficient w1 of the inclination angle is assumed to be 0.6, and the weight coefficient w2 of the integrity is assumed to be 0.4. According to the formula for calculating the priority P of the inspection node, P = θ×w1+(1 - I)×w2, the priority of this inspection node is calculated to be 0.52. Assuming that the basic acquisition duration T_base is 10 seconds and the maximum priority value P_max is 1, according to the formula for calculating the data acquisition duration T = T_base×(1 + P / P_max), the data acquisition duration of this inspection node is calculated to be 15.2 seconds. In the entire inspection sub-region, different inspection nodes determine the priority order and data acquisition duration according to their corresponding bridge pier inclination angles and slope support structure integrity parameters in the above calculation method. For those inspection nodes with larger bridge pier inclination angles or poorer slope support structure integrity, higher priorities and longer data acquisition durations will be assigned to ensure more detailed monitoring of key parts.

[0065] Step S133: Based on the minimum safe flight altitude and obstacle avoidance buffer distance of the UAV in the corresponding inspection sub-region, as well as the priority order of the inspection nodes and the data acquisition duration of each inspection node, use a path optimization algorithm to perform spatial sorting on the inspection nodes to generate an initial flight path, and dynamically adjust the flight parameters based on real-time meteorological data. The flight parameters include flight speed, hover time, and sensor trigger frequency.

[0066] Step S134: Insert emergency avoidance nodes into the initial flight path to generate an adjusted flight path. The emergency avoidance nodes are adaptively configured according to the spatial distribution density of disaster types in historical disaster records.

[0067] For example, in a mountain highway section, the spatial distribution density is relatively high in areas where multiple landslide events have occurred. In these areas, it is necessary to adaptively configure emergency avoidance nodes. For example, insert emergency avoidance nodes on the flight path near a section where landslides often occur, so that the UAV can avoid these dangerous areas during the inspection process and generate an adjusted flight path.

[0068] Step S135, integrate the adjusted flight path and the flight parameters into the dynamic flight path, and synchronize the dynamic flight path to the navigation control unit of the UAV. A path deviation detection mechanism is preset in the navigation control unit. When the lateral offset between the actual flight trajectory of the UAV and the dynamic flight path continuously exceeds a preset ratio of the obstacle avoidance buffer boundary range, trigger local path replanning, and only return to execute the step of spatially sorting the inspection nodes using a path optimization algorithm to generate an initial flight path for the remaining unvisited nodes.

[0069] For example, when the lateral offset between the actual flight trajectory of the UAV and the dynamic flight path continuously exceeds a preset ratio of the obstacle avoidance buffer boundary range, assuming the preset ratio is 20%, if the lateral offset of the UAV continuously exceeds this ratio, trigger local path replanning, and only return to execute the step of spatially sorting the inspection nodes using a path optimization algorithm to generate an initial flight path for the remaining unvisited nodes, so as to ensure that the UAV can complete the inspection task according to the predetermined path and guarantee the effective monitoring of the road and bridge structure of the mountain highway section.

[0070] In a possible implementation manner, step S133 includes:

[0071] Step S1331, based on the minimum safe flight altitude and the obstacle avoidance buffer distance of each inspection sub-region, assign corresponding lower limit values of flight altitude and obstacle avoidance buffer boundary ranges to each inspection node, and generate a set of safety parameters for the inspection nodes including altitude constraints and spatial obstacle avoidance ranges.

[0072] In this embodiment, taking a specific inspection sub-region of a mountain highway as an example, there are multiple inspection nodes in this region. One inspection node near the hillside with more vegetation, according to the previously calculated minimum safe flight altitude of 120 meters, the lower limit value of the flight altitude assigned to this inspection node is 120 meters to ensure that the UAV will not collide with the mountain or vegetation due to too low altitude when flying over this node. At the same time, considering the obstacle avoidance buffer distance of this region is 5 meters, based on this, set the obstacle avoidance buffer boundary range of this inspection node as the area with a radius of 5 meters centered on this node. Operate on each inspection node in the inspection sub-region in the same way, and finally generate a set of safety parameters for the inspection nodes including altitude constraints and spatial obstacle avoidance ranges.

[0073] Step S1332, according to the priority order and data collection duration of the inspection nodes, sort the inspection nodes from high to low according to the priority, and perform a secondary sorting from short to long according to the data collection duration in the case of the same priority, to form a node access sequence with time weights.

[0074] For example, at an inspection node near a bridge on a mountain highway section, the inclination angle of its bridge pier is relatively large and the integrity of the slope support structure is relatively poor. According to calculations, the priority of this inspection node is relatively high. Another inspection node far from the bridge and in good structural condition has a relatively low priority. For the data collection duration, the calculated data collection duration for the inspection node with a high priority is 15.2 seconds, and the data collection duration for the inspection node with a low priority is 10 seconds. According to the above sorting rules, first arrange all inspection nodes in descending order of priority. If there are multiple inspection nodes with the same priority, such as two inspection nodes far from the main structure having the same priority, but one has a data collection duration of 8 seconds and the other has a data collection duration of 10 seconds, then arrange the inspection node corresponding to the 8-second data collection duration in front of the one corresponding to the 10-second data collection duration in ascending order of data collection duration, thus forming a node access sequence with time weights.

[0075] Step S1333, based on the order of the node access sequence and the set of inspection node safety parameters, generate a candidate path set composed of multiple candidate flight paths between two adjacent inspection nodes. Each candidate flight path satisfies that the obstacle avoidance buffer boundary range of the starting node does not overlap with the obstacle avoidance buffer boundary range of the ending node, and the flight height is always not lower than the higher minimum safe flight height of the two nodes.

[0076] For example, in the above-mentioned mountain highway section, for two adjacent inspection nodes in the node access sequence, one is an inspection node for the support structure of the bridge and the other is an inspection node for the road surface near the bridge. For these two nodes, multiple candidate flight paths are generated between them according to their respective obstacle avoidance buffer boundary ranges. One of the candidate flight paths starts from the inspection node for the bridge support structure and flies towards the road surface inspection node at a certain angle. This path should ensure that the obstacle avoidance buffer boundary range of the starting node (the inspection node for the bridge support structure) does not overlap with the obstacle avoidance buffer boundary range of the ending node (the road surface inspection node), and during the flight process, the flight height is always not lower than the higher minimum safe flight height of the two nodes. For example, the minimum safe flight height of the bridge support structure inspection node is 120 meters, and the minimum safe flight height of the road surface inspection node is 100 meters, then the flight height of this candidate flight path should not be lower than 120 meters. According to such rules, multiple candidate flight paths are generated between all adjacent inspection nodes to form a candidate path set.

[0077] Step S1334, for each candidate flight path, calculate the comprehensive cost value of the candidate flight path. The comprehensive cost value is obtained by weighted summation of the flight distance cost, data collection time cost, and safety risk cost. Among them, the safety risk cost is calculated according to the overlap ratio between the candidate flight path and the spatial distribution density of disaster points in the historical disaster records.

[0078] Taking a candidate flight path from a slope inspection node at one end to a bridge inspection node at the other end of a mountain expressway section as an example, first calculate the flight distance cost. Assume the length of this path is 500 meters. According to the set unit distance cost coefficient (for example, the cost per meter is 0.1 yuan), the flight distance cost is 50 yuan. For the data collection time cost, since the total data collection duration of the inspection nodes passed by this path is 30 seconds, according to the time cost coefficient per second (for example, the cost per second is 0.5 yuan), the data collection time cost is 15 yuan. Then look at the safety risk cost. This candidate flight path has a certain overlap with the spatial distribution density of landslide events in the historical disaster records. After detailed calculation, the overlap ratio is 30%. According to the calculation method of the safety risk cost (for example, setting a coefficient relationship proportional to the overlap ratio, with each 10% of the overlap ratio corresponding to 10 yuan of cost), the safety risk cost is 30 yuan. Finally, in the way of weighted summation (assuming the weight of the flight distance cost is 0.4, the weight of the data collection time cost is 0.3, and the weight of the safety risk cost is 0.3), the calculated comprehensive cost value of this candidate flight path is 36 yuan. Calculate the comprehensive cost value of each candidate flight path in the candidate path set in the same way.

[0079] Step S1335, select the path with the lowest comprehensive cost value from the candidate path set as the reference path. Rearrange the paths between adjacent nodes for the nodes in the reference path whose data collection duration exceeds the preset threshold. Generate the optimized target path by exchanging the node order or inserting intermediate transition nodes, and re-evaluate the comprehensive cost value of the target path. Until the convergence condition is reached, in the currently optimized target path, according to the lower limit value of the flight height of each path segment in the target path and the obstacle avoidance buffer boundary range, dynamically match the flight speed of the UAV and the sensor trigger frequency, where the flight speed is positively correlated with the minimum safe flight height of the path segment, and the sensor trigger frequency is negatively correlated with the area of the obstacle avoidance buffer boundary range.

[0080] Suppose there is a data acquisition node with a data acquisition duration of 20 seconds in the reference path selected from the candidate path set, and the preset threshold is 15 seconds. Then, it is necessary to rearrange the path between adjacent nodes for this node. If the adjacent node is a node with a data acquisition duration of 10 seconds and a lower priority, the order of these two nodes is exchanged, and the comprehensive cost value of this new path is re-evaluated. During this process, the node order is continuously adjusted or intermediate transition nodes are inserted, and the comprehensive cost value is recalculated after each adjustment until the comprehensive cost value no longer decreases and reaches the convergence condition. In the optimized target path, for the path segment with a higher lower limit value of the flight altitude, since the flight speed is positively correlated with the minimum safe flight altitude, the UAV can fly at a relatively high speed in this path segment. For example, in the path segment with a minimum safe flight altitude of 150 meters, the flight speed is set to 20 m / s; while for the area with a smaller area of the obstacle avoidance buffer boundary range, since the sensor trigger frequency is negatively correlated with the area of the obstacle avoidance buffer boundary range, the sensor trigger frequency should be increased in this area. For example, in the area with a radius of 3 meters for the obstacle avoidance buffer boundary range, the sensor trigger frequency is set to 5 times per second to ensure accurate data acquisition.

[0081] Step S1336: Detect whether there is a target area in the target path where the flight direction turning angles of consecutive preset numbers of inspection nodes exceed the maximum turning ability of the UAV. If so, insert an auxiliary correction node in this target area. The position of the auxiliary correction node is determined according to the intersection point of the extension tangents of the obstacle avoidance buffer boundary range, and the comprehensive cost value of the path after inserting the auxiliary correction node is recalculated until the target path is optimized and the initial flight path is generated.

[0082] On the target path of a certain complex section of a mountain highway section, assume that the preset number is 3 inspection nodes, and it is found that the flight direction turning angles of 3 consecutive inspection nodes exceed the maximum turning ability of the UAV. At this time, the position of the auxiliary correction node is determined according to the intersection point of the extension tangents of the obstacle avoidance buffer boundary ranges of these 3 inspection nodes, and the auxiliary correction node is inserted at this intersection point. After insertion, the comprehensive cost value of this path including the auxiliary correction node is recalculated, and then it continues to be detected whether there are still similar problem areas in the target path. If so, continue to insert the auxiliary correction node and recalculate the comprehensive cost value until the target path is optimized and the initial flight path is generated.

[0083] Step S1337: Obtain the real-time wind speed, rainfall intensity, and visibility data of the target mountain section.

[0084] For example, meteorological monitoring devices are installed on mountain highway sections, and these meteorological monitoring devices can accurately obtain the real-time meteorological information of the sections. For example, the meteorological monitoring devices show that the real-time wind speed is 15 m / s, the rainfall intensity is 50 mm / h, and the visibility is 50 m.

[0085] Step S1338, if the real-time wind speed exceeds the first preset threshold, reduce the flight speed of the drone according to the preset deceleration strategy and increase the obstacle avoidance buffer distance according to the preset obstacle avoidance buffer strategy; if the rainfall intensity exceeds the second preset threshold, enable the anti-interference mode of the drone, increase the sensor trigger frequency according to the first preset compensation parameter to compensate for the loss of data acquisition accuracy; if the visibility is lower than the third preset threshold, activate the infrared imaging module of the drone to replace the visible light camera, and extend the data acquisition duration of the corresponding inspection node according to the second preset compensation parameter.

[0086] If the real-time wind speed exceeds the first preset threshold, for example, the first preset threshold is set at 10 m / s. Since the real-time wind speed of 15 m / s exceeds this threshold, reduce the flight speed of the drone according to the preset deceleration strategy and increase the obstacle avoidance buffer distance according to the preset obstacle avoidance buffer strategy. Suppose the original flight speed of the drone is 20 m / s. According to the preset deceleration strategy (for example, reducing the flight speed by 1 m / s for every 1 m / s increase in wind speed), the flight speed is reduced to 15 m / s. At the same time, the original obstacle avoidance buffer distance is 5 m. According to the preset obstacle avoidance buffer strategy (for example, increasing the obstacle avoidance buffer distance by 1 m for every 1 m / s increase in wind speed), the obstacle avoidance buffer distance is increased to 10 m.

[0087] If the rainfall intensity exceeds the second preset threshold, assume the second preset threshold is 30 mm / h. Since the rainfall intensity of 50 mm / h exceeds this threshold, enable the anti-interference mode of the drone and increase the sensor trigger frequency according to the first preset compensation parameter to compensate for the loss of data acquisition accuracy. For example, the first preset compensation parameter is to increase the sensor trigger frequency by 2 times / s for every 10 mm / h increase in rainfall intensity. The original sensor trigger frequency is 3 times / s, so now the sensor trigger frequency is increased to 7 times / s to ensure more accurate data can be collected in the rainfall environment.

[0088] If the visibility is lower than the third preset threshold, assume the third preset threshold is 100 m. Since the visibility of 50 m is lower than this threshold, activate the infrared imaging module of the drone to replace the visible light camera, and extend the data acquisition duration of the corresponding inspection node according to the second preset compensation parameter. For example, the second preset compensation parameter is to extend the data acquisition duration by 5 s for every 50 m decrease in visibility. For an inspection node with an original data acquisition duration of 10 s, now the data acquisition duration is extended to 15 s to obtain sufficient monitoring data in the low visibility environment.

[0089] Step S1339, predict the flight risk within a future time window based on the changing trend of meteorological data. If it is predicted that the risk level exceeds the critical value, send a path replanning instruction to the navigation control unit of the UAV.

[0090] For example, based on the historical changing trend and current data of meteorological data, it is predicted that the wind speed will continue to increase and the rainfall intensity will also increase within the next 1 hour. According to the risk assessment model, it is calculated that the risk level will exceed the critical value. At this time, a path replanning instruction is sent to the navigation control unit of the UAV to ensure that the UAV can fly safely and effectively and collect data during the subsequent inspection tasks.

[0091] In a possible implementation manner, step S140 includes:

[0092] Step S141, scan the surface deformation area through the lidar sensor of the UAV to generate a deformation displacement vector map as the surface deformation data.

[0093] Step S142, use an optical camera to capture an image of the road and bridge surface, and extract the crack length, width, and orientation features corresponding to the road and bridge surface image through an edge detection algorithm as the structured data of the road and bridge crack image.

[0094] For example, when the UAV flies above the bridge of a mountain highway, the optical camera captures an image of the bridge surface. The image of the bridge surface captured by the camera contains various information on the bridge surface, including possible defects such as cracks. Then, the captured image is processed through an edge detection algorithm. This edge detection algorithm can identify the edges of objects in the road and bridge surface image. For the cracks on the road and bridge surface, it can accurately determine the boundaries of the cracks. By analyzing this boundary information, the length of the crack is calculated. For example, it is measured that the distance from one end of the crack to the other end is several centimeters. At the same time, the width of the crack can also be determined. By analyzing the pixels of the crack edge and combining the known image scale, the width value of the crack can be obtained. And, according to the orientation of the crack in the image, the orientation feature of the crack on the actual road and bridge surface is determined, such as extending along the transverse or longitudinal direction of the bridge. These crack length, width, and orientation features constitute the structured data of the road and bridge crack image.

[0095] Step S143, call the multi-band radar of the UAV to continuously monitor the slope, and capture the slope displacement trajectory of the rock and soil mass inside the slope. The slope displacement trajectory includes a displacement rate curve and a sliding direction index.

[0096] In the slope area of a mountain highway section, a multi - band radar continuously emits radar waves towards the slope and receives the reflected waves. Due to the movement of the rock and soil mass inside the slope, the reflected waves will change. By analyzing these reflected waves, the multi - band radar can capture the displacement information of the rock and soil mass inside the slope. Over time, by continuously collecting this displacement information, a displacement rate curve can be plotted. For example, within a certain period, the displacement rate of the rock and soil mass at a certain depth may start low and then gradually increase, and this changing process is reflected in the displacement rate curve. At the same time, according to information such as the change in the direction of radar wave reflection, the sliding direction index of the rock and soil mass can be determined, such as whether it is sliding towards the highway direction or towards the inside of the mountain slope. The above - mentioned displacement rate curve and sliding direction index constitute the slope displacement trajectory.

[0097] Step S144, synchronously collect environmental temperature and humidity, wind speed and direction, and vibration frequency parameters as auxiliary verification information for the multi - dimensional monitoring data.

[0098] Step S145, align the surface deformation data, road and bridge crack images, and slope displacement trajectory in time series, bind them with the corresponding geographical coordinates, and store them in a distributed database.

[0099] During the entire inspection process, devices such as the temperature and humidity sensor, wind speed and direction meter, and vibration sensor carried by the UAV work simultaneously. In the inspection sub - area of the mountain highway, the temperature and humidity sensor can accurately measure the environmental temperature and humidity. For example, at a certain moment, the measured environmental temperature is 25 degrees Celsius and the humidity is 60%. The wind speed and direction meter can detect the current wind speed and direction, such as the wind speed is 10 m / s and the wind direction is southeast. The vibration sensor can detect the vibration frequency of the UAV itself or the surrounding environment. Suppose the detected vibration frequency is 100 Hz. These environmental temperature and humidity, wind speed and direction, and vibration frequency parameters are aligned with the surface deformation data, road and bridge crack images, and slope displacement trajectory in time series. For example, when collecting the surface deformation data at a certain moment, the environmental parameters at that moment are also recorded to ensure that all data is corresponding in time. Then these data are bound with the corresponding geographical coordinates. For example, a certain surface deformation data corresponds to the coordinates of a specific section of the mountain highway. These bound data are stored in a distributed database for convenient subsequent query, analysis, and processing.

[0100] In a possible implementation manner, step S141 includes:

[0101] Step S1411, continuously emit laser pulses during the UAV flight, receive the reflected signals, calculate the pulse round - trip time difference, and generate an initial point - cloud data set.

[0102] In a certain inspection sub-region of a mountain highway, there is a surface area where slight landslide signs have occurred. When the drone flies over this area, during the flight, the lidar continuously emits laser pulses. After these laser pulses hit the surface, they will reflect back. The sensor receives the reflected signal and accurately calculates the time difference of the pulse round-trip. For example, after a certain laser pulse is emitted and returns after a period of time, according to the propagation speed of the laser in the air, by calculating this time difference of the round-trip, the distance information from the monitoring point corresponding to this pulse to the drone can be obtained. By emitting and receiving multiple laser pulses for the entire surface deformation area, a large amount of such distance information is collected, thereby generating an initial point cloud data set.

[0103] Step S1412: Denoise the initial point cloud data, remove the abnormal points caused by vegetation occlusion or meteorological interference, and generate the denoised point cloud data.

[0104] In this embodiment, this initial point cloud data set contains information of a large number of points in the surface area, but there may be some abnormal points among them. These abnormal points may be caused by vegetation occlusion or meteorological interference. For example, there are some tall trees in this area. When the laser pulse passes through the branches and leaves of the trees, it may produce scattering or multiple reflections, resulting in inaccurate calculated distance information. Also, under some meteorological conditions, such as foggy days or rainy days, it will also interfere with the propagation of the laser pulse. Therefore, it is necessary to denoise the initial point cloud data and remove these abnormal points caused by vegetation occlusion or meteorological interference, thereby generating the denoised point cloud data.

[0105] Step S1413: Based on the terrain slope matrix, perform elevation correction on the denoised point cloud data to obtain the current point cloud data, and eliminate the error influence of terrain undulation on deformation calculation.

[0106] Step S1414: Use the time series difference algorithm to compare the current point cloud data with the historical reference data, and calculate the three-dimensional displacement amount and displacement direction of each monitoring point.

[0107] Step S1415: Mark the area where the displacement amount exceeds the warning threshold as the risk area, and distinguish the risk level of the risk area in the deformation displacement vector diagram with color gradients.

[0108] Specifically, the historical reference data is the data that was previously collected and processed in the same area and serves as the reference for comparison. By comparing the coordinate information of each monitoring point in the current point cloud data and the historical reference data, the three-dimensional displacement can be calculated. For example, if there are certain differences in the x, y, and z directions between the coordinates of a monitoring point in the current data and those in the historical reference data, this difference is the three-dimensional displacement of the monitoring point. At the same time, the displacement direction can be determined based on the trend of the coordinates, such as towards a specific geographical direction. If the displacement in a certain area exceeds the warning threshold, that area is marked as a risk area, and the risk level of the risk area is distinguished by color gradient in the deformation displacement vector map. For example, areas with smaller displacements are represented by light blue, areas with larger displacements and close to the danger value are represented by yellow, and areas with displacements exceeding the danger value by a large margin are represented by red, thus generating the deformation displacement vector map as the surface deformation data.

[0109] For example, step S1413 includes:

[0110] Step S1413-1: Obtain the denoised point cloud data, and extract the three-dimensional coordinate information of each monitoring point in the denoised point cloud data. The three-dimensional coordinate information includes horizontal coordinates and vertical elevation values.

[0111] Step S1413-2: Retrieve the terrain slope matrix. The terrain slope matrix contains the terrain slope distribution information of the target mountainous section. The terrain slope distribution information consists of multiple slope units, and each slope unit corresponds to a geographical area.

[0112] Step S1413-3: Perform spatial matching between the horizontal coordinates of each monitoring point in the denoised point cloud data and the slope units in the terrain slope matrix to determine the slope unit corresponding to each monitoring point.

[0113] Step S1413-4: Calculate the terrain undulation correction amount for each monitoring point according to the terrain slope distribution information of the slope unit. The terrain undulation correction amount is used to eliminate the influence of terrain slope on the vertical elevation value.

[0114] Step S1413-5: Apply the terrain undulation correction amount to the vertical elevation value of each monitoring point in the denoised point cloud data to generate the corrected vertical elevation value. The corrected vertical elevation value eliminates the error influence of terrain undulation on deformation calculation.

[0115] Step S1413-6: Recombine the corrected vertical elevation value with the horizontal coordinates in the denoised point cloud data to generate the corrected current point cloud data.

[0116] In this embodiment, although the denoised point cloud data is relatively accurate, due to the existence of terrain undulations, it may have an error impact on the deformation calculation. To eliminate this impact, it is necessary to perform elevation correction on the denoised point cloud data based on the terrain slope matrix. First, obtain the denoised point cloud data and extract the three-dimensional coordinate information of each monitoring point therein. This three-dimensional coordinate information includes the horizontal coordinate and the vertical elevation value. Then, retrieve the previously obtained terrain slope matrix. This terrain slope matrix contains the terrain slope distribution information of the target mountainous section of the road. This information is composed of multiple slope units, and each slope unit corresponds to a geographical area. Match the horizontal coordinates of each monitoring point in the denoised point cloud data with the slope units in the terrain slope matrix to determine the slope unit corresponding to each monitoring point. For example, if the horizontal coordinate of a certain monitoring point is within the range of a specific slope unit, then it is determined that this monitoring point corresponds to this slope unit. Then, according to the terrain slope distribution information of this slope unit, calculate the terrain undulation correction amount for each monitoring point. This terrain undulation correction amount is specifically used to eliminate the influence of the terrain slope on the vertical elevation value. For example, if the slope of a certain slope unit is relatively large, then the vertical elevation value of the corresponding monitoring point may have a large deviation due to the terrain slope, and the deviation can be corrected by the calculated terrain undulation correction amount. Apply the terrain undulation correction amount to the vertical elevation value of each monitoring point in the denoised point cloud data, so that the corrected vertical elevation value is generated. This corrected vertical elevation value has eliminated the error impact of terrain undulations on the deformation calculation. Finally, recombine the corrected vertical elevation value with the horizontal coordinates in the denoised point cloud data to generate the corrected current point cloud data.

[0117] In one possible implementation manner, step S150 includes:

[0118] Step S151, call the risk warning model, match the displacement rate in the surface deformation data with the landslide events in the historical disaster records. If the displacement rate continues to increase and the direction is consistent with the historical landslide direction, then trigger a first-level warning signal.

[0119] When analyzing surface deformation data, focus on the displacement rate and match it with landslide events in historical disaster records. For example, the surface deformation data of a certain section of a mountain highway shows that the displacement rate in a specific area shows a continuous increasing trend. By querying the historical disaster records of this area, it is known that a landslide event occurred here before, and the displacement direction monitored this time is consistent with the historical landslide direction. This indicates that there is a very high landslide risk in this area, meeting the conditions for triggering a first-level warning signal. This situation may be due to the relatively fragile geological structure of this area, combined with the possible influence of recent rain erosion or groundwater level changes, resulting in a gradual decrease in the stability of the surface soil mass, and then showing displacement change characteristics similar to historical landslides.

[0120] And, in step S152, analyze the trend characteristics of the road and bridge crack image. If the crack extension direction coincides with the main stress direction of the bridge and the width expansion rate exceeds the critical value, trigger a second-level warning signal.

[0121] During the inspection of mountain highway bridges, after processing the road and bridge crack images captured by an optical camera, relevant characteristic information of the cracks is obtained. If it is found that the extension direction of a certain crack coincides with the main stress direction of the bridge, this means that the development direction of the crack is consistent with the most unfavorable direction of the bridge structure under stress, posing a serious threat to the structural safety of the bridge. At the same time, if the crack width expansion rate exceeds the critical value, for example, during several consecutive inspections, it is found that the crack width increases at a relatively fast speed, exceeding the critical value set according to the bridge structure design and safety standards, this indicates that the damage to the bridge structure is accelerating, and at this time, a second-level warning signal will be triggered. The development of such cracks may be due to long-term vehicle loads, temperature changes, or material aging and other factors, and the coincidence of the crack with the main stress direction will accelerate the destruction process of the bridge structure.

[0122] And, in step S153, according to the sliding direction and rate of the slope displacement trajectory, calculate the slope stability coefficient in combination with the real-time rainfall intensity data. If the slope stability coefficient is lower than the safety threshold, trigger a third-level warning signal.

[0123] In step S154, generate differentiated disposal suggestion information based on the warning signal level. The disposal suggestion information includes emergency road closure, speed limit, or activation of the support structure reinforcement plan.

[0124] For example, when a first-level warning signal is triggered, due to the extremely high landslide risk, in order to ensure the driving safety of mountain highways and the safety of road facilities, it is necessary to take measures to urgently close the road section. This means immediately preventing vehicles from entering this dangerous area, setting up roadblocks and warning signs, and notifying relevant departments for emergency handling, such as conducting geological surveys and reinforcement treatments on the landslide area.

[0125] If a secondary warning signal is triggered, it indicates that there are significant potential safety hazards in the bridge structure, but it has not reached the level of immediately interrupting traffic. At this time, disposal advice information on speed limit for traffic is adopted. Speed limit signs are set at both ends of the bridge to reduce the speed of vehicles passing through the bridge, decrease the impact force of vehicle loads on the bridge, and at the same time, arrange professional personnel to conduct further detailed inspections and evaluations of the bridge and formulate a maintenance and reinforcement plan.

[0126] When a tertiary warning signal is triggered, for the problem of slope stability, a support structure reinforcement plan is initiated. This may include measures such as strengthening the retaining wall of the slope, increasing the quantity and length of anchor rods or cables, and conducting protective treatment on the slope surface, etc., to improve the slope stability and prevent slope landslide accidents.

[0127] Step S155: Push the risk level signal and the disposal advice information to the road and bridge management terminal, and associate the corresponding monitoring data traceability link for manual review.

[0128] For example, after the road and bridge management terminal receives information that the risk level of a certain road section is level one and the disposal advice is to urgently close the road section, it can simultaneously view detailed monitoring data through the associated monitoring data traceability link, such as the displacement rate change curve and displacement direction information in the surface deformation data, as well as relevant records of historical landslide events, etc. In this way, road and bridge management personnel can conduct manual review of the warning information and disposal advice to ensure the accuracy and rationality of the decision-making, and can also adjust or supplement the disposal advice according to the actual situation when necessary.

[0129] In a possible implementation manner, step S153 includes:

[0130] Step S1531: Perform vector decomposition on the sliding direction of the slope displacement trajectory to generate time series data of the horizontal displacement component and the vertical displacement component.

[0131] For example, in the monitoring of a certain slope on a mountainous expressway, a multi-frequency radar captures the displacement trajectory of the rock and soil mass inside the slope. Through vector decomposition technology, the displacement changes in the horizontal and vertical directions within a certain period of time are obtained. The horizontal displacement component reflects the lateral movement trend of the rock and soil mass within the slope plane, and the vertical displacement component reflects the settlement or rising trend of the rock and soil mass.

[0132] Step S1532: Match the similarity between the horizontal displacement component and the displacement pattern of landslide events corresponding to the geographical coordinates in the historical disaster records, and screen out a set of reference events whose displacement trend similarity exceeds the matching threshold.

[0133] In the historical disaster records of mountain expressways, there are detailed landslide event records for each slope area, including the displacement patterns of rock and soil masses during landslides. By comparing the horizontal displacement components of the current slope with the displacement patterns in the historical records, a set of reference events with a displacement trend similarity exceeding the matching threshold is selected. This matching threshold is determined based on a large amount of historical data and engineering experience to ensure that the selected reference events have high reference value.

[0134] Step S1533: Extract the time-series data of rainfall intensity before the occurrence of each landslide event in the set of reference events, and establish an association mapping table between rainfall accumulation and displacement acceleration intervals.

[0135] The time-series data of rainfall intensity records the changes in rainfall intensity during a period before the occurrence of landslide events. By analyzing these data, an association mapping table between rainfall accumulation and displacement acceleration intervals is established. For example, in a certain reference landslide event, it is found that when the rainfall accumulation reaches a certain value, the displacement rate of the slope rock and soil mass begins to increase significantly and enters the displacement acceleration interval. By analyzing multiple reference events, the relationship between different rainfall accumulations and displacement acceleration intervals can be established.

[0136] Step S1534: Calculate the current rainfall accumulation based on the real-time rainfall intensity data, and find the critical rainfall threshold that overlaps with the current displacement acceleration interval in the association mapping table.

[0137] During the inspection process, the real-time rainfall intensity data is obtained through meteorological monitoring equipment set on the mountain expressway section and accumulated at certain time intervals to obtain the current rainfall accumulation. Then, the critical rainfall threshold that overlaps with the current displacement acceleration interval is found in the association mapping table. Suppose the displacement of the current slope is in a certain acceleration interval, and the corresponding critical rainfall threshold found in the association mapping table is 100 mm.

[0138] Step S1535: Generate a dynamic correction factor for the slope stability coefficient based on the ratio of the change rate of the vertical displacement component to the critical rainfall threshold.

[0139] For example, if the change rate of the vertical displacement component is 5 mm / h and the critical rainfall threshold is 100 mm, then the dynamic correction factor is 5 / 100 = 0.05. This dynamic correction factor reflects the degree of change in the vertical displacement of the slope under the current rainfall conditions relative to the critical rainfall situation.

[0140] Step S1536: Perform weighted fusion of the dynamic correction factor and the normalized value of the slope support structure integrity parameter, and output the comprehensive slope stability coefficient.

[0141] Suppose the normalized value of the integrity parameter of the slope support structure is 0.8 after evaluation. According to the set weighting coefficients (for example, the weight of the dynamic correction factor is 0.3, and the weight of the slope support structure integrity parameter is 0.7), weighted fusion calculation is carried out to obtain the comprehensive slope stability coefficient of 0.8×0.7 + 0.05×0.3 = 0.575. If this comprehensive slope stability coefficient is lower than the safety threshold, a third-level warning signal is triggered. This indicates that under the current slope state, due to the influence of factors such as rainfall and rock and soil displacement, the stability of the slope has been in the dangerous range and corresponding measures need to be taken.

[0142] In a possible implementation manner, the method further includes:

[0143] Step S210, establishing a feedback closed-loop mechanism for the multi-dimensional monitoring data and the disposal suggestion information.

[0144] Step S220, when the disposal suggestion information is adopted and executed by the road and bridge management terminal, continuously monitor the structural response data of the corresponding area, compare and analyze the structural response data with the expected disposal effect. If the comparison and analysis result shows that the actual improvement rate is lower than the set proportion of the expected value, a disposal plan optimization instruction is triggered.

[0145] For example, after a disposal suggestion of a support structure reinforcement plan is taken for a certain slope, when the unmanned aerial vehicle (UAV) performs an inspection task, the deformation data of the reinforcement material and the stress distribution data of the support structure in the disposal area are synchronously collected. In the reinforced slope area, the deformation data of the reinforcement material is obtained through sensors set in the reinforcement material, such as the elongation of the anchor rod or the change in the inclination of the retaining wall. At the same time, the stress distribution data of the support structure is obtained through stress sensors installed in the support structure to understand the magnitude and distribution of the internal stress of the support structure.

[0146] Then, these structural response data are compared and analyzed with the expected disposal effect. The expected disposal effect is preset according to the disposal plan. For example, it is expected that within a certain time, the displacement rate of the slope should be reduced to a certain safe range, the deformation of the reinforcement material should be kept within the design allowable range, and the stress distribution of the support structure should conform to the principles of structural mechanics, etc. If the comparison and analysis result shows that the actual improvement rate is lower than the set proportion of the expected value, for example, it is expected that the slope displacement rate is reduced by 80%, but actually only reduced by 50%, a disposal plan optimization instruction is triggered.

[0147] Step S230, based on the disposal plan optimization instruction, adjust the parameter weights of the risk warning model, update the emergency avoidance node configuration in the path planning model, and then synchronize the optimized model parameters and configuration information to the edge computing units of all in-service UAVs to realize the online iterative upgrade of the monitoring strategy.

[0148] For example, if it is found that the current treatment plan has a poor control effect on slope displacement, it may be that the weight setting of the relationship between slope displacement rate and rainfall intensity in the risk warning model is unreasonable. Adjust the weights of relevant parameters in the risk warning model, such as increasing the weight of rainfall intensity on slope stability. At the same time, since the unstable state of the slope may affect the inspection path planning of the UAV, update the configuration of emergency avoidance nodes in the path planning model, for example, add more emergency avoidance nodes near the slope or adjust the positions of existing avoidance nodes. Then synchronize these optimized model parameters and configuration information to the edge computing units of all in-service UAVs, so that the UAVs can perform more effective inspections according to the new monitoring strategy in subsequent inspection tasks.

[0149] For example, the implementation of the feedback closed-loop mechanism includes:

[0150] Step S211, when the UAV performs an inspection task, synchronously collect the deformation data of the reinforcement materials and the stress distribution data of the support structure in the treatment area.

[0151] Step S212, by comparing the differences in slope displacement trajectories before and after treatment, calculate the effective action radius and attenuation coefficient of the treatment measures corresponding to the treatment suggestion information.

[0152] Step S213, if the implementation attenuation coefficient exceeds the standard deviation of a preset multiple of the historical average value, it is determined that there is a design defect in the current treatment plan, and optimization suggestions for material replacement or structural redesign are generated.

[0153] Step S214, input the optimization suggestions into the path planning model, and increase the monitoring frequency and sensor accuracy level for the defective area.

[0154] And step S215, when the new treatment plan is implemented, restart the feedback closed-loop mechanism until the actual improvement rate reaches the standard.

[0155] For example, before and after the slope is reinforced, slope displacement trajectory data are obtained respectively. Through comparison, it is found that within a certain range from the reinforcement structure, the slope displacement is well controlled, and this range is the effective action radius of the treatment measures. As time goes by, the control effect of the treatment measures on slope displacement may gradually weaken, and the attenuation coefficient is calculated by analyzing the change trend of the displacement trajectory data. If the implementation attenuation coefficient exceeds the standard deviation of a preset multiple of the historical average value, for example, the historical average attenuation coefficient is 0.1, the standard deviation is 0.02, and the currently calculated attenuation coefficient is 0.15, exceeding 1.5 times the standard deviation, it is determined that there is a design defect in the current treatment plan, and optimization suggestions for material replacement or structural redesign are generated.

[0156] Input the optimization suggestions into the path planning model to increase the monitoring frequency of the defect area and the accuracy level of the sensors. For example, if it is determined that there is a problem with the reinforcement material, input the optimization suggestion of replacing the material into the path planning model, so that the drone increases the monitoring frequency of the reinforcement material in this area during subsequent inspections, such as increasing from once a day to three times a day. At the same time, improve the accuracy level of the sensors to more accurately obtain the deformation data of the reinforcement material and the stress distribution data of the support structure. After the new disposal plan is implemented, restart the feedback closed-loop mechanism until the actual improvement rate reaches the standard, ensure that the slopes of mountain highway sections are in a safe and stable state, and guarantee the safe operation of the entire road.

[0157] Figure 2 FIG. shows a schematic diagram of exemplary hardware and software components of a server 100 that can implement the ideas of the present application provided by some embodiments of the present application. For example, a processor 120 can be used on the server 100 and is used to execute the functions in the present application.

[0158] The server 100 can be a general-purpose server or a special-purpose server, both of which can be used to implement the inspection data monitoring method for mountain road and bridge early warning applied in the present application. Although only one server is shown in the present application, for convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0159] For example, the server 100 can include a network port 110 connected to the network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as disks, ROM, or RAM, or any combination thereof. Exemplarily, the server 100 can also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The server 100 also includes an input / output (I / O) interface 150 between the computer and other input / output devices.

[0160] For ease of illustration, only one processor is described in the server 100. However, it should be noted that the server 100 in the present application can also include multiple processors. Therefore, the steps executed by one processor described in the present application can also be jointly executed or separately executed by multiple processors. For example, if the processor of the server 100 executes steps A and B, it should be understood that steps A and B can also be jointly executed by two different processors or separately executed in one processor. For example, the first processor executes step A, the second processor executes step B, or the first processor and the second processor jointly execute steps A and B.

[0161] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When a processor executes the computer-executable instructions, the above-mentioned inspection data monitoring method applied to mountain road and bridge early warning is implemented.

[0162] It should be noted that, in order to simplify the description of the present invention disclosure and thus help the understanding of one or more embodiments of the present invention, in the foregoing description of the embodiments of the present invention, sometimes multiple features are incorporated into one embodiment, drawing or description thereof.

Claims

1. A patrol data monitoring method for early warning of roads and bridges in mountainous areas, characterized in that: The method comprises: Acquire remote sensing monitoring data of roads and bridges in target mountainous road sections, wherein the remote sensing monitoring data of roads and bridges includes current terrain distribution characteristics, road and bridge structure status parameters, and historical disaster records; Based on the current terrain distribution characteristics, calling the terrain feature extraction model to perform regional segmentation on the target mountainous road section, and generating multiple inspection sub-areas and corresponding terrain feature labels; According to the terrain feature labels and the road and bridge structure state parameters, a dynamic flight path of the UAV in the inspection sub-area is generated through a path planning model, wherein the dynamic flight path includes a plurality of inspection nodes and flight parameters between the inspection nodes; Based on the dynamic flight path, the UAV is controlled to perform real-time inspection tasks, and multi-dimensional monitoring data in the inspection sub-area is collected, wherein the multi-dimensional monitoring data includes surface deformation data, road and bridge crack images, and slope displacement trajectories; Input the multi-dimensional monitoring data and the historical disaster records into the risk warning model to generate a risk level signal and corresponding disposal suggestion information for the target mountainous road section; The method further comprises: Establish a closed-loop feedback mechanism for the multi-dimensional monitoring data and disposal suggestion information; When the disposal suggestion information is adopted and executed by the road and bridge management terminal, the structural response data of the corresponding area is continuously monitored, and the structural response data is compared and analyzed with the expected disposal effect. If the comparative analysis result indicates that the actual improvement rate is lower than the set ratio of the expected value, the disposal plan optimization instruction is triggered; After adjusting the parameter weights of the risk warning model based on the disposal plan optimization instructions and updating the emergency avoidance node configuration in the path planning model, the optimized model parameters and configuration information are synchronized to the edge computing units of all in-service drones to realize online iterative upgrades of the monitoring strategy.

2. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 1 is characterized in that: The acquisition of the road and bridge remote sensing monitoring data of the target mountainous road section includes: Acquire multispectral image data and three-dimensional point cloud data of the target mountainous road section through satellite remote sensing equipment; Performing ground object classification processing on the multispectral image data, extracting vegetation coverage density, rock exposed area and hydrological distribution characteristics as sub-features of the current terrain distribution characteristics; Performing elevation difference processing on the three-dimensional point cloud data to generate a terrain slope matrix and a surface undulation index, and associating the terrain slope matrix and the surface undulation index with corresponding inspection sub-areas; Retrieving the historical maintenance database of the target mountainous road section, extracting the pier inclination angle, road surface settlement rate and slope support structure integrity parameters from the road and bridge structure status parameters; The historical disaster records are classified according to disaster types, including landslide events, bridge crack expansion events and roadbed collapse events, and the geographical coordinates and occurrence timestamps corresponding to each event are associated.

3. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 1 is characterized in that: The method of generating a dynamic flight path of the UAV in the inspection sub-area through a path planning model according to the terrain feature labels and the road and bridge structure state parameters includes: According to the vegetation coverage density and terrain slope matrix in the terrain feature label, the minimum safe flight altitude and obstacle avoidance buffer distance of the UAV in the corresponding inspection sub-area are calculated; Based on the pier inclination angle and slope support structure integrity parameters in the road and bridge structure status parameters, determine the priority order of the inspection nodes and the data collection time of each inspection node; Based on the minimum safe flight altitude and obstacle avoidance buffer distance of the drone in the corresponding inspection sub-area, as well as the priority order of the inspection nodes and the data collection time of each inspection node, a path optimization algorithm is used to spatially sort the inspection nodes, generate an initial flight path, and dynamically adjust the flight parameters based on real-time meteorological data, including flight speed, hovering time and sensor trigger frequency; Inserting emergency avoidance nodes into the initial flight path to generate an adjusted flight path, wherein the emergency avoidance nodes are adaptively configured according to the spatial distribution density of disaster types in historical disaster records; Integrate the adjusted flight path and the flight parameters into the dynamic flight path, and synchronize the dynamic flight path to the navigation control unit of the UAV, preset a path deviation detection mechanism in the navigation control unit, and trigger local path replanning when the lateral offset between the actual flight trajectory of the UAV and the dynamic flight path continues to exceed a preset ratio of the obstacle avoidance buffer boundary range, and return to execute the step of spatially sorting the inspection nodes using a path optimization algorithm to generate an initial flight path only for the remaining nodes that have not been visited; Among them, the minimum safe flight altitude H_min=H_base+α×V+β×S̄ The obstacle avoidance buffer distance D_buffer=γ×(V / V_max)+δ×(ΔS / S_ref) The priority of the inspection node P = θ × w1 + (1-I) × w2 The data collection duration T = T_base × (1 + P / P_max) H_base is the benchmark safety height, α is the weight coefficient of vegetation coverage density V, β is the correction coefficient of the average slope S̄ of the terrain slope matrix, γ is the influencing factor of vegetation density, V_max is the maximum vegetation coverage density in the region, δ is the adjustment coefficient of the slope change rate ΔS, S_ref is the slope reference threshold, θ is the inclination angle of the pier, I is the normalized value of the integrity parameter of the slope support structure, w1 and w2 are the weight coefficients of the inclination angle and integrity respectively, T_base is the basic collection time, and P_max is the maximum priority value.

4. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 3 is characterized in that: The step of spatially sorting the inspection nodes using a path optimization algorithm based on the minimum safe flight altitude and obstacle avoidance buffer distance of the drone in the corresponding inspection sub-area, the priority order of the inspection nodes and the data collection time of each inspection node to generate an initial flight path includes: Based on the minimum safe flight altitude and obstacle avoidance buffer distance of each inspection sub-area, a corresponding flight altitude lower limit and obstacle avoidance buffer boundary range are assigned to each inspection node, and a set of inspection node safety parameters including altitude constraints and spatial obstacle avoidance ranges is generated; According to the priority order of the inspection nodes and the data collection time, the inspection nodes are sorted from high to low according to the priority, and when the priorities are the same, they are sorted from short to long according to the data collection time to form a node access sequence with time weight; Based on the order of the node access sequence and the inspection node safety parameter set, a candidate path set consisting of multiple candidate flight paths is generated between two adjacent inspection nodes, and each candidate flight path satisfies that the obstacle avoidance buffer boundary range of the starting node and the obstacle avoidance buffer boundary range of the end node do not overlap, and the flight altitude is always not lower than the higher minimum safe flight altitude of the two nodes; For each candidate flight path, a comprehensive cost value of the candidate flight path is calculated, wherein the comprehensive cost value is obtained by weighted summation of flight distance cost, data collection time cost and safety risk cost, wherein the safety risk cost is calculated according to the overlap ratio between the candidate flight path and the spatial distribution density of disaster points in historical disaster records; The path with the lowest comprehensive cost value is selected from the candidate path set as the reference path, and the paths between adjacent nodes are rearranged for nodes whose data collection time exceeds a preset threshold in the reference path, and an optimized target path is generated by exchanging the node order or inserting an intermediate transition node, and the comprehensive cost value of the target path is re-evaluated until the convergence condition is reached. In the currently optimized target path, the flight speed and sensor trigger frequency of the UAV are dynamically matched according to the flight altitude lower limit value and obstacle avoidance buffer boundary range of each path segment in the target path, wherein the flight speed is positively correlated with the minimum safe flight altitude of the path segment, and the sensor trigger frequency is negatively correlated with the area of ​​the obstacle avoidance buffer boundary range; Detect whether there is a target area in the target path where the flight direction turning angles of a preset number of consecutive inspection nodes exceed the maximum steering capability of the drone. If so, insert an auxiliary correction node in the target area, the position of the auxiliary correction node is determined according to the intersection of the extended tangent of the obstacle avoidance buffer boundary range, and recalculate the comprehensive cost value of the path after inserting the auxiliary correction node until the target path optimization is completed to generate the initial flight path; The dynamically adjusting the flight parameters based on real-time meteorological data includes: Obtain real-time wind speed, rainfall intensity and visibility data for target mountainous road sections; If the real-time wind speed exceeds the first preset threshold, the flight speed of the UAV is reduced according to the preset deceleration strategy and the obstacle avoidance buffer distance is increased according to the preset obstacle avoidance buffer strategy; If the rainfall intensity exceeds the second preset threshold, the anti-interference mode of the drone is enabled, and the sensor trigger frequency is increased according to the first preset compensation parameter to compensate for the loss of data collection accuracy; If the visibility is lower than the third preset threshold, the infrared imaging module of the drone is activated to replace the visible light camera, and the data collection time of the corresponding inspection node is extended according to the second preset compensation parameter; The flight risk in the future time window is predicted based on the changing trend of meteorological data. If the predicted risk level exceeds the critical value, a path replanning instruction is sent to the navigation control unit of the drone.

5. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 2 is characterized in that: The controlling of the UAV to perform real-time inspection tasks based on the dynamic flight path and collecting multi-dimensional monitoring data in the inspection sub-area includes: Scanning the surface deformation area by using a laser radar sensor of the drone to generate a deformation displacement vector map as the surface deformation data; Using an optical camera to capture a road bridge surface image, and using an edge detection algorithm to extract crack length, width, and direction features corresponding to the road bridge surface image as structured data of the road bridge crack image; The multi-band radar of the UAV is used to continuously monitor the slope and capture the slope displacement trajectory of the rock and soil inside the slope, which includes the displacement rate curve and the sliding direction index; Synchronously collect environmental temperature and humidity, wind speed and direction, and vibration frequency parameters as auxiliary verification information for the multi-dimensional monitoring data; The surface deformation data, road and bridge crack images and slope displacement trajectories are aligned in time series, bound with corresponding geographic coordinates and stored in a distributed database.

6. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 5 is characterized in that: The laser radar sensor of the drone is used to scan the surface deformation area to generate a deformation displacement vector diagram, including: The UAV continuously emits laser pulses during flight, receives reflected signals and calculates the round-trip time difference of the pulses to generate an initial point cloud data set; De-noising the initial point cloud data to remove abnormal points caused by vegetation occlusion or meteorological interference, thereby generating de-noised point cloud data; Based on the terrain slope matrix, the denoised point cloud data is subjected to elevation correction to obtain current point cloud data, thereby eliminating the error effect of terrain undulation on deformation calculation; A time series difference algorithm is used to compare the current point cloud data with the historical benchmark data to calculate the three-dimensional displacement and displacement direction of each monitoring point; The area where the displacement exceeds the warning threshold is marked as a risk area, and the risk level of the risk area is distinguished by color gradient in the deformation displacement vector diagram.

7. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 1 is characterized in that: The multi-dimensional monitoring data and the historical disaster records are input into the risk warning model to generate a risk level signal and corresponding disposal suggestion information for the target mountainous road section, including: Calling the risk warning model, matching the displacement rate in the surface deformation data with the landslide events in the historical disaster records, and triggering a first-level warning signal if the displacement rate continues to increase and the direction is consistent with the historical landslide direction; And, analyzing the trend characteristics of the road bridge crack image, if the crack extension direction coincides with the main stress direction of the bridge and the width expansion rate exceeds a critical value, a secondary warning signal is triggered; And, according to the sliding direction and speed of the slope displacement trajectory, combined with the real-time rainfall intensity data, the slope stability coefficient is calculated. If the slope stability coefficient is lower than the safety threshold, a third-level warning signal is triggered; Generate differentiated disposal suggestion information based on the warning signal level, including emergency road closure, speed limit or initiation of support structure reinforcement plan; The risk level signal and treatment suggestion information are pushed to the road and bridge management terminal, and the corresponding monitoring data traceability link is associated for manual review.

8. The inspection data monitoring method for early warning of mountainous roads and bridges according to claim 7 is characterized in that: The slope stability coefficient is calculated based on the sliding direction and speed of the slope displacement trajectory in combination with real-time rainfall intensity data, including: Performing vector decomposition on the sliding direction of the slope displacement trajectory to generate time series data of horizontal displacement components and vertical displacement components; Performing similarity matching between the horizontal displacement component and the landslide event displacement pattern of the corresponding geographic coordinates in the historical disaster records, and screening out a reference event set whose displacement trend similarity exceeds a matching threshold; Extracting the rainfall intensity time series data before each landslide event in the reference event set, and establishing a correlation mapping table between rainfall accumulation and displacement acceleration interval; Calculate the current rainfall accumulation according to the real-time rainfall intensity data, and search the association mapping table for a critical rainfall threshold value overlapping with the current displacement acceleration interval; generating a dynamic correction factor for the slope stability coefficient based on a ratio of the rate of change of the vertical displacement component to a critical rainfall threshold; The dynamic correction factor is weightedly fused with the normalized value of the slope support structure integrity parameter to output a comprehensive slope stability coefficient.

9. A server, characterized in that: The server includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the inspection data monitoring method for mountain road and bridge early warning as described in any one of claims 1 to 8.

Images