Automatic inspection method and system for high-rise hyperbolic glass curtain wall based on unmanned aerial vehicle

Abstract

The invention provides an unmanned aerial vehicle-based high-rise hyperbolic glass curtain wall automatic inspection method and system, and the system comprises an unmanned aerial vehicle, a data acquisition module and a controller. The data acquisition module is carried on the unmanned aerial vehicle and comprises an ultrasonic sensor array, an infrared thermal imager and an image acquisition module; the controller is used for performing time-frequency domain analysis on the reflected wave to obtain the signal intensity of the reflected wave; the controller performs temperature gradient calculation on the structural adhesive surface temperature distribution image to obtain temperature anomaly region features, obtains optical image textures according to the surface optical image, and outputs an inspection result according to the reflected wave signal intensity, the temperature anomaly region features and the optical image textures; generating an unmanned aerial vehicle flight path according to the three-dimensional model and the curvature parameter of the hyperbolic glass curtain wall, generating obstacle avoidance position information according to environment information set by the hyperbolic glass curtain wall, and updating the unmanned aerial vehicle flight path according to the obstacle avoidance position information; and controlling the unmanned aerial vehicle to automatically inspect the hyperbolic glass curtain wall according to the flight path of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present application relates to the field of automatic inspection technology, and in particular to an automatic inspection method and system for high-rise hyperbolic glass curtain walls based on drones. Background Art

[0002] With the acceleration of urbanization, high-rise buildings are increasingly using hyperbolic glass curtain walls as part of their facade design. This design is not only beautiful, but also provides good natural lighting and views. However, the maintenance and inspection of hyperbolic glass curtain walls face many challenges. Traditional inspection methods usually require manual climbing or the use of equipment such as hanging baskets for close inspection, which is not only inefficient but also poses a great safety hazard. In addition, due to the complex geometry of the hyperbolic glass curtain wall, manual inspection is difficult to fully cover all areas and is prone to missing subtle defects.

[0003] In recent years, the development of drone technology has provided a new solution for the inspection of high-rise buildings. However, the existing drone inspection system still has some shortcomings when applied to hyperbolic glass curtain walls. For example, a single image acquisition module cannot fully capture the various defect information of the glass curtain wall; the lack of an effective obstacle avoidance mechanism makes drones prone to collision in complex environments; and the lack of targeted flight path planning for the special geometric shape of the hyperbolic glass curtain wall leads to low inspection efficiency and accuracy.

[0004] Therefore, a system and a corresponding method are urgently needed to solve at least one of the above problems. Summary of the invention

[0005] This application provides a method and system for automatic inspection of high-rise hyperbolic glass curtain walls based on drones, aiming to solve some shortcomings of existing drone inspection systems when applied to hyperbolic glass curtain walls. For example, a single image acquisition module cannot fully capture various defect information of glass curtain walls; the lack of an effective obstacle avoidance mechanism makes drones prone to collisions in complex environments; and the lack of targeted flight path planning for the special geometric shapes of hyperbolic glass curtain walls leads to low inspection efficiency and accuracy.

[0006] In a first aspect, the present application provides a high-rise hyperbolic glass curtain wall automatic inspection system based on a drone, comprising:

[0007] Drones;

[0008] A data acquisition module, the data acquisition module is carried on the UAV, the data acquisition module includes an ultrasonic sensor array, an infrared thermal imager and an image acquisition module, wherein the ultrasonic sensor array is used to transmit high-frequency ultrasonic signals to the hyperbolic glass curtain wall to be inspected and receive reflected waves, the infrared thermal imager is used to capture the surface temperature distribution image of the structural adhesive of the hyperbolic glass curtain wall, and the image acquisition module is used to collect the surface optical image of the hyperbolic glass curtain wall;

[0009] A controller is provided, wherein the controller is used to perform time-frequency domain analysis on the reflected wave to obtain the reflected wave signal intensity; the controller performs temperature gradient calculation on the surface temperature distribution image of the structural adhesive to obtain the temperature abnormality area characteristics; the controller obtains the optical image texture according to the surface optical image; the controller outputs the inspection result according to the reflected wave signal intensity, the temperature abnormality area characteristics and the optical image texture; the controller generates a UAV flight trajectory according to the three-dimensional model and curvature parameters of the hyperbolic glass curtain wall, generates obstacle avoidance position information according to the environmental information of the hyperbolic glass curtain wall setting, and updates the UAV flight trajectory according to the obstacle avoidance position information; the controller controls the UAV to automatically inspect the hyperbolic glass curtain wall according to the UAV flight trajectory.

[0010] In some embodiments, the data acquisition module includes: a polarization filter, which is arranged at the front end of the image acquisition module to suppress the surface reflection interference of the hyperbolic glass curtain wall.

[0011] In some embodiments, the controller generates an ultrasonic signal attenuation coefficient based on the reflected wave signal intensity and the ultrasonic signal intensity; the controller calculates the area ratio of the temperature abnormality region based on the characteristics of the temperature abnormality region and the area corresponding to the hyperbolic glass curtain wall; the controller determines the crack morphology characteristics based on the optical image texture; the controller outputs the inspection result based on the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

[0012] Exemplarily, the controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

[0013] In some embodiments, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall and the real-time pose vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; the controller generates the flight trajectory of the drone based on a genetic algorithm according to the fitness function.

[0014] Exemplarily, the expression of the fitness function includes:

[0015] ;

[0016] in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information, and the second-order difference term is used to measure the acceleration change of the trajectory.

[0017] It should be noted that, in some embodiments, the expression of the curvature smoothing weight coefficient includes:

[0018] ;

[0019] in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

[0020] In some embodiments, it also includes: a meteorological sensing unit, which monitors the wind speed information and precipitation information corresponding to the drone in real time; an autonomous obstacle avoidance unit, which detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall through the fusion of millimeter-wave radar and binocular vision, and controls the drone to perform autonomous obstacle avoidance when the distance between the convex structure and the temporary obstacle is less than a preset distance; a multi-link redundant communication unit, which is mounted on the drone and uses LoRa and 4G dual channels to transmit data in parallel with the controller.

[0021] In some embodiments, the controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall, the curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results, and the controller outputs an inspection cycle adaptive adjustment suggestion based on the defect expansion rate and environmental factor correlation.

[0022] In a second aspect, the present application provides a method for automatic inspection of high-rise hyperbolic glass curtain walls based on a drone, which is applied to a controller of a system provided in any embodiment of the present application, and the method includes:

[0023] Perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength;

[0024] The temperature gradient of the surface temperature distribution image of the structural adhesive captured by the infrared thermal imager is calculated to obtain the characteristics of the temperature abnormality area;

[0025] Acquire optical image texture according to the surface optical image acquired by the image acquisition module;

[0026] Generate the UAV flight trajectory based on the 3D model and curvature parameters of the hyperbolic glass curtain wall;

[0027] Generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall setting, and update the flight trajectory of the drone according to the obstacle avoidance position information;

[0028] The drone is controlled according to the flight trajectory of the drone to automatically inspect the hyperbolic glass curtain wall.

[0029] In a third aspect, the present application provides a high-rise hyperbolic glass curtain wall automatic inspection device based on a drone, comprising:

[0030] The time-frequency analysis module is used to perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength;

[0031] The abnormal acquisition module is used to calculate the temperature gradient of the temperature distribution image of the structural adhesive surface captured by the infrared thermal imager to obtain the characteristics of the temperature abnormal area;

[0032] An image acquisition module, used for acquiring optical image texture according to the surface optical image acquired by the image acquisition module;

[0033] The trajectory generation module is used to generate the UAV flight trajectory according to the three-dimensional model of the hyperbolic glass curtain wall and the curvature parameters;

[0034] A trajectory updating module, used to generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall, and update the flight trajectory of the UAV according to the obstacle avoidance position information;

[0035] The inspection control module is used to control the drone to automatically inspect the hyperbolic glass curtain wall according to the flight trajectory of the drone.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable instructions are executed by the processor, one or more processors execute a method as provided in any embodiment of the present application.

[0037] The embodiment of the present application provides a method and system for automatic inspection of high-rise hyperbolic glass curtain walls based on drones. The system aims to overcome the shortcomings of existing drone inspection technology when applied to hyperbolic glass curtain walls. Specifically, the system integrates multiple sensors and intelligent control algorithms to achieve a more comprehensive, efficient and safe inspection of hyperbolic glass curtain walls. The following is the detailed technical content of the system:

[0038] System composition:

[0039] UAV: As the main flying platform, it carries the data acquisition module and controller.

[0040] Data acquisition module: includes ultrasonic sensor array, infrared thermal imager and image acquisition module, which is used to collect information of hyperbolic glass curtain wall from different dimensions.

[0041] Ultrasonic sensor array: emits high-frequency ultrasonic signals and receives reflected waves, and detects defects inside or on the surface of the glass curtain wall by analyzing the reflected waves.

[0042] Infrared thermal imager: Captures temperature distribution images on the surface of glass curtain wall structural adhesive to help identify areas of abnormal temperature caused by structural problems.

[0043] Image acquisition module: Collects surface optical images of glass curtain walls to detect damage or other visible problems on the appearance.

[0044] Controller: Responsible for processing the data from various sensors and generating corresponding inspection results; at the same time, it plans the flight path of the drone according to the specific geometric characteristics of the glass curtain wall and implements obstacle avoidance strategies.

[0045] The corresponding workflow of the system includes:

[0046] Data collection and preliminary processing: An ultrasonic sensor array transmits signals to the target and analyzes the echo to assess the material condition. Infrared thermal imagers record temperature distribution, paying special attention to locations that may indicate potential failure points. Image acquisition modules take high-resolution photos for subsequent visual inspection.

[0047] Data Analysis: The controller performs a comprehensive analysis of the above three types of data, including but not limited to reflected wave signal strength, temperature gradient changes, and texture characteristics, etc. Based on this information, it is determined whether there are any problem areas that require further investigation.

[0048] Path planning and execution: Based on the pre-built 3D model and known curvature parameters, the controller calculates the best flight path. Combined with real-time environmental perception (such as obstacle location), the trajectory is dynamically adjusted to ensure safe operation. Finally, the drone is guided to complete the entire inspection task according to the optimized path.

[0049] The provided system has at least the following beneficial effects:

[0050] Improved detection accuracy: By combining multiple sensing technologies, different types of problems can be captured more comprehensively, thereby improving the ability to detect problems.

[0051] Enhanced safety: The introduction of advanced obstacle avoidance mechanism can effectively avoid the risk of collision between the drone and surrounding objects, ensuring the safety of the operation process.

[0052] Improve efficiency: Automated path planning reduces the need for manual intervention, making the entire inspection process smoother and faster, saving a lot of time costs.

[0053] Strong adaptability: The functions specially developed for hyperbolic design enable it to better serve this type of special architectural form, showing good flexibility and scope of application.

[0054] Cost-effectiveness: In the long run, adopting this automation solution can significantly reduce maintenance expenses while extending the life of the building, bringing financial benefits to the owner.

[0055] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 It is a structural schematic diagram of a high-rise hyperbolic glass curtain wall automatic inspection system based on a drone provided in one embodiment of the present application;

[0058] Figure 2 This is a schematic diagram of the inspection principle of a high-rise hyperbolic glass curtain wall automatic inspection system based on a drone provided in one embodiment of the present application;

[0059] Figure 3 This is a schematic flow chart of the steps of an automatic inspection method for high-rise hyperbolic glass curtain walls based on a drone provided in one embodiment of the present application;

[0060] Figure 4 It is a schematic block diagram of the structure of a controller provided in one embodiment of the present application.

[0061] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0064] It should be understood that, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0065] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0066] It should also be understood that the term “and / or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0067] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0068] With the acceleration of urbanization, high-rise buildings are increasingly using hyperbolic glass curtain walls as part of their facade design. This design is not only beautiful, but also provides good natural lighting and views. However, the maintenance and inspection of hyperbolic glass curtain walls face many challenges. Traditional inspection methods usually require manual climbing or the use of equipment such as hanging baskets for close inspection, which is not only inefficient but also poses a great safety hazard. In addition, due to the complex geometry of the hyperbolic glass curtain wall, manual inspection is difficult to fully cover all areas and is prone to missing subtle defects.

[0069] In recent years, the development of drone technology has provided a new solution for the inspection of high-rise buildings. However, the existing drone inspection system still has some shortcomings when applied to hyperbolic glass curtain walls. For example, a single image acquisition module cannot fully capture the various defect information of the glass curtain wall; the lack of an effective obstacle avoidance mechanism makes drones prone to collision in complex environments; and the lack of targeted flight path planning for the special geometric shape of the hyperbolic glass curtain wall leads to low inspection efficiency and accuracy.

[0070] Therefore, a system and a corresponding method are urgently needed to solve at least one of the above problems.

[0071] To solve the above problems, please refer to Figure 1 .like Figure 1As shown, the present application provides a high-rise hyperbolic glass curtain wall automatic inspection system based on a drone, comprising: a drone, a data acquisition module (not shown in the figure), the data acquisition module is carried on the drone, the data acquisition module comprises an ultrasonic sensor array, an infrared thermal imager and an image acquisition module, wherein the ultrasonic sensor array is used to transmit high-frequency ultrasonic signals to the hyperbolic glass curtain wall to be inspected and receive reflected waves, the infrared thermal imager is used to capture the surface temperature distribution image of the structural adhesive of the hyperbolic glass curtain wall, and the image acquisition module is used to collect the surface optical image of the hyperbolic glass curtain wall; a controller, the controller is used to perform time-frequency domain analysis on the reflected waves to obtain The reflected wave signal intensity is obtained; the controller calculates the temperature gradient of the structural adhesive surface temperature distribution image to obtain the temperature abnormality area characteristics; the controller obtains the optical image texture according to the surface optical image; the controller outputs the inspection result according to the reflected wave signal intensity, the temperature abnormality area characteristics and the optical image texture; the controller generates the UAV flight trajectory according to the three-dimensional model and curvature parameters of the hyperbolic glass curtain wall, generates the obstacle avoidance position information according to the environmental information of the hyperbolic glass curtain wall setting, and updates the UAV flight trajectory according to the obstacle avoidance position information; the controller controls the UAV to automatically inspect the hyperbolic glass curtain wall according to the UAV flight trajectory.

[0072] Specifically, this system aims to provide an efficient, safe and comprehensive automatic inspection solution for the hyperbolic glass curtain walls used in high-rise buildings by combining advanced sensor technology, image processing technology and path planning algorithms. The system is mainly composed of the following key components:

[0073] UAV: As a platform for carrying various types of testing equipment, it has good flight stability and maneuverability.

[0074] Data acquisition module: Ultrasonic sensor array: used to transmit high-frequency ultrasonic signals to the hyperbolic glass curtain wall to be inspected, and receive the reflected waves to detect whether there are problems such as cavities or cracks in the internal structure of the curtain wall. Infrared thermal imager: can capture the surface temperature distribution of the glass curtain wall, especially its joints (such as the parts using structural adhesive), so as to identify areas where hidden dangers may exist. Image acquisition module: responsible for obtaining high-definition optical images of the outer surface of the curtain wall to detect damage or other visible defects on the appearance.

[0075] Controller: It integrates powerful data processing capabilities, which can not only analyze and process the various information collected, but also automatically generate the optimal flight route according to preset conditions, and make real-time adjustments to avoid obstacles.

[0076] like Figure 2 As shown, the specific implementation of this system includes the following stages:

[0077] Initialization phase: First, we need to build an accurate 3D model of the target building, especially its hyperbolic glass curtain wall ( Figure 2 The algorithm model shown in the figure is prepared), and this model is input into the control system together with the relevant environmental parameters.

[0078] Inspection preparation: Based on the above 3D model and geometric characteristics such as curvature, the controller will pre-calculate an optimal flight trajectory covering the entire inspection range ( Figure 2 At the same time, considering other buildings or other objects that may exist in the actual working environment, some additional obstacle avoidance points will be set.

[0079] Perform inspection tasks (corresponding to Figure 2 Cruise test): Start the drone and start working along the established route. During this process, various sensors (including Figure 2 The UAV system composition and component preparation) continuously collects relevant data and transmits it to the ground station or directly processes it on the onboard computer. The ultrasonic sensor array sends pulse signals regularly and records the time difference and intensity changes of the echoes. These data help to evaluate the internal condition of the material. The infrared camera focuses on monitoring the changing trend of the temperature difference on the wall surface in different time periods. Abnormally high or low temperature areas often indicate potential problems. The high-definition camera is responsible for taking clear photos or video streams for more detailed viewing of details later.

[0080] All collected information will eventually be aggregated on a unified platform and further analyzed by specialized software to form a complete diagnostic report (corresponding to Figure 2 The report contains not only text descriptions but also intuitive charts to help users quickly understand the problem and its severity.

[0081] The system provided thereby has at least the following beneficial effects:

[0082] Improve efficiency: Compared with traditional manual operation mode, the use of drones can significantly shorten the time required to complete a comprehensive inspection.

[0083] Enhanced safety: Reduces workers’ exposure to high-risk environments and reduces the likelihood of accidents.

[0084] Improved accuracy: The application of multimodal sensing technology makes it difficult for even the smallest defects to escape the system's detection, ensuring higher detection accuracy.

[0085] Cost-effectiveness: In the long run, although the initial investment is large, the overall economic benefits will gradually emerge as the operating and maintenance costs decrease.

[0086] Strong flexibility: Different sensor combinations can be flexibly configured according to specific needs to adapt to special requirements in various application scenarios.

[0087] Promoting sustainable development: By timely discovering and repairing problems, the service life of buildings is extended, resource waste is reduced, and it is conducive to achieving green and low-carbon goals.

[0088] In summary, this drone-based automatic inspection system for high-rise hyperbolic glass curtain walls not only solves the current technical difficulties, but also provides strong support for the construction of future smart cities.

[0089] In some embodiments, the data acquisition module includes: a polarization filter, which is arranged at the front end of the image acquisition module to suppress the surface reflection interference of the hyperbolic glass curtain wall.

[0090] In an embodiment, the data acquisition module includes a polarization filter, which is arranged at the front end of the image acquisition module. The main function of the polarization filter is to suppress the reflection interference on the surface of the hyperbolic glass curtain wall, thereby improving the quality and accuracy of image acquisition.

[0091] Select the appropriate polarizing filter to ensure that it can effectively reduce the reflected light on the glass surface without affecting the transmission of other light. The image acquisition module uses a high-resolution camera to capture the surface optical image of the hyperbolic glass curtain wall.

[0092] The drone starts the inspection mission according to the preset flight trajectory. The image acquisition module captures the surface image of the hyperbolic glass curtain wall through a polarizing filter. The polarizing filter can significantly reduce the reflected light caused by sunlight or other light sources, making the image clearer. The captured image is transmitted to the ground station or the onboard controller in real time through the wireless communication module for processing. The controller processes the captured image and identifies possible defects such as cracks and scratches. Based on the image analysis results, a detailed inspection report is generated, including the defect type, location and severity.

[0093] Polarizing filters can significantly reduce reflections on the glass surface, making the captured images clearer and improving the accuracy of detection. By reducing reflection interference, the system can more accurately identify subtle defects such as small cracks or scratches. High-quality images reduce post-processing time and improve overall inspection efficiency. Reducing reflection interference helps reduce false alarms caused by changing lighting conditions and improves system reliability.

[0094] In some embodiments, the controller generates an ultrasonic signal attenuation coefficient based on the reflected wave signal intensity and the ultrasonic signal intensity; the controller calculates the area ratio of the temperature abnormality region based on the characteristics of the temperature abnormality region and the area corresponding to the hyperbolic glass curtain wall; the controller determines the crack morphology characteristics based on the optical image texture; the controller outputs the inspection result based on the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

[0095] The controller performs comprehensive analysis based on multiple sensor data to generate detailed inspection results. Data acquisition: Ultrasonic sensor array: emits high-frequency ultrasonic signals and receives reflected waves. Infrared thermal imager: captures the surface temperature distribution image of the structural adhesive of the hyperbolic glass curtain wall. Image acquisition module: collects the surface optical image of the hyperbolic glass curtain wall.

[0096] The controller performs time-frequency domain analysis on the reflected wave, obtains the reflected wave signal strength, and calculates the ultrasonic signal attenuation coefficient. The controller calculates the temperature gradient of the surface temperature distribution image of the structural adhesive, identifies the temperature abnormality area, and calculates the area ratio of the temperature abnormality area. Optical image texture analysis: The controller determines the crack morphology characteristics based on the surface optical image. The ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality area, and the crack morphology characteristics are input into the deep learning model based on the attention mechanism, and the inspection results are output. The inspection results include defect type, defect location, and defect severity score.

[0097] Combining multiple data sources such as ultrasound, infrared thermal imaging and optical imaging, it provides more comprehensive inspection information. Through deep learning models, different types of defects can be more accurately identified and classified. The system automatically analyzes data and generates inspection reports, reducing manual intervention and improving work efficiency. Real-time processing and analysis of data can provide detailed inspection results in a short time, making it easier to take timely measures.

[0098] Exemplarily, the controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

[0099] Input data: ultrasonic signal attenuation coefficient, temperature anomaly area ratio, crack morphology characteristics (including crack morphology curvature). Label data: defect type, location and severity score in historical inspection records.

[0100] The model architecture uses a deep learning model based on the attention mechanism, such as the Transformer model. A large amount of historical data is used for training and the model parameters are optimized to enable it to accurately predict the defect type, location, and severity.

[0101] Reasoning process: Data input: Input the data collected during the current inspection process into the trained model. Result output: The model outputs the inspection results, including defect type, location, and severity score.

[0102] The attention mechanism can better capture key features and improve the accuracy of defect identification. The model can be adaptively adjusted according to different data inputs and is applicable to a variety of complex environments. The model has a fast reasoning speed and can generate inspection results in a short time, which improves the real-time performance of the system. The attention mechanism provides interpretability, which can help understand the model decision-making process and enhance the transparency of the system.

[0103] In some embodiments, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall and the real-time pose vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; the controller generates the flight trajectory of the drone based on a genetic algorithm according to the fitness function.

[0104] In an embodiment, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall, the real-time pose vector of the drone, the estimated total inspection time, and the battery life threshold, and generates an optimal flight trajectory based on a genetic algorithm. By considering the curvature change rate and smoothness, the generated flight trajectory is smoother, the violent movement of the drone is reduced, and the flight safety is improved. By optimizing the inspection time and path length, the inspection efficiency is improved and the drone's endurance is extended. The fitness function can dynamically adjust the weight coefficient according to actual needs, which improves the flexibility and adaptability of the system. The genetic algorithm can search for the global optimal solution, avoid the problem of the local optimal solution, and improve the quality of path planning.

[0105] Exemplarily, the expression of the fitness function includes:

[0106] ;

[0107] in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information, and the second-order difference term is used to measure the acceleration change of the trajectory.

[0108] Dynamically adjust the weight coefficient according to the actual curvature changes, which improves the flexibility and adaptability of path planning. By dynamically adjusting the weight coefficient, the path is smoother in areas with large curvature changes, which improves the safety and stability of flight. Dynamically adjusting the weight coefficient helps balance path smoothness and inspection efficiency, improving the performance of the overall system.

[0109] It should be noted that, in some embodiments, the expression of the curvature smoothing weight coefficient includes:

[0110] ;

[0111] in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

[0112] In some embodiments, it also includes: a meteorological sensing unit, which monitors the wind speed information and precipitation information corresponding to the drone in real time; an autonomous obstacle avoidance unit, which detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall through the fusion of millimeter-wave radar and binocular vision, and controls the drone to perform autonomous obstacle avoidance when the distance between the convex structure and the temporary obstacle is less than a preset distance; a multi-link redundant communication unit, which is mounted on the drone and uses LoRa and 4G dual channels to transmit data in parallel with the controller.

[0113] In an embodiment, a weather sensing unit, an autonomous obstacle avoidance unit, and a multi-link redundant communication unit are added to the system to improve the robustness and safety of the system.

[0114] The wind speed sensor monitors the wind speed information at the location of the drone in real time. The precipitation sensor monitors the precipitation information in real time.

[0115] Autonomous obstacle avoidance unit: Millimeter wave radar: used for long-distance obstacle detection. Binocular vision system: used for close-range obstacle detection and 3D reconstruction. Obstacle avoidance algorithm: when the distance to the convex structure or temporary obstacle is detected to be less than the preset distance, the drone is controlled to perform autonomous obstacle avoidance.

[0116] Multi-link redundant communication unit: LoRa communication module: for long-distance low-power communication. 4G communication module: for high-speed data transmission. Dual-channel parallel transmission: ensure the reliability and real-time performance of data transmission.

[0117] By monitoring meteorological conditions in real time, inspections can be avoided in bad weather, reducing risks. Combining millimeter-wave radar and binocular vision systems, efficient obstacle detection and avoidance are achieved, improving flight safety. Multi-link redundant communication ensures the stability and reliability of data transmission, and can work normally even when a single communication link fails. Real-time monitoring of meteorological conditions and obstacle information helps to adjust the flight plan in a timely manner, improving the response speed and flexibility of the system.

[0118] In some embodiments, the controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall, the curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results, and the controller outputs an inspection cycle adaptive adjustment suggestion based on the defect expansion rate and environmental factor correlation.

[0119] The controller builds a curtain wall performance degradation prediction model based on the historical inspection data of the hyperbolic glass curtain wall, analyzes the correlation between the defect expansion rate and environmental factors according to the inspection results, and outputs adaptive adjustment suggestions for the inspection cycle.

[0120] Data collection: Historical inspection data: including the results of each inspection, defect type, location and severity score. Environmental data: including environmental factors such as temperature, humidity, wind speed, etc.

[0121] Model construction: Based on historical data, a curtain wall performance degradation prediction model is constructed to analyze the correlation between the defect expansion rate and environmental factors. The prediction model is established using regression analysis, time series analysis and other methods.

[0122] Inspection cycle adjustment: Analyze the expansion rate of defects based on inspection results and historical data. Analyze the impact of environmental factors on defect expansion. Output inspection cycle adaptive adjustment suggestions based on the correlation between defect expansion rate and environmental factors.

[0123] The inspection cycle is dynamically adjusted according to the actual defect expansion rate and environmental factors, which improves the effectiveness and economy of the inspection. By predicting the defect expansion trend in advance, maintenance measures can be taken in time to extend the service life of the curtain wall. The inspection cycle is reasonably arranged to avoid excessive or insufficient inspections, which optimizes resource allocation. Based on the comprehensive analysis of historical data and environmental factors, the scientificity and reliability of the inspection cycle adjustment are improved.

[0124] The embodiment of the present application provides a method and system for automatic inspection of high-rise hyperbolic glass curtain walls based on drones. The system aims to overcome the shortcomings of existing drone inspection technology when applied to hyperbolic glass curtain walls. Specifically, the system integrates multiple sensors and intelligent control algorithms to achieve a more comprehensive, efficient and safe inspection of hyperbolic glass curtain walls. The following is the detailed technical content of the system:

[0125] System composition:

[0126] UAV: As the main flying platform, it carries the data acquisition module and controller.

[0127] Data acquisition module: includes ultrasonic sensor array, infrared thermal imager and image acquisition module, which is used to collect information of hyperbolic glass curtain wall from different dimensions.

[0128] Ultrasonic sensor array: emits high-frequency ultrasonic signals and receives reflected waves, and detects defects inside or on the surface of the glass curtain wall by analyzing the reflected waves.

[0129] Infrared thermal imager: Captures temperature distribution images on the surface of glass curtain wall structural adhesive to help identify areas of abnormal temperature caused by structural problems.

[0130] Image acquisition module: Collects surface optical images of glass curtain walls to detect damage or other visible problems on the appearance.

[0131] Controller: Responsible for processing the data from various sensors and generating corresponding inspection results; at the same time, it plans the flight path of the drone according to the specific geometric characteristics of the glass curtain wall and implements obstacle avoidance strategies.

[0132] The corresponding workflow of the system includes:

[0133] Data collection and preliminary processing: An ultrasonic sensor array transmits signals to the target and analyzes the echo to assess the material condition. Infrared thermal imagers record temperature distribution, paying special attention to locations that may indicate potential failure points. Image acquisition modules take high-resolution photos for subsequent visual inspection.

[0134] Data Analysis: The controller performs a comprehensive analysis of the above three types of data, including but not limited to reflected wave signal strength, temperature gradient changes, and texture characteristics, etc. Based on this information, it is determined whether there are any problem areas that require further investigation.

[0135] Path planning and execution: Based on the pre-built 3D model and known curvature parameters, the controller calculates the best flight path. Combined with real-time environmental perception (such as obstacle location), the trajectory is dynamically adjusted to ensure safe operation. Finally, the drone is guided to complete the entire inspection task according to the optimized path.

[0136] The provided system has at least the following beneficial effects:

[0137] Improved detection accuracy: By combining multiple sensing technologies, different types of problems can be captured more comprehensively, thereby improving the ability to detect problems.

[0138] Enhanced safety: The introduction of advanced obstacle avoidance mechanism can effectively avoid the risk of collision between the drone and surrounding objects, ensuring the safety of the operation process.

[0139] Improve efficiency: Automated path planning reduces the need for manual intervention, making the entire inspection process smoother and faster, saving a lot of time costs.

[0140] Strong adaptability: The functions specially developed for hyperbolic design enable it to better serve this type of special architectural form, showing good flexibility and scope of application.

[0141] Cost-effectiveness: In the long run, adopting this automation solution can significantly reduce maintenance expenses while extending the life of the building, bringing financial benefits to the owner.

[0142] See also Figure 3 ,like Figure 3 As shown, the provided high-rise hyperbolic glass curtain wall automatic inspection method based on drone is applied to the controller of the system provided in any embodiment of the present application, and the method includes steps S101 to S106. The details are as follows:

[0143] Step S101. Perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength;

[0144] Step S102: Calculate the temperature gradient of the surface temperature distribution image of the structural adhesive captured by the infrared thermal imager to obtain the characteristics of the temperature abnormality area;

[0145] Step S103. Acquire optical image texture according to the surface optical image acquired by the image acquisition module;

[0146] Step S104. Generate a UAV flight trajectory according to the three-dimensional model of the hyperbolic glass curtain wall and the curvature parameters;

[0147] Step S105. Generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall, and update the flight trajectory of the drone according to the obstacle avoidance position information;

[0148] Step S106: Controlling the drone to automatically inspect the hyperbolic glass curtain wall according to the flight trajectory of the drone.

[0149] The specific implementation methods corresponding to steps S101-S106 are as follows:

[0150] Step S101. Perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength:

[0151] Data acquisition: The ultrasonic sensor array transmits high-frequency ultrasonic signals to the hyperbolic glass curtain wall and receives the reflected waves. Time-frequency domain analysis: The reflected wave signal is processed using time-frequency domain analysis techniques (such as Fourier transform) to extract the frequency and time characteristics of the signal.

[0152] Signal strength calculation: Calculate the strength of the reflected wave signal, which reflects the integrity of the internal structure of the glass curtain wall. If there are holes or cracks, the reflected wave signal strength will change.

[0153] Step S102. Calculate the temperature gradient of the surface temperature distribution image of the structural adhesive captured by the infrared thermal imager to obtain the characteristics of the temperature abnormal area: Data acquisition: The infrared thermal imager captures the surface temperature distribution image of the structural adhesive of the hyperbolic glass curtain wall. Temperature gradient calculation: Calculate the temperature gradient of the temperature distribution image to identify the temperature abnormal area. These areas may be caused by aging, cracks or other defects of the structural adhesive. Feature extraction: Extract the characteristics of the temperature abnormal area, such as temperature gradient, temperature distribution, etc.

[0154] Step S103. Obtain optical image texture based on the surface optical image collected by the image acquisition module: Data acquisition: The image acquisition module captures the surface optical image of the hyperbolic glass curtain wall. Image processing: Use image processing technology (such as edge detection, texture analysis, etc.) to process the image and extract surface texture features. Feature extraction: Identify and extract surface defect features such as cracks and scratches.

[0155] Step S104. Generate the flight trajectory of the drone based on the 3D model and curvature parameters of the hyperbolic glass curtain wall: 3D model establishment: Establish an accurate 3D model of the hyperbolic glass curtain wall, including its geometry and curvature parameters. Path planning: Generate the optimal flight trajectory covering the entire curtain wall based on the 3D model and curvature parameters. Consider the complex geometry of the curtain wall to ensure that the drone can fully cover all areas.

[0156] Step S105. Generate obstacle avoidance position information according to the environmental information of the hyperbolic glass curtain wall, and update the flight trajectory of the drone according to the obstacle avoidance position information: Environmental information collection: Collect environmental information around the hyperbolic glass curtain wall, including other buildings, temporary obstacles, etc. Obstacle avoidance position generation: Generate obstacle avoidance position information and mark the area to be avoided. Path update: According to the obstacle avoidance position information, update the flight trajectory of the drone in real time to ensure that the drone can safely avoid obstacles during the inspection process.

[0157] Step S106. Control the drone to automatically inspect the hyperbolic glass curtain wall according to the flight trajectory of the drone: Flight control: The controller sends instructions to the drone according to the generated flight trajectory to control it to fly along the predetermined path. Data collection and transmission: During the flight, the drone continuously collects ultrasonic, infrared thermal imaging and optical imaging data, and transmits them to the ground station or airborne controller in real time through the wireless communication module. Inspection report generation: After the data is processed, a detailed inspection report is generated, including the defect type, location and severity score.

[0158] The provided method has the following beneficial effects: Improved detection accuracy: The accuracy and comprehensiveness of defect detection are improved through comprehensive analysis of multimodal data (ultrasound, infrared thermal imaging, optical imaging).

[0159] Enhanced safety: By generating obstacle avoidance position information and updating the flight trajectory in real time, the risk of UAV collision in complex environments is effectively avoided.

[0160] Improve work efficiency: Automated flight trajectory planning and data processing reduce manual intervention and improve inspection efficiency.

[0161] Optimized path planning: The flight trajectory generated based on the three-dimensional model and curvature parameters ensures that the drone can fully cover all areas and improve the coverage of the inspection.

[0162] Real-time monitoring and feedback: Real-time data collection and transmission enable problems during the inspection process to be discovered and handled in a timely manner, enhancing the system's response speed and flexibility.

[0163] Adaptive adjustment: Dynamically adjust the flight trajectory according to actual environmental information, improving the adaptability and robustness of the system.

[0164] Reduce resource waste: Through reasonable path planning and efficient inspection methods, unnecessary flight time and energy consumption are reduced, extending the service life of the drone.

[0165] In summary, the drone-based automatic inspection method for high-rise hyperbolic glass curtain walls not only solves many problems of traditional manual inspections, but also improves the efficiency and accuracy of inspections through advanced technologies and algorithms, providing strong support for the safe maintenance of high-rise buildings.

[0166] In some embodiments, the data acquisition module includes: a polarization filter, which is arranged at the front end of the image acquisition module to suppress the surface reflection interference of the hyperbolic glass curtain wall.

[0167] In some embodiments, the controller generates an ultrasonic signal attenuation coefficient based on the reflected wave signal intensity and the ultrasonic signal intensity; the controller calculates the area ratio of the temperature abnormality region based on the characteristics of the temperature abnormality region and the area corresponding to the hyperbolic glass curtain wall; the controller determines the crack morphology characteristics based on the optical image texture; the controller outputs the inspection result based on the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

[0168] Exemplarily, the controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

[0169] In some embodiments, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall and the real-time pose vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; the controller generates the flight trajectory of the drone based on a genetic algorithm according to the fitness function.

[0170] Exemplarily, the expression of the fitness function includes:

[0171] ;

[0172] in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information. The second-order difference term is used to measure the acceleration change of the trajectory. is the calculation formula of the second norm.

[0173] It should be noted that, in some embodiments, the expression of the curvature smoothing weight coefficient includes:

[0174] ;

[0175] in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

[0176] In some embodiments, it also includes: a meteorological sensing unit, which monitors the wind speed information and precipitation information corresponding to the drone in real time; an autonomous obstacle avoidance unit, which detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall through the fusion of millimeter-wave radar and binocular vision, and controls the drone to perform autonomous obstacle avoidance when the distance between the convex structure and the temporary obstacle is less than a preset distance; a multi-link redundant communication unit, which is mounted on the drone and uses LoRa and 4G dual channels to transmit data in parallel with the controller.

[0177] In some embodiments, the controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall, the curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results, and the controller outputs an inspection cycle adaptive adjustment suggestion based on the defect expansion rate and environmental factor correlation.

[0178] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the above-described automatic inspection method for high-rise hyperbolic glass curtain walls based on drones and the specific working process of each step can refer to the corresponding process in the embodiments of the automatic inspection method for high-rise hyperbolic glass curtain walls based on drones described in the above-mentioned embodiments, and will not be repeated here.

[0179] The embodiment of the present application provides an automatic inspection device for high-rise hyperbolic glass curtain walls based on drones. The automatic inspection device for high-rise hyperbolic glass curtain walls based on drones is used to execute the steps of the automatic inspection method for high-rise hyperbolic glass curtain walls based on drones shown in the above embodiments. The automatic inspection device for high-rise hyperbolic glass curtain walls based on drones can be a single server or a server cluster, or the automatic inspection device for high-rise hyperbolic glass curtain walls based on drones can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device, a robot, etc.

[0180] The high-rise hyperbolic glass curtain wall automatic inspection device based on drones includes:

[0181] The time-frequency analysis module is used to perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength;

[0182] The abnormal acquisition module is used to calculate the temperature gradient of the temperature distribution image of the structural adhesive surface captured by the infrared thermal imager to obtain the characteristics of the temperature abnormal area;

[0183] An image acquisition module, used for acquiring optical image texture according to the surface optical image acquired by the image acquisition module;

[0184] The trajectory generation module is used to generate the UAV flight trajectory according to the three-dimensional model of the hyperbolic glass curtain wall and the curvature parameters;

[0185] A trajectory updating module, used to generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall, and update the flight trajectory of the UAV according to the obstacle avoidance position information;

[0186] The inspection control module is used to control the drone to automatically inspect the hyperbolic glass curtain wall according to the flight trajectory of the drone.

[0187] In some embodiments, the data acquisition module includes: a polarization filter, which is arranged at the front end of the image acquisition module to suppress the surface reflection interference of the hyperbolic glass curtain wall.

[0188] In some embodiments, the controller generates an ultrasonic signal attenuation coefficient based on the reflected wave signal intensity and the ultrasonic signal intensity; the controller calculates the area ratio of the temperature abnormality region based on the characteristics of the temperature abnormality region and the area corresponding to the hyperbolic glass curtain wall; the controller determines the crack morphology characteristics based on the optical image texture; the controller outputs the inspection result based on the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

[0189] Exemplarily, the controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

[0190] In some embodiments, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall and the real-time pose vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; the controller generates the flight trajectory of the drone based on a genetic algorithm according to the fitness function.

[0191] Exemplarily, the expression of the fitness function includes:

[0192] ;

[0193] in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information, and the second-order difference term is used to measure the acceleration change of the trajectory.

[0194] It should be noted that, in some embodiments, the expression of the curvature smoothing weight coefficient includes:

[0195] ;

[0196] in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

[0197] In some embodiments, it also includes: a meteorological sensing unit, which monitors the wind speed information and precipitation information corresponding to the drone in real time; an autonomous obstacle avoidance unit, which detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall through the fusion of millimeter-wave radar and binocular vision, and controls the drone to perform autonomous obstacle avoidance when the distance between the convex structure and the temporary obstacle is less than a preset distance; a multi-link redundant communication unit, which is mounted on the drone and uses LoRa and 4G dual channels to transmit data in parallel with the controller.

[0198] In some embodiments, the controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall, the curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results, and the controller outputs an inspection cycle adaptive adjustment suggestion based on the defect expansion rate and environmental factor correlation.

[0199] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described high-rise hyperbolic glass curtain wall automatic inspection device based on drone and each module can refer to the corresponding process in the embodiment of the high-rise hyperbolic glass curtain wall automatic inspection method based on drone described in the above-mentioned embodiments, and will not be repeated here.

[0200] The above-mentioned automatic inspection method of high-rise hyperbolic glass curtain walls based on drones can be implemented in the form of a computer program, which can be run on the provided device.

[0201] See also Figure 4 , Figure 4 : is a schematic block diagram of the structure of a controller provided in an embodiment of the present application. The controller includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0202] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the automatic inspection methods for high-rise hyperbolic glass curtain walls based on drones.

[0203] The processor is used to provide computing and control capabilities and support the operation of the entire controller.

[0204] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the automatic inspection methods for high-rise hyperbolic glass curtain walls based on drones.

[0205] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 4 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal to which the scheme of the present application is applied. The specific controller may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0206] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0207] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0208] Perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength;

[0209] The temperature gradient of the surface temperature distribution image of the structural adhesive captured by the infrared thermal imager is calculated to obtain the characteristics of the temperature abnormality area;

[0210] Acquire optical image texture according to the surface optical image acquired by the image acquisition module;

[0211] Generate the UAV flight trajectory based on the 3D model and curvature parameters of the hyperbolic glass curtain wall;

[0212] Generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall setting, and update the flight trajectory of the drone according to the obstacle avoidance position information;

[0213] The drone is controlled according to the flight trajectory of the drone to automatically inspect the hyperbolic glass curtain wall.

[0214] In some embodiments, before the visible light image and thermal imaging image are input into a damage feature recognition model based on a convolutional neural network, the method further includes: preprocessing the sensor acquisition information, visible light image and thermal imaging image; the preprocessing includes at least filtering, denoising, enhancement, and cropping preprocessing; marking damage information in the preprocessed sensor acquisition information, visible light image and thermal imaging image; the damage information includes at least damage type and timing abnormality.

[0215] In some embodiments, the data acquisition module includes: a polarization filter, which is arranged at the front end of the image acquisition module to suppress the surface reflection interference of the hyperbolic glass curtain wall.

[0216] In some embodiments, the controller generates an ultrasonic signal attenuation coefficient based on the reflected wave signal intensity and the ultrasonic signal intensity; the controller calculates the area ratio of the temperature abnormality region based on the characteristics of the temperature abnormality region and the area corresponding to the hyperbolic glass curtain wall; the controller determines the crack morphology characteristics based on the optical image texture; the controller outputs the inspection result based on the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

[0217] Exemplarily, the controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

[0218] In some embodiments, the controller generates a fitness function based on the curvature change rate of the hyperbolic glass curtain wall and the real-time pose vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; the controller generates the flight trajectory of the drone based on a genetic algorithm according to the fitness function.

[0219] Exemplarily, the expression of the fitness function includes:

[0220] ;

[0221] in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information, and the second-order difference term is used to measure the acceleration change of the trajectory.

[0222] It should be noted that, in some embodiments, the expression of the curvature smoothing weight coefficient includes:

[0223] ;

[0224] in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

[0225] In some embodiments, it also includes: a meteorological sensing unit, which monitors the wind speed information and precipitation information corresponding to the drone in real time; an autonomous obstacle avoidance unit, which detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall through the fusion of millimeter-wave radar and binocular vision, and controls the drone to perform autonomous obstacle avoidance when the distance between the convex structure and the temporary obstacle is less than a preset distance; a multi-link redundant communication unit, which is mounted on the drone and uses LoRa and 4G dual channels to transmit data in parallel with the controller.

[0226] In some embodiments, the controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall, the curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results, and the controller outputs an inspection cycle adaptive adjustment suggestion based on the defect expansion rate and environmental factor correlation.

[0227] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working processes of the controller and each module described above can refer to the corresponding processes in the method embodiments described in the above embodiments, and will not be repeated here.

[0228] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the steps of the automatic inspection method of high-rise hyperbolic glass curtain walls based on drones as provided in any embodiment of the present application.

[0229] The computer-readable storage medium may be an internal storage unit of the controller described in the foregoing embodiment, such as a hard disk or memory of the controller. The computer-readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the controller.

[0230] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working processes of the storage medium and each module described above can refer to the corresponding processes in the method embodiments described in the above embodiments, and will not be repeated here.

[0231] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An automatic inspection system for high-rise hyperbolic glass curtain walls based on drones, characterized in that: include: Drones; A data acquisition module, the data acquisition module is carried on the UAV, the data acquisition module includes an ultrasonic sensor array, an infrared thermal imager and an image acquisition module, wherein the ultrasonic sensor array is used to transmit high-frequency ultrasonic signals to the hyperbolic glass curtain wall to be inspected and receive reflected waves, the infrared thermal imager is used to capture the surface temperature distribution image of the structural adhesive of the hyperbolic glass curtain wall, and the image acquisition module is used to collect the surface optical image of the hyperbolic glass curtain wall; A controller is provided, wherein the controller is used to perform time-frequency domain analysis on the reflected wave to obtain the reflected wave signal intensity; the controller performs temperature gradient calculation on the surface temperature distribution image of the structural adhesive to obtain the temperature abnormality area characteristics; the controller obtains the optical image texture according to the surface optical image; the controller outputs the inspection result according to the reflected wave signal intensity, the temperature abnormality area characteristics and the optical image texture; the controller generates a UAV flight trajectory according to the three-dimensional model and curvature parameters of the hyperbolic glass curtain wall, generates obstacle avoidance position information according to the environmental information of the hyperbolic glass curtain wall setting, and updates the UAV flight trajectory according to the obstacle avoidance position information; the controller controls the UAV to automatically inspect the hyperbolic glass curtain wall according to the UAV flight trajectory.

2. The system according to claim 1, characterized in that The data acquisition module comprises: A polarizing filter is disposed at the front end of the image acquisition module and is used to suppress the surface reflection interference of the hyperbolic glass curtain wall.

3. The system according to claim 1, characterized in that The controller generates an ultrasonic signal attenuation coefficient according to the reflected wave signal strength and the ultrasonic signal strength; The controller calculates the area ratio of the temperature abnormality area according to the characteristics of the temperature abnormality area and the area corresponding to the hyperbolic glass curtain wall; The controller determines crack morphological characteristics according to the optical image texture; The controller outputs the inspection result according to the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region and the crack morphology characteristics; the inspection result includes the defect type, defect location and defect severity score.

4. The system according to claim 3, characterized in that The controller inputs the ultrasonic signal attenuation coefficient, the area ratio of the temperature abnormality region, and the crack morphology curvature corresponding to the crack morphology characteristics into a deep learning model based on the attention mechanism, and the deep learning model outputs the inspection result.

5. The system according to claim 1, characterized in that The controller generates a fitness function according to the curvature change rate of the hyperbolic glass curtain wall and the real-time posture vector corresponding to the drone, the estimated total inspection time, and the battery life threshold; The controller generates the flight trajectory of the UAV based on the fitness function and a genetic algorithm.

6. The system according to claim 5, characterized in that The expression of the fitness function includes: ； in, is the fitness function, is the curvature smoothing weight coefficient, which is used to adjust the importance of the curvature change rate in the fitness function. is the total number of flight segments corresponding to the UAV flight trajectory, For the The rate of change of the curtain wall curvature of the flight segment indicates the degree of change of the curtain wall curvature of a certain section of the UAV's flight path, which is used to measure the curvature change of the path. is the estimated total inspection duration, is the battery life threshold, indicating the maximum allowed time for a single flight of the drone, is the time efficiency weight coefficient, which adjusts the importance of inspection time in the fitness function. is the coefficient of the second-order difference penalty term of the trajectory, which is used to control the smoothness of the trajectory. , and They are , and The drone pose vector at the moment includes position and attitude information, and the second-order difference term is used to measure the acceleration change of the trajectory.

7. The system according to claim 6, characterized in that The expression of the curvature smoothing weight coefficient includes: ； in, is the curvature smoothing weight coefficient, is the average curvature change gradient, which represents the average value of the absolute value of the curvature change rate of all segments, reflecting the curvature of the overall path. is the curvature change rate threshold, which is used to trigger the critical value of weight adjustment. When the average curvature exceeds hour, Increase.

8. The system according to claim 1, characterized in that Also includes: A meteorological sensing unit monitors the wind speed information and precipitation information corresponding to the UAV in real time; An autonomous obstacle avoidance unit detects the convex structure and temporary obstacles of the hyperbolic glass curtain wall by integrating millimeter-wave radar and binocular vision, and controls the drone to autonomously avoid obstacles when the distance between the convex structure and the temporary obstacle is less than a preset distance; The multi-link redundant communication unit is mounted on the UAV and transmits data in parallel with the controller using LoRa and 4G dual channels.

9. The system according to claim 1, characterized in that The controller builds a curtain wall performance degradation prediction model based on historical inspection data corresponding to the hyperbolic glass curtain wall. The curtain wall performance degradation prediction model analyzes the defect expansion rate and environmental factor correlation corresponding to the hyperbolic glass curtain wall according to the inspection results. The controller outputs an inspection cycle adaptive adjustment suggestion according to the defect expansion rate and environmental factor correlation.

10. An automatic inspection method for high-rise hyperbolic glass curtain walls based on drones, characterized in that: A controller applied to the system according to any one of claims 1 to 9, wherein the method comprises: Perform time-frequency domain analysis on the reflected waves received by the ultrasonic sensor array to obtain the reflected wave signal strength; The temperature gradient of the surface temperature distribution image of the structural adhesive captured by the infrared thermal imager is calculated to obtain the characteristics of the temperature abnormality area; Acquire optical image texture according to the surface optical image acquired by the image acquisition module; Generate the UAV flight trajectory based on the 3D model and curvature parameters of the hyperbolic glass curtain wall; Generate obstacle avoidance position information according to the environment information of the hyperbolic glass curtain wall setting, and update the flight trajectory of the drone according to the obstacle avoidance position information; The drone is controlled according to the flight trajectory of the drone to automatically inspect the hyperbolic glass curtain wall.

Images