Method, device and system for predicting damage of hyperbolic glass curtain wall

Abstract

The present application provides a method, device, and system for predicting damage to a hyperbolic glass curtain wall. The method includes obtaining sensor-collected information of the hyperbolic glass curtain wall; controlling a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager; the visible light image and the thermal imaging image are input into a damage feature recognition model based on a convolutional neural network, and image feature information is output; the sensor-collected information is input into a time-series-based physical parameter analysis model, and parameter feature information is output; the image feature information is fused with the parameter feature information to obtain a damage feature recognition result; and a health status prediction model is constructed based on the damage feature recognition, so that the real-time sensor-collected information, real-time visible light image, and real-time thermal imaging image corresponding to the hyperbolic glass curtain wall are input into the health status prediction model, and a damage prediction result corresponding to the hyperbolic glass curtain wall is output.

Description

Technical Field

[0001] The present application relates to the field of defect detection technology, and in particular to a method, device and system for predicting damage of a hyperbolic glass curtain wall. Background Art

[0002] With the development of modern architectural design, hyperbolic glass curtain walls, as a unique building facade material, are widely used in large buildings due to their aesthetics and unique shape. The curved shape of the hyperbolic glass curtain wall increases the complexity of its structure and places higher demands on damage detection. Traditional glass curtain wall inspection methods, such as visual inspection, vibration detection, thermal imaging, and ultrasonic testing, are unable to adapt to the special geometric form of hyperbolic glass curtain walls, resulting in insufficient detection accuracy and positioning accuracy. It is impossible to obtain real-time and comprehensive information on the status of the curtain wall, making it difficult to detect subtle damage in the early stages and difficult to accurately predict and analyze the potential damage to the curtain wall. Existing inspection methods have at least the following problems:

[0003] Low detection accuracy: Hyperbolic curtain walls have complex geometric shapes. Traditional methods have low detection accuracy for damage on complex hyperbolic surfaces, making it difficult to detect subtle damage in the early stages.

[0004] Difficulty in achieving real-time monitoring and trend analysis: Traditional detection methods cannot obtain real-time and continuous status information of hyperbolic glass curtain walls. This makes it difficult to scientifically analyze damage trends, predict potential safety risks in advance, and provide a strong basis for maintenance decisions.

[0005] Lack of accurate lifespan assessment: Existing damage prediction methods for hyperbolic glass curtain walls are simply based on the design service life or limited experience. They do not fully consider the impact of various complex factors during the actual use of the curtain wall, making it difficult to accurately assess the remaining service life of the curtain wall, which is not conducive to formulating reasonable curtain wall maintenance plans and replacement plans.

[0006] Therefore, a method is urgently needed to solve at least one of the above problems. Summary of the Invention

[0007] This application provides a method, device, and system for predicting damage to hyperbolic glass curtain walls. These methods aim to address the challenges of traditional design methods, which often rely on experienced engineers manually adjusting parameters. This is not only time-consuming and labor-intensive, but also makes it difficult to guarantee the optimality of the final design. In situations where multiple factors must be considered, achieving an aesthetically pleasing, cost-effective solution while meeting functional requirements becomes a pressing issue.

[0008] In a first aspect, the present application provides a method for predicting damage of a hyperbolic glass curtain wall, comprising:

[0009] Acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information, and displacement sensor information;

[0010] Controlling a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager;

[0011] Inputting the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network, and outputting image feature information;

[0012] Inputting the sensor collected information into a time-series-based physical parameter analysis model to output parameter characteristic information;

[0013] Fusing the image feature information with the parameter feature information to obtain a damage feature recognition result;

[0014] A health status prediction model is constructed based on the damage feature identification, so that real-time sensor information, real-time visible light images, and real-time thermal imaging images corresponding to the hyperbolic glass curtain wall are input into the health status prediction model, and the health status prediction model outputs damage prediction results corresponding to the hyperbolic glass curtain wall in real time.

[0015] In some embodiments, before inputting the visible light image and thermal imaging image into a damage feature recognition model based on a convolutional neural network, it also 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 anomalies.

[0016] In some embodiments, the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs a crack index and a deformation index corresponding to the hyperbolic glass curtain wall based on the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs a temperature influence factor and a stress distribution factor based on the real-time sensor collected information; and the damage prediction result is generated based on the crack index, deformation index, temperature influence factor, and stress distribution factor.

[0017] Exemplarily, generating the damage prediction result according to the crack index, deformation index, temperature influence factor, and stress distribution factor includes: calculating a health score index according to the crack index, deformation index, temperature influence factor, and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes:

[0018] ;in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score.

[0019] It should be noted that, in some embodiments, the expression of the dynamic weight coefficient includes:

[0020] ;

[0021] in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of the damage type.

[0022] It should be noted that, in some embodiments, if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.18.

[0023] In a second aspect, the present application provides a device for predicting damage to a hyperbolic glass curtain wall, comprising:

[0024] An information acquisition module is used to acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information and displacement sensor information;

[0025] An image acquisition module, configured to control a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager;

[0026] An image output module, configured to input the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network and output image feature information;

[0027] A feature output module, configured to input the sensor collected information into a time-series-based physical parameter analysis model and output parameter feature information;

[0028] A feature fusion module, configured to fuse the image feature information with the parameter feature information to obtain a damage feature recognition result;

[0029] A prediction completion module is used to construct a health status prediction model based on the damage feature identification, so as to input real-time sensor acquisition information, real-time visible light images, and real-time thermal imaging images corresponding to the hyperbolic glass curtain wall into the health status prediction model, and the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time.

[0030] In a third aspect, the present application provides a hyperbolic glass curtain wall damage prediction system, comprising: a plurality of sensors, the sensors being arranged at target points of the hyperbolic glass curtain wall, the sensors comprising at least a strain sensor, a temperature sensor, and a displacement sensor; a drone, the drone being equipped with a visible light device and an infrared thermal imager; a controller, the controller comprising a memory and a processor; the memory being used to store a computer program; the processor being used to execute the computer program and implement a method as provided in any embodiment of the present application when executing the computer program.

[0031] In some embodiments, the target points include glass panel edges, connection nodes, and stress concentration areas corresponding to the hyperbolic glass curtain wall.

[0032] In some embodiments, the arrangement density of the sensors in the hyperbolic glass curtain wall is dynamically adjusted according to the curvature radius of the hyperbolic glass curtain wall. In the area where the curvature radius is less than 3m, the arrangement density is increased by a preset density coefficient compared to the area where the curvature radius is greater than or equal to 3m. The preset density coefficient corresponds to a value range of 30% to 50%.

[0033] 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 the method provided in any embodiment of the present application.

[0034] The present invention provides a method, device, and system for predicting damage to a hyperbolic glass curtain wall. The method includes the following technical steps:

[0035] Sensor information collection: Strain sensor: used to monitor the stress distribution of the hyperbolic glass curtain wall. Temperature sensor: used to monitor temperature changes on the curtain wall surface and the surrounding environment. Displacement sensor: used to monitor the deformation of the curtain wall.

[0036] Drone Image Capture: Visible light equipment: Mounted on a drone, it is used to capture high-resolution visible light images of the hyperbolic glass curtain wall. Infrared thermal imager: Mounted on a drone, it is used to capture thermal imaging images of the curtain wall to detect potential areas of temperature anomalies.

[0037] Damage feature recognition model based on a convolutional neural network (CNN): Input: Visible light images and thermal images. Processing: Extracts feature information from the images through convolutional, pooling, and fully connected layers. Output: Image feature information, including but not limited to damage features such as cracks, scratches, and deformation.

[0038] Time-series-based physical parameter analysis model: Input: Strain sensor information, temperature sensor information, and displacement sensor information. Processing: Use time series analysis methods (such as ARIMA and LSTM) to model the sensor data and extract key physical parameter characteristics. Output: Parameter characteristic information, including stress distribution, temperature change trends, displacement change trends, etc.

[0039] Feature Fusion and Damage Identification: Fusion Method: Image feature information and parameter feature information are integrated. Weighted fusion, principal component analysis (PCA), or deep learning methods (such as multimodal fusion networks) can be used. Output: Damage feature identification results that comprehensively reflect the health status of the curtain wall.

[0040] Health Status Prediction Model: Input: Real-time sensor data, real-time visible light images, and real-time thermal images. Processing: This information is fed into a pre-trained health status prediction model, which can be based on machine learning or deep learning methods such as support vector machines (SVMs), random forests, or convolutional neural networks (CNNs). Output: Real-time damage prediction results for the hyperbolic glass curtain wall, including damage type, location, and severity.

[0041] The specific implementation of the above technical features may be:

[0042] Sensor Deployment: Install strain sensors, temperature sensors, and displacement sensors on the hyperbolic glass curtain wall and ensure their proper function. The sensor data collection frequency and accuracy should be set according to actual needs. Select an appropriate drone model equipped with a visible light device and an infrared thermal imager. Design a flight path to ensure comprehensive coverage of all areas of the hyperbolic glass curtain wall. Regularly conduct drone inspections to collect visible light and thermal images. Collect a large amount of hyperbolic glass curtain wall damage sample data, including visible light images, thermal images, and sensor data. Use a convolutional neural network (CNN) to train the image data and extract damage features. Use time series analysis to train the sensor data and extract physical parameter features. Fusion of image and physical parameter features is used to train a damage feature recognition model. Collect historical data on the hyperbolic glass curtain wall, including sensor data, image data, and known damage conditions. Select an appropriate machine learning or deep learning algorithm to build a health status prediction model. Train and validate the model to ensure high prediction accuracy. Integrate the sensor data acquisition system, drone image acquisition system, damage feature recognition model, and health status prediction model. Deployed on the cloud or local server, it enables real-time data transmission and processing. It also provides a user interface to display real-time damage prediction results and historical data analysis reports.

[0043] The provided method has at least the following beneficial effects:

[0044] Improving damage prediction accuracy: By combining image data and sensor data, the damage characteristics of hyperbolic glass curtain walls can be more comprehensively captured, improving prediction accuracy.

[0045] Reduce manual intervention: Automated data collection and processing processes reduce dependence on experienced engineers and reduce labor costs.

[0046] Real-time monitoring and early warning: It can monitor the health status of the curtain wall in real time, promptly identify potential damage risks, take measures for maintenance in advance, and avoid major accidents.

[0047] Optimize design solutions: By analyzing large amounts of data, we can provide references for the design of hyperbolic glass curtain walls, help optimize design solutions, and improve the overall performance of buildings.

[0048] Reduce costs: By detecting and repairing damage early, the service life of the curtain wall can be effectively extended and long-term maintenance costs can be reduced.

[0049] In summary, the present application provides a method for predicting damage to hyperbolic glass curtain walls. By comprehensively utilizing sensor data and image processing technology, this method achieves efficient and accurate prediction of curtain wall damage, providing strong support for building safety and maintenance.

[0050] 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

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. 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 any creative work.

[0052] Figure 1 This is a schematic flow chart of the steps of a method for predicting damage of a hyperbolic glass curtain wall provided in one embodiment of the present application;

[0053] Figure 2 This is a schematic block diagram of the structure of a device for predicting damage to a hyperbolic glass curtain wall provided in one embodiment of the present application;

[0054] Figure 3 This is a schematic block diagram of the structure of a controller provided in one embodiment of the present application.

[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. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0058] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish between identical or similar items having substantially the same functions and effects. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or order of execution, and that terms such as "first" and "second" do not necessarily define differences.

[0059] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0060] It will also be understood that the term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0061] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0062] With the development of modern architectural design, hyperbolic glass curtain walls, as a unique building facade material, are widely used in large buildings due to their aesthetics and unique shape. The curved shape of the hyperbolic glass curtain wall increases the complexity of its structure and places higher demands on damage detection. Traditional glass curtain wall inspection methods, such as visual inspection, vibration detection, thermal imaging, and ultrasonic testing, are unable to adapt to the special geometric form of hyperbolic glass curtain walls, resulting in insufficient detection accuracy and positioning accuracy. It is impossible to obtain real-time and comprehensive information on the status of the curtain wall, making it difficult to detect subtle damage in the early stages and difficult to accurately predict and analyze the potential damage to the curtain wall. Existing inspection methods have at least the following problems:

[0063] Low detection accuracy: Hyperbolic curtain walls have complex geometric shapes. Traditional methods have low detection accuracy for damage on complex hyperbolic surfaces, making it difficult to detect subtle damage in the early stages.

[0064] Difficulty in achieving real-time monitoring and trend analysis: Traditional detection methods cannot obtain real-time and continuous status information of hyperbolic glass curtain walls. This makes it difficult to scientifically analyze damage trends, predict potential safety risks in advance, and provide a strong basis for maintenance decisions.

[0065] Lack of accurate lifespan assessment: Existing damage prediction methods for hyperbolic glass curtain walls are simply based on the design service life or limited experience. They do not fully consider the impact of various complex factors during the actual use of the curtain wall, making it difficult to accurately assess the remaining service life of the curtain wall, which is not conducive to formulating reasonable curtain wall maintenance plans and replacement plans.

[0066] Therefore, a method is urgently needed to solve at least one of the above problems.

[0067] To resolve the above issues, please refer to Figure 1 ,like Figure 1As shown, the provided method for predicting damage of a hyperbolic glass curtain wall includes steps S101 to S106. The details are as follows:

[0068] Step S101: Acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information, and displacement sensor information.

[0069] Specifically, the sensors installed on the hyperbolic glass curtain wall include but are not limited to strain sensors, temperature sensors and displacement sensors. Strain sensors are used to monitor stress changes in the curtain wall structure and reflect material deformation. Temperature sensing: Measuring the ambient temperature and the temperature distribution on the curtain wall surface helps to identify potential risks caused by temperature changes. Displacement sensors monitor the relative position changes between curtain wall components to help detect structural movement or deformation problems. The data collection frequency is set according to actual needs, usually every minute or more frequently to ensure that rapidly changing status information can be captured. Sensor data is sent to the central processing unit through wireless communication modules (such as LoRa, NB-IoT, etc.).

[0070] For example, various sensors are strategically placed on the hyperbolic glass curtain wall to ensure coverage of all key areas. Sensors are regularly calibrated to ensure data accuracy. An IoT platform is used to manage the sensor network, collecting and storing data from each node.

[0071] This step enables comprehensive monitoring of the curtain wall's condition, particularly effective for areas that are difficult to directly observe. It provides rich physical parameter data to support subsequent analysis, improving the reliability and accuracy of damage detection.

[0072] Step S102: Control a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager.

[0073] Choose a commercial drone with autonomous flight capabilities and equipped with a high-definition camera and thermal imaging camera. Create a detailed flight path in advance to ensure the drone can follow the planned trajectory around the building's exterior, capturing comprehensive images. Ensure the captured images are high enough resolution for easy post-processing. Also, adjust the thermal imaging camera parameters to clearly display temperature differences, making it easier to distinguish between normal and abnormal areas.

[0074] For example, you can design the appropriate flight altitude and angle based on the size and shape of the building. You can also set up a scheduled drone mission mode, such as automatically taking off for inspections at a specific time each day. You can also remotely control the drone through ground station software to complete designated actions and download and save the captured data.

[0075] This technology allows for the acquisition of high-quality visual data without the need for manual labor at height, reducing operational complexity and safety risks. Combining image data from multiple perspectives enhances the overall perception of complex curved structures. Infrared thermal imaging technology can effectively reveal hidden internal issues, providing additional information that is difficult to access using traditional methods.

[0076] Step S103: Input the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network, and output image feature information.

[0077] Specifically, a CNN architecture, such as classic models like VGGNet and ResNet, is used, optimized using a large number of training samples. The model is trained using a labeled dataset containing various known damage types, enabling it to learn to identify typical defects such as cracks and fissures from different image types. The model extracts multi-level features from the input image to form a high-level abstract representation.

[0078] Raw drone-collected images are fed into a pre-trained neural network in batches. The model automatically generates one or more feature maps that highlight suspected locations of damage. A threshold is set to filter out noise interference, retaining the truly meaningful signals as the basis for further analysis.

[0079] This significantly improves the ability to quickly locate problems within massive image volumes, saving labor costs. Compared to visual inspection, it is more objective and impartial, less susceptible to subjective factors. Through machine learning, it continuously iterates and improves algorithm performance, continuously enhancing accuracy and robustness.

[0080] Step S104: Input the sensor collected information into a time series-based physical parameter analysis model, and output parameter characteristic information.

[0081] Specifically, Long Short-Term Memory (LSTM) networks or other Recurrent Neural Network (RNN) variants suitable for time series data processing are applied. Data preprocessing: Normalization and denoising are performed on raw sensor readings to ensure they meet the model input format requirements. Feature engineering: New feature variables, such as rate of change and cumulative effect, are constructed to enhance the model's learning capabilities.

[0082] For example, by feeding organized historical records into an LSTM model, it can learn trends that evolve over time. During training, be mindful of overfitting and adjust hyperparameters appropriately to avoid overly complex models. Regularly update the training set and incorporate the latest observations to maintain model freshness.

[0083] It can capture subtle trends and provide early warning of potential problems. This provides a strong quantitative basis for subsequent phases and enhances the scientific nature of the overall system. Predictions based on historical data can help guide future maintenance work arrangements.

[0084] Step S105: Fusing the image feature information with the parameter feature information to obtain a damage feature recognition result.

[0085] Specifically, fusion strategies can employ a variety of methods, including simple splicing or mapping the two components into the same space followed by weighted summation. Weight distribution dynamically adjusts the proportional coefficient based on the contribution of each component in different scenarios. A comprehensive assessment, combining visual cues and physical indicators, determines the final conclusion.

[0086] Design a rational evaluation system to quantify the importance of each indicator. Develop specialized software tools to automate the integration process and reduce human intervention. Verify and test the integrated results to ensure their effectiveness.

[0087] This leverages the complementary strengths of different data types, enhancing the practical value of the overall solution. It makes decision-making more comprehensive and reliable, reducing the probability of misjudgment. It also promotes the integration of interdisciplinary knowledge and advances technological progress in related fields.

[0088] Step S106. Construct a health status prediction model based on the damage feature identification, so that real-time sensor information, real-time visible light images, and real-time thermal imaging images corresponding to the hyperbolic glass curtain wall are input into the health status prediction model, and the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time.

[0089] Specifically, the model framework should use an ensemble learning method such as random forest, gradient boosting machine (GBM), or deep belief network (DBN). Input and output definitions should clarify which are the independent variables and which are the target variables, and determine the logical relationship between them. Online learning mechanisms should allow the model to adapt to new situations over time.

[0090] Build the initial version of the prediction system and deploy it online. Configure a feedback loop to allow users to submit corrections to continuously optimize the algorithm. Regularly release updates to fix known bugs and add new features.

[0091] This system creates a closed-loop control system, providing a one-stop service from data collection to result display and action recommendations. It provides managers with an intuitive and easy-to-understand interface, streamlining daily management workflows. This promotes efficient resource utilization, extends facility lifespan, and reduces long-term operating costs.

[0092] The present invention provides a method, device, and system for predicting damage to a hyperbolic glass curtain wall. The method includes the following technical steps:

[0093] Sensor information collection: Strain sensor: used to monitor the stress distribution of the hyperbolic glass curtain wall. Temperature sensor: used to monitor temperature changes on the curtain wall surface and the surrounding environment. Displacement sensor: used to monitor the deformation of the curtain wall.

[0094] Drone Image Capture: Visible light equipment: Mounted on a drone, it is used to capture high-resolution visible light images of the hyperbolic glass curtain wall. Infrared thermal imager: Mounted on a drone, it is used to capture thermal imaging images of the curtain wall to detect potential areas of temperature anomalies.

[0095] Damage feature recognition model based on a convolutional neural network (CNN): Input: Visible light images and thermal images. Processing: Extracts feature information from the images through convolutional, pooling, and fully connected layers. Output: Image feature information, including but not limited to damage features such as cracks, scratches, and deformation.

[0096] Time-series-based physical parameter analysis model: Input: Strain sensor information, temperature sensor information, and displacement sensor information. Processing: Use time series analysis methods (such as ARIMA and LSTM) to model the sensor data and extract key physical parameter characteristics. Output: Parameter characteristic information, including stress distribution, temperature change trends, displacement change trends, etc.

[0097] Feature Fusion and Damage Identification: Fusion Method: Image feature information and parameter feature information are integrated. Weighted fusion, principal component analysis (PCA), or deep learning methods (such as multimodal fusion networks) can be used. Output: Damage feature identification results that comprehensively reflect the health status of the curtain wall.

[0098] Health Status Prediction Model: Input: Real-time sensor data, real-time visible light images, and real-time thermal images. Processing: This information is fed into a pre-trained health status prediction model, which can be based on machine learning or deep learning methods such as support vector machines (SVMs), random forests, or convolutional neural networks (CNNs). Output: Real-time damage prediction results for the hyperbolic glass curtain wall, including damage type, location, and severity.

[0099] The specific implementation of the above technical features may be:

[0100] Sensor Deployment: Install strain sensors, temperature sensors, and displacement sensors on the hyperbolic glass curtain wall and ensure their proper function. The sensor data collection frequency and accuracy should be set according to actual needs. Select an appropriate drone model equipped with a visible light device and an infrared thermal imager. Design a flight path to ensure comprehensive coverage of all areas of the hyperbolic glass curtain wall. Regularly conduct drone inspections to collect visible light and thermal images. Collect a large amount of hyperbolic glass curtain wall damage sample data, including visible light images, thermal images, and sensor data. Use a convolutional neural network (CNN) to train the image data and extract damage features. Use time series analysis to train the sensor data and extract physical parameter features. Fusion of image and physical parameter features is used to train a damage feature recognition model. Collect historical data on the hyperbolic glass curtain wall, including sensor data, image data, and known damage conditions. Select an appropriate machine learning or deep learning algorithm to build a health status prediction model. Train and validate the model to ensure high prediction accuracy. Integrate the sensor data acquisition system, drone image acquisition system, damage feature recognition model, and health status prediction model. Deployed on the cloud or local server, it enables real-time data transmission and processing. It also provides a user interface to display real-time damage prediction results and historical data analysis reports.

[0101] The provided method has at least the following beneficial effects:

[0102] Improving damage prediction accuracy: By combining image data and sensor data, the damage characteristics of hyperbolic glass curtain walls can be more comprehensively captured, improving prediction accuracy.

[0103] Reduce manual intervention: Automated data collection and processing processes reduce dependence on experienced engineers and reduce labor costs.

[0104] Real-time monitoring and early warning: It can monitor the health status of the curtain wall in real time, promptly identify potential damage risks, take measures for maintenance in advance, and avoid major accidents.

[0105] Optimize design solutions: By analyzing large amounts of data, we can provide references for the design of hyperbolic glass curtain walls, help optimize design solutions, and improve the overall performance of buildings.

[0106] Reduce costs: By detecting and repairing damage early, the service life of the curtain wall can be effectively extended and long-term maintenance costs can be reduced.

[0107] In summary, the present application provides a method for predicting damage to hyperbolic glass curtain walls. By comprehensively utilizing sensor data and image processing technology, this method achieves efficient and accurate prediction of curtain wall damage, providing strong support for building safety and maintenance.

[0108] In some embodiments, before inputting the visible light image and thermal imaging image into a damage feature recognition model based on a convolutional neural network, it also 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 anomalies.

[0109] Preprocessing includes: Filtering: Using a low-pass filter to remove high-frequency noise and ensure smooth data. Denoising: Using methods such as median filtering and Gaussian filtering to remove random noise from the image. Enhancement: Improving image clarity through techniques such as contrast enhancement and brightness adjustment. Cropping: Crop the image as needed to remove irrelevant background and retain key areas.

[0110] Labeling damage information includes: Labeling tools: Use professional image annotation tools (such as Labelbox, VGG ImageAnnotator) for labeling.

[0111] The annotation contents include: Damage type: including cracks, deformation, corrosion, etc. Time series anomaly: record the changes of damage over time, such as the speed of crack expansion, changes in deformation degree, etc.

[0112] For example, normalize sensor data to ensure that data from different sensors is at the same scale. For visible light images, filter, denoise, enhance, and crop the images, then use annotation tools to mark the location and type of damage. For thermal images, similarly filter, denoise, enhance, and crop the images, and mark areas of temperature anomalies and their types.

[0113] Preprocessing significantly reduces noise interference and improves data reliability and consistency. High-quality data input helps improve convolutional neural network training, thereby enhancing damage identification accuracy. Detailed damage annotation provides the model with rich supervision information, helping it better learn and understand damage characteristics. This annotation information can be used for subsequent analysis and verification to ensure the reliability of the model output.

[0114] In some embodiments, the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs a crack index and a deformation index corresponding to the hyperbolic glass curtain wall based on the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs a temperature influence factor and a stress distribution factor based on the real-time sensor collected information; and the damage prediction result is generated based on the crack index, deformation index, temperature influence factor, and stress distribution factor.

[0115] Based on real-time visible light images and thermal imaging images, a convolutional neural network is used to extract crack features and calculate the crack index. Based on real-time visible light images and thermal imaging images, a convolutional neural network is used to extract deformation features and calculate the deformation index.

[0116] Based on real-time temperature sensor data, the influence of ambient temperature on the curtain wall is calculated. Based on real-time strain sensor data, the stress distribution of the curtain wall is calculated. A health score index is calculated based on the crack index, deformation index, temperature influence factor, and stress distribution factor. A comprehensive assessment combining multiple factors (cracks, deformation, temperature, and stress) improves the comprehensiveness and accuracy of damage prediction. Dynamic weighting coefficients are used to account for the temporal changes of different types of damage, enhancing the model's temporal adaptability. The introduction of an environmental and geometric coupling coefficient accounts for the impact of seasonal changes and hyperbolic geometry on curtain wall damage, making predictions more scientific and reasonable. The system can output a health score index in real time, enabling timely identification of potential problems and early warning, providing strong support for maintenance decisions.

[0117] Exemplarily, generating the damage prediction result according to the crack index, deformation index, temperature influence factor, and stress distribution factor includes: calculating a health score index according to the crack index, deformation index, temperature influence factor, and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes:

[0118] ;in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score.

[0119] By integrating multiple factors for comprehensive assessment, the damage prediction is more comprehensive and accurate. Dynamic weighting factors account for the temporal changes of different damage types, enhancing the model's temporal adaptability. The introduction of environmental and geometric coupling factors accounts for the impact of seasonal changes and hyperbolic geometry on curtain wall damage, making the prediction more scientific and reasonable. The system can output a health score index in real time, identifying potential problems and providing early warnings, providing strong support for maintenance decisions.

[0120] It should be noted that, in some embodiments, the expression of the dynamic weight coefficient includes:

[0121] ;

[0122] in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of the damage type.

[0123] Through the dynamic weight coefficient, the weight can be automatically adjusted according to the changes of different damage types over time, making the model more flexible and adaptive.

[0124] The damage sensitivity attenuation factor controls the timeliness of different damage types, allowing the model to more accurately reflect actual conditions. By setting the initial weight coefficient and attenuation factor, the weight balance between different damage types is ensured, improving the rationality of the overall assessment.

[0125] It should be noted that, in some embodiments, if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.18.

[0126] By setting specific parameters, we can more precisely control the weights and timeliness of different types of damage, improving the accuracy and robustness of the model. Setting parameter ranges allows for fine-tuning based on actual conditions, enhancing the model's flexibility and adaptability. Reasonable parameter settings ensure the model's stability and reliability over time and under different environmental conditions.

[0127] See also Figure 2 As shown, Figure 2 2 is a schematic diagram of the structure of a hyperbolic glass curtain wall damage prediction device 200 provided in an embodiment of the present application. This hyperbolic glass curtain wall damage prediction device 200 is used to execute the steps of the hyperbolic glass curtain wall damage prediction method described in each of the above embodiments. This hyperbolic glass curtain wall damage prediction device 200 can be a single server or a server cluster, or it can be a terminal, such as a handheld terminal, a laptop computer, a wearable device, or a robot.

[0128] like Figure 2 As shown, the hyperbolic glass curtain wall damage prediction device 200 includes:

[0129] The information acquisition module 201 is used to acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information and displacement sensor information;

[0130] An image acquisition module 202 is configured to control a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager;

[0131] An image output module 203 is configured to input the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network and output image feature information;

[0132] A feature output module 204 is configured to input the sensor collected information into a time series-based physical parameter analysis model and output parameter feature information;

[0133] A feature fusion module 205 is configured to fuse the image feature information with the parameter feature information to obtain a damage feature recognition result;

[0134] The prediction completion module 206 is used to build a health status prediction model based on the damage feature identification, so as to input the real-time sensor acquisition information, real-time visible light image and real-time thermal imaging image corresponding to the hyperbolic glass curtain wall into the health status prediction model, and the health status prediction model outputs the damage prediction result corresponding to the hyperbolic glass curtain wall in real time.

[0135] In some embodiments, before inputting the visible light image and thermal imaging image into a damage feature recognition model based on a convolutional neural network, it also 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 anomalies.

[0136] In some embodiments, the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs a crack index and a deformation index corresponding to the hyperbolic glass curtain wall based on the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs a temperature influence factor and a stress distribution factor based on the real-time sensor collected information; and the damage prediction result is generated based on the crack index, deformation index, temperature influence factor, and stress distribution factor.

[0137] Exemplarily, generating the damage prediction result according to the crack index, deformation index, temperature influence factor, and stress distribution factor includes: calculating a health score index according to the crack index, deformation index, temperature influence factor, and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes:

[0138] ;in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score.

[0139] It should be noted that, in some embodiments, the expression of the dynamic weight coefficient includes:

[0140] ;

[0141] in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of the damage type.

[0142] It should be noted that, in some embodiments, if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.18.

[0143] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the hyperbolic glass curtain wall damage prediction device and each module described above can refer to the corresponding processes in the embodiments of the hyperbolic glass curtain wall damage prediction method described in the above embodiments, and will not be repeated here.

[0144] The above-mentioned damage prediction method of the hyperbolic glass curtain wall can be realized in the form of a computer program. The computer program can be used in Figure 2 Run on the device shown.

[0145] The present application provides a hyperbolic glass curtain wall damage prediction system, comprising a plurality of sensors, the sensors being arranged at target points on the hyperbolic glass curtain wall, the sensors including at least a strain sensor, a temperature sensor, and a displacement sensor; an unmanned aerial vehicle (UAV), the UAV being equipped with a visible light device and an infrared thermal imager; a controller comprising a memory and a processor; the memory being used to store a computer program; and the processor being used to execute the computer program and, when executing the computer program, implement the hyperbolic glass curtain wall damage prediction method provided in any one of the embodiments of the present application.

[0146] Sensor types: strain sensors, temperature sensors, and displacement sensors. Layout: Sensors are installed at key points on the hyperbolic glass curtain wall to ensure coverage of all important areas. For example, sensors are placed at the four corners, center point, and joints that may be subject to greater stress. Function: Strain sensor: Monitors stress changes in the curtain wall structure and reflects material deformation. Temperature sensor: Measures ambient temperature and temperature distribution on the curtain wall surface, helping to identify potential risks caused by temperature changes. Displacement sensor: Monitors changes in the relative position of curtain wall components to help detect structural movement or deformation problems.

[0147] Drone Configuration: Equipped with visible light equipment (such as a high-definition camera) and an infrared thermal imager. Function: Visible light image acquisition: Captures high-resolution visible light images of hyperbolic glass curtain walls for visual inspection. Thermal imaging image acquisition: Uses an infrared thermal imager to obtain thermal images of the curtain wall, detecting areas of abnormal temperature and revealing hidden problems within. Flight path planning: A detailed flight route map is pre-set to ensure that the drone can fully capture the exterior of the building along the predetermined trajectory. Data transmission: Data collected by the drone is transmitted to the controller in real time via a wireless communication module (such as Wi-Fi, 4G / 5G).

[0148] Controller Hardware: Memory: Used to store computer programs, sensor data, image data collected by drones, and model parameters. Processor: A high-performance processor used to execute computer programs and perform data processing and analysis. Software: Operating System: An operating system that supports multitasking, such as Linux. Application Programs: Includes data acquisition modules, image processing modules, feature extraction modules, and health status prediction modules. Database: Stores historical data and datasets required for model training. Function: Data Acquisition and Storage: Collects data from sensors and drones and stores it in memory. Data Preprocessing: Performs preprocessing steps such as filtering, denoising, enhancement, and cropping on sensor and image data. Feature Extraction: Uses convolutional neural networks to extract damage features from visible light images and thermal imaging images, and uses time series models to extract physical parameter features from sensor data. Feature Fusion: Fuses image feature information with physical parameter features to generate a comprehensive feature vector. Health Status Prediction: Based on the fused feature vector, a health status prediction model is used to output damage prediction results for the hyperbolic glass curtain wall in real time, including crack index, deformation index, temperature influence factor, and stress distribution factor. Health score calculation: The health score index is calculated based on the crack index, deformation index, temperature impact factor, and stress distribution factor, and the final damage prediction result is generated. Alarm and notification: When an abnormal situation is detected, the system automatically sends an alarm notification to maintenance personnel so that timely measures can be taken.

[0149] The specific implementation of the system can be as follows: Sensor installation and wiring: strain sensors, temperature sensors, and displacement sensors are installed at key points of the hyperbolic glass curtain wall. Sensor data is transmitted to the controller in real time via wireless communication modules (such as LoRa and NB-IoT).

[0150] Drone Configuration and Flight Path Planning: Configure the drone, ensuring it's equipped with a high-definition camera and thermal imaging camera. Use ground station software to design a detailed flight path to ensure the drone covers all areas of the facade. Set up scheduled drone missions, such as automatically taking off for inspections at specific times of the day.

[0151] Controller Setup and Software Deployment: Configure the controller hardware, including a high-performance processor and large-capacity memory. Install the operating system and related applications, and configure the database. Develop the data acquisition module, image processing module, feature extraction module, feature fusion module, and health status prediction module. Integrate all modules into a unified application, ensuring smooth data flow between modules.

[0152] Data Acquisition and Processing: Sensors collect strain, temperature, and displacement data in real time and transmit them to the controller via wireless communication. Drones regularly perform inspections, collecting visible light and thermal images and transmitting them to the controller via wireless communication. The collected data undergoes preprocessing, including filtering, denoising, enhancement, and cropping.

[0153] Feature extraction and fusion: Use convolutional neural networks to extract damage features from visible light and thermal images. Use time series models (such as LSTM) to extract physical parameter features from sensor data. Fusion of image feature information and physical parameter features generates a comprehensive feature vector.

[0154] Health Status Prediction and Score Calculation: Based on the fused feature vectors, the health status prediction model outputs the hyperbolic glass curtain wall's crack index, deformation index, temperature impact factor, and stress distribution factor in real time. Based on these factors, a health score is calculated, generating the final damage prediction result. When an anomaly is detected, the system automatically sends an alarm notification to maintenance personnel.

[0155] System Maintenance and Updates: Regularly calibrate sensors to ensure data accuracy. Update drone flight path planning to adapt to building changes. Regularly update training sets to incorporate the latest observations to maintain model currency. Release updates to fix known bugs and add new features.

[0156] The system has at least the following beneficial effects:

[0157] Comprehensive Monitoring: By combining multiple sensors and drones, comprehensive monitoring of the hyperbolic glass curtain wall is achieved, effectively monitoring even difficult-to-observe sections. This provides rich physical parameter data to support subsequent analysis, improving the reliability and accuracy of damage detection.

[0158] Real-time monitoring and early warning: This system monitors the condition of the hyperbolic glass curtain wall in real time, enabling the timely detection of early-stage minor damage. A health status prediction model can predict potential safety risks in advance, providing a strong basis for maintenance decisions.

[0159] Accurate Assessment: By comprehensively considering multiple factors (cracks, deformation, temperature, and stress), a more accurate damage assessment is provided. The introduction of dynamic weight coefficients and environmental and geometric coupling coefficients makes the assessment results more scientific and reasonable.

[0160] Automation and Intelligence: The system is highly automated, reducing manual intervention, operational difficulty, and safety risks. Through machine learning, algorithm performance is continuously improved, with increased accuracy and robustness.

[0161] Efficient resource utilization: Through real-time monitoring and early warning, problems can be discovered and addressed promptly, extending the service life of facilities, saving long-term operating costs, and improving resource utilization efficiency.

[0162] Easy to manage: Provides managers with an intuitive and easy-to-understand operation interface, simplifying daily management workflows. Through a closed-loop control system, it provides a one-stop service from data collection to result display and action recommendations.

[0163] In summary, the hyperbolic glass curtain wall damage prediction system achieves comprehensive, real-time, and accurate monitoring and evaluation of hyperbolic glass curtain walls through multi-sensor information fusion and drone image acquisition, combined with deep learning models for feature extraction and fusion, providing strong support for maintenance decisions.

[0164] In some embodiments, the target points include glass panel edges, connection nodes, and stress concentration areas corresponding to the hyperbolic glass curtain wall.

[0165] Target Location Selection: Glass Panel Edges: Sensors are installed at the edges of each pane of glass in a hyperbolic glass curtain wall. These locations are often stress concentration areas and are prone to cracking and deformation. Connection Nodes: Sensors are installed at each connection node of the curtain wall. Connection nodes are critical structural features and are subject to significant stress and displacement fluctuations. Stress Concentration Areas: Based on design and engineering analysis, stress concentration areas on the curtain wall are identified and sensors are placed in these areas. For example, areas with significant curvature changes and uneven stress distribution.

[0166] Sensor Type and Function: Strain sensors monitor stress changes at glass panel edges, joints, and areas of stress concentration. Temperature sensors monitor temperature distribution in these critical areas, particularly during seasons or time periods with significant temperature fluctuations. Displacement sensors monitor relative displacement changes in these areas, particularly at joints.

[0167] Conduct a comprehensive on-site survey of the hyperbolic glass curtain wall to determine the specific locations of all target points. Install appropriate sensors at each target point, ensuring they are secure and reliable. Transmit sensor data to the controller in real time via wireless communication modules (such as LoRa or NB-IoT). Perform an initial calibration of the installed sensors to ensure data accuracy.

[0168] By focusing on glass panel edges, joints, and areas of stress concentration, comprehensive coverage is achieved for critical areas of the hyperbolic glass curtain wall. These areas are often most susceptible to damage, and focused monitoring can detect subtle damage earlier, improving detection accuracy. Promptly identifying and addressing issues in these critical areas can effectively prevent major accidents and enhance building safety. This focused monitoring allows for more targeted maintenance plans, reduces unnecessary inspections and repairs, and improves maintenance efficiency.

[0169] In some embodiments, the arrangement density of the sensors in the hyperbolic glass curtain wall is dynamically adjusted according to the curvature radius of the hyperbolic glass curtain wall. In the area where the curvature radius is less than 3m, the arrangement density is increased by a preset density coefficient compared to the area where the curvature radius is greater than or equal to 3m. The preset density coefficient corresponds to a value range of 30% to 50%.

[0170] Based on the design drawings of the hyperbolic glass curtain wall, the curtain wall is divided into areas with different curvature radii. Areas with a curvature radius less than 3m are defined as high curvature areas, and areas with a curvature radius greater than or equal to 3m are defined as low curvature areas. Sensor layout density adjustment: High curvature areas: Increase the sensor layout density in areas with a curvature radius less than 3m. Specifically, the layout density is increased by a preset density coefficient compared to the low curvature area, and the preset density coefficient value range is 30% to 50%. Low curvature areas: Maintain the standard sensor layout density in areas with a curvature radius greater than or equal to 3m.

[0171] The specific steps corresponding to the embodiment may be: Curvature analysis: using computer-aided design (CAD) software or three-dimensional scanning technology, a detailed curvature analysis is performed on the hyperbolic glass curtain wall to determine the curvature radius of each area.

[0172] Density calculation: Based on the division results of the curvature radius, the sensor layout density in the high curvature area and the low curvature area is calculated.

[0173] Sensor installation: Arrange sensors at an increased density in areas of high curvature and at a standard density in areas of low curvature.

[0174] Data transmission and calibration: The sensor data is transmitted to the controller in real time through the wireless communication module, and the installed sensors are initially calibrated.

[0175] Increasing sensor density in areas of high curvature allows for more detailed monitoring of state changes in these areas, improving monitoring accuracy. Dynamically adjusting sensor density ensures effective monitoring while rationally allocating sensor resources and avoiding waste. For complex hyperbolic geometries, the division of curvature radii and density adjustment better accommodate monitoring needs in different areas. High-curvature areas are often more prone to stress concentration and material fatigue. Increasing sensor density can detect these issues earlier and improve system reliability. Appropriate sensor placement avoids over-deploying sensors in areas of low curvature, thereby reducing overall system cost.

[0176] See also Figure 3 , Figure 3 : 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.

[0177] 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 methods for predicting damage of a hyperbolic glass curtain wall.

[0178] The processor is used to provide computing and control capabilities and support the operation of the entire controller.

[0179] 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 hyperbolic glass curtain wall damage prediction methods.

[0180] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution 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.

[0181] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0182] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0183] Acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information, and displacement sensor information;

[0184] Controlling a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager;

[0185] Inputting the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network, and outputting image feature information;

[0186] Inputting the sensor collected information into a time-series-based physical parameter analysis model to output parameter characteristic information;

[0187] Fusing the image feature information with the parameter feature information to obtain a damage feature recognition result;

[0188] A health status prediction model is constructed based on the damage feature identification, so that real-time sensor information, real-time visible light images, and real-time thermal imaging images corresponding to the hyperbolic glass curtain wall are input into the health status prediction model, and the health status prediction model outputs damage prediction results corresponding to the hyperbolic glass curtain wall in real time.

[0189] In some embodiments, before inputting the visible light image and thermal imaging image into a damage feature recognition model based on a convolutional neural network, it also 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 anomalies.

[0190] In some embodiments, the health status prediction model outputs a damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs a crack index and a deformation index corresponding to the hyperbolic glass curtain wall based on the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs a temperature influence factor and a stress distribution factor based on the real-time sensor collected information; and the damage prediction result is generated based on the crack index, deformation index, temperature influence factor, and stress distribution factor.

[0191] Exemplarily, generating the damage prediction result according to the crack index, deformation index, temperature influence factor, and stress distribution factor includes: calculating a health score index according to the crack index, deformation index, temperature influence factor, and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes:

[0192] ;in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score.

[0193] It should be noted that, in some embodiments, the expression of the dynamic weight coefficient includes:

[0194] ;

[0195] in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of the damage type.

[0196] It should be noted that, in some embodiments, if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.18.

[0197] 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.

[0198] The present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the steps of the method for predicting damage of a hyperbolic glass curtain wall as provided in any embodiment of the present application.

[0199] The computer-readable storage medium may be an internal storage unit of the controller described in the aforementioned 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 media card (SMC), a secure digital (SD) card, a flash memory card, etc., equipped on the controller.

[0200] 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.

[0201] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for predicting damage of a hyperbolic glass curtain wall, characterized in that: include: Acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information, and displacement sensor information; Controlling a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager; Inputting the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network, and outputting image feature information; Inputting the sensor collected information into a time-series-based physical parameter analysis model to output parameter characteristic information; Fusing the image feature information with the parameter feature information to obtain a damage feature recognition result; A health status prediction model is constructed based on the damage feature identification, so that the real-time sensor acquisition information, real-time visible light image and real-time thermal imaging image corresponding to the hyperbolic glass curtain wall are input into the health status prediction model, and the health status prediction model outputs the damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs the crack index and deformation index corresponding to the hyperbolic glass curtain wall according to the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs the temperature influence factor and the stress distribution factor according to the real-time sensor acquisition information; the damage prediction result is generated according to the crack index, deformation index, temperature influence factor and stress distribution factor, including: calculating the health score index according to the crack index, deformation index, temperature influence factor and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes: ； in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score; the expression of the dynamic weight coefficient includes: ； in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of damage types; if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.

18.

2. The method according to claim 1, characterized in that Before inputting the visible light image and the thermal imaging image into the damage feature recognition model based on the convolutional neural network, the method further includes: Preprocessing the sensor collected information, visible light image and thermal imaging image; the preprocessing includes at least filtering, denoising, enhancement and cropping preprocessing; Damage information is annotated in the pre-processed sensor acquisition information, visible light image, and thermal imaging image; the damage information at least includes the damage type and timing anomaly.

3. A device for predicting damage to a hyperbolic glass curtain wall, characterized in that: include: An information acquisition module is used to acquire sensor information collected by the hyperbolic glass curtain wall; the sensor information collected includes at least strain sensor information, temperature sensor information and displacement sensor information; An image acquisition module, configured to control a preset drone to collect visible light images and thermal imaging images corresponding to the hyperbolic glass curtain wall; the drone is equipped with a visible light device and an infrared thermal imager; An image output module, configured to input the visible light image and the thermal imaging image into a damage feature recognition model based on a convolutional neural network and output image feature information; A feature output module, configured to input the sensor collected information into a time-series-based physical parameter analysis model and output parameter feature information; A feature fusion module, configured to fuse the image feature information with the parameter feature information to obtain a damage feature recognition result; A prediction completion module is used to construct a health status prediction model based on the damage feature identification, so as to input the real-time sensor acquisition information, real-time visible light image and real-time thermal imaging image corresponding to the hyperbolic glass curtain wall into the health status prediction model, and the health status prediction model outputs the damage prediction result corresponding to the hyperbolic glass curtain wall in real time, including: the health status prediction model outputs the crack index and deformation index corresponding to the hyperbolic glass curtain wall according to the real-time visible light image and the real-time thermal imaging image; the health status prediction model outputs the temperature influence factor and the stress distribution factor according to the real-time sensor acquisition information; generates the damage prediction result according to the crack index, deformation index, temperature influence factor and stress distribution factor, including: calculating the health score index according to the crack index, deformation index, temperature influence factor and stress distribution factor; generating the damage prediction result according to the health score index; the expression of the health score index includes: ； in, for Health score index at all times, for Moment Dynamic weight coefficient of the damage type, for Moment Injury type score, is the number of damage types, which include at least cracks and deformations, is the environmental and geometric coupling coefficient corresponding to the hyperbolic glass curtain wall, which is used to reflect the accelerating effect of seasonal changes on curtain wall damage. is the curvature change correction term, which is used to quantify the additional impact of hyperbolic surface geometric deformation on the health score; the expression of the dynamic weight coefficient includes: ； in, for Moment Dynamic weight coefficient of the damage type, is the initial weight coefficient, For the The damage sensitivity attenuation factor of the damage index is used to control the timeliness of different damage types. For the Damage sensitivity attenuation factor of damage-like indicators, is the number of damage types; if the damage type is crack, the initial weight coefficient is 0.4, and the corresponding value range of the damage sensitivity attenuation factor is 0.05 to 0.15; if the damage type is deformation, the initial weight coefficient is 0.3, and the corresponding value range of the damage sensitivity attenuation factor is 0.03 to 0.

18.

4. A hyperbolic glass curtain wall damage prediction system, characterized in that: include A plurality of sensors, each of which is arranged at a target point of the hyperbolic glass curtain wall, and each of which includes at least a strain sensor, a temperature sensor, and a displacement sensor; Unmanned aerial vehicles, without the aforementioned drones being equipped with visible light equipment and infrared thermal imagers; A controller comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method according to any one of claims 1 to 2 when executing the computer program.

5. The double-curved glass curtain wall damage prediction system according to claim 4, characterized in that: The target points include glass panel edges, connection nodes and stress concentration areas corresponding to the hyperbolic glass curtain wall.

6. The double-curved glass curtain wall damage prediction system according to claim 4, characterized in that: The arrangement density of the sensors in the hyperbolic glass curtain wall is dynamically adjusted according to the curvature radius of the hyperbolic glass curtain wall. In the area where the curvature radius is less than 3m, the arrangement density is increased by a preset density coefficient compared with the area where the curvature radius is greater than or equal to 3m. The preset density coefficient corresponds to a value range of 30% to 50%.

Images