Optimization Method for Lamb Wave Excitation and Reception in Nondestructive Testing and Positioning of Hyperbolic Glass Curtain Walls

Abstract

The present application provides an optimized method for Lamb wave excitation and reception in non-destructive testing and positioning of hyperbolic glass curtain walls. The method includes: obtaining the curtain wall parameter information of the hyperbolic glass curtain wall to be tested and positioned; the curtain wall parameter information at least includes geometric parameters, thickness parameters, material parameters and environmental parameters; optimizing the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include excitation frequency, waveform coefficient and excitation angle; performing signal transmission and reception on the hyperbolic glass curtain wall according to the optimized Lamb wave parameters to obtain the damage reflection signal corresponding to the hyperbolic glass curtain wall; performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector; obtaining a neural network positioning model containing hyperbolic geometric constraints, inputting the damage feature vector into the neural network positioning model, and outputting the three-dimensional coordinates of the damage to complete the non-destructive testing and positioning of the hyperbolic glass curtain wall.

Description

Technical Field

[0001] This application relates to the technical field of glass curtain walls, and particularly to an optimization method for Lamb wave excitation and reception in non-destructive testing and positioning of hyperbolic glass curtain walls. Background Art

[0002] With the development of modern architectural design, hyperbolic glass curtain walls, as a unique building exterior wall material, are widely used in large buildings due to their aesthetic appearance and unique shape. The curved shape of hyperbolic glass curtain walls increases the complexity of their structure and poses higher requirements for damage detection. Traditional glass curtain wall detection methods, such as visual inspection, vibration detection, thermal imaging, and ultrasonic detection, cannot adapt to the special geometric form of hyperbolic glass curtain walls, resulting in insufficient detection accuracy and positioning accuracy.

[0003] Therefore, there is an urgent need for a method to solve at least one of the above problems. Summary of the Invention

[0004] This application provides an optimization method for Lamb wave excitation and reception in non-destructive testing and positioning of hyperbolic glass curtain walls, aiming to solve the problem that traditional glass curtain wall detection methods, such as visual inspection, vibration detection, thermal imaging, and ultrasonic detection, cannot adapt to the special geometric form of hyperbolic glass curtain walls, resulting in insufficient detection accuracy and positioning accuracy.

[0005] In a first aspect, this application provides an optimization method for Lamb wave excitation and reception in non-destructive testing and positioning of hyperbolic glass curtain walls, including:

[0006] Obtain the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information includes at least geometric parameters, thickness parameters, material parameters, and environmental parameters;

[0007] Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters include at least excitation frequency, waveform coefficient, and excitation angle;

[0008] Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain the damage reflection signal corresponding to the hyperbolic glass curtain wall;

[0009] Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector;

[0010] Obtain a neural network positioning model containing hyperbolic geometric constraints, input the damage feature vector into the neural network positioning model, and output the damage three-dimensional coordinates to complete the non-destructive testing and positioning of the hyperbolic glass curtain wall.

[0011] In some embodiments, obtaining the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and located includes: obtaining the three-dimensional laser scanning image and visual image corresponding to the hyperbolic glass curtain wall; transforming the feature points corresponding to the three-dimensional laser scanning image and visual image to the same coordinate system based on the point cloud registration algorithm; performing surface reconstruction on the hyperbolic glass curtain wall according to the registered three-dimensional laser scanning image and visual image to obtain the curtain wall parameter information.

[0012] In some embodiments, the expression of the excitation frequency includes:

[0013] ; where represents the excitation frequency, represents the temperature compensation coefficient, is the thickness parameter, is the Young's modulus, is the Poisson's ratio, is the material density corresponding to the hyperbolic glass, is used to represent the effective stiffness under plane stress state, is used to represent the influence of Poisson's ratio on the three-dimensional strain of the hyperbolic glass curtain wall.

[0014] In some embodiments, the expression of the excitation angle includes:

[0015] ; where represents the excitation angle, and respectively represent the local slope of the surface corresponding to the hyperbolic glass curtain wall, represents the environmental compensation angle corresponding to the hyperbolic glass curtain wall, which is used to correct the wave velocity anisotropy caused by environmental factors, represents adjusting the excitation angle according to the local curvature of the hyperbolic surface corresponding to the hyperbolic glass curtain wall to ensure that the lamb wavefront always maintains the best incident angle with the surface normal of the hyperbolic glass curtain wall and avoid lamb wave signal scattering.

[0016] Exemplarily, if the environmental temperature corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to subtract the first compensation angle, and the first compensation angle is within the first compensation angle range, and the first compensation angle range is 0.05 to 0.15 rad; if the environmental humidity corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to add the second compensation angle, and the second compensation angle is within the second compensation angle range, and the second compensation angle range is 0.02 to 0.08 rad.

[0017] In some embodiments, inputting the damage feature vector into the neural network localization model to output the three-dimensional damage coordinates includes: inputting the damage feature vector into the neural network localization model, where the neural network localization model generates geometric damage features through three-dimensional convolutional kernels and processes and generates signal damage features through time-frequency convolutional kernels; and performing feature fusion based on the geometric damage features and the signal damage features to output the three-dimensional damage coordinates.

[0018] In some embodiments, before transmitting and receiving signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, it further includes: obtaining the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle corresponding to the Lamb wave; and adjusting the spatial density of the array piezoelectric sensors for receiving the damage reflection signals according to the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle.

[0019] Exemplarily, the expression corresponding to the spatial density includes:

[0020] ; where is the spatial density, is the lowest phase velocity, is the highest excitation frequency, is the maximum excitation angle.

[0021] In some embodiments, performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector includes: performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a signal energy attenuation coefficient, a main frequency offset, and a wavelet packet node energy entropy; and generating the damage feature vector according to the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy.

[0022] In some embodiments, after outputting the three-dimensional damage coordinates, it further includes: generating a visual inspection atlas according to the three-dimensional damage coordinates and the curtain wall model corresponding to the hyperbolic glass curtain wall; the visual inspection atlas includes a hyperbolic surface unfolding diagram of the hyperbolic glass curtain wall, the hyperbolic surface unfolding diagram includes a damage projection corresponding to the three-dimensional damage coordinates, a three-dimensional rendering model corresponding to the hyperbolic glass curtain wall, the three-dimensional rendering model includes a defect mark corresponding to the three-dimensional damage coordinates, a stacked display diagram corresponding to the hyperbolic glass curtain wall, and the stacked display diagram includes a defect size and a depth parameter.

[0023] In a second aspect, the present application provides a device for optimizing Lamb wave excitation and reception for non-destructive detection and localization of a hyperbolic glass curtain wall, including:

[0024] A parameter acquisition unit for acquiring the curtain wall parameter information of a hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information at least includes geometric parameters, thickness parameters, material parameters, and environmental parameters;

[0025] A parameter optimization unit for optimizing the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include excitation frequency, waveform coefficient, and excitation angle;

[0026] A signal acquisition unit for transmitting and receiving signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and acquiring the damage reflection signals corresponding to the hyperbolic glass curtain wall;

[0027] A signal decomposition unit for performing time-frequency domain decomposition on the damage reflection signals according to wavelet packet transform to obtain damage feature vectors;

[0028] A coordinate output unit for acquiring a neural network positioning model including hyperbolic geometric constraints, inputting the damage feature vectors into the neural network positioning model, and outputting damage three-dimensional coordinates to complete non-destructive detection and positioning of the hyperbolic glass curtain wall.

[0029] In a third aspect, the present application provides a computer device, including 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 provided in any embodiment of the present application when executing the computer program.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer-readable instructions are executed by the processor, one or more processors are caused to execute the method provided in any embodiment of the present application.

[0031] A method for optimizing Lamb wave excitation and reception for non-destructive detection and positioning of a hyperbolic glass curtain wall provided by an embodiment of the present application. The specific technical process is as follows:

[0032] Acquire the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned. Geometric parameters: including the curvature radius, shape parameters, etc. of the hyperboloid. Thickness parameters: the thickness of the glass curtain wall. Material parameters: the material type of the glass and its physical properties (such as elastic modulus, Poisson's ratio, etc.). Environmental parameters: environmental conditions such as temperature and humidity.

[0033] Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information. Excitation frequency: Select an appropriate excitation frequency to ensure the propagation efficiency and resolution of Lamb waves in the glass. Waveform coefficient: Determine the shape and pulse width of the waveform to adapt to different types of damage. Excitation angle: Adjust the excitation angle so that the Lamb wave can effectively cover the entire hyperbolic surface area.

[0034] Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain the damage reflection signal corresponding to the hyperbolic glass curtain wall. Use the optimized Lamb wave parameters to transmit signals to the hyperbolic glass curtain wall through a sensor array. Receive the damage reflection signals captured by the sensor array, and record the time and intensity of the signals.

[0035] Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain the damage feature vector. Use wavelet packet transform to convert the damage reflection signal from the time domain to the time-frequency domain, and extract the multi-scale features of the signal. Through the analysis of the time-frequency domain signal, extract the feature vector containing the damage location and degree. Obtain a neural network localization model containing hyperbolic geometric constraints, input the damage feature vector into the neural network localization model, and output the three-dimensional coordinates of the damage to complete the non-destructive testing and localization of the hyperbolic glass curtain wall.

[0036] By constructing a neural network model containing hyperbolic geometric constraints, this model can handle complex geometric forms. Input the extracted damage feature vector into the neural network model, and calculate the three-dimensional coordinates of the damage through the trained model. Output the results to complete the non-destructive testing and localization of the hyperbolic glass curtain wall.

[0037] The specific implementation of the above steps can be: Data collection and preprocessing: Use a high-precision sensor array to scan the hyperbolic glass curtain wall and collect initial data. Preprocess the collected data to remove noise and interference signals to ensure data quality.

[0038] Parameter optimization: According to the specific parameters of the curtain wall (geometric parameters, thickness parameters, material parameters, and environmental parameters), use a method combining numerical simulation and experimental verification to optimize the excitation frequency, waveform coefficient, and excitation angle of Lamb waves. Through multiple iterations and feedback adjustments, find the optimal combination of Lamb wave parameters.

[0039] Signal transmission and reception: Use the optimized Lamb wave parameters to transmit signals to the hyperbolic glass curtain wall through a sensor array. Receive the damage reflection signals captured by the sensor array and record the time and intensity of the signals.

[0040] Signal Processing and Feature Extraction: The wavelet packet transform is used to decompose the damage reflection signal in the time-frequency domain, and the feature vector containing the damage location and degree is extracted. By analyzing the time-frequency domain signal, the feature vector is further refined to improve the detection accuracy.

[0041] Neural Network Location Model Construction and Application: A neural network model with hyperbolic geometric constraints is constructed, which can handle complex geometric forms. A large amount of labeled data is used to train the neural network model to ensure its good generalization ability. The extracted damage feature vector is input into the trained neural network model to calculate the three-dimensional coordinates of the damage. The output result completes the non-destructive detection and location of the hyperbolic glass curtain wall.

[0042] The method provided at least has the following beneficial effects:

[0043] Improve detection accuracy: By optimizing the Lamb wave parameters, the propagation efficiency and resolution of the signal in the hyperbolic glass curtain wall are improved, thus improving the detection accuracy.

[0044] Enhance location accuracy: Combining the wavelet packet transform and the neural network model can accurately extract damage features and perform three-dimensional location, significantly improving the location accuracy.

[0045] Adapt to complex geometric forms: This method can adapt to the complex geometric form of the hyperbolic glass curtain wall, solving the problem that traditional detection methods cannot effectively handle.

[0046] Real-time and automation: Through the sensor array and the automated signal processing system, a fast and efficient detection process is realized, which is suitable for the regular maintenance and detection of large-scale buildings.

[0047] Reduce manual intervention: The automated detection and location process reduces the need for manual intervention, reducing the detection cost and time.

[0048] Scalability: This method is not only applicable to hyperbolic glass curtain walls, but can also be extended to the structural detection of other complex geometric forms, with wide applicability.

[0049] In summary, a method for optimizing the excitation and reception of Lamb waves for non-destructive detection and location of hyperbolic glass curtain walls provided in this application significantly improves the detection accuracy and location accuracy by optimizing Lamb wave parameters, signal processing, and the neural network location model, providing effective technical support for the maintenance and detection of hyperbolic glass curtain walls.

[0050] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Brief Description of the Drawings

[0051] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a schematic flow chart of the steps of the Lamb wave excitation and reception optimization method for non-destructive detection and positioning of a hyperbolic glass curtain wall provided by an embodiment of the present application;

[0053] Figure 2 It is a schematic block diagram of the structure of the Lamb wave excitation and reception optimization method device for non-destructive detection and positioning of a hyperbolic glass curtain wall provided by an embodiment of the present application;

[0054] Figure 3 It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application.

[0055] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Detailed implementation manners

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0057] The flow chart shown in the drawings is only an example, and does not necessarily include all contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0058] 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, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

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

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

[0061] The following will, with reference to the accompanying drawings, elaborate on some embodiments of this application. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0062] With the development of modern architectural design, the hyperbolic glass curtain wall, as a unique building facade material, is widely used in large buildings due to its aesthetic appearance and unique shape. The curved shape of the hyperbolic glass curtain wall increases the complexity of its structure and at the same time poses higher requirements for damage detection. Traditional glass curtain wall detection methods, such as visual inspection, vibration detection, thermal imaging, and ultrasonic detection, etc., cannot adapt to the special geometric shape of the hyperbolic glass curtain wall, resulting in insufficient detection accuracy and positioning accuracy.

[0063] Therefore, there is an urgent need for a method to solve at least one of the above problems.

[0064] To solve the above problems, please refer to Figure 1 As shown in Figure 1 the provided method for optimizing the excitation and reception of Lamb waves for non-destructive detection and positioning of hyperbolic glass curtain walls includes steps S101 to S105. This method for optimizing the excitation and reception of Lamb waves for non-destructive detection and positioning of hyperbolic glass curtain walls is executed by a computer device, which can be a single server or a server cluster, or can be a handheld terminal, a laptop, a wearable device, or a robot, etc.

[0065] As shown in Figure 1 the details of steps S101 - S105 are as follows:

[0066] Step S101. Obtain the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information includes at least geometric parameters, thickness parameters, material parameters, and environmental parameters.

[0067] Specifically, first, all relevant parameters of the hyperbolic glass curtain wall need to be collected. These parameters can be divided into four major categories: geometric parameters, thickness parameters, material parameters, and environmental parameters. Geometric parameters include, but are not limited to, information describing the shape of the curtain wall such as the overall dimensions (length, width), radius of curvature, specific shape of the curved surface, and curvature distribution. These parameters can be determined through on-site measurement or by referring to architectural design drawings. Thickness parameters refer to the actual thickness value of the glass layer, which is directly related to the sound wave propagation speed and attenuation degree. An ultrasonic thickness gauge or other non-destructive testing tools can be used for accurate measurement. Material parameters involve the specific types of materials used to manufacture the curtain wall (such as tempered glass, laminated glass, etc.) and their physical properties (density, elastic modulus, Poisson's ratio, etc.). These data can be obtained from the product specification sheets provided by the suppliers. Environmental parameters cover factors such as temperature, humidity, and wind speed at the installation location, as these conditions affect the behavior of sound waves. Devices such as thermohygrometers and anemometers can be used to record the current environmental conditions.

[0068] Exemplarily, for the acquisition of geometric parameters: Use a high-precision 3D scanner to comprehensively scan the hyperbolic glass curtain wall to obtain a detailed geometric model. Convert the scanned data into a digital model through CAD software and extract key geometric parameters such as the radius of curvature, surface equation, etc. For complex curved surface structures, specialized geometric analysis software can be used for further processing and verification.

[0069] For the acquisition of thickness parameters: Use an ultrasonic thickness gauge to measure at multiple points to ensure coverage of different areas of the entire curtain wall. Record the data at each measurement point and calculate the average value and standard deviation to evaluate the consistency and uniformity of the thickness. For hard-to-reach locations, a portable ultrasonic thickness gauge or robot-assisted measurement can be used.

[0070] For the acquisition of material parameters: Refer to the product specification sheets provided by the suppliers to obtain the detailed physical properties of the glass. If the specification sheets are incomplete, missing data can be supplemented through laboratory tests (such as tensile tests, compression tests, etc.). For composite materials (such as laminated glass), the interfacial characteristics between the layers of materials also need to be considered.

[0071] For the acquisition of environmental parameters: Use thermohygrometers and anemometers to record environmental parameters at different time periods and weather conditions. Upload the data to a computer system for statistical analysis to determine typical working environmental conditions. Consider the influence of seasonal changes and extreme weather and formulate corresponding detection strategies.

[0072] Accurately grasping all the above parameters helps to more precisely adjust the relevant settings of Lamb waves in subsequent steps, thereby improving the detection accuracy. In addition, detailed parameter information can also be used to establish a more accurate numerical model to further optimize the detection scheme.

[0073] Step S102. Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include the excitation frequency, waveform coefficient, and excitation angle.

[0074] Specifically, based on the data obtained in the previous step, this step aims to determine the Lamb wave characteristics most suitable for use under the current specific conditions. It mainly includes: the selection of the excitation frequency needs to consider factors such as the target defect size and depth to ensure that potential problem areas can be effectively detected. The waveform coefficient determines the shape of the emitted sound wave, affecting the signal penetration ability and resolution. The excitation angle refers to the angle of the sound source relative to the normal direction of the surface of the object to be measured, which is particularly important for detection on complex curved surfaces.

[0075] For example, use the Rayleigh-Lamb equation combined with finite element analysis software (such as COMSOL Multiphysics) to predict the sound field distribution under different parameter combinations. Through numerical simulation, determine the optimal excitation frequency range so that the sound wave can effectively propagate and reflect back to the sensor. Simulate the sound wave propagation characteristics under different waveform coefficients and select the waveform that can provide the highest resolution and signal-to-noise ratio.

[0076] Build a simplified hyperbolic glass curtain wall model in the laboratory environment for preliminary experimental verification. By changing the excitation frequency, waveform coefficient, and excitation angle, record the reflection signals under different conditions. Analyze the experimental data, determine the optimal parameter combination, and conduct multiple repeated experiments to verify the reliability of the results.

[0077] Due to the characteristics of the hyperbolic structure, it is necessary to introduce an appropriate coordinate transformation algorithm to convert the sound wave propagation model in the plane coordinate system into a model in the curved surface coordinate system. Use mathematical tools (such as tensor analysis) for coordinate transformation to ensure that the propagation path and reflection characteristics of the sound wave on the curved surface are accurately described. Verify the effectiveness of the coordinate transformation algorithm through numerical simulation and make necessary adjustments.

[0078] In this way, the customized Lamb wave configuration can significantly enhance the sensitivity to specific types of damage, reduce background noise interference, and improve the overall signal-to-noise ratio. The optimized Lamb wave parameters can better adapt to the special geometric shape of the hyperbolic glass curtain wall, improving the accuracy and reliability of detection.

[0079] Step S103. Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain the damage reflection signals corresponding to the hyperbolic glass curtain wall.

[0080] Specifically, in this step, signals will be sent to the hyperbolic glass curtain wall using the previously determined optimal Lamb wave parameters, and the echo information returned will be captured using a sensor array. To cover the entire detection area, a multi-point or multi-angle scanning strategy may be required.

[0081] For example, install high-sensitivity piezoelectric transducers as the excitation source and receiving end to ensure the quality of signal transmission and reception. The piezoelectric transducers should be evenly distributed at key positions on the curtain wall to achieve full coverage. For difficult-to-reach positions, robot assistance can be used to complete the installation task.

[0082] Set reasonable sampling rates and gain amplification factors to ensure sufficient dynamic range and signal strength. Adopt a multi-point or multi-angle scanning strategy to ensure that the signal can cover the entire curtain wall area. For each scanning point, record the time-domain waveform diagram as the basis for preliminary analysis. Through multiple scans and signal superposition, improve the signal-to-noise ratio and reliability of the signal.

[0083] Use a high-speed data acquisition card to record the reflected signals in real time and store them in the computer system. During the data acquisition process, the stability and consistency of the system should be maintained to avoid external interference. Preprocess the acquired data to remove noise and outliers to ensure the quality of the data.

[0084] This method can not only comprehensively reflect the internal state of the object under inspection, but also, due to the use of optimized acoustic parameter settings, obtain clearer and more informative reflected signals, which is conducive to the work in the subsequent processing stage. Through a multi-point or multi-angle scanning strategy, comprehensive detection of the hyperbolic glass curtain wall can be achieved, improving the detection coverage rate and accuracy.

[0085] Step S104. Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector.

[0086] Specifically, once the original damage reflection signal is obtained, the next task is to extract useful features from it for defect identification and location. Here, it is recommended to use wavelet packet transform technology for signal processing because it can provide high frequency resolution while maintaining good time resolution.

[0087] Select an appropriate wavelet basis function (such as the Daubechies series), and then perform binary tree decomposition according to a predetermined level. Select the energy-concentrated section in the decomposition result at each level as a candidate feature. Combine statistical methods (such as principal component analysis PCA) to further streamline the feature set and remove redundant information. Finally, form a set of feature vectors containing multiple dimensions (such as amplitude, phase, instantaneous frequency, etc.).

[0088] Denoise the original reflected signal, and use a filter to remove high-frequency noise and low-frequency drift. Through normalization, the signals can be compared and analyzed on a unified scale. Segment the signals to ensure that each segment of the signal has similar length and characteristics.

[0089] Apply wavelet packet transform to decompose each segment of the signal in the time-frequency domain, and extract the energy distribution of each frequency band. Calculate the statistical characteristics of each frequency band, such as mean, variance, peak value, etc. Screen out the most representative features through feature selection algorithms (such as mutual information, recursive feature elimination, etc.). Combine the selected features into a high-dimensional feature vector for subsequent damage identification and location.

[0090] Standardize the extracted feature vector to ensure the comparability between different features. Build a feature vector database, which contains different types of damage feature vectors for training and validating the neural network model. Conduct visual analysis on the feature vector to help understand the distribution of different damage types in the feature space.

[0091] With the powerful localization analysis ability of wavelet packet transform, the part that truly reflects the damage characteristics can be separated from the complex reflected signal, laying a solid foundation for the next step of applying machine learning algorithms to achieve automatic diagnosis. In addition, this process helps to reduce the computational complexity and speed up the response speed of the entire system. By constructing a high-dimensional feature vector, the characteristics of the damage can be described more accurately, and the accuracy of damage identification and location can be improved.

[0092] Step S105. Obtain a neural network localization model containing hyperbolic geometric constraints, input the damage feature vector into the neural network localization model, and output the three-dimensional coordinates of the damage to complete the non-destructive testing and localization of the hyperbolic glass curtain wall.

[0093] Specifically, at this stage, input the damage feature vector into the trained neural network localization model, and this model can output the three-dimensional coordinates of the damage according to geometric constraints and signal characteristics.

[0094] Construction of the neural network localization model: Design a neural network architecture containing three-dimensional convolutional kernels and time-frequency convolutional kernels. The three-dimensional convolutional kernels are used to process geometric features and generate geometric damage features. The time-frequency convolutional kernels are used to process signal features and generate signal damage features. Fuse the geometric damage features and signal damage features through a feature fusion layer to generate a comprehensive feature vector. Finally, output the three-dimensional coordinates of the damage through a fully connected layer and a regression layer.

[0095] Model training: Collect a large number of damage sample data of hyperbolic glass curtain walls, including the three-dimensional coordinates of the damage and the corresponding damage feature vectors. Use this data to train a neural network and optimize the model parameters through the backpropagation algorithm. Adopt cross-validation and regularization techniques to prevent overfitting and improve the generalization ability of the model.

[0096] Model application: Input the extracted damage feature vectors into the trained neural network localization model. The model generates geometric damage features through three-dimensional convolutional kernels and processes and generates signal damage features through time-frequency convolutional kernels. The feature fusion layer fuses the geometric damage features and the signal damage features to generate a comprehensive feature vector. Finally, the three-dimensional coordinates of the damage are output through the fully connected layer and the regression layer.

[0097] Visual inspection atlas: Generate a visual inspection atlas based on the three-dimensional coordinates of the damage and the curtain wall model. The visual inspection atlas includes the unfolded view of the hyperboloid, showing the damage projection and the three-dimensional rendering model. The three-dimensional rendering model marks the defect location and provides an overlay display diagram showing the defect size and depth parameters. Through the overlay display diagram, the specific situation of the damage can be intuitively displayed.

[0098] Through the combination of three-dimensional convolutional kernels and time-frequency convolutional kernels, the geometric and signal features of the damage can be comprehensively captured. The feature fusion technology improves the accuracy of damage localization. The neural network model can automatically learn and identify complex damage patterns, improving the intelligent level of detection. The visual inspection atlas provides intuitive damage distribution and detailed information, facilitating further processing and repair by maintenance personnel. The three-dimensional rendering model and the overlay display diagram help users better understand and analyze the detection results. It improves the readability and practicality of the detection report, facilitating further processing and repair by maintenance personnel.

[0099] An optimized method for Lamb wave excitation and reception for non-destructive detection and localization of hyperbolic glass curtain walls provided by an embodiment of the present application. The specific technical process is as follows:

[0100] Obtain the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and located. Geometric parameters: including the curvature radius of the hyperboloid, shape parameters, etc. Thickness parameters: the thickness of the glass curtain wall. Material parameters: the material type of the glass and its physical properties (such as elastic modulus, Poisson's ratio, etc.). Environmental parameters: environmental conditions such as temperature and humidity.

[0101] Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information. Excitation frequency: Select an appropriate excitation frequency to ensure the propagation efficiency and resolution of Lamb waves in the glass. Waveform coefficient: Determine the shape and pulse width of the waveform to adapt to different types of damage. Excitation angle: Adjust the excitation angle so that Lamb waves can effectively cover the entire hyperbolic region.

[0102] Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain the damage reflection signals corresponding to the hyperbolic glass curtain wall. Use the optimized Lamb wave parameters to transmit signals to the hyperbolic glass curtain wall through a sensor array. Receive the damage reflection signals captured by the sensor array, and record the time and intensity of the signals.

[0103] Perform time-frequency domain decomposition on the damage reflection signals according to wavelet packet transform to obtain damage feature vectors. Use wavelet packet transform to convert the damage reflection signals from the time domain to the time-frequency domain, and extract the multi-scale features of the signals. Through the analysis of the time-frequency domain signals, extract the feature vectors containing the damage location and degree. Obtain a neural network localization model containing hyperbolic geometric constraints, input the damage feature vectors into the neural network localization model, and output the three-dimensional coordinates of the damage to complete the non-destructive testing and localization of the hyperbolic glass curtain wall.

[0104] By constructing a neural network model containing hyperbolic geometric constraints, this model can handle complex geometric forms. Input the extracted damage feature vectors into the neural network model, and calculate the three-dimensional coordinates of the damage through the trained model. Output the results to complete the non-destructive testing and localization of the hyperbolic glass curtain wall.

[0105] The specific implementation of the above steps can be: data collection and preprocessing: Use a high-precision sensor array to scan the hyperbolic glass curtain wall and collect initial data. Preprocess the collected data to remove noise and interference signals to ensure data quality.

[0106] Parameter optimization: According to the specific parameters of the curtain wall (geometric parameters, thickness parameters, material parameters, and environmental parameters), use a method combining numerical simulation and experimental verification to optimize the excitation frequency, waveform coefficient, and excitation angle of Lamb waves. Through multiple iterations and feedback adjustments, find the optimal combination of Lamb wave parameters.

[0107] Signal transmission and reception: Use the optimized Lamb wave parameters to transmit signals to the hyperbolic glass curtain wall through a sensor array. Receive the damage reflection signals captured by the sensor array and record the time and intensity of the signals.

[0108] Signal processing and feature extraction: Use wavelet packet transform to perform time-frequency domain decomposition on the damage reflection signals and extract the feature vectors containing the damage location and degree. Through the analysis of the time-frequency domain signals, further refine the feature vectors to improve the detection accuracy.

[0109] Construction and Application of Neural Network Location Model: Construct a neural network model with hyperbolic geometric constraints, which can handle complex geometric forms. Use a large amount of labeled data to train the neural network model to ensure its good generalization ability. Input the extracted damage feature vectors into the trained neural network model to calculate the three-dimensional coordinates of the damage. Output the results to complete the non-destructive detection and location of the hyperbolic glass curtain wall.

[0110] The provided method has at least the following beneficial effects:

[0111] Improve detection accuracy: By optimizing Lamb wave parameters, the propagation efficiency and resolution of signals in the hyperbolic glass curtain wall are improved, thus improving the detection accuracy.

[0112] Enhance location accuracy: Combining wavelet packet transform and neural network model can accurately extract damage features and perform three-dimensional location, significantly improving the location accuracy.

[0113] Adapt to complex geometric forms: This method can adapt to the complex geometric forms of hyperbolic glass curtain walls, solving the problems that traditional detection methods cannot effectively handle.

[0114] Real-time and automation: Through the sensor array and automated signal processing system, a fast and efficient detection process is achieved, which is suitable for the regular maintenance and detection of large-scale buildings.

[0115] Reduce manual intervention: The automated detection and location process reduces the need for manual intervention, lowering the detection cost and time.

[0116] Scalability: This method is not only applicable to hyperbolic glass curtain walls but can also be extended to the structural detection of other complex geometric forms, having wide applicability.

[0117] In summary, a method for optimizing Lamb wave excitation and reception for non-destructive detection and location of hyperbolic glass curtain walls provided in this application significantly improves the detection accuracy and location accuracy by optimizing Lamb wave parameters, signal processing, and neural network location models, providing effective technical support for the maintenance and detection of hyperbolic glass curtain walls.

[0118] In some embodiments, obtaining the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and located includes: obtaining the three-dimensional laser scanning image and visual image corresponding to the hyperbolic glass curtain wall; transforming the feature points corresponding to the three-dimensional laser scanning image and visual image to the same coordinate system based on the point cloud registration algorithm; performing surface reconstruction on the hyperbolic glass curtain wall according to the registered three-dimensional laser scanning image and visual image to obtain the curtain wall parameter information.

[0119] Use a high-precision 3D laser scanner to comprehensively scan the hyperbolic glass curtain wall to obtain detailed 3D point cloud data. At the same time, use a high-resolution camera to take visual images from multiple angles to ensure coverage of the entire curtain wall area. Use a point cloud registration algorithm (such as the ICP algorithm) to transform the corresponding feature points of the 3D laser scan image and the visual image into the same coordinate system. By matching feature points (such as corner points, edges, etc.), calculate the transformation matrix to align the two sets of data spatially.

[0120] Utilize the registered 3D laser scan image and visual image for surface reconstruction. Use surface reconstruction algorithms (such as Delaunay triangulation, NURBS surface fitting, etc.) to generate a geometric model of the hyperbolic glass curtain wall. Extract key geometric parameters, such as the radius of curvature, surface equation, etc.

[0121] By combining 3D laser scanning and visual images, more comprehensive and accurate curtain wall parameter information can be obtained. The point cloud registration algorithm ensures accurate alignment between different data sources, improving the consistency and reliability of the data. The surface reconstruction technology can generate a high-precision geometric model, providing reliable basic data for subsequent steps.

[0122] In some embodiments, the expression of the excitation frequency includes:

[0123] ; where represents the excitation frequency, represents the temperature compensation coefficient, is the thickness parameter, is the Young's modulus, is the Poisson's ratio, is the material density corresponding to the hyperbolic glass, is used to represent the effective stiffness under plane stress conditions, is used to represent the influence of the Poisson's ratio on the three-dimensional strain of the hyperbolic glass curtain wall.

[0124] Obtain the values of , and through experiments or by referring to material manuals. Measure the ambient temperature in real time through a temperature sensor and calculate . Measure and record the thickness of the curtain wall.

[0125] Substitute the above parameters into the formula to calculate the optimal excitation frequency. Adjust the acoustic wave emission device and set the calculated excitation frequency.

[0126] By considering the temperature compensation coefficient, a stable detection effect can be maintained under different environmental conditions. The physical parameters in the formula closely combine the excitation frequency with the material properties, improving the detection accuracy. The optimized excitation frequency can better adapt to the special geometric shape of the hyperbolic glass curtain wall, enhancing the sensitivity and resolution of damage detection.

[0127] In some embodiments, the expression of the excitation angle includes:

[0128] ; where represents the excitation angle, and respectively represent the local slope of the corresponding curved surface of the hyperbolic glass curtain wall, represents the environmental compensation angle corresponding to the hyperbolic glass curtain wall, which is used to correct the wave velocity anisotropy caused by environmental factors, represents adjusting the excitation angle according to the local curvature of the hyperbolic surface corresponding to the hyperbolic glass curtain wall to ensure that the Lamb wavefront always maintains the best incident angle with the normal of the curved surface of the hyperbolic glass curtain wall, avoiding the scattering of Lamb wave signals.

[0129] According to the changes in environmental temperature and humidity, adjust the environmental compensation angle. If the environmental temperature rises, subtract the first compensation angle (0.05 to 0.15 rad); if the environmental humidity rises, add the second compensation angle (0.02 to 0.08 rad). Substitute into the formula to calculate the final excitation angle. Adjust the angle of the acoustic wave emission device to ensure that the Lamb wavefront always maintains the best incident angle with the normal of the curved surface of the curtain wall.

[0130] By considering the local slope of the curved surface and environmental factors, the excitation angle can be adjusted more precisely to avoid signal scattering. The introduction of the environmental compensation angle enables the system to maintain a stable detection effect under different environmental conditions. The optimized excitation angle can improve the propagation efficiency and detection accuracy of Lamb waves.

[0131] Exemplarily, if the environmental temperature corresponding to the hyperbolic glass curtain wall rises, the environmental compensation angle needs to subtract the first compensation angle, and the first compensation angle is within the first compensation angle range, and the first compensation angle range is 0.05 to 0.15 rad; if the environmental humidity corresponding to the hyperbolic glass curtain wall rises, the environmental compensation angle needs to add the second compensation angle, and the second compensation angle is within the second compensation angle range, and the second compensation angle range is 0.02 to 0.08 rad.

[0132] In some embodiments, inputting the damage feature vector into the neural network localization model to output the three-dimensional coordinates of the damage includes: inputting the damage feature vector into the neural network localization model, where the neural network localization model generates geometric damage features through three-dimensional convolutional kernels and processes and generates signal damage features through time-frequency convolutional kernels; and performing feature fusion based on the geometric damage features and the signal damage features to output the three-dimensional coordinates of the damage.

[0133] Input the extracted damage feature vector into the neural network localization model. Process the input feature vector using three-dimensional convolutional kernels to generate geometric damage features. Process the input feature vector using time-frequency convolutional kernels to generate signal damage features. Fuse the geometric damage features and the signal damage features to output the three-dimensional coordinates of the damage.

[0134] Through the combination of three-dimensional convolutional kernels and time-frequency convolutional kernels, the geometric and signal features of the damage can be comprehensively captured. The feature fusion technology improves the accuracy of damage localization. The neural network model can automatically learn and identify complex damage patterns, improving the intelligent level of detection.

[0135] In some embodiments, before transmitting and receiving signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, it further includes: obtaining the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle corresponding to the Lamb wave; adjusting the spatial density of the array piezoelectric sensors for receiving the damage reflection signals according to the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle. Determine the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle of the Lamb wave through experiments or theoretical calculations.

[0136] Exemplarily, the expression corresponding to the spatial density includes:

[0137] ; where is the spatial density, is the lowest phase velocity, is the highest excitation frequency, is the maximum excitation angle.

[0138] Calculate the spatial density according to the above formula. By reasonably adjusting the spatial density of the piezoelectric sensors, the quality and resolution of signal reception can be improved. Adjust the spatial layout of the array piezoelectric sensors according to the calculation results to ensure sufficient coverage and resolution. Ensure that the reflection signals can be effectively captured at different excitation frequencies and angles. Improve the overall performance and reliability of the detection system.

[0139] In some embodiments, performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector includes: performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a signal energy attenuation coefficient, a main frequency offset, and a wavelet packet node energy entropy; generating the damage feature vector according to the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy.

[0140] Perform wavelet packet transform on the damage reflection signal to decompose it into multiple frequency bands. Calculate the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy of each frequency band. Combine the above features into a high-dimensional damage feature vector.

[0141] Through wavelet packet transform, rich feature information can be extracted from the time-frequency domain. The signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy can comprehensively describe the characteristics of the damage. The generated damage feature vector helps to improve the accuracy of damage identification and location.

[0142] In some embodiments, after outputting the damage three-dimensional coordinates, it further includes: generating a visual inspection atlas according to the damage three-dimensional coordinates and the curtain wall model corresponding to the hyperbolic glass curtain wall; the visual inspection atlas includes a hyperbolic surface unfolding diagram of the hyperbolic glass curtain wall, the hyperbolic surface unfolding diagram includes a damage projection corresponding to the damage three-dimensional coordinates, a three-dimensional rendering model corresponding to the hyperbolic glass curtain wall, the three-dimensional rendering model includes a defect mark corresponding to the damage three-dimensional coordinates, a stacked display diagram corresponding to the hyperbolic glass curtain wall, and the stacked display diagram includes a defect size and a depth parameter.

[0143] Generate a visual inspection atlas according to the damage three-dimensional coordinates and the curtain wall model. Include a damage projection corresponding to the damage three-dimensional coordinates. Display the three-dimensional rendering model of the hyperbolic glass curtain wall and mark the defect position. Include a defect size and a depth parameter. Through the stacked display diagram, the specific situation of the damage can be intuitively displayed. The visual inspection atlas provides an intuitive damage distribution and detailed information. The three-dimensional rendering model and the stacked display diagram help users better understand and analyze the detection results. Improve the readability and practicality of the detection report and facilitate maintenance personnel for further processing and repair.

[0144] Please refer to Figure 2 as shown in Figure 2It is a schematic structural diagram of an optimization device 200 for Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall provided by an embodiment of the present application. The optimization device 200 for Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall is used to execute the steps of the method for optimizing Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall shown in the above embodiments. The optimization device 200 for Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall can be a single server or a server cluster, or the optimization device 200 for Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall can be a terminal, and the terminal can be a handheld terminal, a laptop computer, a wearable device, a robot, etc.

[0145] As Figure 2 shown, the device 200 for optimizing Lamb wave excitation and reception in non-destructive testing and positioning of a hyperbolic glass curtain wall includes:

[0146] A parameter acquisition unit 201, configured to acquire curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information includes at least geometric parameters, thickness parameters, material parameters, and environmental parameters;

[0147] A parameter optimization unit 202, configured to optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters include at least excitation frequency, waveform coefficient, and excitation angle;

[0148] A signal acquisition unit 203, configured to transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and acquire damage reflection signals corresponding to the hyperbolic glass curtain wall;

[0149] A signal decomposition unit 204, configured to perform time-frequency domain decomposition on the damage reflection signals according to wavelet packet transform to acquire damage feature vectors;

[0150] A coordinate output unit 205, configured to acquire a neural network positioning model including hyperbolic surface geometric constraints, input the damage feature vectors into the neural network positioning model, and output damage three-dimensional coordinates to complete non-destructive testing and positioning of the hyperbolic glass curtain wall.

[0151] In some embodiments, the acquiring the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned includes: acquiring a three-dimensional laser scanning image and a visual image corresponding to the hyperbolic glass curtain wall; transforming the feature points corresponding to the three-dimensional laser scanning image and the visual image to the same coordinate system based on a point cloud registration algorithm; and performing surface reconstruction on the hyperbolic glass curtain wall according to the registered three-dimensional laser scanning image and visual image to acquire the curtain wall parameter information.

[0152] In some embodiments, the expression of the excitation frequency includes:

[0153] ; wherein, represents the excitation frequency, represents the temperature compensation coefficient, is the thickness parameter, is the Young's modulus, is the Poisson's ratio, is the material density corresponding to the hyperbolic glass, is used to represent the effective stiffness under plane stress state, is used to represent the influence of Poisson's ratio on the three-dimensional strain of the hyperbolic glass curtain wall.

[0154] In some embodiments, the expression of the excitation angle includes:

[0155] ; wherein, represents the excitation angle, and respectively represent the local slope of the curved surface corresponding to the hyperbolic glass curtain wall, represents the environmental compensation angle corresponding to the hyperbolic glass curtain wall, which is used to correct the wave velocity anisotropy caused by environmental factors, represents adjusting the excitation angle according to the local curvature of the hyperboloid corresponding to the hyperbolic glass curtain wall to ensure that the lamb wavefront always maintains the best incident angle with the normal of the curved surface of the hyperbolic glass curtain wall and avoid lamb wave signal scattering.

[0156] Exemplarily, if the environmental temperature corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to subtract the first compensation angle, and the first compensation angle is within the first compensation angle range, and the first compensation angle range is 0.05 to 0.15 rad; if the environmental humidity corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to add the second compensation angle, and the second compensation angle is within the second compensation angle range, and the second compensation angle range is 0.02 to 0.08 rad.

[0157] In some embodiments, inputting the damage feature vector into the neural network localization model to output the three-dimensional damage coordinates includes: inputting the damage feature vector into the neural network localization model, and the neural network localization model generates geometric damage features through a three-dimensional convolution kernel and processes and generates signal damage features through a time-frequency convolution kernel; and performing feature fusion according to the geometric damage features and the signal damage features to output the three-dimensional damage coordinates.

[0158] In some embodiments, before transmitting and receiving signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, the method further includes: obtaining the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle corresponding to the Lamb wave; adjusting the spatial density of the array piezoelectric sensor for receiving the damage reflection signal according to the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle.

[0159] Exemplarily, the expression corresponding to the spatial density includes:

[0160] ; where is the spatial density, is the lowest phase velocity, is the highest excitation frequency, is the maximum excitation angle.

[0161] In some embodiments, the time-frequency domain decomposition of the damage reflection signal according to wavelet packet transform to obtain the damage feature vector includes: performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy; generating the damage feature vector according to the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy.

[0162] In some embodiments, after outputting the damage three-dimensional coordinates, the method further includes: generating a visualization detection map according to the damage three-dimensional coordinates and the curtain wall model corresponding to the hyperbolic glass curtain wall; the visualization detection map includes the hyperbolic unfolding diagram of the hyperbolic glass curtain wall, the hyperbolic unfolding diagram includes the damage projection corresponding to the damage three-dimensional coordinates, the three-dimensional rendering model corresponding to the hyperbolic glass curtain wall, the three-dimensional rendering model includes the defect mark corresponding to the damage three-dimensional coordinates, the stacked display diagram corresponding to the hyperbolic glass curtain wall, and the stacked display diagram includes the defect size and the depth parameter.

[0163] 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 above-described Lamb wave excitation and reception optimization method, device, and each module for non-destructive testing and positioning of the hyperbolic glass curtain wall can refer to the corresponding processes in the embodiments of the Lamb wave excitation and reception optimization method for non-destructive testing and positioning of the hyperbolic glass curtain wall described in the above embodiments, and will not be repeated here.

[0164] The above-described Lamb wave excitation and reception optimization method for non-destructive testing and positioning of the hyperbolic glass curtain wall can be implemented in the form of a computer program, and the computer program can run on a device as shown in Figure 2 shown.

[0165] Please refer to Figure 3 ,Figure 3 It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory may include a storage medium and an internal memory.

[0166] 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 be caused to execute any one of the Lamb wave excitation and reception optimization methods for non-destructive detection and positioning of hyperbolic glass curtain walls.

[0167] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0168] 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 be caused to execute any one of the Lamb wave excitation and reception optimization methods for non-destructive detection and positioning of hyperbolic glass curtain walls.

[0169] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 3 the structure shown in

[0170] is only a block diagram of some structures 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. A specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0171] Among them, in one embodiment, the processor is used to run the computer program stored in the memory to implement the following steps:

[0172] Obtain the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information at least includes geometric parameters, thickness parameters, material parameters, and environmental parameters;

[0173] Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include the excitation frequency, waveform coefficient, and excitation angle;

[0174] Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain the damage reflection signal corresponding to the hyperbolic glass curtain wall;

[0175] Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector;

[0176] Obtain a neural network positioning model including hyperboloid geometric constraints, input the damage feature vector into the neural network positioning model, and output the three-dimensional coordinates of the damage to complete the non-destructive testing and positioning of the hyperbolic glass curtain wall.

[0177] In some embodiments, obtaining the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned includes: obtaining the three-dimensional laser scanning image and visual image corresponding to the hyperbolic glass curtain wall; based on the point cloud registration algorithm, transforming the feature points corresponding to the three-dimensional laser scanning image and visual image to the same coordinate system; performing surface reconstruction on the hyperbolic glass curtain wall according to the registered three-dimensional laser scanning image and visual image to obtain the curtain wall parameter information.

[0178] In some embodiments, the expression of the excitation frequency includes:

[0179] ; where represents the excitation frequency, represents the temperature compensation coefficient, is the thickness parameter, is the Young's modulus, is the Poisson's ratio, is the material density corresponding to the hyperbolic glass, is used to represent the effective stiffness under plane stress conditions, is used to represent the influence of Poisson's ratio on the three-dimensional strain of the hyperbolic glass curtain wall.

[0180] In some embodiments, the expression of the excitation angle includes:

[0181] ; where represents the excitation angle, and respectively represent the local slope of the surface corresponding to the hyperbolic glass curtain wall, represents the environmental compensation angle corresponding to the hyperbolic glass curtain wall, which is used to correct the wave velocity anisotropy caused by environmental factors, It means to adjust the excitation angle according to the local curvature of the hyperboloid corresponding to the hyperbolic glass curtain wall, ensuring that the lamb wavefront always maintains the best incident angle with the surface normal of the hyperbolic glass curtain wall to avoid the scattering of lamb wave signals.

[0182] Exemplarily, if the ambient temperature corresponding to the hyperbolic glass curtain wall increases, the ambient compensation angle needs to subtract the first compensation angle, and the first compensation angle is within the first compensation angle range, and the first compensation angle range is 0.05 to 0.15 rad; if the ambient humidity corresponding to the hyperbolic glass curtain wall increases, the ambient compensation angle needs to add the second compensation angle, and the second compensation angle is within the second compensation angle range, and the second compensation angle range is 0.02 to 0.08 rad.

[0183] In some embodiments, inputting the damage feature vector into the neural network localization model to output the three-dimensional damage coordinates includes: inputting the damage feature vector into the neural network localization model, and the neural network localization model generates geometric damage features through a three-dimensional convolution kernel and processes and generates signal damage features through a time-frequency convolution kernel; performing feature fusion according to the geometric damage features and the signal damage features to output the three-dimensional damage coordinates.

[0184] In some embodiments, before transmitting and receiving signals from the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, it further includes: obtaining the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle corresponding to the Lamb wave; adjusting the spatial density of the array piezoelectric sensors for receiving the damage reflection signals according to the lowest phase velocity, the highest excitation frequency, and the maximum excitation angle.

[0185] Exemplarily, the expression corresponding to the spatial density includes:

[0186] ; where is the spatial density, is the lowest phase velocity, is the highest excitation frequency, is the maximum excitation angle.

[0187] In some embodiments, performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector includes: performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a signal energy attenuation coefficient, a main frequency offset, and a wavelet packet node energy entropy; generating the damage feature vector according to the signal energy attenuation coefficient, the main frequency offset, and the wavelet packet node energy entropy.

[0188] In some embodiments, after outputting the three-dimensional coordinates of the damage, the method further includes: generating a visualization detection atlas according to the three-dimensional coordinates of the damage and the curtain wall model corresponding to the hyperbolic glass curtain wall; the visualization detection atlas includes a hyperbolic unfolded view of the hyperbolic glass curtain wall, the hyperbolic unfolded view includes a damage projection corresponding to the three-dimensional coordinates of the damage, a three-dimensional rendering model corresponding to the hyperbolic glass curtain wall, the three-dimensional rendering model includes a defect mark corresponding to the three-dimensional coordinates of the damage, a stacked display view corresponding to the hyperbolic glass curtain wall, and the stacked display view includes a defect size and a depth parameter.

[0189] 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 above-described computer device and each module can refer to the corresponding processes in the embodiments of the Lamb wave excitation and reception optimization method for non-destructive detection and positioning of hyperbolic glass curtain walls described in the above embodiments, and will not be elaborated here.

[0190] The present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the processor is caused to implement the steps of the Lamb wave excitation and reception optimization method for non-destructive detection and positioning of hyperbolic glass curtain walls provided in any embodiment of the present application.

[0191] Among them, the computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device.

[0192] Exemplarily, the medium is used to implement the following steps:

[0193] Obtain curtain wall parameter information of the hyperbolic glass curtain wall to be detected and positioned; the curtain wall parameter information at least includes geometric parameters, thickness parameters, material parameters, and environmental parameters;

[0194] Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include an excitation frequency, a waveform coefficient, and an excitation angle;

[0195] Transmit and receive signals to the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, and obtain damage reflection signals corresponding to the hyperbolic glass curtain wall;

[0196] Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector;

[0197] Obtain a neural network positioning model containing hyperbolic geometric constraints, input the damage feature vector into the neural network positioning model, and output the three-dimensional coordinates of the damage to complete the non-destructive detection and positioning of the hyperbolic glass curtain wall.

[0198] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described storage medium and each module can refer to the corresponding processes in the embodiments of the Lamb wave excitation and reception optimization method for non-destructive detection and positioning of hyperbolic glass curtain walls described in the above embodiments, and will not be elaborated here.

[0199] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An optimized method for Lamb wave excitation and reception in non-destructive testing and positioning of hyperbolic glass curtain walls, characterized in that, Including: Obtain the curtain wall parameter information of the hyperbolic glass curtain wall to be detected and located, including: obtaining the three-dimensional laser scanning image and visual image corresponding to the hyperbolic glass curtain wall; transforming the feature points corresponding to the three-dimensional laser scanning image and visual image to the same coordinate system based on the point cloud registration algorithm; performing surface reconstruction on the hyperbolic glass curtain wall according to the registered three-dimensional laser scanning image and visual image to obtain the curtain wall parameter information; the curtain wall parameter information at least includes geometric parameters, thickness parameters, material parameters and environmental parameters; Optimize the Lamb wave parameters corresponding to the glass curtain wall according to the curtain wall parameter information; the Lamb wave parameters at least include excitation frequency, waveform coefficient and excitation angle; the expression of the excitation frequency includes: ; Among them, represents the excitation frequency, represents the temperature compensation coefficient, is the thickness parameter, is the Young's modulus, is the Poisson's ratio, is the material density corresponding to the hyperbolic glass, is used to represent the effective stiffness under plane stress state, is used to represent the influence of Poisson's ratio on the three-dimensional strain of the hyperbolic glass curtain wall; the expression of the excitation angle includes: ; Among them, represents the excitation angle, and respectively represent the local slope of the curved surface corresponding to the hyperbolic glass curtain wall, represents the environmental compensation angle corresponding to the hyperbolic glass curtain wall, which is used to correct the wave velocity anisotropy caused by environmental factors, represents adjusting the excitation angle according to the local curvature of the hyperboloid corresponding to the hyperbolic glass curtain wall to ensure that the lamb wavefront always maintains the best incident angle with the normal of the curved surface of the hyperbolic glass curtain wall and avoid the scattering of lamb wave signals; Perform signal transmission and reception on the hyperbolic glass curtain wall according to the optimized Lamb wave parameters to obtain the damage reflection signal corresponding to the hyperbolic glass curtain wall; Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector; Obtain a neural network positioning model including hyperbolic geometric constraints, input the damage feature vector into the neural network positioning model, and output the damage three-dimensional coordinates to complete the non-destructive detection and positioning of the hyperbolic glass curtain wall.

2. The method according to claim 1, characterized in that, If the environmental temperature corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to subtract the first compensation angle, the first compensation angle is within the first compensation angle range, and the first compensation angle range is 0.05 to 0.15 rad; If the environmental humidity corresponding to the hyperbolic glass curtain wall increases, the environmental compensation angle needs to add the second compensation angle, the second compensation angle is within the second compensation angle range, and the second compensation angle range is 0.02 to 0.08 rad.

3. The method according to claim 1, characterized in that, The step of inputting the damage feature vector into the neural network positioning model and outputting the damage three-dimensional coordinates includes: Input the damage feature vector into the neural network positioning model, and the neural network positioning model generates geometric damage features through a three-dimensional convolution kernel and processes and generates signal damage features through a time-frequency convolution kernel; perform feature fusion according to the geometric damage features and signal damage features, and output the damage three-dimensional coordinates.

4. The method according to claim 1, wherein Before performing signal transmission and reception on the hyperbolic glass curtain wall according to the optimized Lamb wave parameters, it further includes: Obtain the lowest phase velocity, highest excitation frequency and maximum excitation angle corresponding to the Lamb wave; Adjust the spatial density of the array piezoelectric sensor for receiving the damage reflection signal according to the lowest phase velocity, highest excitation frequency and maximum excitation angle.

5. The method according to claim 4, characterized in that The expression corresponding to the spatial density includes: ; wherein, is the spatial density, is the lowest phase velocity, is the highest excitation frequency, is the maximum excitation angle.

6. The method according to claim 1, wherein The step of performing time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain a damage feature vector includes: Perform time-frequency domain decomposition on the damage reflection signal according to wavelet packet transform to obtain the signal energy attenuation coefficient, main frequency offset and wavelet packet node energy entropy; Generate the damage feature vector according to the signal energy attenuation coefficient, main frequency offset and wavelet packet node energy entropy.

7. The method according to claim 1, wherein After outputting the damage three-dimensional coordinates, it further includes: Generate a visual inspection atlas based on the three-dimensional coordinates of the damage and the curtain wall model corresponding to the hyperbolic glass curtain wall; the visual inspection atlas includes the unfolded hyperbolic surface of the hyperbolic glass curtain wall, the unfolded hyperbolic surface includes the damage projection corresponding to the three-dimensional coordinates of the damage, the three-dimensional rendering model corresponding to the hyperbolic glass curtain wall, the three-dimensional rendering model includes the defect mark corresponding to the three-dimensional coordinates of the damage, the stacked display diagram corresponding to the hyperbolic glass curtain wall, and the stacked display diagram includes the defect size and depth parameters.

Images