Convolutional neural network and single-channel carbon nanotube sensor-based damage positioning method and device for carbon fiber composite material

By using single-channel carbon nanotube sensors and convolutional neural networks in the CFRP structure, combining the VGG-16 model and the Gram angle summation field method, the complexity problem brought about by multi-channel data acquisition in the CFRP structure is solved, and the complexity problem is achieved. High-precision damage positioning and automated monitoring, suitable for composite material structures.

CN119026644AActive Publication Date: 2024-11-26TONGJI UNIV

Patent Information

Application Number
CN202411122731.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26
Estimated Expiration
2044-08-15

Smart Images

  • Figure CN119026644A_ABST
    Figure CN119026644A_ABST
Patent Text Reader

Abstract

The invention discloses a carbon fiber composite material damage positioning method and device based on a convolutional neural network and a single-channel carbon nanotube sensor. The method comprises the following steps: preparing the single-channel carbon nanotube sensor; preparing to obtain a carbon fiber composite material laminated plate for damage positioning data acquisition; equally dividing the tested area according to the coordinate system to form a plurality of grid coordinates; establishing a convolutional neural network model; taking the obtained data label as an input and output data set, and randomly dividing the input and output data set into a training set and a test set of a convolutional neural network model; training and verifying the convolutional neural network model by using a training set and a test set until the convolutional neural network model reaches convergence; and carrying out structural damage positioning by using the convolutional neural network model. According to the technical scheme provided by the invention, the problem of data complexity caused by multi-channel data acquisition is avoided, and end-to-end damage positioning of the carbon fiber reinforced matrix composite is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of structural damage location, and in particular to a damage location method and device for carbon fiber composite materials based on a convolutional neural network and a single-channel carbon nanotube sensor. Background Art

[0002] With the development trend of global carbon neutrality and energy efficiency policies, the market share of CFRP (Carbon Fibre-reinforced Polymer) has continued to increase in recent years. CFRP structures have the characteristics of high stiffness and light weight, and are increasingly used in rail transportation, aerospace, wind turbine blades and other fields. However, large composite structures are affected by loads, environment and other factors during service, which can easily cause structural failure and lead to safety accidents. Therefore, there is an increasing need for structural health monitoring technology (SHM) to monitor the health status of composite structures.

[0003] Traditional damage location detection methods include ultrasonic scanning, X-ray detection, and thermal imaging. However, these methods are difficult to use for real-time inspection and are limited by the detection cycle. Real-time monitoring technologies such as fiber Bragg gratings, piezoelectric ceramics, and acoustic emission overcome the shortcomings of offline monitoring technologies and have been widely studied in CFRP damage location. Researchers generally use multi-channel data acquisition schemes to carry out damage location research on CFRP. For example: Sikdar et al. used 8 acoustic emission sensors to build a monitoring network and classified the CFRP damage source based on the acoustic emission data through a convolutional neural network model; Jung et al. introduced four piezoelectric films into the CFRP interlayer. They performed discrete wavelet transformation on the impact signal collected in the impact test and converted it into image data for training and testing of the deep learning model. Finally, the trained model was used to predict the impact position; Alsaadi et al. solidified a polyimide film with 16 groups of electrodes on the surface of the CFRP structure. In the impact test, the resistance data of 16 positions were collected simultaneously to generate a 2D damage cloud map to predict the damage position. The above damage location methods have more or less the following problems: multi-channel data acquisition will increase the data dimension, increase the difficulty of data processing and the amount of calculation; the serpentine CNT sensor with concentration gradient can achieve damage location of CFRP structure through single-channel data acquisition. However, the monitoring data usually contains noise and nonlinear relationships, which are difficult to process using traditional mathematical models. Summary of the invention

[0004] The present invention provides a damage localization method and device for carbon fiber composite materials based on convolutional neural networks and single-channel carbon nanotube sensors. The damage localization of CFRP can be achieved only through single-channel data acquisition, thus avoiding the problem of data complexity caused by multi-channel data acquisition. In addition, end-to-end CFRP damage localization is achieved by combining with convolutional neural networks.

[0005] According to a first aspect of the present invention, the present invention provides a damage localization method for a carbon fiber composite material based on a convolutional neural network and a single-channel carbon nanotube sensor, comprising the following steps:

[0006] The carbon nanotube solution is sprayed onto the template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor;

[0007] The prepared single-channel carbon nanotube sensor is introduced into the middle interface of the carbon fiber composite material to prepare a carbon fiber composite laminate for damage location data collection;

[0008] Selecting a tested area of ​​the carbon fiber composite material laminate, establishing a coordinate system in the tested area, and equally dividing the tested area according to the coordinate system to form a plurality of grid coordinates;

[0009] Build a convolutional neural network model;

[0010] sequentially loading at least part of the plurality of grid coordinates, so as to obtain data labels for single-channel carbon nanotube sensor signals according to the loading position coordinates, using the obtained data labels as input and output data sets, and randomly dividing the input and output data sets into a training set and a test set of a convolutional neural network model;

[0011] Using the training set to train the convolutional neural network model, and using the test set to verify the trained convolutional neural network model until the convolutional neural network model reaches convergence;

[0012] The converged convolutional neural network model is used to locate structural damage and output the damage coordinates.

[0013] In addition to or as an alternative to one or more of the features disclosed above, the concentration of the carbon nanotube solution is 2-2.5% by gravity.

[0014] In addition to or as an alternative to one or more of the features disclosed above, the carbon nanotube solution is sprayed into the template according to a preset concentration gradient, and the carbon nanotube solution is sprayed into at least one of a bent shape, a circuitous shape, an S shape, a bow shape and a W shape.

[0015] In addition to or as an alternative to one or more of the features disclosed above, spraying the carbon nanotube solution into the template according to a preset concentration gradient includes:

[0016] Set the unit area of ​​concentration gradient change to 80-120mm 2 In each spraying process, a unit area is added from one end of the template along the template path, and this is repeated 3 to 5 times until the carbon nanotubes completely cover the template surface.

[0017] In addition to or as an alternative to one or more of the features disclosed above, the template is made of one of copper, aluminum, stainless steel, plastic and a composite material.

[0018] In addition to one or more of the features disclosed above, or as an alternative, after spraying, the template is immersed in an etching solution and etched for 6 to 10 hours, and finally washed and dried to obtain the single-channel carbon nanotube sensor with a concentration gradient.

[0019] In addition to or as an alternative to one or more of the features disclosed above, the ply of the carbon fiber composite laminate is [0 / 90 / 0 / 90 / 0 / CNT 1 / 2 ] S , where s means that the ply design is symmetrical; CNT means single-channel carbon nanotube sensor, CNT 1 / 2 It indicates that a single-channel carbon nanotube sensor is used as the middle layer of the carbon fiber composite material laminate; and insulating layers are laid on the upper and lower surfaces of the single-channel carbon nanotube sensor.

[0020] In addition to or instead of one or more of the features disclosed above, in the process of sequentially loading at least part of the plurality of grid coordinates, the loading rate of the indenter is 0.5 to 1.5 mm / min, and the displacement of the indenter is maintained for 1 to 3 minutes after the indenter is pressed down by 1 unit distance. The obtained one-dimensional resistance signal of the single-channel carbon nanotube sensor is preprocessed, and the Gram angle sum field method is used to encode the resistance data into a two-dimensional image for training and testing of the convolutional neural network model.

[0021] In addition to or as an alternative to one or more of the features disclosed above, the establishing of the convolutional neural network model comprises the following steps:

[0022] Step S1: Network initialization. The VGG-16 model is used as the network architecture, which contains 13 convolutional layers and 3 fully connected layers. The number of network input layer nodes n, the number of output layer nodes m, the learning efficiency η, and the activation function f are determined according to the input and output data sets; the convolutional layer weights W and the fully connected layer weights W are initialized. fc ; Initialize the convolutional layer and fully connected layer bias b;

[0023] Step S2: Perform a series of convolution operations on the input image, calculate the output of each convolution layer, and apply the ReLU excitation function. Let X be the input image, the weight of the convolution layer be W, the bias be b, the output of the hidden layer be H, and the ReLU excitation function be f. The convolution layer output calculation formula is as follows: H = f(W*X+b), where * represents the convolution operation;

[0024] Step S3: Flatten the final output of the convolutional layer into a one-dimensional vector. Let the flattened input vector be Z and the weight of the fully connected layer be W. fc , with a bias of b fc , the output of the fully connected layer is O, O = W fc □Z+b fc , the last layer outputs the predicted value O k ;

[0025] Step S4: Error calculation, output O according to network prediction k and the expected output Y k , calculate the network prediction error e k , using mean square error as the loss function,

[0026] Step S5: Weight update, based on the network prediction error e k Calculate the gradient and update the weights of the convolutional layer and the fully connected layer through the back-propagation algorithm.

[0027] Step S6: Threshold update, based on the error e k Update the bias items of the convolutional and fully connected layers,

[0028] Step S7: Determine whether the algorithm iteration is completed. If the iteration is not completed, re-execute step S2. If the iteration is completed, output the convolutional neural network prediction model.

[0029] In addition to or as an alternative to one or more features disclosed above, the training of the convolutional neural network model using the training set comprises the following steps:

[0030] Step T1: Randomly provide the input parameters of the training set samples to the input layer of the initialized convolutional neural network, and then forward the signal layer by layer until the output result is generated;

[0031] Step T2: Calculate the error by comparing the output result with the actual value, propagate the error back to the fully connected layer and convolutional layer, and update the weights and thresholds;

[0032] Step T3: Pass the error signal to the convolutional layer again, and update the weights between the convolutional layer and the fully connected layer;

[0033] Step T4: Repeat steps T1 to T3 until the sum of the training errors of the training set samples reaches a preset maximum number of iterations, and the training stops. At this time, the trained convolutional neural network model is obtained.

[0034] In addition to or as an alternative to one or more of the features disclosed above, the verifying the trained convolutional neural network model using the test set comprises the following steps:

[0035] Step T1: Keeping the parameters of the trained convolutional neural network model unchanged, each test sample in the test set is applied to the trained convolutional neural network model for verification;

[0036] Step T2: Calculate the test error and evaluate the generalization ability of the model based on the test error. Use the mean square error as the error metric.

[0037] In addition to or as an alternative to one or more features disclosed above, the sequentially loading at least part of the plurality of grid coordinates comprises:

[0038] At least part of the plurality of grid coordinates are loaded in sequence through a static indentation test, wherein the grid coordinates corresponding to the loading are the loading position coordinates.

[0039] According to a second aspect of the present invention, the present invention further provides a damage localization device for carbon fiber composite materials based on a convolutional neural network and a single-channel carbon nanotube sensor, comprising:

[0040] A sensor preparation unit, used for spraying a carbon nanotube solution onto a template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor;

[0041] A laminate preparation unit, used for introducing the prepared single-channel carbon nanotube sensor into the middle interface of the carbon fiber composite material, to prepare a carbon fiber composite laminate for damage location data collection;

[0042] A grid division unit is used to select a tested area of ​​the carbon fiber composite material laminate, establish a coordinate system in the tested area, and equally divide the tested area according to the coordinate system to form a plurality of grid coordinates;

[0043] A data grouping unit, for sequentially loading at least part of the plurality of grid coordinates through a static indentation experiment, so as to obtain data labels for single-channel carbon nanotube sensor signals according to the loading position coordinates, using the obtained data labels as input and output data sets, and randomly dividing the input and output data sets into a training set and a test set of a convolutional neural network model;

[0044] Neural network building unit, used to build convolutional neural network models;

[0045] A neural network training and verification unit, used to train the convolutional neural network model using the training set, and verify the trained convolutional neural network model using the test set until the convolutional neural network model reaches convergence;

[0046] The damage localization unit is used to locate structural damage using the converged convolutional neural network model and output the damage coordinates.

[0047] One of the above technical solutions has the following advantages or beneficial effects:

[0048] The present invention realizes damage location of CFRP through single-channel data acquisition, which effectively simplifies the complexity and hardware cost brought by traditional multi-channel data acquisition and highlights the simplicity of system design. On this basis, combined with the end-to-end learning ability of convolutional neural network (CNN), damage-related features are automatically extracted from the original data, avoiding the tediousness of manual feature extraction, and realizing the automation of the whole process from data input to damage location. This technology not only solves the balance between data complexity and positioning accuracy, but also demonstrates the innovative ability to maintain high-precision damage location under the premise of simplifying hardware design. In addition, due to the reduced hardware requirements and improved automation, this technology shows stronger scalability and adaptability in practical applications. It is not only suitable for CFRP structure monitoring, but also has the potential to be extended to other composite material structure monitoring, which further highlights the technical level and broad application prospects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The technical solutions and other beneficial effects of the present invention will be made apparent by describing in detail the specific embodiments of the present invention in conjunction with the accompanying drawings.

[0050] Figure 1 is a flow chart of preparing a serpentine CNT sensor according to an embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of sample preparation and experiment according to Example 1 of the present invention;

[0052] Figure 3 is a flow chart of CFRP damage location according to an embodiment of the present invention;

[0053] Figure 4 is a comparison between predicted coordinates and actual coordinates according to the first embodiment of the present invention;

[0054] Figure 5 It is a verification of the generalization ability of the prediction coordinates according to the first embodiment of the present invention;

[0055] Figure 6 is a flow chart of a damage localization method provided according to an embodiment of the present invention;

[0056] Figure 7 It is a virtual structure diagram of a damage localization device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The technical scheme in the embodiment of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0058] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein, unless otherwise specified, generally indicates that the associated objects before and after are in an "or" relationship.

[0059] For descriptive purposes, spatially relative terms such as "below," "beneath," "below," "above," "on," etc. may be used herein to describe the relationship of one element or feature illustrated in the accompanying drawings to another element or feature. Spatially relative terms are intended to cover different orientations of the device when in use, in operation, and / or in manufacture other than the orientation depicted in the accompanying drawings. For example, if the device in the accompanying drawings is turned over, elements described as being "below" or "below" other elements or features will be "above" the other elements or features. Therefore, the exemplary term "below" may include both above and below orientations. Moreover, the device may be oriented in other directions (e.g., rotated 90 degrees or in other orientations), and the spatially relative descriptors used herein are therefore interpreted accordingly.

[0060] Reference Figure 6 In one embodiment of the present invention, a method for locating damage of a carbon fiber composite material based on a convolutional neural network and a single-channel carbon nanotube sensor is disclosed, which may include the following steps:

[0061] Step S1, spraying a carbon nanotube solution onto a template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor;

[0062] Step S2, introducing the prepared single-channel carbon nanotube sensor into the middle interface of the carbon fiber composite material to prepare a carbon fiber composite laminate for damage location data acquisition;

[0063] Step S3, selecting a tested area of ​​the carbon fiber composite material laminate, establishing a coordinate system in the tested area, and equally dividing the tested area according to the coordinate system to form a plurality of grid coordinates;

[0064] Step S4, establishing a convolutional neural network model;

[0065] Step S5, sequentially loading at least part of the plurality of grid coordinates, labeling the acquired single-channel carbon nanotube sensor signals according to the loading position coordinates, using the acquired data labels as input and output data sets, and randomly dividing the input and output data sets into a training set and a test set of a convolutional neural network model;

[0066] Step S6, training the convolutional neural network model using the training set, and verifying the trained convolutional neural network model using the test set until the convolutional neural network model reaches convergence;

[0067] Step S7, using the converged convolutional neural network model to locate structural damage and output damage coordinates.

[0068] It can be understood that the order of step S4 and step S5 can be changed. Step S4 can be executed first and then step S5, or step S5 can be executed first and then step S4. The two steps can also be performed simultaneously. The specific execution order can be set according to actual conditions and is not limited here.

[0069] Furthermore, the concentration of the carbon nanotube solution is 2-2.5% in terms of gravity fraction. During the spraying process using the airbrush, this concentration range will not cause the airbrush to be blocked, and the spraying can be carried out smoothly.

[0070] Furthermore, in the step of spraying the carbon nanotube solution onto the template according to a preset concentration gradient, the carbon nanotube solution is sprayed into at least one of a bent shape, a circuitous shape, an S shape, a bow shape, and a W shape. Spraying the carbon nanotube solution into at least one of a bent shape, a circuitous shape, an S shape, a bow shape, and a W shape according to a preset concentration gradient can significantly enhance the sensitive capture capability of stress waves. These complex shapes increase the effective coverage area of ​​the material surface, enabling the sensor to more comprehensively capture and conduct stress waves in different directions, thereby improving the accuracy of damage location. The design of the non-linear shape enables the sensor to have multi-directional response capabilities, which is particularly prominent under complex stress fields. In addition, the circuitous and bent shapes improve the stability and consistency of the signal by dispersing the propagation path of the stress wave, further enhancing the positioning accuracy. More importantly, the flexible design of these shapes can be optimized and adjusted according to different CFRP structures and monitoring requirements to achieve customized sensor design, thereby improving the overall performance and adaptability of the sensor.

[0071] Furthermore, the step of spraying the carbon nanotube solution onto the template according to a preset concentration gradient includes:

[0072] Set the unit area of ​​concentration gradient change to 80-120mm 2 In each spraying process, a unit area is added from one end of the template along the template path, and this is repeated 3 to 5 times until the carbon nanotubes completely cover the template surface.

[0073] First, this method of gradually increasing the concentration ensures the uniform distribution of carbon nanotubes on the template surface, effectively reducing performance fluctuations caused by uneven concentration. Secondly, by increasing the unit area in each spraying and repeating the operation multiple times, a progressive concentration gradient structure can be formed on the template surface, making the sensor more sensitive to stress wave responses in different areas, thereby improving detection accuracy and reliability. In addition, the layer-by-layer progressive concentration setting can also enhance the overall structural stability of the sensor, ensure the adhesion and durability of the carbon nanotube coating, and thus extend the service life of the sensor. Overall, this setting method not only optimizes the performance of the sensor, but also improves its adaptability to complex stress fields.

[0074] Optionally, the template is made of one of copper, aluminum, stainless steel, plastic and a composite material.

[0075] Furthermore, after the spraying is completed, the template is immersed in an etching solution and etched for 6 to 10 hours, and finally washed and dried to obtain the single-channel carbon nanotube sensor with a concentration gradient.

[0076] Optionally, the ply structure of the carbon fiber composite laminate is [0 / 90 / 0 / 90 / 0 / CNT 1 / 2 ]S , where s means that the ply design is symmetrical; CNT means single-channel carbon nanotube sensor, CNT 1 / 2 It indicates that a single-channel carbon nanotube sensor is used as the middle layer of the carbon fiber composite material laminate; and insulating layers are laid on the upper and lower surfaces of the single-channel carbon nanotube sensor.

[0077] Optionally, in the process of loading at least part of the several grid coordinates in sequence, the loading rate of the pressure head is 0.5-1.5 mm / min, and the displacement of the pressure head is maintained for 1-3 minutes after it is pressed down by 1 unit distance. The one-dimensional resistance signal of the obtained single-channel carbon nanotube sensor is preprocessed, and the Gram angle sum field method is used to encode the resistance data into a two-dimensional image for training and testing of the convolutional neural network model.

[0078] Furthermore, the establishment of the convolutional neural network model includes the following steps:

[0079] Step T1: Network initialization. The VGG-16 model is used as the network architecture, which contains 13 convolutional layers and 3 fully connected layers. The number of network input layer nodes n, the number of output layer nodes m, the learning efficiency η, and the activation function f are determined according to the input and output data sets; the convolutional layer weights W and the fully connected layer weights W are initialized. fc ; Initialize the convolutional layer and fully connected layer bias b;

[0080] Among them, the VGG16 model is a deep convolutional neural network developed by the research team of Oxford University (Visual Geometry Group) in 2014. The VGG16 model is well suited for classification and positioning tasks; the convolutional layers of VGG16 all use 3×3 convolution kernels. This design is a notable feature of VGG16. A 3×3 convolution kernel contains the smallest unit of a pixel up, down, left, and right. Continuous layers of 3×3 convolution kernels can fit more complex features and increase the depth of the network; two 3×3 convolution kernels can replace a 5×5 convolution kernel, and three 3×3 convolution kernels can replace a 7×7 convolution kernel. In this way, a convolution layer with multiple small convolution kernels replaces a convolution layer with a larger convolution kernel. On the one hand, the number of parameters is reduced, and on the other hand, the number of nonlinearities is increased, the learning ability is better, and the expression ability of the network is also improved;

[0081] Step T2: Perform a series of convolution operations on the input image, calculate the output of each convolution layer, and apply the ReLU excitation function. Let X be the input image, the weight of the convolution layer is W, the bias is b, the output of the hidden layer is H, and the ReLU excitation function is f. The convolution layer output calculation formula is as follows: H = f(W*X+b), where * represents the convolution operation;

[0082] Step T3: Flatten the final output of the convolutional layer into a one-dimensional vector. Let the flattened input vector be Z and the weight of the fully connected layer be W. fc , with a bias of b fc , the output of the fully connected layer is O, O = W fc □Z+b fc , the last layer outputs the predicted value O k ;

[0083] Step T4: Error calculation, output O according to network prediction k and the expected output Y k , calculate the network prediction error e k , using mean square error as the loss function,

[0084] Step T5: Weight update, based on the network prediction error e k Calculate the gradient and update the weights of the convolutional layer and the fully connected layer through the back-propagation algorithm.

[0085] Step T6: Threshold update, based on the error e k Update the bias items of the convolutional and fully connected layers,

[0086]

[0087] Step T7: Determine whether the algorithm iteration is completed. If the iteration is not completed, re-execute step S2. If the iteration is completed, output the convolutional neural network prediction model.

[0088] Modifying the VGG16 model to predict coordinates through a regression layer and train and test on a picture dataset brings significant technical advantages. First, this modification enables the model to have a high-precision mapping capability directly from image features to spatial positions, enabling more accurate target positioning. By leveraging the powerful feature extraction capabilities of VGG16, the model not only performs well in classification tasks, but also directly outputs coordinate predictions through a regression layer, achieving efficient end-to-end learning and reducing intermediate steps and computational overhead. This structure makes the model more adaptable and can be extended to tasks such as pose estimation and key point detection, expanding its scope of application. In addition, the direct prediction of coordinates simplifies the post-processing steps, improves the real-time and response speed of the system, and enhances the generalization ability of the model, making it more stable and reliable in different scenarios. In summary, this modification improves the positioning accuracy, adaptability and performance of the model, making it more practical in a variety of applications.

[0089] Furthermore, the training of the convolutional neural network model using the training set comprises the following steps:

[0090] Step P1: Randomly provide the input parameters of the training set samples to the input layer of the initialized convolutional neural network, and then forward the signal layer by layer until the output result is generated;

[0091] Step P2: Calculate the error by comparing the output result with the actual value, propagate the error back to the fully connected layer and convolutional layer, and update the weights and thresholds;

[0092] Step P3: Pass the error signal to the convolutional layer again, and update the weights between the convolutional layer and the fully connected layer;

[0093] Step P4: Repeat steps T1 to T3 until the sum of the training errors of the training set samples reaches a preset maximum number of iterations, and the training stops. At this time, the trained convolutional neural network model is obtained.

[0094] Using training sets to train convolutional neural network models can bring many technical advantages. First, by continuously iterating and optimizing model parameters, the accuracy of feature extraction and the generalization ability of the model are improved, so that it can still perform well on unseen data. During the training process, the model gradually learns and extracts more representative high-dimensional features, enhancing recognition and positioning capabilities. In addition, through diversified training sets and regularization techniques, the model can avoid overfitting, improve robustness, and ensure stable performance in complex scenarios. The multi-layer structure of the convolutional neural network enables it to grasp complex nonlinear relationships and has higher flexibility and accuracy when handling delicate tasks. Finally, as the training data increases, the model is continuously optimized through adaptive learning, continuously improving its prediction accuracy and performance. In summary, this training process significantly improves the accuracy, generalization ability, and reliability of the model in practical applications.

[0095] Furthermore, the verification of the trained convolutional neural network model using the test set includes the following steps:

[0096] Step R1: Keeping the parameters of the trained convolutional neural network model unchanged, each test sample in the test set is applied to the trained convolutional neural network model for verification;

[0097] Step R2: Calculate the test error and evaluate the generalization ability of the model based on the test error. Use the mean square error as the error metric.

[0098] Through the above implementation, using the test set to verify the convolutional neural network model can bring the following technical benefits. First, through the verification of the test set, the performance of the model on unseen data can be comprehensively evaluated, and the generalization ability and prediction accuracy of the model can be accurately measured. Test set verification helps to discover overfitting problems that may occur in the model during the training process, thereby guiding the further optimization and adjustment of the model to ensure that the model not only performs well on the training set, but also maintains high accuracy in practical applications. In addition, through the feedback of the test set, model developers can identify the weaknesses of the model in different scenarios and conditions, and then perform targeted optimization to improve the robustness and reliability of the model. In general, using the test set to verify the convolutional neural network model can effectively improve the practicality and stability of the model, and lay a solid foundation for its application in complex real-world environments.

[0099] Further, the sequentially loading at least part of the plurality of grid coordinates comprises:

[0100] At least part of the plurality of grid coordinates are loaded in sequence through a static indentation test, wherein the grid coordinates corresponding to the loading are the loading position coordinates.

[0101] Reference Figure 7 The present application also discloses a damage location device for carbon fiber composite materials based on a convolutional neural network and a single-channel carbon nanotube sensor, comprising:

[0102] The sensor preparation unit 101 is used to spray the carbon nanotube solution onto the template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor;

[0103] A laminate preparation unit 102 is used to introduce the prepared single-channel carbon nanotube sensor into the middle interface of the carbon fiber composite material to prepare a carbon fiber composite laminate for damage location data collection;

[0104] A grid division unit 103 is used to select a tested area of ​​the carbon fiber composite material laminate, establish a coordinate system in the tested area, and equally divide the tested area according to the coordinate system to form a plurality of grid coordinates;

[0105] A data grouping unit 104 is used to sequentially load at least part of the plurality of grid coordinates through a static indentation experiment, so as to obtain data labels for the single-channel carbon nanotube sensor signals according to the loading position coordinates, use the obtained data labels as input and output data sets, and randomly divide the input and output data sets into a training set and a test set of a convolutional neural network model;

[0106] A neural network building unit 105, used to build a convolutional neural network model;

[0107] A neural network training and verification unit 106, configured to train the convolutional neural network model using the training set, and verify the trained convolutional neural network model using the test set, until the convolutional neural network model reaches convergence;

[0108] The damage localization unit 107 is used to locate structural damage using the converged convolutional neural network model and output damage coordinates.

[0109] The methods and approaches involved in each unit have been described in detail in the aforementioned damage location method and will not be repeated here.

[0110] The following describes in detail a method and device for predicting dynamic stress at a structural defect based on a BP neural network through several specific embodiments.

[0111] Embodiment 1:

[0112] Figure 1 Demonstrate the use of etched copper mesh template method to prepare serpentine CNT sensors with concentration gradient by spraying.

[0113] Specifically, the preparation method of the serpentine CNT sensor with concentration gradient includes:

[0114] Step F1, such as Figure 1 As shown in a, the copper mesh is cut into a 100mm*100mm serpentine structure by laser cutting, and its width and spacing are both 10mm. The serpentine copper mesh structure is then ultrasonically treated to remove surface contaminants and oxide layers;

[0115] Step F2, further diluting the CNTs (10 wt%) N,N-dimethylformamide (DMF) solution and the DMF solution in a ratio of 1:2 to prepare a CNTs dispersion that can be used for spraying;

[0116] Step F3, using an ultrasonic probe (Ymnl-1000Y, Nanjing Emanuel Instrument Equipment Co., Ltd.) to ultrasonically treat the CNTs dispersion at a constant temperature of 11°C, with a probe diameter of 15 mm, a power of 80%, a working time of 3 s, a pause time of 5 s, and a total dispersion time of 20 min;

[0117] Step F4, such as Figure 1 As shown in b, a spray brush is used to spray the CNTs dispersion onto the surface of the serpentine copper mesh structure. The entire spraying process is carried out on an electric heating plate with a temperature set at 90°C to accelerate the volatilization of the DMF solution.

[0118] Step F5: In order to achieve a concentration gradient effect on CNT, the unit area of ​​the concentration gradient change is set to 100 mm 2, in each spraying process, a unit area is sequentially increased from one end along the copper mesh path, and the process is repeated 3 times until the CNTs are fully deposited on the copper wire surface under an optical microscope; during the spraying process, the distance from the copper mesh to the spray brush is controlled (10 cm); in other embodiments, the spraying is repeated 4 or 5 times, which is not particularly limited, as long as the CNTs can be fully deposited on the copper wire surface;

[0119] Step F6, such as Figure 1 As shown in c, after the spraying is completed, the copper mesh is etched with a dilute nitric acid solution, and a serpentine CNT sensor with a concentration gradient is obtained after drying. The drying process is carried out in an air drying oven at 65°C;

[0120] Step F7, introducing the prepared serpentine CNT sensor into the interlayer of the CFRP structure to prepare a specimen for damage location research.

[0121] Furthermore, the preparation method of the experimental specimen includes:

[0122] Step M1, such as Figure 2 As shown in a, the CFRP laminate is [0 / 90 / 0 / 90 / 0 / CNT 1 / 2 ]s, the size of the CFRP laminate is 110mm*110mm*2mm;

[0123] Step M2, the prepared serpentine CNT sensor is introduced into the middle of the ply to form a sensor network. In order to insulate the serpentine CNT sensor introduced into the CFRP from the CFRP, a layer of epoxy resin film with a thickness of 20 μm is laid on the upper and lower surfaces of the serpentine CNT sensor;

[0124] Step M3, copper tapes are bonded as electrodes at both ends of the serpentine CNT sensor for resistance measurement, and conductive silver paste is used to minimize contact resistance;

[0125] Step M4, preparing the laminated prepreg into a CFRP laminate by a hot press, setting the hot press pressure to 1 MPa, maintaining at 90°C for 30 minutes, then raising the temperature to 120°C and maintaining for 90 minutes, and finally cooling to room temperature at a rate of 1°C per minute;

[0126] Step M5, such as Figure 2 As shown in b, a tested area of ​​CFRP is selected, a coordinate system xoy is established in the tested area, and the tested area is equally divided according to the coordinate system xoy, with a grid coordinate spacing of 10 mm;

[0127] Step M6, such as Figure 2As shown in Fig. BC, nine coordinate points (1,0), (1,4), (1,8), (5,0), (5,4), (5,8), (8,0), (8,4), (8,8) were selected to carry out static indentation experiments in sequence. In the static indentation experiments, the loading rate of the indenter was 1 mm / min. After the indenter was pressed down by 1 mm, the displacement was maintained for 2 min. The resistance signal of the serpentine CNT sensor was collected by the Keithley digital source meter.

[0128] Step M7, such as Figure 3 As shown in ab, the resistance signal of the obtained serpentine CNT sensor is preprocessed, and the resistance signal is encoded into a two-dimensional image every 3 seconds by the Gramian summation angular field (GASF) encoding method, and the data set label is the grid coordinate corresponding to the indenter loading.

[0129] Step M8, divide these images into data according to 7:3 and use them as input of training set and test set respectively for training and testing of convolutional neural network model.

[0130] Furthermore, the training of the convolutional neural network model using the training set comprises the following steps:

[0131] Step N1, use Figure 3 The two-dimensional image dataset obtained in ab is used as input data ( Figure 2 c), image dataset (input feature X d ) is composed of the convolution kernel (W P ) is convolved and activated by ReLU to obtain an output (Y P ), which is halved to 112*112*64 after maximum pooling. The two-dimensional image is convolved, ReLU activated and pooled, and the dimension is finally converted from 112*112*128 to 7*7*512 (see Figure 3 d) The features extracted from the 2D image are represented as flat vectors and the size is converted from 1*1*4096 to 1*1*1000 after the fully connected layer. Figure 3 As shown in Figure 5, the output value of a fully connected layer is finally transmitted to the regression layer to predict the coordinates (x, y) of the center of the damaged area.

[0132] Step N2, using the mean absolute error to evaluate the positioning accuracy of the model.

[0133] Where m is the number of samples, y i is the distance between the actual coordinate and the origin, is the distance between the predicted coordinates and the origin.

[0134] Step N3, Figure 4A comparison of the predicted positions of the selected 8 points (except point (8, 8)) between ultrasound scanning and the CNN model is given, with a mean absolute error of less than 0.52 mm.

[0135] Step N4, input the untrained point (8, 8) coordinate point data into the established CNN model to evaluate its generalization ability. Figure 5 ac shows that at Δt2, Δt 27 and Δt 60 The positioning situation at three moments, MAE is as follows Figure 5 d, they are 5.09mm, 5.51mm and 5.23mm respectively, and the average MAE is less than 5.5mm. Figure 5 ad showed that the CNN model can well learn the features of 2D images from large-scale datasets and exhibit good generalization ability, thus enabling the prediction of new damage locations.

[0136] The technical solution of this application has the following advantages:

[0137] 1. The sensor pattern of the present application is designable, and the sensor size can be individually designed according to the actual application requirements.

[0138] 2. Traditional CFRP damage location methods usually rely on multi-channel data acquisition, which will increase the complexity of data processing and hardware costs. Through single-channel data acquisition, the present invention significantly reduces the complexity and cost of data processing while maintaining accurate damage location. This advantage reflects the technical innovation of reducing system complexity while still maintaining performance.

[0139] 3. While reducing the number of data channels, the present invention combines the application of CNN to extract sufficient information through single-channel data to achieve high-precision damage positioning. In this way, the present invention solves the contradiction between data complexity and positioning accuracy, and demonstrates the innovative point of being able to achieve efficient and accurate positioning under the premise of simplifying hardware design.

[0140] The above description is only a partial implementation of the embodiments of the present invention and does not impose any form of limitation on the application. The protection scope of the embodiments of the present invention is not limited to this. Any simple modifications, equivalent changes and modifications that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the embodiments of the present invention should be covered within the protection scope of the embodiments of the present invention.

Claims

1. A damage location method for carbon fiber composite materials based on convolutional neural network and single-channel carbon nanotube sensor, characterized in that: The following steps are involved: The carbon nanotube solution is sprayed onto the template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor; The prepared single-channel carbon nanotube sensor is introduced into the middle interface of the carbon fiber composite material to prepare a carbon fiber composite laminate for damage location data collection; Selecting a tested area of ​​the carbon fiber composite material laminate, establishing a coordinate system in the tested area, and equally dividing the tested area according to the coordinate system to form a plurality of grid coordinates; Build a convolutional neural network model; sequentially loading at least part of the plurality of grid coordinates, so as to obtain data labels for single-channel carbon nanotube sensor signals according to the loading position coordinates, using the obtained data labels as input and output data sets, and randomly dividing the input and output data sets into a training set and a test set of a convolutional neural network model; Using the training set to train the convolutional neural network model, and using the test set to verify the trained convolutional neural network model until the convolutional neural network model reaches convergence; The converged convolutional neural network model is used to locate structural damage and output the damage coordinates.

2. The damage localization method according to claim 1, characterized in that: Calculated by gravity fraction, the concentration of the carbon nanotube solution is 2-2.5%.

3. The damage localization method according to claim 1, characterized in that: The carbon nanotube solution is sprayed into the template according to a preset concentration gradient, and the carbon nanotube solution is sprayed into at least one of a bent shape, a circuitous shape, an S shape, a bow shape and a W shape.

4. The damage localization method according to claim 3, characterized in that: The step of spraying the carbon nanotube solution into the template according to a preset concentration gradient comprises: Set the unit area of ​​concentration gradient change to 80-120mm 2 In each spraying process, a unit area is added from one end of the template along the template path, and this is repeated 3 to 5 times until the carbon nanotubes completely cover the template surface.

5. The damage localization method according to claim 4, characterized in that: The material of the template is one of copper, aluminum, stainless steel, plastic and composite material.

6. The damage localization method according to claim 4, characterized in that: After the spraying is completed, the template is immersed in an etching solution and etched for 6 to 10 hours. Finally, the single-channel carbon nanotube sensor with a concentration gradient is obtained by washing and drying.

7. The damage localization method according to claim 1, characterized in that: The ply of the carbon fiber composite laminate is [0 / 90 / 0 / 90 / 0 / CNT 1 / 2 ] S , where s means that the ply design is symmetrical; CNT means single-channel carbon nanotube sensor, CNT 1 / 2 It indicates that a single-channel carbon nanotube sensor is used as the middle layer of the carbon fiber composite material laminate; and insulating layers are laid on the upper and lower surfaces of the single-channel carbon nanotube sensor.

8. The damage localization method according to claim 1, characterized in that: In the process of loading at least part of the several grid coordinates in sequence, the loading rate of the indenter is 0.5-1.5 mm / min. After the indenter is pressed down by 1 unit distance, the displacement is maintained for 1-3 minutes. The one-dimensional resistance signal of the obtained single-channel carbon nanotube sensor is preprocessed, and the Gram angle sum field method is used to encode the resistance data into a two-dimensional image for training and testing of the convolutional neural network model.

9. The damage localization method according to claim 1, characterized in that: The establishment of the convolutional neural network model includes the following steps: Step S1: Network initialization. The VGG-16 model is used as the network architecture, which contains 13 convolutional layers and 3 fully connected layers. The number of network input layer nodes n, the number of output layer nodes m, the learning efficiency η, and the activation function f are determined according to the input and output data sets; the convolutional layer weights W and the fully connected layer weights W are initialized. fc ; Initialize the convolutional layer and fully connected layer bias b; Step S2: Perform a series of convolution operations on the input image, calculate the output of each convolution layer, and apply the ReLU excitation function. Let X be the input image, the weight of the convolution layer be W, the bias be b, the output of the hidden layer be H, and the ReLU excitation function be f. The convolution layer output calculation formula is as follows: H = f(W*X+b), where * represents the convolution operation; Step S3: Flatten the final output of the convolutional layer into a one-dimensional vector. Let the flattened input vector be Z and the weight of the fully connected layer be W. fc , with a bias of b fc , the output of the fully connected layer is O, The last layer outputs the predicted value O k ; Step S4: Error calculation, output O according to network prediction k and the expected output Y k , calculate the network prediction error e k , using mean square error as the loss function, Step S5: Weight update, based on the network prediction error e k Calculate the gradient and update the weights of the convolutional layer and the fully connected layer through the back-propagation algorithm. Step S6: Threshold update, based on the error e k Update the bias items of the convolutional and fully connected layers, Step S7: Determine whether the algorithm iteration is completed. If the iteration is not completed, re-execute step S2. If the iteration is completed, output the convolutional neural network prediction model.

10. The damage localization method according to claim 1, characterized in that: The step of training the convolutional neural network model using the training set comprises the following steps: Step T1: Randomly provide the input parameters of the training set samples to the input layer of the initialized convolutional neural network, and then forward the signal layer by layer until the output result is generated; Step T2: Calculate the error by comparing the output result with the actual value, propagate the error back to the fully connected layer and convolutional layer, and update the weights and thresholds; Step T3: Pass the error signal to the convolutional layer again, and update the weights between the convolutional layer and the fully connected layer; Step T4: Repeat steps T1 to T3 until the sum of the training errors of the training set samples reaches a preset maximum number of iterations, and the training stops. At this time, the trained convolutional neural network model is obtained.

11. The damage localization method according to claim 1, characterized in that: The method of verifying the trained convolutional neural network model using the test set comprises the following steps: Step T1: Keeping the parameters of the trained convolutional neural network model unchanged, each test sample in the test set is applied to the trained convolutional neural network model for verification; Step T2: Calculate the test error and evaluate the generalization ability of the model based on the test error. Use the mean square error as the error metric.

12. The damage localization method according to claim 1, characterized in that: The sequentially loading at least part of the plurality of grid coordinates comprises: At least part of the plurality of grid coordinates are loaded in sequence through a static indentation test, wherein the grid coordinates corresponding to the loading are the loading position coordinates.

13. A damage location device for carbon fiber composite materials based on convolutional neural network and single-channel carbon nanotube sensor, characterized in that: include: A sensor preparation unit, used for spraying a carbon nanotube solution onto a template according to a preset concentration gradient to prepare a single-channel carbon nanotube sensor; A laminate preparation unit, used for introducing the prepared single-channel carbon nanotube sensor into the middle interface of the carbon fiber composite material, to prepare a carbon fiber composite laminate for damage location data collection; A grid division unit is used to select a tested area of ​​the carbon fiber composite material laminate, establish a coordinate system in the tested area, and equally divide the tested area according to the coordinate system to form a plurality of grid coordinates; A data grouping unit, for sequentially loading at least part of the plurality of grid coordinates through a static indentation experiment, so as to obtain data labels for single-channel carbon nanotube sensor signals according to the loading position coordinates, using the obtained data labels as input and output data sets, and randomly dividing the input and output data sets into a training set and a test set of a convolutional neural network model; Neural network building unit, used to build convolutional neural network models; A neural network training and verification unit, used to train the convolutional neural network model using the training set, and verify the trained convolutional neural network model using the test set until the convolutional neural network model reaches convergence; The damage localization unit is used to locate structural damage using the converged convolutional neural network model and output the damage coordinates.

Citation Information

Patent Citations

  • Fatigue damage diagnosis method for carbon fiber reinforced matrix composite structure

    CN110389176A

  • Composite material structure damage quantitative monitoring method and system

    CN111307944A

  • Fiber reinforced pressure vessel and damage monitoring method based on same

    CN112834575A

  • Impact positioning and energy detection method and system based on convolutional neural network

    CN115458088A

  • Composite material-concrete interface monitoring method based on carbon nanotube filling interface

    CN116165251A

Cited By

  • Non-inductive operation quality tracing method in glass fiber industry

    CN119619234A