Structural damage grading identification method and system based on deep learning classification algorithm

Abstract

The invention discloses a structural damage grading identification method and system based on a deep learning classification algorithm, and relates to the technical field of structural health monitoring, and the method comprises the following steps: carrying out the preprocessing and enhancement of structural damage image data in a first-stage data set, and forming a second-stage data set; retaining the structure damage image with the optimal quality as a third-level data set; taking the category with the maximum classification probability value as the damage type of the damaged image block; and splicing the non-damaged image blocks and the marked damaged image blocks to obtain a final identification result. According to the method, a multi-level structure damage identification function is realized based on a deep learning classification algorithm, and compared with a traditional single-layer model or other existing detection models, the deep neural network model has the characteristic of gradually refining detection and identification through modular design; the method has the structural damage self-adaptive identification capability capable of automatically identifying various damage types, positions and degrees of the structure.

Description

Technical Field

[0001] The present invention relates to the technical field of structural health monitoring, and in particular to a structural damage classification identification method and system based on a deep learning classification algorithm. Background Art

[0002] With the continuous expansion of the scale and complexity of modern engineering structures, structural health monitoring has become one of the key means to ensure structural safety and extend service life. In the fields of civil engineering, aerospace, marine engineering, etc., the demand for structural health monitoring systems is increasing. Traditional structural damage identification technology mainly relies on manual detection, analysis based on vibration signals or simple image processing methods. Although these methods can identify structural damage to a certain extent, they often have disadvantages such as low recognition efficiency, long detection cycle, insufficient ability to distinguish damage types, and results are easily affected by environmental noise.

[0003] Manual inspection usually requires professionals to use portable equipment or visual inspection, which is not only time-consuming and laborious, but also the inspection results largely rely on the experience and subjective judgment of the inspectors, making it difficult to ensure the comprehensiveness and consistency of the inspection. Structural damage detection methods based on vibration signals usually judge the health status of the structure by analyzing the vibration response of the structure under external forces. However, vibration signals are easily disturbed by environmental noise and have limited ability to identify minor or complex damage. In addition, traditional image processing methods mainly rely on low-level image processing techniques such as edge detection and image segmentation. These methods often perform poorly in complex backgrounds and are difficult to accurately identify various types of structural damage.

[0004] In recent years, with the development of artificial intelligence technology, deep learning has demonstrated powerful image recognition and classification capabilities in the field of computer vision. This has brought new development opportunities for image recognition technology in structural health monitoring. Especially in the field of structural damage identification, deep learning technology can automatically extract the characteristics of structural damage by learning a large number of labeled samples, and accurately identify the type, location and degree of damage. Compared with traditional methods, damage identification technology based on deep learning can not only significantly improve the accuracy and robustness of identification, but also adapt to complex and changing environmental conditions.

[0005] However, the application of deep learning technology also faces some challenges. First, the performance of deep learning models is highly dependent on large-scale, high-quality training data sets, while the data on structural damage in actual engineering is often scarce and unbalanced. Second, the training of deep learning models requires a lot of computing resources, and the complexity of the model may lead to insufficient real-time performance. In addition, as the structural use environment changes, how to maintain the long-term effectiveness of the model is also an urgent problem to be solved.

[0006] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0007] In response to the problems in the related art, the present invention proposes a structural damage classification identification method and system based on a deep learning classification algorithm to overcome the above-mentioned technical problems existing in the existing related technology.

[0008] To this end, the specific technical solution adopted by the present invention is as follows:

[0009] According to one aspect of the present invention, a structural damage classification identification method based on a deep learning classification algorithm is provided, and the structural damage classification identification method comprises the following steps:

[0010] S1, obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set;

[0011] S2, using the screening technology integrated with Laplace transform algorithm to preliminarily screen the secondary data set, and retain the best quality structural damage images as the tertiary data set;

[0012] S3. Based on the deep learning classification algorithm and the three-level data set, a primary recognition model and a secondary recognition sub-model are constructed; the primary recognition model is used to perform preliminary recognition and classification on the three-level data set to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification;

[0013] S4. Based on the deep convolutional neural network, feature extraction and classification are performed on the results of the secondary recognition and classification. The category with the largest classification probability value is taken as the damage type of the damaged image block, and the damaged image block is marked; the undamaged image block is spliced ​​with the marked damaged image block to obtain the final recognition result.

[0014] Further, obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set includes the following steps:

[0015] S11, obtaining a structural damage image dataset as a primary dataset, and setting up a generative adversarial network;

[0016] Among them, the generative adversarial network includes a generator and a discriminator;

[0017] S12, inputting the primary data set as a training set into the generative adversarial network for training, using the generator to generate structural damage image data samples, and using the discriminator to distinguish them;

[0018] S13. After the training is completed, a generator is used to generate new structural damage image data samples, random noise is input, the new structural damage image data samples are added to the original primary data set, and the labels are adjusted to form a secondary data set.

[0019] Furthermore, the screening technology fused with the Laplace transform algorithm is used to preliminarily screen the secondary data set, and the best quality structural damage images are retained as the tertiary data set, which includes the following steps:

[0020] S21, using a Laplace transform algorithm to mark the structural damage image data whose clarity is lower than a preset threshold, and based on manual screening to confirm the marked structural damage image data, screen out images that are not related to structural damage, obtain the structural damage image with the best quality and retain it;

[0021] S22. Store the retained structural damage images with the best quality in a separate folder to form the final three-level dataset.

[0022] Furthermore, based on the deep learning classification algorithm and the three-level data set, a primary recognition model and a secondary recognition sub-model are constructed; the primary recognition model is used to perform preliminary recognition and classification on the three-level data set to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification, including the following steps:

[0023] S31. Select the ResNet-50 architecture as the basic architecture, label the three-level data sets as non-damaged and damaged, divide the best quality structural damage image into several image blocks, and use each image block as the input of the first-level recognition model;

[0024] S32, use ResNet-50 to process the input image blocks layer by layer to extract high-level structural features;

[0025] S34, using the fully connected layer to output the probability value of the second classification, and converting the output of the first-level recognition model into a probability distribution through the softmax activation function;

[0026] S35. Use the binary weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method;

[0027] S36, performing binary classification on all image blocks in the third-level data set based on the first-level recognition model, and screening out damage-free image blocks and damaged image blocks;

[0028] S37. Based on the damaged image blocks, a plurality of parallel secondary recognition sub-models are constructed, and different types of structural damage are classified into a plurality of damage levels through each secondary recognition sub-model.

[0029] Furthermore, ResNet-50 is used to process the input image blocks layer by layer to extract high-level structural features including:

[0030] The input image block passes through the convolution layer, pooling layer and residual block of ResNet-50 to extract low-level features layer by layer and gradually aggregate them into high-level structural features.

[0031] Furthermore, the formula for the binary weighted cross entropy loss function is:

[0032]

[0033] In the formula, Loss(1) represents the loss function value of the first-level recognition model;

[0034] N represents the total number of input image blocks for one training;

[0035] y i Represented as the true label of the i-th image block;

[0036] p i It is represented as the predicted category distribution probability of the first-level recognition model of the i-th image block.

[0037] Furthermore, based on the damaged image blocks, a plurality of parallel secondary recognition sub-models are constructed, and different types of structural damage are classified into a plurality of damage levels by each secondary recognition sub-model, including the following steps:

[0038] S371. Based on the damaged image block, construct several parallel secondary recognition sub-models, and select a ResNet-50 architecture for each secondary recognition sub-model;

[0039] S372. Classify and label different types of structural damage, and divide structural damage into several damage levels.

[0040] Furthermore, based on the deep convolutional neural network, feature extraction and classification are performed on the results of the secondary recognition and classification, and the category with the largest classification probability value is used as the damage type of the damaged image block, and the damaged image block is labeled; the damage-free image block is spliced ​​with the labeled damaged image block, and the final recognition result is obtained, including the following steps:

[0041] S41, performing sliding window scanning on the input damaged image block based on the convolution layer of the deep convolutional neural network, and extracting the damaged image block with local features using a number of filters;

[0042] S42, downsampling the feature damaged image block by using a maximum pooling layer to reduce the size of the feature damaged image block;

[0043] S43, after multi-layer convolution and pooling, the extracted high-level feature damaged image is flattened into a one-dimensional vector and passed to the fully connected layer, through which the feature damaged image is mapped to the final category space, and based on the Softmax activation function, the output value of the secondary recognition sub-model is converted into the probability distribution of various damage categories;

[0044] S44. Use a multi-classification weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method;

[0045] S45, based on the Softmax layer, output the probability distribution of various types of damage for each damaged image block, select the category with the highest probability value as the final damage type of the damaged image block, and make corresponding annotations;

[0046] S46, splicing the intact image block with the marked damaged image block to form a result image consistent with the specifications of the original image as the final recognition result.

[0047] Furthermore, the formula of the multi-classification weighted cross entropy loss function is:

[0048]

[0049] In the formula, Loss(2) represents the loss function value of each secondary recognition sub-model;

[0050] N represents the total number of input image blocks for one training;

[0051] M represents the total number of categories;

[0052] y i，c Represented as the true label of the i-th image block in the c-th category;

[0053] p i，c It is represented as the category distribution probability predicted by the secondary recognition sub-model of the i-th image block on the c-th category.

[0054] According to another aspect of the present invention, a structural damage classification identification system based on a deep learning classification algorithm is also provided, and the structural damage classification identification system comprises:

[0055] A data acquisition module is used to acquire a structural damage image data set as a primary data set, and preprocess and enhance the structural damage image data to form a secondary data set;

[0056] A data screening module, used to perform preliminary screening on the secondary data set using a preset screening technique, and retain the best quality structural damage images as the tertiary data set;

[0057] The data classification module is used to construct a primary recognition model and a secondary recognition sub-model using a deep learning classification algorithm and a three-level data set; the three-level data set is preliminarily recognized and classified based on the primary recognition model to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification;

[0058] The result recognition module is used to extract features and classify the results of secondary recognition and classification based on a deep convolutional neural network, take the category with the largest classification probability value as the damage type of the damaged image block, and mark the damaged image block; splice the non-damaged image block with the marked damaged image block to obtain the final recognition result.

[0059] The beneficial effects of the present invention are:

[0060] 1. The present invention realizes the multi-level structural damage identification function based on the deep learning classification algorithm. Compared with the traditional single-layer model or other existing detection models, its deep neural network model has the characteristics of gradually refined detection and identification through modular design, and has the ability to automatically identify various types, locations and degrees of structural damage adaptive identification. It realizes the automation and efficiency of structural damage detection, can automatically identify the damage type and severity, and allows the model to perform coarse-grained classification first, and then perform more accurate classification at a fine-grained level, which can not only reduce the consumption of computing resources, but also improve the accuracy of detection, thereby combining efficient screening and fine classification, making the entire system more modular, flexible and scalable, and also has the potential to further expand the scope of identifiable categories and databases by supplementing sub-networks.

[0061] 2. The present invention realizes efficient and accurate detection of structural surface damage by constructing a primary recognition model and multiple secondary recognition sub-models. It has the advantages of gradually refined detection, modular design, optimization of computing resources, low misjudgment rate, etc. It can greatly improve the accuracy and robustness of detection while ensuring the overall detection efficiency, realize efficient identification of various damage types, locations and degrees of engineering structures, and improve the accuracy and efficiency of detection.

[0062] 3. The present invention adopts hierarchical detection and recognition. First, the first-level recognition model quickly screens out areas where damage may exist, reducing interference from irrelevant areas. On this basis, multiple parallel second-level recognition sub-models further refine the classification and improve the recognition accuracy of different damage types and levels. Such a hierarchical structure significantly improves the overall detection accuracy, especially in complex and diverse damage scenarios, and can more accurately distinguish subtle damage types.

[0063] 4. The present invention decomposes the detection process into two stages, combines efficient screening and fine classification, can efficiently and accurately identify various types of structural damage, and has strong scalability and adaptability. It not only improves the accuracy and efficiency of detection, but also screens out damaged areas through simple and fast binary classification, and then conducts more detailed detection. It can significantly reduce the computational burden and optimize resource utilization, which will significantly improve the intelligence and automation level of structural health monitoring and provide important technical support for the safety management of engineering structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 is a flow chart of a structural damage classification identification method based on a deep learning classification algorithm according to an embodiment of the present invention;

[0066] Figure 2 is a principle block diagram of a structural damage classification identification system based on a deep learning classification algorithm according to an embodiment of the present invention;

[0067] Figure 3 It is the overall architecture of the primary recognition model and the secondary recognition sub-model according to the embodiment of the present invention;

[0068] Figure 4 is a workflow diagram of a primary recognition model and a secondary recognition sub-model according to an embodiment of the present invention;

[0069] Figure 5 is a schematic diagram illustrating the scalability of a primary recognition model and a secondary recognition sub-model according to an embodiment of the present invention;

[0070] Figure 6 It is a schematic diagram of the result output of the primary recognition model and the secondary recognition sub-model according to an embodiment of the present invention.

[0071] In the figure:

[0072] 1. Data acquisition module; 2. Data screening module; 3. Data classification module; 4. Result recognition module. DETAILED DESCRIPTION

[0073] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0074] According to an embodiment of the present invention, a method and system for structural damage classification identification based on a deep learning classification algorithm are provided.

[0075] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the structural damage classification identification method based on the deep learning classification algorithm according to an embodiment of the present invention, the structural damage classification identification method includes the following steps:

[0076] S1, obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set;

[0077] It should be explained that training data sets are prepared according to task requirements, and a large amount of structural damage image data is collected through various channels, including but not limited to cracks, corrosion, material fatigue, deformation, spalling, connection failure and other damage types. These data sets come from various engineering structures, such as buildings, bridges, mechanical equipment, etc., covering different material types and damage degrees, forming a primary data set. Data preprocessing and data enhancement are performed on the image data in the primary data set, where data enhancement refers to the processing or transformation of the existing data set, including the generation of new data samples through geometric transformation or generative neural network, in order to increase the diversity of the data, thereby improving the generalization ability of the machine learning model, and forming a secondary data set after data enhancement.

[0078] It needs to be explained that in data enhancement, classical data enhancement methods (i.e., geometric transformation) and generative (i.e., generative neural network) data enhancement methods are used to increase data diversity. Classic data enhancement methods include image scaling, cropping, grayscale adjustment, rotation, translation, flipping, color adjustment and other operations, while generative data enhancement methods use deep learning technologies such as generative adversarial networks to generate new structural damage image samples to enrich the representation of the data set.

[0079] It should be explained that geometric transformation mainly transforms existing data (usually image data) by rotation, scaling, translation, shearing, flipping, etc. to generate more data samples. Through these transformations, although the data samples have changed, their basic semantic features are still maintained. The implementation steps include:

[0080] Step 1: Data preparation: Prepare an existing dataset, usually image data, but it can also be other types of data.

[0081] Step 2: Select the geometric transformation method: Select the appropriate geometric transformation method, such as rotation, scaling, translation, flipping, etc. You can use one method alone or combine multiple methods.

[0082] 1) Rotation: Randomly rotate the image within a certain range, such as ±30 degrees.

[0083] 2) Scaling: Randomly scale the image within a certain range, such as enlarging or reducing the image to 0.8 or 1.2 times the original image.

[0084] 3) Translation: Randomly translate the image, moving it horizontally or vertically.

[0085] 4) Flip: Flip the image horizontally or vertically.

[0086] 5) Shear: Apply a shear transformation to the image.

[0087] Step 3: Apply transformation: Use programming tools (such as Python's opencv library, PIL library, and imgaug library) to transform the data samples one by one to generate new data samples.

[0088] Step 4: Save and expand the data set: Add the newly generated samples to the original data set and label the new data.

[0089] Step 5: Generate new data samples: After training is completed, use the generator to generate new data samples. Input random noise, and the generator will generate samples that conform to the distribution of the original data. Add the newly generated data to the original data set and adjust the labels appropriately.

[0090] S2, using the screening technology integrated with Laplace transform algorithm to preliminarily screen the secondary data set, and retain the best quality structural damage images as the tertiary data set;

[0091] It should be explained that the image data in the secondary dataset is further manually screened to remove data of poor quality or data that cannot correctly reflect structural damage generated during the data enhancement process, and only retain image data containing structural damage to ensure the purity and relevance of the dataset, forming a screened tertiary dataset, which is used for training deep learning models (i.e., the primary recognition model and the secondary recognition sub-model). The tertiary data is divided into a training dataset and a verification dataset for deep learning model training in a ratio of 8:2.

[0092] It should be explained that the image data in the secondary dataset is further manually screened to remove the data with poor quality or that cannot correctly reflect the structural damage generated during the data enhancement process, and only retain the image data containing structural damage to ensure the purity and relevance of the dataset. The screened tertiary dataset includes:

[0093] Removing low-quality images: During the data augmentation process, some images of poor quality may be generated, such as blurred, distorted, or noisy images, which may not accurately reflect structural damage. The goal of screening is to remove these low-quality samples.

[0094] Ensure accurate reflection of structural damage: retain images that correctly reflect structural damage and remove samples that do not contain damage or have unclear damage to ensure the relevance of the dataset.

[0095] Improve the purity of the dataset: The images finally retained should be highly relevant to the task objective (structural damage detection), avoid interference from irrelevant samples, and improve the overall quality of the three-level dataset.

[0096] The specific screening steps include:

[0097] Step 1. Preliminary inspection and filtering: First, a comprehensive preliminary inspection of the secondary dataset is performed, and images are filtered using a combination of automated detection and manual screening.

[0098] Clarity detection: Use automated tools to detect image clarity and remove blurry or poor quality images. Laplace transform or other image gradient-based algorithms can be used to automatically mark images with clarity below a preset threshold.

[0099] Step 2: Manual screening: The goal of manual screening is to filter out images that are not related to structural damage through manual observation, and focus on retaining images that reflect damage.

[0100] Manual image inspection: Manually observe each image, focusing on checking whether there are obvious structural damage features in the image, such as cracks, deformation, breakage, etc.

[0101] Step 3: Delete images without damage or misclassified images: After manual screening, delete images without obvious structural damage. These images may be erroneous samples caused by data augmentation or do not meet the requirements of the damage identification task.

[0102] Step 4: Form a tertiary dataset: Save the retained high-quality images as a tertiary dataset and store these images in a separate folder.

[0103] S3. Based on the deep learning classification algorithm and the three-level data set, a primary recognition model and a secondary recognition sub-model are constructed; the primary recognition model is used to perform preliminary recognition and classification on the three-level data set to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification;

[0104] It should be explained that building a first-level recognition model includes:

[0105] 1) Model architecture selection: Select the ResNet-50 architecture. ResNet-50 is a model based on residual networks. It solves the gradient vanishing problem of deep networks through skip connections. It can effectively extract deep features of images.

[0106] 2) Data preparation: Prepare a binary classification dataset, labeled as “no damage” and “damaged”. The dataset can include actual image data and increase data diversity after image enhancement (such as rotation, scaling, flipping).

[0107] 3) Model input: The input image is divided into several small images (image blocks), each of which is used as the input of the model. The input size is generally fixed, such as 224×224 pixels.

[0108] 4) ResNet-50 hierarchical structure: The input image passes through 50 layers of residual blocks of ResNet-50 to extract image features layer by layer. As the network deepens, the model can extract high-level features of the image and distinguish whether there is structural damage in the image.

[0109] 5) Classification layer and activation function: The last layer is a fully connected layer, which outputs the probability values ​​of two categories (no damage or damage). The softmax activation function is used to convert the output results into probability distribution for binary classification.

[0110] 6) Loss function: The cross entropy loss function (i.e., binary weighted cross entropy loss function) is used to measure the difference between the prediction results of the first-level recognition model and the true label.

[0111] 7) Model optimization: Use back-propagation and gradient descent methods (such as Adam or SGD optimizer) to update the model weights, reduce the loss value, and gradually improve the classification accuracy of the first-level recognition model.

[0112] It should be explained that the damaged image block is input into the secondary recognition sub-model for secondary recognition and classification, including:

[0113] Step 1: Build the sub-model architecture: Each sub-model uses the ResNet-50 architecture, but the final fully connected layer outputs are different, corresponding to different types of damage and their fine-grained classification.

[0114] For example, the output of the crack identification sub-model is 3 categories (primary cracks, secondary cracks, tertiary cracks), and the output of the concrete spalling identification sub-model is also 3 categories (primary spalling, secondary spalling, tertiary spalling).

[0115] Step 2: Data preparation: Preprocess the image blocks that the primary recognition model judges as "damaged" to ensure that they are of the same size (such as 224×224 pixels), and pass them to the corresponding sub-model. The training data set of each sub-model should include different fine-grained classification annotations for the type of damage. For example, the data set of the crack recognition model needs to be annotated as primary cracks, secondary cracks, and tertiary cracks.

[0116] Step 3: Train sub-models: Each sub-model is trained on its corresponding damage type dataset, and the model weights are optimized using the cross entropy loss function and optimizer.

[0117] Step 4: Secondary recognition and prediction: When the primary recognition model determines that a certain area is damaged, the image block will be passed to the corresponding sub-model for secondary recognition.

[0118] For example, when the crack recognition model receives a “damaged” image patch, it performs fine-grained classification on the image patch and outputs the crack level (such as primary crack, secondary crack, or tertiary crack).

[0119] Step 5: Parallel processing of multiple sub-models: Each sub-model works in parallel, and each sub-model is responsible for processing different types of damage. For areas that are judged as "damaged" by the first-level recognition model, the image blocks will be sent to the corresponding sub-model according to the damage type. In each sub-model, similar fine-grained classification processing is performed.

[0120] Step 6: Result summary: Finally, the fine-grained classification results of each sub-model are summarized and displayed on the original image as the final result output.

[0121] Specifically, Figure 6 As shown in the figure, further subdivision means that after the first-level recognition model identifies the "damaged" image blocks, the second-level recognition sub-model will classify these damaged areas in more detail. The subdivision process is to further classify a certain type of damage (such as cracks, concrete spalling, exposed steel bars, etc.) into different levels, such as first-level damage, second-level damage, and third-level damage. The purpose of subdivision is to more accurately describe the degree or nature of the damage so that more specific treatment measures can be taken. Including:

[0122] Step 1: Define segmentation criteria:

[0123] First, clarify the subdivision criteria for each type of injury. For example:

[0124] Crack subdivision criteria:

[0125] Level 1 crack: crack width is less than 1 mm.

[0126] Secondary cracks: Crack width is between 1-3 mm.

[0127] Level 3 cracks: crack width is greater than 3 mm.

[0128] Concrete spalling subdivision standards:

[0129] Primary spalling: The spalling area is small and the impact is small.

[0130] Secondary spalling: The spalling area is medium and may affect the structural surface.

[0131] Level 3 spalling: The spalling area is large, affecting the structural performance.

[0132] These criteria need to be derived from experience, industry standards, or engineering studies and provide a clear basis for the classification of models.

[0133] Step 2: Data annotation:

[0134] Segmentation dataset: Prepare damaged images and segment and annotate each image according to the damage standard. For the crack category dataset, it needs to be annotated as "primary crack", "secondary crack" or "tertiary crack"; for the concrete spalling category, it needs to be annotated with different spalling levels.

[0135] Data augmentation: To improve the diversity of the dataset, data augmentation methods (such as rotation, scaling, and flipping) can help generate more damage image samples at different angles and positions, allowing the model to learn more fine-grained features.

[0136] It should be explained that the overall structure of the deep learning model designed for the classification algorithm based on deep learning mainly includes a primary recognition model and multiple parallel secondary recognition sub-models. Among them, the input data of the primary recognition model is first processed by the primary recognition model. The main task of the primary recognition model is to perform preliminary analysis and recognition of the input data, and only classify the input data into two categories (no damage or damage), quickly exclude the undamaged area, and do not perform subsequent processing on the image blocks judged to be undamaged and save them in the final result. Only the areas judged to be damaged enter the secondary recognition sub-model.

[0137] Specifically, the specific implementation steps of the secondary recognition model include:

[0138] Step 1: Data preprocessing: For image blocks judged as "damaged" from the first-level recognition model, preprocessing is required to adapt to the input of the second-level recognition model.

[0139] Resize image: Resize the input image to a fixed size (e.g. 224×224 pixels).

[0140] Normalize image: Normalize the image.

[0141] Step 2: Build a secondary recognition model: The secondary recognition model uses ResNet-50 as the basic architecture and modifies its final output layer according to the specific task to adapt to the fine-grained classification task.

[0142] Step 3. Define the loss function and optimizer: The secondary recognition model uses the cross entropy loss function to calculate the difference between the model prediction and the actual label, and the optimizer uses Adam or SGD to adjust the model weights.

[0143] Step 4: Model training: By training on a dataset labeled with fine-grained categories, the secondary recognition model can gradually learn and accurately classify different degrees of damage.

[0144] Step 5: Model evaluation and prediction: After training is completed, use the model for prediction. Input the image block that is judged as "damaged" by the first-level recognition model, and the second-level recognition model will output a fine-grained damage classification result.

[0145] Step 6: Result summary and subsequent processing: After the secondary recognition model outputs the fine-grained damage classification results, the classification results are marked on the original image as the final result output.

[0146] It needs to be explained that Figure 3 As shown in the figure, the first-level recognition model is a binary classification deep learning model, which classifies image blocks as undamaged or damaged, and the first-level recognition model uses a binary classification weighted cross entropy loss function for convergence calculation. The image blocks judged as undamaged by the first-level recognition model are not processed, and the original image is saved until the final result is output. The image blocks judged as damaged by the first-level recognition model are further input into multiple parallel second-level recognition sub-models for refined classification and recognition. Among them, the second-level recognition sub-model includes multiple parallel sub-models, each of which performs fine-grained classification for different types of damage, processes the output results of the first-level recognition model, and each sub-model performs secondary recognition on the areas judged as damaged in the first-level recognition model, and judges the possibility that the damage belongs to the corresponding damage category of each sub-model.

[0147] For example, Figure 4As shown: Secondary identification sub-model #1 corresponds to crack category: it processes the damage of the first category and further subdivides it into primary cracks, secondary cracks and tertiary cracks, and outputs classification result #1.

[0148] Secondary identification sub-model #2 corresponds to the concrete spalling category: it processes the second category of damage, further subdividing it into primary spalling, secondary spalling, and tertiary spalling, and outputs classification result #2.

[0149] Secondary identification sub-model #3 corresponds to the exposed steel bar category: it processes the third category of damage and further subdivides it into first-level exposed steel bars, second-level exposed steel bars, and third-level exposed steel bars, and outputs classification result #3.

[0150] Secondary identification sub-model #4 corresponds to the steel bar corrosion category: it processes the damage of the fourth category and further subdivides it into primary steel bar corrosion, secondary steel bar corrosion, and tertiary steel bar corrosion, and outputs classification result #4.

[0151] Secondary identification sub-model #5 corresponds to component concrete crushing category: it processes the fifth category of damage and further subdivides it into primary concrete crushing, secondary concrete crushing, and tertiary concrete crushing, and outputs classification result #5.

[0152] Secondary identification sub-model #6 corresponds to the category of obvious deformation of components: it processes the damage of the sixth category and further subdivides it into primary deformation, secondary deformation and tertiary deformation, and outputs classification result #6. ...

[0154] Secondary identification sub-model #n corresponds to the category of obvious deformation of the component: it processes the damage of the nth category, further subdividing it into primary damage, secondary damage and tertiary damage, and outputs the classification result #n.

[0155] It should be explained that, although this embodiment only lists the above categories #1 to #n, similar category divisions and category supplements (i.e., new categories) based on this concept, such as Figure 5 As shown, for example:

[0156] Secondary identification sub-model #n+1 corresponds to the category of obvious deformation of the component: it processes the damage of the n+1th category, further subdividing it into primary damage, secondary damage and tertiary damage, and outputs the classification result #n+1.

[0157] Secondary identification sub-model #n+2 corresponds to the category of obvious deformation of components: it processes the damage of the n+2th category, further subdividing it into primary damage, secondary damage and tertiary damage, and outputs classification result #n+2. ...

[0159] Secondary identification sub-model #n+m corresponds to the category of obvious deformation of the component: it processes the damage of the n+mth category, further subdividing it into primary damage, secondary damage and tertiary damage, and outputs the classification result #n+m.

[0160] It should be explained that the binary classification deep learning model refers to a deep learning algorithm that is used to perform binary classification tasks on input data. Specifically, it will classify the input image into one of two categories, namely "no damage" or "damaged". This binary classification deep learning model uses a deep neural network to automatically extract the features of the image, converts the original image into a more abstract feature representation through a multi-layer neural network, and finally outputs the probability of each category through a fully connected layer and a classifier. The category corresponding to the highest probability is the classification result predicted by the binary classification deep learning model.

[0161] S4. Based on the deep convolutional neural network, feature extraction and classification are performed on the results of the secondary recognition and classification. The category with the largest classification probability value is taken as the damage type of the damaged image block, and the damaged image block is marked; the undamaged image block is spliced ​​with the marked damaged image block to obtain the final recognition result.

[0162] It should be explained that each secondary recognition sub-model extracts and classifies the input image blocks through a deep convolutional neural network, outputs the probability values ​​of each category, and finally takes the category with the largest classification probability value as the damage type of the image block and marks it on the image block. And each secondary recognition sub-model uses a multi-classification weighted cross entropy loss function for convergence calculation. Finally, all the image blocks judged as undamaged by the first-level recognition model and the damaged image blocks with damage type labels output by each secondary recognition sub-model are spliced ​​to form a result image with the same size as the original image, which is the overall recognition output result of the secondary recognition sub-model.

[0163] Preferably, obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set comprises the following steps:

[0164] S11, obtaining a structural damage image dataset as a primary dataset, and setting up a generative adversarial network;

[0165] Among them, the generative adversarial network includes a generator and a discriminator;

[0166] S12, inputting the primary data set as a training set into the generative adversarial network for training, using the generator to generate structural damage image data samples, and using the discriminator to distinguish them;

[0167] S13. After the training is completed, a generator is used to generate new structural damage image data samples, random noise is input, the new structural damage image data samples are added to the original primary data set, and the labels are adjusted to form a secondary data set.

[0168] Preferably, using the screening technology integrated with the Laplace transform algorithm to preliminarily screen the secondary data set and retaining the best quality structural damage images as the tertiary data set includes the following steps:

[0169] S21, using a Laplace transform algorithm to mark the structural damage image data whose clarity is lower than a preset threshold, and based on manual screening to confirm the marked structural damage image data, screen out images that are not related to structural damage, obtain the structural damage image with the best quality and retain it;

[0170] S22. Store the retained structural damage images with the best quality in a separate folder to form the final three-level dataset.

[0171] It should be explained that the present invention also includes a comprehensive result output function. For the image blocks classified by the secondary recognition sub-model, the results are marked on the original image and saved in the result folder. The marking color and text size are set according to preset rules. For example, cracks are marked with different shades of red, peeling is marked with different shades of green, and crushing is marked with blue.

[0172] Preferably, based on the deep learning classification algorithm and the three-level data set, a primary recognition model and a secondary recognition sub-model are constructed; the three-level data set is preliminarily recognized and classified using the primary recognition model to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification, which includes the following steps:

[0173] S31. Select the ResNet-50 architecture as the basic architecture, label the three-level data sets as non-damaged and damaged, divide the best quality structural damage image into several image blocks, and use each image block as the input of the first-level recognition model;

[0174] S32, use ResNet-50 to process the input image blocks layer by layer to extract high-level structural features;

[0175] S34, using the fully connected layer to output the probability value of the second classification, and converting the output of the first-level recognition model into a probability distribution through the softmax activation function;

[0176] S35. Use the binary weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method;

[0177] S36, performing binary classification on all image blocks in the third-level data set based on the first-level recognition model, and screening out damage-free image blocks and damaged image blocks;

[0178] S37. Based on the damaged image blocks, a plurality of parallel secondary recognition sub-models are constructed, and different types of structural damage are classified into a plurality of damage levels through each secondary recognition sub-model.

[0179] It should be explained that the first-level recognition model and each second-level recognition sub-model use the ResNet-50 model as the basic model. Its core feature is its residual connection. These connections allow the network input to be directly added to the subsequent layers, which helps to solve the gradient disappearance and gradient explosion problems in deep networks and enables the network to be trained more deeply. Specifically, it includes the following:

[0180] In the first layer, the processed image is input into the ResNet-50 model. Through the deep network structure of the model, the image features are extracted layer by layer. At the end of the network, the fully connected layer and softmax activation function are used for classification prediction, the loss is calculated (using the cross entropy loss function), and the model weights are updated through back propagation and gradient descent methods. When the input image passes through each layer of ResNet-50, it will be converted into a higher-level feature representation until a classification result of whether it is damaged or not is finally obtained.

[0181] Specifically, the features of the image are extracted layer by layer through multiple convolutional layers. Its main feature is the residual block, which allows the input to skip several layers and pass directly to the following layers, thereby effectively solving the gradient vanishing problem in deep networks.

[0182] Preferably, ResNet-50 is used to process the input image blocks layer by layer to extract high-level structural features including:

[0183] The input image block passes through the convolution layer, pooling layer and residual block of ResNet-50 to extract low-level features layer by layer and gradually aggregate them into high-level structural features.

[0184] Preferably, the formula of the binary weighted cross entropy loss function is:

[0185]

[0186] In the formula, Loss(1) represents the loss function value of the first-level recognition model;

[0187] N represents the total number of input image blocks for one training;

[0188] y i Represented as the true label of the i-th image block;

[0189] p i It is represented as the predicted category distribution probability of the first-level recognition model of the i-th image block.

[0190] Preferably, based on the damaged image block, constructing a plurality of parallel secondary recognition sub-models, and classifying different types of structural damage into a plurality of damage levels by each secondary recognition sub-model comprises the following steps:

[0191] S371. Based on the damaged image block, construct several parallel secondary recognition sub-models, and select a ResNet-50 architecture for each secondary recognition sub-model;

[0192] S372. Classify and label different types of structural damage, and divide structural damage into several damage levels.

[0193] Preferably, feature extraction and classification are performed on the results of the secondary recognition and classification based on a deep convolutional neural network, the category with the largest classification probability value is used as the damage type of the damaged image block, and the damaged image block is labeled; the damage-free image block is spliced ​​with the labeled damaged image block, and obtaining the final recognition result includes the following steps:

[0194] S41, performing sliding window scanning on the input damaged image block based on the convolution layer of the deep convolutional neural network, and extracting the damaged image block with local features using a number of filters;

[0195] S42, downsampling the feature damaged image block by using a maximum pooling layer to reduce the size of the feature damaged image block;

[0196] S43, after multi-layer convolution and pooling, the extracted high-level feature damaged image is flattened into a one-dimensional vector and passed to the fully connected layer, through which the feature damaged image is mapped to the final category space, and based on the Softmax activation function, the output value of the secondary recognition sub-model is converted into the probability distribution of various damage categories;

[0197] S44. Use a multi-classification weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method;

[0198] S45, based on the Softmax layer, output the probability distribution of various types of damage for each damaged image block, select the category with the highest probability value as the final damage type of the damaged image block, and make corresponding annotations;

[0199] S46, splicing the intact image block with the marked damaged image block to form a result image consistent with the specifications of the original image as the final recognition result.

[0200] It is worth explaining that the working principle of deep convolutional neural network feature extraction and classification is as follows:

[0201] 1) Convolutional Layer

[0202] Feature extraction: The convolution layer is the core layer of CNN, which is used to extract features from the input image. The convolution operation uses multiple filters to perform a sliding window scan on the image to extract different features, such as edges, textures, etc. Each filter can capture different local features.

[0203] 2) Activation Function

[0204] After the convolutional layer, a nonlinear activation function (ReLU) is usually applied to introduce nonlinearity, allowing the model to learn more complex features. ReLU sets all negative values ​​to 0 and keeps positive values ​​unchanged, ensuring that the model can effectively distinguish complex patterns.

[0205] 3) Pooling Layer

[0206] Downsampling: The pooling layer is used to reduce the size of the feature map. Max Pooling is usually used to reduce the dimension of the feature by taking the maximum value in the local area while retaining important features. The pooling operation can reduce the amount of calculation and prevent overfitting.

[0207] 4) Fully Connected Layer (FC Layer)

[0208] Classification: After multiple layers of convolution and pooling, the extracted high-level features are flattened into a one-dimensional vector and passed to the fully connected layer, which maps these features to the final category space.

[0209] 5) Softmax layer

[0210] Probability output: After the fully connected layer, the Softmax activation function is usually used to convert the output value of the model into a probability distribution. Softmax converts the output value of each category into a probability value between [0, 1], and the sum of the probability values ​​of all categories is 1. The category with the highest probability value is the prediction result of the model.

[0211] The specific implementation steps include:

[0212] Step 1: Input data preparation: Preprocess the image into a format acceptable to CNN, including resizing, normalizing, and converting it into a tensor.

[0213] Step 2: Construct a deep convolutional neural network (CNN): This is the primary and secondary sub-networks constructed by the present invention.

[0214] It should be explained that the primary network is a network that only recognizes the presence of damage but does not judge the damage type and degree. It is the first layer of the network that the image to be tested is first input into. The secondary network is only the part of the image to be tested that is judged to have damage in the primary network, and will be further input into the secondary sub-network to match and identify in different damage categories and their corresponding multiple levels. Here, the secondary network is composed of multiple damage category recognition networks arranged in parallel.

[0215] Step 3. Define the loss function and optimizer: Select the appropriate loss function (cross entropy loss function) and optimizer.

[0216] Step 4: Train the model: Through multiple rounds of iterations, the model will be continuously optimized through forward propagation, loss calculation, back propagation, and weight update.

[0217] Step 5: Model evaluation and prediction: After training is completed, use the model to classify and predict new image patches. The model will output the probability values ​​of belonging to each category, and select the category with the highest probability as the prediction result.

[0218] Step 6: Probability interpretation and result output: The output of the Softmax layer is a probability distribution, which is used to explain the probability value of each category. This output can help us understand the model's judgment results for each category.

[0219] Preferably, the formula of the multi-classification weighted cross entropy loss function is:

[0220]

[0221] In the formula, Loss(2) represents the loss function value of each secondary recognition sub-model;

[0222] N represents the total number of input image blocks for one training;

[0223] M represents the total number of categories;

[0224] y i，c Represented as the true label of the i-th image block in the c-th category;

[0225] It should be explained that if the i-th image block belongs to category c, then y i，c =1, otherwise y i，c =0.

[0226] p i，c It is represented as the category distribution probability predicted by the secondary recognition sub-model of the i-th image block on the c-th category.

[0227] According to another embodiment of the present invention, Figure 2 As shown, a structural damage classification identification system based on a deep learning classification algorithm is also provided, and the structural damage classification identification system includes:

[0228] The data acquisition module 1 is used to acquire a structural damage image data set as a primary data set, and preprocess and enhance the structural damage image data to form a secondary data set;

[0229] Data screening module 2, used for performing preliminary screening on the secondary data set using a preset screening technology, and retaining the best quality structural damage images as the tertiary data set;

[0230] Data classification module 3 is used to construct a primary recognition model and a secondary recognition sub-model using a deep learning classification algorithm and a three-level data set; perform preliminary recognition and classification on the three-level data set based on the primary recognition model to obtain damage-free image blocks and damaged image blocks, and input the damaged image blocks into the secondary recognition sub-model for secondary recognition and classification;

[0231] The result recognition module 4 is used to extract features and classify the results of the secondary recognition and classification based on a deep convolutional neural network, take the category with the largest classification probability value as the damage type of the damaged image block, and mark the damaged image block; splice the undamaged image block with the marked damaged image block to obtain the final recognition result.

[0232] In summary, with the aid of the above technical solution of the present invention, the present invention realizes efficient and accurate detection of surface damage of the structure by constructing a first-level recognition model and multiple second-level recognition sub-models. It has the advantages of gradually refined detection, modular design, optimization of computing resources, and low misjudgment rate. It can greatly improve the accuracy and robustness of detection while ensuring the overall detection efficiency, and realize efficient recognition of various types, locations and degrees of damage to engineering structures, thereby improving the accuracy and efficiency of detection. The present invention adopts hierarchical detection and recognition. First, the first-level recognition model quickly screens out areas where damage may exist, reducing interference from irrelevant areas; on this basis, multiple parallel second-level recognition sub-models further refine the classification, thereby improving the recognition accuracy of different damage types and levels. Such a hierarchical structure significantly improves the overall detection accuracy, especially in complex and diverse damage scenarios, and can more accurately distinguish subtle types of damage. The present invention decomposes the detection process into two stages, combines efficient screening and fine classification, can efficiently and accurately identify various types of structural damage, and has strong scalability and adaptability. It not only improves the accuracy and efficiency of detection, but also screens out damaged areas through simple and fast binary classification, and then conducts more detailed detection, which can significantly reduce the computational burden and optimize resource utilization. It will significantly improve the intelligence and automation level of structural health monitoring and provide important technical support for the safety management of engineering structures.

[0233] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A structural damage classification identification method based on a deep learning classification algorithm, characterized in that: The structural damage classification identification method includes the following steps: S1, obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set; S2, using the screening technology integrated with Laplace transform algorithm to preliminarily screen the secondary data set, and retain the best quality structural damage images as the tertiary data set; S3. Based on the deep learning classification algorithm and the three-level data set, a primary recognition model and a secondary recognition sub-model are constructed; the primary recognition model is used to perform preliminary recognition and classification on the three-level data set to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification; S4. Based on the deep convolutional neural network, feature extraction and classification are performed on the results of the secondary recognition and classification. The category with the largest classification probability value is taken as the damage type of the damaged image block, and the damaged image block is marked; the undamaged image block is spliced ​​with the marked damaged image block to obtain the final recognition result.

2. The structural damage classification identification method based on deep learning classification algorithm according to claim 1 is characterized in that: The step of obtaining a structural damage image data set as a primary data set, and preprocessing and enhancing the structural damage image data in the primary data set to form a secondary data set comprises the following steps: S11, obtaining a structural damage image dataset as a primary dataset, and setting up a generative adversarial network; Among them, the generative adversarial network includes a generator and a discriminator; S12, inputting the primary data set as a training set into the generative adversarial network for training, using the generator to generate structural damage image data samples, and using the discriminator to distinguish them; S13. After the training is completed, a generator is used to generate new structural damage image data samples, random noise is input, the new structural damage image data samples are added to the original primary data set, and the labels are adjusted to form a secondary data set.

3. The structural damage classification identification method based on deep learning classification algorithm according to claim 2 is characterized in that: The method of using the screening technology integrated with the Laplace transform algorithm to preliminarily screen the secondary data set and retain the best quality structural damage images as the tertiary data set includes the following steps: S21, using a Laplace transform algorithm to mark the structural damage image data whose clarity is lower than a preset threshold, and based on manual screening to confirm the marked structural damage image data, screen out images that are not related to structural damage, obtain the structural damage image with the best quality and retain it; S22. Store the retained structural damage images with the best quality in a separate folder to form the final three-level dataset.

4. The structural damage classification identification method based on deep learning classification algorithm according to claim 1 is characterized in that: The method comprises the following steps: constructing a primary recognition model and a secondary recognition sub-model based on a deep learning classification algorithm and a three-level data set; using the primary recognition model to preliminarily recognize and classify the three-level data set to obtain damage-free image blocks and damaged image blocks, and inputting the damaged image blocks into the secondary recognition sub-model for secondary recognition and classification: S31. Select the ResNet-50 architecture as the basic architecture, label the three-level data sets as non-damaged and damaged, divide the best quality structural damage image into several image blocks, and use each image block as the input of the first-level recognition model; S32, use ResNet-50 to process the input image blocks layer by layer to extract high-level structural features; S34, using the fully connected layer to output the probability value of the second classification, and converting the output of the first-level recognition model into a probability distribution through the softmax activation function; S35. Use the binary weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method; S36, performing binary classification on all image blocks in the third-level data set based on the first-level recognition model, and screening out damage-free image blocks and damaged image blocks; S37. Based on the damaged image blocks, a plurality of parallel secondary recognition sub-models are constructed, and different types of structural damage are classified into a plurality of damage levels through each secondary recognition sub-model.

5. The structural damage classification identification method based on deep learning classification algorithm according to claim 4 is characterized in that: The use of ResNet-50 to process the input image blocks layer by layer and extract high-level structural features includes: The input image block passes through the convolution layer, pooling layer and residual block of ResNet-50 to extract low-level features layer by layer and gradually aggregate them into high-level structural features.

6. The structural damage classification identification method based on deep learning classification algorithm according to claim 4 is characterized in that: The formula of the binary weighted cross entropy loss function is: In the formula, Loss(1) represents the loss function value of the first-level recognition model; N represents the total number of input image blocks for one training; y i Represented as the true label of the i-th image block; p i It is represented as the predicted category distribution probability of the first-level recognition model of the i-th image block.

7. The structural damage classification identification method based on deep learning classification algorithm according to claim 4 is characterized in that: The method of constructing a plurality of parallel secondary recognition sub-models based on the damaged image blocks and classifying different types of structural damage into a plurality of damage levels by each secondary recognition sub-model comprises the following steps: S371. Based on the damaged image block, construct several parallel secondary recognition sub-models, and select a ResNet-50 architecture for each secondary recognition sub-model; S372. Classify and label different types of structural damage, and divide structural damage into several damage levels.

8. The structural damage classification identification method based on deep learning classification algorithm according to claim 1 is characterized in that: The method of extracting features and classifying the results of the secondary recognition and classification based on a deep convolutional neural network, taking the category with the largest classification probability value as the damage type of the damaged image block, and marking the damaged image block; splicing the non-damaged image block with the marked damaged image block, and obtaining the final recognition result includes the following steps: S41, performing sliding window scanning on the input damaged image block based on the convolution layer of the deep convolutional neural network, and extracting the damaged image block with local features using a number of filters; S42, downsampling the feature damaged image block by using a maximum pooling layer to reduce the size of the feature damaged image block; S43, after multi-layer convolution and pooling, the extracted high-level feature damaged image is flattened into a one-dimensional vector and passed to the fully connected layer, through which the feature damaged image is mapped to the final category space, and based on the Softmax activation function, the output value of the secondary recognition sub-model is converted into the probability distribution of various damage categories; S44. Use a multi-classification weighted cross entropy loss function to measure the difference between the output of the primary recognition model and the true label, and update the weight of the primary recognition model through back propagation and gradient descent method; S45, based on the Softmax layer, output the probability distribution of various types of damage for each damaged image block, select the category with the highest probability value as the final damage type of the damaged image block, and make corresponding annotations; S46, splicing the intact image block with the marked damaged image block to form a result image consistent with the specifications of the original image as the final recognition result.

9. The structural damage classification identification method based on deep learning classification algorithm according to claim 8 is characterized in that: The formula of the multi-classification weighted cross entropy loss function is: In the formula, Loss(2) represents the loss function value of each secondary recognition sub-model; N represents the total number of input image blocks for one training; M represents the total number of categories; y i，c Represented as the true label of the i-th image block in the c-th category; p i，c It is represented as the category distribution probability predicted by the secondary recognition sub-model of the i-th image block on the c-th category.

10. A structural damage classification identification system based on a deep learning classification algorithm, used to implement the structural damage classification identification method based on a deep learning classification algorithm according to any one of claims 1 to 9, characterized in that: The structural damage classification identification system includes: A data acquisition module is used to acquire a structural damage image data set as a primary data set, and preprocess and enhance the structural damage image data to form a secondary data set; A data screening module, used to perform preliminary screening on the secondary data set using a preset screening technology, and retain the best quality structural damage images as the tertiary data set; The data classification module is used to construct a primary recognition model and a secondary recognition sub-model using a deep learning classification algorithm and a three-level data set; the three-level data set is preliminarily recognized and classified based on the primary recognition model to obtain damage-free image blocks and damaged image blocks, and the damaged image blocks are input into the secondary recognition sub-model for secondary recognition and classification; The result recognition module is used to extract features and classify the results of secondary recognition and classification based on a deep convolutional neural network, take the category with the largest classification probability value as the damage type of the damaged image block, and mark the damaged image block; splice the non-damaged image block with the marked damaged image block to obtain the final recognition result.

Images