Method and terminal for detecting damage degree of reinforced concrete member

Abstract

The invention relates to the technical field of image processing, and discloses a reinforced concrete member damage degree detection method and a terminal, and the method comprises the steps: obtaining an apparent damage image of a damaged reinforced concrete member, and extracting the damage texture of the apparent damage image; calculating the damage fractal dimension of the damaged reinforced concrete member according to the damage texture; and according to the damage fractal dimension, obtaining a damage index of the damaged reinforced concrete member. According to the method, the damage texture of the apparent damage image is identified, the damage fractal dimension of the damage texture of the apparent damage image is extracted, and the intrinsic characteristics of the damage are analyzed through the damage fractal dimension, so that the judgment of the damage index is realized, the interference caused by human subjective factors is eliminated, and the method has the characteristic of high efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for detecting the damage degree of a reinforced concrete component, a terminal and a readable storage medium. Background Art

[0002] Earthquakes are one of the most serious natural disasters. After an earthquake, rapid detection and post-earthquake assessment of building structures are crucial. There is a certain correlation between earthquake action and apparent structural damage. As the earthquake action intensifies, cracks, concrete peeling, exposed steel bars, etc. will appear on the surface of components. These visual characteristics of earthquake damage can be used to determine the post-earthquake residual mechanical properties of building structures.

[0003] However, the traditional earthquake damage assessment method requires experts to observe and measure the damaged components and judge the degree of earthquake damage and the remaining seismic capacity based on experience. This assessment method is not only time-consuming but also has certain risks. At the same time, different experts may come to inconsistent earthquake damage assessment results, that is, this judgment method has errors caused by human subjectivity. Summary of the invention

[0004] The purpose of the present invention is to provide a method and terminal for detecting the damage degree of reinforced concrete components, aiming to solve the problem that the existing technology is time-consuming and has inconsistencies caused by subjective errors when evaluating reinforced concrete damage detection.

[0005] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0006] The present invention provides a method for detecting the damage degree of a reinforced concrete member, the method comprising:

[0007] Acquire an apparent damage image of a damaged reinforced concrete component, and extract a damage texture of the apparent damage image;

[0008] Calculating the damage fractal dimension of the damaged reinforced concrete component according to the damage texture;

[0009] A damage index of the damaged reinforced concrete component is obtained according to the damage fractal dimension.

[0010] Furthermore, the extracting the damage texture of the apparent damage image specifically includes:

[0011] Acquire an image model, and input the apparent damage image into the image model;

[0012] Obtaining a damage texture output by the image model.

[0013] Furthermore, the calculating the damage fractal dimension of the damaged reinforced concrete component according to the damage texture specifically includes:

[0014] Calculating a single fractal dimension or a generalized fractal dimension of the damage texture;

[0015] The single fractal dimension or the generalized fractal dimension is used as the damage fractal dimension.

[0016] Furthermore, the damage fractal dimension is specifically a single fractal dimension of the damage texture, and the calculation of the damage fractal dimension of the damage texture specifically includes:

[0017] Performing box counting on the damaged texture multiple times to obtain the number of boxes with damaged texture under different box sizes;

[0018] Fit the single fractal dimension D0 based on the number of boxes with damaged texture at different box sizes:

[0019]

[0020] Where r is the ratio of the box size to the image size, and N(r) is the number of boxes with damaged texture when the ratio of the box size to the image size is r.

[0021] Furthermore, the box counting is performed on the damaged texture multiple times to obtain the number of boxes with damaged textures under different box sizes, and each time the box counting is performed on the damaged texture, it includes:

[0022] Evenly dividing the apparent damage image into 1 / r boxes;

[0023] Identify pixels box by box to obtain all boxes with damaged textures;

[0024] The number of all boxes with damaged textures is counted to obtain the number of boxes with damaged textures N(r) when the ratio of the box size to the image size is r.

[0025] Furthermore, the damage fractal dimension is specifically a generalized fractal dimension of the damage texture, and the calculation of the damage fractal dimension of the damage texture specifically includes:

[0026] Performing box probability counting on the damage texture multiple times to obtain weighted probabilities that each box under different box sizes has the damage texture;

[0027] The generalized fractal dimension is fitted according to the weighted probability that each box under the different box sizes has a damaged texture:

[0028]

[0029] Among them, q represents the weight, Dq represents the generalized fractal dimension with weight q, P i q (r) is the weighted probability of the ith box when the ratio of box size to image size is r, and M(r) is the total number of boxes when the ratio of box size to image size is r.

[0030] Furthermore, the generalized fractal dimension includes generalized fractal dimensions with weights q of -40, -2, -1, 0, 1, 2 and 40.

[0031] Furthermore, obtaining the damage index of the damaged reinforced concrete component according to the damage fractal dimension specifically includes:

[0032] Acquire the aspect ratio of the concrete component image, and input the damage fractal dimension and the aspect ratio into a classifier;

[0033] The classifier outputs the damage indicator.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, which includes: a memory, a processor, and a reinforced concrete component damage degree detection program stored in the memory and executable on the processor, wherein the reinforced concrete component damage degree detection program, when executed by the processor, controls the terminal to implement the steps of a reinforced concrete component damage degree detection method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a readable storage medium, which stores a reinforced concrete component damage degree detection program, and when the reinforced concrete component damage degree detection program is executed by a processor, the steps of the reinforced concrete component damage degree detection method described above are implemented.

[0036] The present invention adopts the above technical solution to achieve the following effects:

[0037] The present invention identifies the damage texture of the reinforced concrete component image and proposes the damage fractal dimension of the damage texture. The damage fractal dimension is used to analyze the intrinsic characteristics of the damage, thereby realizing the judgment of the damage index, eliminating the interference caused by human subjective factors, and having the characteristics of high efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of the steps of a method for detecting the degree of damage of a reinforced concrete member in a preferred embodiment of the present invention;

[0039] Figure 2 It is a flowchart of the steps of constructing each model in a preferred embodiment of the present invention;

[0040] Figure 3 Schematic diagram of the effect of extracting damaged texture using an image model in a preferred embodiment of the present invention;

[0041] Figure 4 It is a schematic diagram of parameters of different reinforced concrete structure frame columns in a preferred embodiment of the present invention;

[0042] Figure 5 It is a schematic diagram of the dimensions of different reinforced concrete structure frame columns in a preferred embodiment of the present invention;

[0043] Figure 6 It is a structural schematic diagram of a static hysteresis test device in a preferred embodiment of the present invention;

[0044] Figure 7 It is a schematic diagram of fractal analysis with different weight values ​​of multifractal dimension;

[0045] Figure 8 1 is a schematic diagram of damage and data comparison in a static hysteresis test in a preferred embodiment of the present invention;

[0046] Fig. 9 Schematic diagram of the training steps of the adaptive enhancement algorithm in a preferred embodiment of the present invention;

[0047] Fig.10 It is a schematic diagram of the prediction effect of damage indicators in a preferred embodiment of the present invention;

[0048] Fig.11 It is a schematic diagram of the interface of the damage identification-damage degree assessment integrated platform in a preferred embodiment of the present invention.

[0049] Fig.12 A schematic diagram of an operating environment of a preferred embodiment of a terminal of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Embodiment 1

[0052] Specifically, see Figure 1 and Figure 2 Embodiment 1 of the present application is a method for detecting the damage degree of a reinforced concrete member, which comprises the following steps:

[0053] S1. Obtain an apparent damage image of a damaged reinforced concrete component, and extract damage texture of the apparent damage image.

[0054] Specifically, in this embodiment, drones or robots can be used to collect images of damaged reinforced concrete components in earthquake areas to avoid the dangers of manual collection. After the images are collected, they are first preprocessed, that is, a series of processes including rotation, scaling and deformation are performed on the images to obtain frontal images of uniform size and format.

[0055] After the image of the reinforced concrete component is collected, the image of the reinforced concrete component is input into the image model, and the image model outputs the damage texture. In this embodiment, the image model specifically adopts the Yolov8 model as the image model. First, a large number of manually annotated apparent damage images are used as training data of the image model to form a training data set, so that the image model can learn to obtain the judgment ability of the damage texture. After that, the image model can be used to extract the damage texture of the concrete image. The extracted image is as follows: Figure 3 As shown, Figure 3 In the figure, the crack box is the damage texture, and the number behind it represents the confidence rate of the damage.

[0056] Specifically, in this embodiment, the result data collected by the RC (reinforced concrete structure) static hysteresis test is collected to obtain the reinforced concrete component image as training data. In this embodiment, please refer to Figure 4 and Figure 5 , Figure 4 It is a schematic diagram of parameters of different reinforced concrete structure frame columns of the present invention, Figure 5 It is a schematic diagram of the dimensions of different reinforced concrete structure frame columns of the present invention. The data required for the research were obtained by conducting static hysteresis tests on reinforced concrete structure frame columns of 8 different dimensions, reinforcement ratios, and shear span ratios.

[0057] Among them, the static hysteresis test refers to obtaining the load-deformation data of the specimen under the cyclic action of the loading force. The hysteresis curve drawn by the data points can reflect the seismic performance, energy consumption capacity and other information of the component during repeated stress. Figure 6 In order to carry out the device used for the quasi-static loading test, the bottom end of the reinforced concrete column is anchored, and an axial force is applied to the top of the column and a low-cycle repeated horizontal load is applied through a four-bar device until the first cycle horizontal force of the structure drops to less than 80% of the peak horizontal force. During the test, a mortar surface layer is added to the side surface of the column and latex paint is applied to simulate the earthquake damage phenomenon of actual building components.

[0058] During the test, a high-speed, high-definition camera was used to record the surface damage phenomena of components at each loading stage, so that only the apparent damage distribution of reinforced concrete structure frame columns could be obtained later.

[0059] S2. Calculating the damage fractal dimension of the damaged reinforced concrete component according to the damage texture.

[0060] In this embodiment, program codes are written on a Matlab (matrix & laboratory) platform to obtain the damage fractal dimension of the damage texture.

[0061] Regarding the damage fractal dimension, it is a fractal dimension used to describe the damage condition, and fractal dimension is a concept of fractal geometry. There are many highly irregular shapes similar to coastlines in nature. Through research, it can be found that when these shapes are examined at different scales, these shapes show similar complexity and irregularity in a smaller range, that is, the local structure of this type of geometric shape is similar to the overall structure, and they show similar morphological characteristics at different magnifications. This characteristic is called self-similarity. Fractal geometry is a branch of mathematics that studies the self-similarity and complex boundary structures of complex graphics that recur at different scales. The core feature of fractal geometry is that these graphics show the same or similar structural features at different magnifications. Therefore, a concept used to characterize the complexity of geometric shapes is introduced, namely fractal dimension. In fractal theory, fractal dimension is an important tool for describing and measuring these complex shapes, which can be either an integer or a fraction.

[0062] It is not difficult to see from the above description of fractal dimension that fractal dimension is scale-independent, and therefore can reveal the intrinsic characteristics of post-earthquake damage distribution on the surface of reinforced concrete components. Therefore, in this embodiment, fractal parameters are used to describe the damage surface, that is, to obtain the damage fractal dimension, which can not only truly reflect the spatial distribution and arrangement of the damaged area, but also reflect the degree of damage to the column.

[0063] The damage fractal dimension may be a single fractal dimension or a multi-fractal dimension. In this embodiment, it is a multi-fractal dimension.

[0064] The mainstream calculation method of the single fractal dimension is to use the box counting principle, in which the required image is evenly divided into 1 / r boxes (cubes), where r is a variable value. Then, pixel recognition is performed box by box, and the boxes filled with damaged textures are counted to obtain the number of boxes filled with damaged textures when the number of boxes is r. By adjusting the number of r multiple times, the number of boxes filled with damaged textures under different numbers N(r) is obtained. Finally, according to the number of boxes filled with multiple damaged textures N(r), the single fractal dimension D0 can be fitted and calculated as follows:

[0065]

[0066] Generalized fractal dimension (GFD), also known as multifractal dimension, is used to extract more information from an image. Multifractal dimension is denoted by D.q express:

[0067]

[0068] Among them, D q It represents the generalized fractal dimension with weight q. M(r) is the total number of boxes, i.e. 1 / r. q is a weight factor, also called the characterization value. When q>1, the information of high concentration or high aggregation (dense area, high probability) is amplified; when q<1, the information of low concentration or low aggregation (sparse area, low probability) is amplified. i q (r) is the probability P with weight factor q i (r), probability P i (r) is the ratio of the number of pixels filled with damaged texture in the i-th box to the total number of pixels filled with damaged texture in the image:

[0069]

[0070] Among them, N i (r) represents the number of pixels filled with damaged texture in the i-th box in the image, N j (r) represents the number of pixels filled with damaged texture in the jth box in the image, P i (r) is a relative probability mass coefficient, representing the relative strength of the damage in the i-th box in the image.

[0071] For the multifractal analysis of binary black and white images, in order to further explain the relationship between q and P i q (r) value, Figure 7 The fractal analysis results of the damaged area image at different q values ​​are shown. Figure 7 (a) is a schematic diagram of damage distribution. Figure 7 (b) is the calculated probability P of different boxes i q (r) Schematic diagram, Figure 7 (c) in the figure is the normalized P of different boxes under different q values. i q (r),

[0072] It can be found that for boxes with a larger proportion of black pixels due to cracking and peeling, P i q The value of (r) is higher. Figure 7 (c) shows the value distribution of the normalized probability of the damaged area considering the weight factor q. The normalized probability λ i The calculation of (q,r) is as follows:

[0073]

[0074] When q = 0, the box containing cracked and peeled pixels is black, and the box without damaged pixel distribution is white. At this time, only whether there is a crack in each box is considered, and the intensity of the damage is not important to it, and the difference between cracks and fragments is not considered. Positive q values ​​will increase the intensity of the box containing pixels with a greater degree of peeling or cracking. Figure 7 As shown in (c) in Figure 1, when the q value is positive, the focus is on the most severely damaged box, while the remaining boxes with sparsely distributed pixels are almost white. When q is negative, the normalized probability distribution result is opposite to that of the positive q value. For example, when the q value is equal to -1, the box with smaller damaged pixels is actually the darker box.

[0075] In this embodiment, the q values ​​of D are -40, -2, -1, 0, 1, 2, 40. q The value is an important parameter for damage assessment.

[0076] S3. Determine the damage index of the damaged reinforced concrete component according to the damage fractal dimension.

[0077] In this embodiment, when judging the damage index, in addition to the seven damage fractal dimensions, the aspect ratio (h / b) of the component is also used as a reference.

[0078] The damage index is a quantitative parameter established on the basis of various engineering demand parameters (such as strength, stiffness, energy dissipation, deformation, etc.). In this embodiment, the following new strength-based damage index is specifically used to measure the degree of strength loss of reinforced concrete structural components under earthquake action.

[0079]

[0080] Among them, DI s represents the damage index, S represents the strength of the column at a specific displacement level, S c Indicates the peak strength of the damaged reinforced concrete column in the skeleton curve, please refer to Figure 8 The lateral load-displacement hysteresis curve of reinforced concrete columns reaches the peak strength S c Before and after correspond to the pre-capping and post-capping stages respectively. The damage distribution images marked on the lateral load-displacement cycle curve are shown in Figure 8 shown.

[0081] In this embodiment, experimental data is obtained in a static hysteresis test, and the test photos are matched one by one with the corresponding loading points on the hysteresis curve. The corresponding damage fractal dimension of each component at each stage is calculated based on the photos. The post-earthquake damage degree of the component is output by defining and estimating the degradation state index value of the mechanical properties (i.e., stiffness and strength) of the component at a certain loading point on the hysteresis curve, combined with the regression model.

[0082] At this point, the damage images, multi-fractal dimensions, aspect ratios (h / b) and strength degradation index values ​​at each loading stage were matched one by one, and the seismic damage database of reinforced concrete structure test columns required for the research was successfully established.

[0083] Then, the present invention adopts AdaBoost (Adaptive Boosting) algorithm to judge the damage index, wherein AdaBoost (Adaptive Boosting) algorithm is an integrated learning method, which improves the accuracy of weak learners by changing the distribution of sample weights. For classification problems, the AdaBoost algorithm adjusts the weight of the data according to the previous classification effect. The weight of the sample that was misclassified in the previous weak learner will be increased in the next weak learner, and the weight of the sample that was correctly classified will be reduced accordingly, and a new weak learner will be added to the model in each round of iteration. Repeat the adjustment of weights and training of weak learners until the number of misclassifications is lower than the preset value or the number of iterations reaches the specified maximum value, and finally a strong learner is obtained. In short, the core idea of ​​the AdaBoost algorithm is to adjust the weight of the wrong sample, and then iterate and upgrade. Its training steps are as follows: Fig. 9 shown.

[0084] Assume a sample set consisting of m samples:

[0085] D={(x1,y1),(x2,y2),...,(x m ,y m )}

[0086] Each sample data has d features. In this embodiment, the features are seven damage fractal dimensions and aspect ratios, y m For sample x m The target value is the corresponding damage index value. The weight of each sample in the initial state is D1, and the weight of each sample is initialized to 1 / m. The weight of each sample in the kth iteration is D k , it should be noted that D1 is used for training the first weak classifier, D k For the kth weak classifier h k training.

[0087] The loop is repeated for n rounds, and the classifier h is calculated after each round of iteration. k The maximum error on the training set is calculated as:

[0088] E k =max|y l -h k (x l )|;

[0089] Among them, h k That is, the classifier h k , E k is the classifier h k The maximum error.

[0090] The relative error of each sample is:

[0091]

[0092] Among them, e kl is the classifier h k The relative error on the lth sample.

[0093] So the current weak classifier h k The error rate is:

[0094]

[0095] That is, the sum of the products of the weights and errors of all samples in the data set.

[0096] Update the current weak classifier h k The weight is calculated as:

[0097]

[0098] Among them, w k is the weak classifier h k The weight of .

[0099] So, for sample x l , the calculation formula for updating weights is:

[0100]

[0101] Among them, Z k is the normalization factor, D k (x l ) is the k-th iteration for sample x l The weighted value of k+1 (x l ) is the k+1th round of iteration for sample x l The weighted value of is calculated as follows:

[0102]

[0103] After n rounds of iterations, the final strong regressor H(x) is as follows:

[0104]

[0105] Among them, f(x) is the median of the weighted output results of all weak learners.

[0106] The coefficient of determination, R 2 , as a parameter to measure the goodness of fit of the regression model. The coefficient of determination indicates how well the regression model fits the data set, that is, the percentage of explanation given by the regression model. 2 The closer the value is to 1, the better the performance of the regression model. It can be expressed by the following formula:

[0107]

[0108] in is the predicted value of the regression model, is the average value of all damage indicators, y l is the value of the damage index in the data set.

[0109] The AdaBoost model is used to perform regression prediction on the damage degree of each sample in the test set. The effect diagram is shown in the figure below. Fig.10 As shown in the figure, the horizontal axis represents the sample number of the test machine, and the vertical axis represents the value of the damage degree. The average prediction accuracy of the sample damage degree can reach 65% or above.

[0110] Finally, this embodiment completes an integrated platform for damage identification and damage degree assessment based on the method of the present invention, and its interface is as follows: Fig.11 shown.

[0111] Embodiment 2

[0112] See also Fig.12 Based on the above method, the present invention further provides a terminal, which includes a processor 10, a memory 20 and a display 30. However, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0113] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a reinforced concrete component damage degree detection program 40 is stored on the memory 20, and the reinforced concrete component damage degree detection program 40 can be executed by the processor 10, thereby realizing the terminal in the present application.

[0114] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing relevant programs of the method for detecting the degree of damage of reinforced concrete components.

[0115] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface.

[0116] In one embodiment, when the processor 10 executes a reinforced concrete component damage degree detection program 40 in the memory 20, the steps of the reinforced concrete component damage degree detection method described above are implemented.

[0117] Embodiment 3

[0118] This embodiment provides a storage medium, wherein the readable storage medium stores a reinforced concrete component damage degree detection program, and when the reinforced concrete component damage degree detection program is executed by a processor, the steps of the reinforced concrete component damage degree detection method described above are implemented.

[0119] In summary, the present invention identifies the damage texture of the apparent damage image and extracts the damage fractal dimension of the damage texture of the apparent damage image. The damage fractal dimension is used to analyze the intrinsic characteristics of the damage, thereby realizing the judgment of the damage index, eliminating the interference caused by human subjective factors, and having the characteristics of high efficiency.

[0120] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0121] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0122] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for detecting the damage degree of reinforced concrete components, characterized in that: The reinforced concrete member damage degree detection method comprises: Acquire an apparent damage image of a damaged reinforced concrete component, and extract a damage texture of the apparent damage image; Calculating the damage fractal dimension of the damaged reinforced concrete component according to the damage texture; A damage index of the damaged reinforced concrete component is obtained according to the damage fractal dimension.

2. A method for detecting damage degree of reinforced concrete components according to claim 1, characterized in that: The extracting of the damage texture of the apparent damage image specifically includes: Acquire an image model, and input the apparent damage image into the image model; Obtaining a damage texture output by the image model.

3. A method for detecting damage degree of reinforced concrete components according to claim 1, characterized in that: The damage fractal dimension is a single fractal dimension or a generalized fractal dimension of the damage texture.

4. A method for detecting damage degree of reinforced concrete components according to claim 3, characterized in that: The damage fractal dimension is specifically a single fractal dimension of the damage texture, and the step of calculating the damage fractal dimension of the damage texture specifically includes: Performing box counting on the damaged texture multiple times to obtain the number of boxes with damaged texture under different box sizes; Fit the single fractal dimension D0 based on the number of boxes with damaged texture at different box sizes: Where r is the ratio of the box size to the image size, and N(r) is the number of boxes with damaged texture when the ratio of the box size to the image size is r.

5. A method for detecting damage degree of reinforced concrete components according to claim 4, characterized in that: The multiple box counting of the damaged texture is performed to obtain the number of boxes with damaged textures under different box sizes, and each time the box counting of the damaged texture is performed, the method includes: Evenly dividing the apparent damage image into 1 / r boxes; Identify pixels box by box to obtain all boxes with damaged textures; The number of all boxes with damaged textures is counted to obtain the number of boxes with damaged textures N(r) when the ratio of the box size to the image size is r.

6. A method for detecting damage degree of reinforced concrete components according to claim 3, characterized in that: The damage fractal dimension is specifically the generalized fractal dimension of the damage texture, and the step of calculating the damage fractal dimension of the damage texture specifically includes: Performing box probability counting on the damage texture multiple times to obtain weighted probabilities that each box under different box sizes has the damage texture; The generalized fractal dimension is fitted according to the weighted probability that each box under the different box sizes has a damaged texture: Among them, q represents the weight, D q represents the generalized fractal dimension with weight q, P i q (r) is the weighted probability of the ith box when the ratio of box size to image size is r, and M(r) is the total number of boxes when the ratio of box size to image size is r.

7. A method for detecting damage degree of reinforced concrete member according to claim 6, characterized in that: The generalized fractal dimensions include generalized fractal dimensions with weights q of -40, -2, -1, 0, 1, 2 and 40.

8. A method for detecting damage degree of reinforced concrete components according to claim 1, characterized in that: The step of obtaining the damage index of the damaged reinforced concrete component according to the damage fractal dimension specifically includes: Acquire the aspect ratio of the concrete component image, and input the damage fractal dimension and the aspect ratio into a classifier; The classifier outputs the damage indicator.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a reinforced concrete component damage degree detection program stored in the memory and executable on the processor. When the reinforced concrete component damage degree detection program is executed by the processor, the terminal is controlled to implement the steps of a reinforced concrete component damage degree detection method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores a reinforced concrete component damage degree detection program, and when the reinforced concrete component damage degree detection program is executed by the processor, the steps of a reinforced concrete component damage degree detection method as described in any one of claims 1-8 are implemented.

Images