Concrete damage spatio-temporal evolution identification method and related equipment

Abstract

The invention relates to the technical field of concrete damage identification, and provides a concrete damage spatio-temporal evolution identification method and related equipment, and the method comprises the steps: carrying out the damage mapping based on all damage information, and obtaining an initial damage label of each sub-region in each historical time period; performing quantitative separation on the damage information according to the initial damage label by utilizing a support vector machine to obtain a final damage label; for each historical time period, performing spatial damage analysis based on all damage information of the historical time period to obtain a damage gray matrix of each sub-region in the historical time period; and constructing a three-dimensional damage model of the target concrete area in each historical time period according to the damage gray matrix and the final damage label of all the sub-areas in each historical time period, and serializing all the three-dimensional damage models to obtain a spatio-temporal evolution damage model of the target concrete area. According to the method, the identification accuracy of concrete damage spatio-temporal evolution can be improved.

Description

Technical Field

[0001] This application relates to the technical field of concrete damage identification, and particularly to a method for identifying the spatio-temporal evolution of concrete damage and related equipment. Background Art

[0002] The core difficulty in the intelligent monitoring of concrete structures lies in the accurate capture of the multi-scale damage spatio-temporal evolution mechanism. The inherent aggregate interface defects, shrinkage cracks and other initial damages inside the concrete will form a microcrack network under the coupled action of service load and environment. The three-dimensional dynamic expansion process of the microcrack network directly leads to the degradation of material strength and the decline of durability. Existing monitoring methods are limited by the insufficient spatio-temporal dimension analysis ability, especially the lack of the online classification ability for crack propagation modes (tensile / shear), and it is difficult to realize the full-process dynamic tracking from the initiation, stable propagation of microcracks to macroscopic cracking, resulting in a significant lag in the early warning of structural performance degradation.

[0003] Current mainstream damage identification technologies, such as acoustic emission detection technology, have technical bottlenecks in the analysis of multi-dimensional signals. The data analysis of traditional acoustic emission (AE) technology relies on artificial feature extraction and static parameter statistics (such as ring count, energy accumulation), lacking the intelligent fusion analysis ability for spatio-temporal multi-dimensional signal features. And the existing detection methods have significant defects in aspects such as spatial positioning accuracy and dynamic evolution characterization. This leads to the problem of poor accuracy in identifying the spatio-temporal evolution of concrete damage. Summary of the Invention

[0004] This application provides a method for identifying the spatio-temporal evolution of concrete damage and related equipment, which can solve the problem of poor accuracy in identifying the spatio-temporal evolution of concrete damage.

[0005] In a first aspect, this application provides a method for identifying the spatio-temporal evolution of concrete damage. The method for identifying the spatio-temporal evolution of concrete damage includes: Obtaining the damage information of each sub-region in a target concrete area in multiple historical time periods; Performing damage mapping based on all damage information to obtain the initial damage label of each sub-region in each historical time period; the initial damage label is used to classify all damage information; Using a support vector machine, quantitatively separating all damage information according to all initial damage labels to obtain the final damage label of each sub-region in each historical time period; the final damage label is used to describe the damage category of the sub-region in the historical time period; For each historical time period respectively, performing spatial damage analysis based on all damage information of the historical time period to obtain the damage gray scale matrix of each sub-region in the historical time period; the damage gray scale matrix is used to describe the damage degree of the sub-region. Based on the damage grayscale matrix and the final damage labels of all sub-regions in each historical time period, construct a three-dimensional damage model of the target concrete region in each historical time period, and serialize all three-dimensional damage models to obtain a spatio-temporal evolution damage model of the target concrete region; the three-dimensional damage model is used to describe the damaged sub-regions and damage categories of the target concrete region in the historical time period, and the spatio-temporal evolution damage model is used to describe the damage evolution process of the target concrete region in all historical time periods.

[0006] Optionally, perform damage mapping based on all damage information to obtain the initial damage label of each sub-region in each historical time period, including: For each damage information, analyze the damage information to obtain the damage value corresponding to the damage information; Initialize the weight matrix, and standardize each damage value to obtain a standard damage value; multiple elements in the weight matrix correspond one-to-one with multiple damage values; Use all standard damage values to iteratively update the weight matrix to obtain the final weight matrix; Cluster all damage values according to all elements in the final weight matrix to obtain multiple clustering clusters; Perform secondary clustering on all clustering clusters to obtain multiple target clustering clusters; Perform label assignment according to the target clustering cluster corresponding to each damage information to obtain the initial damage label of the sub-region corresponding to each damage information in the corresponding historical time period.

[0007] Optionally, use all standard damage values to iteratively update the weight matrix to obtain the final weight matrix, including: Increment the iteration count by 1; Determine whether the iteration count has reached the preset number of times; If so, use the weight matrix as the final weight matrix; Otherwise, randomly select a standard damage value from all standard damage values as the sample damage value; Calculate the similarity between the sample damage value and each element in the weight matrix, and use the element with the maximum similarity as the target element; For each element in the weight matrix, determine whether the element is equal to the target element. If so, update the element according to the target element to obtain the updated element. Otherwise, use the element as the updated element; Integrate all updated elements to obtain the updated weight matrix, and use the updated weight matrix as the weight matrix, and return to the step of incrementing the iteration count by 1.

[0008] Optionally, perform secondary clustering on all clustering clusters to obtain multiple target clustering clusters, including: For each clustering cluster respectively, combine the elements of the final weight matrix corresponding to all damage values in the clustering cluster into a vector to obtain the weight vector of the clustering cluster; Calculate the cosine similarity between every two clustering clusters according to all the weight vectors; Perform a clustering operation on all the clustering clusters according to all the cosine similarities to obtain multiple target clustering clusters.

[0009] Optionally, the final damage label is shear damage or tensile damage; Using a support vector machine, quantitatively separate all the damage information according to all the initial damage labels to obtain the final damage label of each sub-region at each historical time period, including: Construct a Lagrangian function according to all the initial damage labels; Solve the parameter solution that should be satisfied by minimizing the Lagrangian function, and substitute the parameter solution into the Lagrangian function to obtain the objective function; Minimize the objective function to obtain the normal vector and the threshold of the support vector machine; Construct a hyperplane according to the normal vector and the threshold of the support vector machine; Map all the damage information to the feature space, and quantitatively separate all the initial damage labels by using the hyperplane in the feature space to obtain the directional separation result; For each damage information respectively, judge whether the damage information is on the first side of the hyperplane in the directional separation result. If so, take tensile damage as the final damage label of the sub-region corresponding to the damage information at the corresponding historical time period. Otherwise, take shear damage as the final damage label of the sub-region corresponding to the damage information at the corresponding historical time period.

[0010] Optionally, the Lagrangian function is: ; Wherein, represents the value of the Lagrangian function, represents the normal vector of the hyperplane, represents the threshold of the support vector machine, represents the non-negative slack coefficient is the non-negative penalty coefficient, and represent the Lagrange multipliers, represents the th non-negative penalty coefficient, represents the number of damage information, and are both the th Lagrange multipliers, represents the th initial damage label corresponding to the damage information, Indicates the damage value of the th damage information.

[0011] Optionally, the parameter solution is: ; ; ; The objective function is: ; Among them, Indicates the damage weight matrix, Indicates the th Lagrange multiplier, Indicates the initial damage label corresponding to the th damage information, Indicates the th damage value of the damage information, Indicates the transpose operation.

[0012] Optionally, the hyperplane is: ; Among them, Indicates the vector on the hyperplane.

[0013] On the second aspect, the present application provides a device for identifying the spatio-temporal evolution of concrete damage, including: An acquisition module, configured to acquire the damage information of each sub-region of the target concrete region in multiple historical time periods; A damage mapping module, configured to perform damage mapping based on all damage information to obtain the initial damage label of each sub-region in each historical time period; the initial damage label is used to classify all damage information; A quantitative separation module, configured to use a support vector machine to quantitatively separate all damage information according to all initial damage labels to obtain the final damage label of each sub-region in each historical time period; the final damage label is used to describe the damage category of the sub-region in the historical time period; A damage analysis module, configured to perform spatial damage analysis on all damage information in the historical time period respectively for each historical time period to obtain the damage gray-scale matrix of each sub-region in the historical time period; the damage gray-scale matrix is used to describe the damage degree of the sub-region; A construction module is used to construct a three-dimensional damage model of the target concrete area for each historical time period based on the damage gray-scale matrices and the final damage labels of all sub-areas in each historical time period, and serialize all the three-dimensional damage models to obtain a spatio-temporal evolution damage model of the target concrete area. The three-dimensional damage model is used to describe the damaged sub-areas and damage categories of the target concrete area in the historical time period, and the spatio-temporal evolution damage model is used to describe the damage evolution process of the target concrete area in all historical time periods.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned concrete damage spatio-temporal evolution recognition method is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned concrete damage spatio-temporal evolution recognition method is implemented.

[0016] The above solution of the present application has the following beneficial effects: In some embodiments of the present application, by obtaining the damage information of each sub-area of the target concrete area in multiple historical time periods, then performing damage mapping based on all the damage information to obtain the initial damage label of each sub-area in each historical time period, and then using a support vector machine to quantitatively separate all the damage information according to all the initial damage labels to obtain the final damage label of each sub-area in each historical time period. Then, for each historical time period, spatial damage analysis is performed based on all the damage information of the historical time period to obtain the damage gray-scale matrix of each sub-area in the historical time period. Finally, based on the damage gray-scale matrices and the final damage labels of all sub-areas in each historical time period, a three-dimensional damage model of the target concrete area is constructed for each historical time period, and all the three-dimensional damage models are serialized to obtain a spatio-temporal evolution damage model of the target concrete area. Among them, performing damage mapping on the damage information can achieve a preliminary distinction of the damage information. Using a support vector machine to quantitatively separate the damage information to obtain the final damage label can further classify the damage information in detail and improve the accuracy of the final damage label. Constructing a spatio-temporal evolution damage model based on the accurate final damage label can effectively improve the recognition accuracy of the concrete damage spatio-temporal evolution.

[0017] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 Flowchart of the concrete damage spatio-temporal evolution recognition method provided by an embodiment of the present application; Figure 2 Schematic diagram of the directional separation result provided by an embodiment of the present application; Figure 3 Schematic diagram of the three-dimensional numerical model provided by an embodiment of the present application; Figure 4 Grayscale image provided by an embodiment of the present application; Figure 5 Grayscale image after binarization and visual differentiation provided by an embodiment of the present application; Figure 6 Front view of the spatio-temporal evolution damage model provided by an embodiment of the present application; Figure 7 Top view of the spatio-temporal evolution damage model provided by an embodiment of the present application; Figure 8 Schematic diagram of the structure of the concrete damage spatio-temporal evolution recognition device provided by an embodiment of the present application; Figure 9 Schematic diagram of the structure of the terminal device provided by an embodiment of the present application. Detailed implementation manners

[0020] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0021] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0022] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] As used in the specification of this application and the appended claims, the term "if" may be construed to mean "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" may be construed to mean "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0024] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are used only for descriptive distinction and should not be construed as indicating or implying relative importance.

[0025] Reference to "an embodiment" or "some embodiments" or the like described in the specification of this application means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in an embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0026] In view of the problem of poor accuracy in the spatio-temporal evolution of existing concrete damage, the embodiments of the present application provide a method for identifying the spatio-temporal evolution of concrete damage. The spatio-temporal evolution identification method obtains the damage information of each sub-region in a target concrete region in multiple historical time periods, and then performs damage mapping based on all the damage information to obtain the initial damage label of each sub-region in each historical time period. Then, using a support vector machine, all the damage information is quantitatively separated according to all the initial damage labels to obtain the final damage label of each sub-region in each historical time period. Then, for each historical time period, spatial damage analysis is performed based on all the damage information of the historical time period to obtain the damage gray-scale matrix of each sub-region in the historical time period. Finally, according to the damage gray-scale matrix and the final damage label of all sub-regions in each historical time period, a three-dimensional damage model of the target concrete region in each historical time period is constructed, and all the three-dimensional damage models are serialized to obtain the spatio-temporal evolution damage model of the target concrete region. Among them, performing damage mapping on the damage information can achieve a preliminary distinction of the damage information. Using a support vector machine to quantitatively separate the damage information to obtain the final damage label can further classify the damage information in detail and improve the accuracy of the final damage label. Constructing the spatio-temporal evolution damage model according to the accurate final damage label can effectively improve the accuracy of identifying the spatio-temporal evolution of concrete damage.

[0027] Next, an exemplary description will be given of the method for identifying the spatio-temporal evolution of concrete damage provided by the present application.

[0028] As Figure 1 shown, the method for identifying the spatio-temporal evolution of concrete damage provided by the present application includes the following steps: Step 11, obtain the damage information of each sub-region in a target concrete region in multiple historical time periods.

[0029] The above-mentioned target concrete region is a concrete block that needs to be identified for spatio-temporal evolution of damage (such as the parts of a bridge or a building cast with concrete). The above-mentioned damage information is used to describe the state of the sub-regions in the target concrete region (such as the acoustic emission signal, internal three-dimensional modeling, piezoelectric vibration wave signal, etc. of the target concrete region). The multiple historical time periods are set according to the historical time periods required for actual damage analysis. The above-mentioned sub-regions can be obtained by spatially dividing the target concrete region. For example, the target concrete region can be evenly divided into grids, and the divided grid regions are used as sub-regions.

[0030] In some embodiments of the present application, devices such as an acoustic emission probe array, a radar, and a piezoelectric sensor can be used to obtain the damage information.

[0031] Step 12, perform damage mapping based on all the damage information to obtain the initial damage label of each sub-region in each historical time period.

[0032] The above-mentioned initial damage labels are used to classify all damage information, mainly to preliminarily classify the states of all sub-regions at each historical time period according to the damage information.

[0033] In some embodiments of the present application, the step of performing damage mapping based on all damage information to obtain the initial damage label of each sub-region at each historical time period includes: In the first step, for each damage information, analyze the damage information to obtain the damage value corresponding to the damage information.

[0034] The above-mentioned damage value is used to quantify the damage degree of the sub-region corresponding to the damage information.

[0035] Exemplarily, methods such as acoustic emission calculation formula, Fourier transform and Mel value mapping can be used to obtain the damage value corresponding to the damage information. For example, when the damage information is an acoustic emission signal, the AF value and RA value of the acoustic emission signal are calculated according to the rise time, acoustic emission amplitude, duration and acoustic emission count of the acoustic emission signal. The AF value is the frequency characteristic of the acoustic emission signal, and the RA value reflects the relationship between the amplitude characteristic and the rise time. AF and RA are the damage values of the damage information. The expressions are: ; ; In the second step, initialize the weight matrix and standardize each damage value to obtain the standard damage value.

[0036] Multiple elements in the weight matrix correspond to multiple damage values one by one. The elements in the weight matrix are the weights of the damage values.

[0037] It should be noted that all the weights in the weight matrix are divided into multiple weight components. The weight components correspond to a preset label (such as the numbers 1, 0, -1). Each weight component includes at least one weight, that is, for a weight component, all the weights divided into this weight component have the same preset label, and the number and value of its weights are set during initialization (usually randomly).

[0038] Exemplarily, algorithms such as deviation standardization can be used to standardize the damage values.

[0039] In the third step, use all the standard damage values to iteratively update the weight matrix to obtain the final weight matrix.

[0040] First, increment the iteration count by 1.

[0041] Then, determine whether the iteration count has reached the preset number of times.

[0042] If so, use the weight matrix as the final weight matrix.

[0043] Otherwise, randomly select a standard damage value from all standard damage values as the sample damage value.

[0044] Then, calculate the similarity between the sample damage value and each element in the weight matrix, and take the element with the maximum similarity as the target element.

[0045] For each element in the weight matrix, determine whether the element is equal to the target element. If so, update the element according to the target element to obtain the updated element. Otherwise, take the element as the updated element.

[0046] Integrate all the updated elements to obtain the updated weight matrix, and use the updated weight matrix as the weight matrix, then return to the step of adding 1 to the iteration count.

[0047] It should be noted that the initial value of the iteration count is 0. The above similarity can be calculated according to the cosine similarity calculation formula, Euclidean distance, etc. The above update of the element according to the target element to obtain the updated element, the specific expression is: ; Where, represents the th updated element in the weight matrix, represents the th element in the weight matrix, represents the learning rate, represents the update coefficient adjusted according to the target element, represents the th damage value.

[0048] Fourth step, cluster all damage values according to all elements in the final weight matrix to obtain multiple clusters.

[0049] Specifically, through the formula: ; obtain the label set .

[0050] Where, represents all damage values, represents the label of the weight corresponding to all damage values in the final weight matrix, The function is used to find the label of the damage value , represents the final weight matrix.

[0051] That is, through the above formula, the label of the element corresponding to the damage value in the final weight matrix is used as the label of the damage value, and then all damage values with the same label are used as a clustering cluster.

[0052] Step 5: Perform secondary clustering on all clustering clusters to obtain multiple target clustering clusters.

[0053] First, for each clustering cluster respectively, the elements of the final weight matrix corresponding to all damage values in the clustering cluster are combined into a vector to obtain the weight vector of the clustering cluster.

[0054] Then, calculate the cosine similarity between every two clustering clusters according to all weight vectors.

[0055] Finally, perform a clustering operation on all clustering clusters according to all cosine similarities to obtain multiple target clustering clusters.

[0056] Exemplarily, a density-based clustering algorithm (DBSCAN, Density-Based Spatial Clustering of Applications with Noise) can be used for the clustering operation. The clustering clusters are used as data points in DBSCAN, the cosine similarity is used as the distance between data points, and the DBSCAN algorithm is used to cluster all data points to obtain the target clustering clusters.

[0057] Step 6: Perform label assignment according to the target clustering cluster corresponding to each damage information to obtain the initial damage label of the corresponding sub-region in the corresponding historical time period.

[0058] Exemplarily, assign a label for distinction to each target clustering cluster (such as numbers 1, 2, 3, used to distinguish different target clustering clusters, and has nothing to do with the labels in the final weight matrix), and use the label of the target clustering cluster as the label of the damage information corresponding to the damage value in the target clustering cluster. The label of the damage information is used as the initial damage label of the corresponding sub-region in the corresponding historical time period.

[0059] Step 13: Use a support vector machine to quantitatively separate all damage information according to all initial damage labels to obtain the final damage label of each sub-region in each historical time period.

[0060] The above final damage label is used to describe the damage category of the sub-region in the historical time period. The damage category is shear damage or tensile damage, that is, the final damage label is shear damage or tensile damage.

[0061] In some embodiments of the present application, the step of quantitatively separating all damage information according to all initial damage labels by using a support vector machine to obtain the final damage label of each sub-region at each historical time period includes: First, construct a Lagrangian function according to all initial damage labels.

[0062] Specifically, the Lagrangian function is: ; Wherein, represents the value of the Lagrangian function, represents the normal vector of the hyperplane, represents the threshold of the support vector machine, represents the non-negative slack coefficient of the non-negative penalty coefficient, and represent Lagrange multipliers, represents the th non-negative penalty coefficient, represents the number of damage information, and are both the th Lagrange multiplier, represents the th initial damage label corresponding to the th damage information, represents the damage value of the

[0063] Second, solve the parameter solutions that should be satisfied for minimizing the Lagrangian function, and substitute the parameter solutions into the Lagrangian function to obtain the objective function.

[0064] Specifically, the parameter solutions are: ; ; ; The objective function is: ; Wherein, represents the damage weight matrix, represents the th Lagrange multiplier, represents the th initial damage label corresponding to the th damage information, represents the damage value of the th damage information,

[0065] In the third step, minimize the objective function to obtain the normal vector and the threshold of the support vector machine.

[0066] Exemplarily, the sequential minimal optimization algorithm can be used to minimize the objective function.

[0067] In the fourth step, construct a hyperplane based on the normal vector and the threshold of the support vector machine.

[0068] Specifically, the hyperplane is: ; where represents the vector on the hyperplane.

[0069] In the fifth step, map all damage information to the feature space, and quantitatively separate all initial damage labels using the hyperplane in the feature space to obtain the directional separation result.

[0070] Specifically, calculate the damage value of each damage information (calculated according to the process of calculating the damage value in step 12), then map the damage value to the feature space, and set the hyperplane in the feature space. The hyperplane divides the feature space into two subspaces, and all damage values are separated in the two subspaces to obtain the directional separation result.

[0071] It should be noted that the above directional separation result is used to describe the subspace where each damage value is located, and the above feature space is used to actually map the damage value and the hyperplane. Specifically, it can be set according to the data format of the damage value. It can be a two-dimensional coordinate system, the hyperplane is a straight line in this two-dimensional coordinate system, and the damage value is a point in this two-dimensional coordinate system.

[0072] In the sixth step, for each damage information, determine whether the damage information is on the first side of the hyperplane in the directional separation result. If so, use tensile damage as the final damage label for the sub-region corresponding to the damage information in the corresponding historical time period; otherwise, use shear damage as the final damage label for the sub-region corresponding to the damage information in the corresponding historical time period.

[0073] Exemplarily, if the damage values are AF and RA, a feature space of a two-dimensional coordinate system as shown in Figure 2 can be constructed. The horizontal axis of this feature space is RA, with the unit of ms / V, the vertical axis is AF, with the unit of kHz, the oblique line is the hyperplane, the side of the hyperplane close to the vertical axis is the first side, the side close to the horizontal axis is the second side. All damage information corresponding to the damage values on the first side is tensile damage, and all damage information corresponding to the damage values on the second side is shear damage. The proportion of tensile damage is 38.3%, and the proportion of shear damage is 61.7%.

[0074] It is understandable that all the above operation processes are those of the support vector machine.

[0075] Step 14: For each historical time period, perform spatial damage analysis based on all the damage information of the historical time period to obtain the damage gray matrix of each sub-region under the historical time period.

[0076] The above damage gray matrix is used to describe the damage degree of the sub-region, and the elements in the damage gray matrix are used to describe the damage degree at the sampling points in the sub-region.

[0077] Exemplarily, the damage degree of the sub-region can be analyzed based on the damage value of the damage information. For example, if the damage information is an acoustic emission signal, the following processing is performed on the sub-region corresponding to the damage information: The concrete three-point bending test model is as Figure 3 shown. The dashed rectangular box is the sub-region under study. Based on the concrete characteristics, a concrete grid model of this sub-region is established, and a calculation domain of 100×120 mm is generated, where Figure 3 a in Figure 3 is the front view,

[0078] Then, according to the spatial coordinate information of the acoustic emission events detected by the acoustic emission signal (i.e., the damaged part in the sub-region) and the above-set parameters, calculate the spatial b value of the concrete (i.e., the damage degree. The smaller the spatial b value, the greater the degree of crack development of the concrete). The specific steps are as follows: Based on the spatial coordinate data of the acoustic emission events, select the sub-region of the mid-span section as the calculation domain for the acoustic emission b value, and perform the calculation according to the following process: Construct the reference point coordinate matrix A according to the L-index criterion (i.e., obtain the coordinate matrix required for the sampling points), and generate k discrete reference points (i.e., sampling points) in the target sub-region according to the reference point coordinate matrix A; Starting from the first reference point, perform the following operations on each reference point in turn: Set the initial search radius r = 0.01 m; Establish a cylindrical spatial domain with the reference point as the center, a radius of the search radius r, and a height of H; Extract the number of acoustic emission events n in the time window t within this spatial domain; If n≥N threshold, use the least squares method to fit and obtain the spatial b value; If <N,以Δr=0.01 m为步长迭代扩展搜索半径,返回建立以基准点为中心、半径为搜索半径r、高度H的圆柱体空间域的步骤; All reference points are traversed, and the spatial b values ​​of all reference points are integrated into a matrix to obtain the damage grayscale matrix.

[0079] Among them, the formula for obtaining the spatial b value by least squares fitting is as follows: ; in, is the amplitude of the acoustic emission (AE) event, The amplitude is greater than The number of AE events, is an empirical constant, is the spatial b value (damage degree) of the AE event, Calculates the base 10 logarithm.

[0080] Step 15, based on the damage grayscale matrix and final damage labels of all sub-areas in each historical time period, a three-dimensional damage model of the target concrete area in each historical time period is constructed, and all three-dimensional damage models are serialized to obtain a spatiotemporal evolution damage model of the target concrete area.

[0081] The above three-dimensional damage model is used to describe the damaged sub-areas and damage categories of the target concrete area in the historical time period. The spatiotemporal evolution damage model is used to describe the damage evolution process of the target concrete area in all historical time periods. The spatiotemporal evolution damage model is all three-dimensional damage models arranged in order from early to late.

[0082] Specifically, first, each damage grayscale matrix is ​​displayed as a graph to obtain a grayscale image; then, for each historical time period, all grayscale images in the historical time period are stacked according to the position of each sub-area to obtain the initial three-dimensional damage model of the target concrete area in the historical time period, and then the watershed segmentation algorithm is used to separate the damage grayscale matrix to divide the severely damaged sub-area and other sub-areas in the initial three-dimensional damage model, and then the threshold binarization method is used to set the grayscale value of the severely damaged sub-area to 1 and the grayscale value of other sub-areas to 0, and the sub-areas of shear damage and tensile damage in the initial three-dimensional damage model are visually distinguished according to the final damage label (such as using different colors to represent them) to obtain a three-dimensional damage model; finally, all three-dimensional damage models are sorted in the order of all historical time periods from early to late to obtain the spatiotemporal evolution damage model of the target concrete area.

[0083] The method of the present application is illustrated below with reference to a specific example.

[0084] The method of this application is used to process a certain concrete block, and a damage gray matrix of a sub-region in the concrete block is obtained. The gray-scale image obtained by displaying the damage gray matrix as a graph is as Figure 4 shown. The gray-scale image after threshold binaryzation and visual discrimination is as Figure 5 shown. The front view of the spatio-temporal evolution damage model after stacking and sorting all gray-scale images is as Figure 6 shown. Figure 6 a represents the front view of the three-dimensional damage model corresponding to 0 - 300 seconds (s), Figure 6 b represents the front view of the three-dimensional damage model corresponding to 300 - 600 seconds (s), Figure 6 c represents the front view of the three-dimensional damage model corresponding to 600 - 900 seconds (s). The top view of the spatio-temporal evolution damage model is as Figure 7 shown. Figure 7 a represents the top view of the three-dimensional damage model corresponding to 0 - 300 seconds (s), Figure 7 b represents the top view of the three-dimensional damage model corresponding to 300 - 600 seconds (s), Figure 7 c represents the top view of the three-dimensional damage model corresponding to 600 - 900 seconds (s).

[0085] It is worth mentioning that damage mapping of damage information can realize the preliminary discrimination of damage information. Using a support vector machine to quantitatively separate damage information to obtain the final damage label can further classify damage information in detail, improve the accuracy of the final damage label, and construct a spatio-temporal evolution damage model based on the accurate final damage label, which can effectively improve the accuracy of concrete damage spatio-temporal evolution. It realizes the technical leap of concrete damage from "passive perception" to "active prediction", providing an intelligent decision-making basis for engineering stability control.

[0086] As Figure 8 shown, an embodiment of this application provides a concrete damage spatio-temporal evolution recognition device. The concrete damage spatio-temporal evolution recognition device 800 includes: An acquisition module 801, configured to acquire damage information of each sub-region of a target concrete area in multiple historical time periods; A damage mapping module 802, configured to perform damage mapping based on all damage information to obtain an initial damage label for each sub-region in each historical time period; the initial damage label is used to classify all damage information; A quantitative separation module 803, configured to use a support vector machine to quantitatively separate all damage information according to all initial damage labels to obtain a final damage label for each sub-region in each historical time period; the final damage label is used to describe the damage category of the sub-region in the historical time period; An injury analysis module 804 is configured to perform spatial injury analysis based on all injury information of each historical time period for each historical time period, so as to obtain an injury gray scale matrix of each sub-region under the historical time period; the injury gray scale matrix is used to describe the injury degree of the sub-region. A construction module 805 is configured to construct a three-dimensional injury model of the target concrete region for each historical time period according to the injury gray scale matrices of all sub-regions and the final injury labels under each historical time period, and serialize all the three-dimensional injury models to obtain a spatio-temporal evolution injury model of the target concrete region; the three-dimensional injury model is used to describe the damaged sub-regions and injury categories of the target concrete region under the historical time period, and the spatio-temporal evolution injury model is used to describe the injury evolution process of the target concrete region in all historical time periods.

[0087] It should be noted that for the information interaction, execution process, etc. between the above-mentioned devices / units, since they are based on the same concept as the method embodiments of the present application, their specific functions and the technical effects brought thereby can be specifically referred to the method embodiment part, and will not be elaborated here.

[0088] Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0089] As Figure 9 shown, an embodiment of the present application provides a terminal device. The terminal device D10 in this embodiment includes: at least one processor D100 ( Figure 9 only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, the steps in any of the above method embodiments are implemented.

[0090] Specifically, when the processor D100 executes the computer program D102, it obtains the damage information of each sub-region in the target concrete area in multiple historical time periods, then performs damage mapping based on all the damage information to obtain the initial damage label of each sub-region in each historical time period. Then, using a support vector machine, it quantitatively separates all the damage information according to all the initial damage labels to obtain the final damage label of each sub-region in each historical time period. Then, for each historical time period respectively, it performs spatial damage analysis based on all the damage information of the historical time period to obtain the damage gray matrix of each sub-region in the historical time period. Finally, according to the damage gray matrix and the final damage label of all sub-regions in each historical time period, it constructs a three-dimensional damage model of the target concrete area in each historical time period, and serializes all the three-dimensional damage models to obtain the spatio-temporal evolution damage model of the target concrete area. Among them, performing damage mapping on the damage information can achieve a preliminary distinction of the damage information. Using a support vector machine to quantitatively separate the damage information to obtain the final damage label can further classify the damage information in detail and improve the accuracy of the final damage label. Constructing a spatio-temporal evolution damage model based on the accurate final damage label can effectively improve the accuracy of the spatio-temporal evolution of concrete damage.

[0091] The so-called processor D100 may be a central processing unit (CPU, Central Processing Unit), and this processor D100 may also be other general-purpose processors, digital signal processors (DSP, Digital Signal Processor), application specific integrated circuits (ASIC, Application Specific Integrated Circuit), field-programmable gate arrays (FPGA, Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0092] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In some other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk equipped on the terminal device D10, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory D101 may also include both the internal storage unit and the external storage device of the terminal device D10. The memory D101 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as program codes of the computer program. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0093] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor, can implement the steps in the above-mentioned method embodiments.

[0094] An embodiment of the present application provides a computer program product, which when running on a terminal device, enables the terminal device to execute the steps in the above-mentioned method embodiments.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program codes, and the computer program codes can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can at least include: any entity or device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media that can carry the computer program codes to the concrete damage spatio-temporal evolution recognition method device / terminal device. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc.

[0096] In the above embodiments, the descriptions of the respective embodiments each have their own emphasis. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0097] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0098] The above is the preferred implementation manner of this application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle described in this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for identifying the spatio-temporal evolution of concrete damage, characterized in that, Including: Obtaining the damage information of each sub-region in the target concrete area for multiple historical time periods; Performing damage mapping based on all the damage information to obtain the initial damage labels of each sub-region for each historical time period; The initial damage labels are used to classify all the damage information; Using a support vector machine, quantitatively separating all the damage information according to all the initial damage labels to obtain the final damage labels of each sub-region for each historical time period; The final damage labels are used to describe the damage categories of the sub-regions in the historical time periods; For each historical time period respectively, performing spatial damage analysis based on all the damage information of the historical time period to obtain the damage gray-scale matrix of each sub-region in the historical time period; the damage gray-scale matrix is used to describe the damage degree of the sub-region; According to the damage gray-scale matrices and the final damage labels of all the sub-regions for each historical time period, constructing a three-dimensional damage model of the target concrete area for each historical time period, and serializing all the three-dimensional damage models to obtain the spatio-temporal evolution damage model of the target concrete area; the three-dimensional damage model is used to describe the damaged sub-regions and the damage categories in the target concrete area for the historical time period, and the spatio-temporal evolution damage model is used to describe the damage evolution process of the target concrete area for all the historical time periods.

2. The method for identifying the spatio-temporal evolution of concrete damage according to claim 1, characterized in that The performing damage mapping based on all the damage information to obtain the initial damage labels of each sub-region for each historical time period includes: For each of the damage information respectively, analyzing the damage information to obtain the damage value corresponding to the damage information; Initializing a weight matrix, and normalizing each of the damage values to obtain a standard damage value; multiple elements in the weight matrix correspond one by one to multiple damage values; Using all the standard damage values to iteratively update the weight matrix to obtain a final weight matrix; Clustering all the damage values according to all the elements in the final weight matrix to obtain multiple clustering clusters; Performing secondary clustering on all the clustering clusters to obtain multiple target clustering clusters; Performing label assignment according to the target clustering cluster corresponding to each damage information to obtain the initial damage label of the sub-region corresponding to each damage information for the corresponding historical time period.

3. The method for identifying the spatio-temporal evolution of concrete damage according to claim 2, characterized in that, The using all the standard damage values to iteratively update the weight matrix to obtain a final weight matrix includes: Incrementing the iteration count by 1; Judging whether the iteration count reaches a preset number; If so, taking the weight matrix as the final weight matrix; Otherwise, randomly selecting a standard damage value from all the standard damage values as a sample damage value; Calculating the similarity between the sample damage value and each element in the weight matrix, and taking the element with the maximum similarity as the target element; For each element in the weight matrix respectively, judging whether the element is equal to the target element, if so, updating the element according to the target element to obtain the updated element, otherwise, taking the element as the updated element; Integrate all updated elements to obtain an updated weight matrix, and use the updated weight matrix as the weight matrix, then return to the step of adding 1 to the iteration number.

4. The method for identifying the spatio-temporal evolution of concrete damage according to claim 2, wherein The secondary clustering of all clustering clusters to obtain multiple target clustering clusters includes: For each of the clustering clusters, combine the elements of the final weight matrix corresponding to all damage values in the clustering cluster into a vector to obtain the weight vector of the clustering cluster; Calculate the cosine similarity between every two clustering clusters according to all weight vectors; Perform a clustering operation on all clustering clusters according to all cosine similarities to obtain multiple target clustering clusters.

5. The method for identifying the spatio-temporal evolution of concrete damage according to claim 1, characterized in that, The final damage label is shear damage or tensile damage; Using the support vector machine to quantitatively separate all damage information according to all initial damage labels to obtain the final damage label of each sub-region at each historical time period, including: Construct a Lagrangian function according to all initial damage labels; Solve the parameter solution that should be satisfied by minimizing the Lagrangian function, and substitute the parameter solution into the Lagrangian function to obtain an objective function; Minimize the objective function to obtain the normal vector and the threshold of the support vector machine; Construct a hyperplane according to the normal vector and the threshold of the support vector machine; Map all damage information to the feature space, and use the hyperplane in the feature space to quantitatively separate all initial damage labels to obtain an oriented separation result; For each damage information, determine whether the damage information is on the first side of the hyperplane in the oriented separation result. If so, use tensile damage as the final damage label of the sub-region corresponding to the damage information at the corresponding historical time period. Otherwise, use shear damage as the final damage label of the sub-region corresponding to the damage information at the corresponding historical time period.

6. The method for identifying the spatio-temporal evolution of concrete damage according to claim 5, characterized in that, The Lagrangian function is: Among them, represents the value of the Lagrangian function, represents the normal vector of the hyperplane, represents the threshold of the support vector machine, represents the non - negative slack coefficient is the non - negative penalty coefficient, and represent the Lagrange multipliers, represents the th non - negative penalty coefficient, represents the number of damage information, and are both the th Lagrange multipliers, represents the initial damage label corresponding to the th damage information, represents the damage value of the th damage information.

7. The method for identifying the spatio-temporal evolution of concrete damage according to claim 6, wherein The parameter solution is: ； The objective function is: Among them, represents the damage weight matrix, represents the th Lagrange multiplier, represents the initial damage label corresponding to the th damage information, represents the damage value of the th damage information, represents the transpose operation.

8. The method for identifying the spatio-temporal evolution of concrete damage according to claim 7, characterized in that, The hyperplane is: Among them, represents the vector on the said hyperplane.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the concrete damage spatio-temporal evolution recognition method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the concrete damage spatio-temporal evolution recognition method according to any one of claims 1 to 8.

Images