Method and system for predicting crack angle of three-cantilever beam structure based on multi-classification problem

Abstract

The invention belongs to the technical field of building monitoring, and discloses a three-cantilever beam structure crack angle prediction method and system based on a multi-classification problem, and the method comprises the following steps: obtaining simulation data sets of a three-cantilever beam identification body structure under different crack conditions; according to the simulation data set, through multivariable visualization and correlation analysis, identifying multicollinearity between the crack angle data and the cantilever beam strain data, and deleting redundant variables to obtain an optimized data set; on the basis of the optimized data set, a crack angle prediction model is constructed by adopting multiple algorithms oriented to a multi-classification problem; and the obtained cantilever beam strain data are input into the crack angle prediction model, and corresponding crack angle data are predicted through the crack angle prediction model. According to the invention, the dynamic change of the existing crack under the load effect can be monitored, and the trend information of the new crack can be identified.

Description

Technical Field

[0001] The present invention relates to the technical field of building monitoring, and particularly to a method and system for predicting crack angles of a three-cantilever beam structure based on multi-classification problems. Background Art

[0002] Buildings are important places or facilities for humans to live or engage in various survival activities, and their safety directly affects human survival and development. Therefore, accurate health monitoring of buildings such as buildings and bridges is an important research direction in modern engineering. The main purpose of building structure health monitoring is to collect information on various different physical quantities by installing various sensors on structures such as buildings, roads, and bridges, obtain the structural responses of buildings, roads, and bridges to factors such as human or environmental excitation, and further judge the degree of structural damage, provide safety assessments and maintenance references for the human living environment, and provide a basis for predicting its future health trends. The core of structural health monitoring is information acquisition, analysis, and judgment. With the continuous improvement of humans' requirements for the safety of the living environment, sensing the structural health through sensors is becoming an effective means and measure and is widely used; at the same time, traditional structural health monitoring means and measurement methods that highly rely on manual work are gradually withdrawing from the historical stage, and intelligent sensors and massive data processing technologies based on artificial intelligence are quickly highlighting their advantages and will play an increasingly important role in the field of structural health monitoring.

[0003] Currently, the connotation of building structure health monitoring is all-encompassing, and cracks are one of the important monitoring objects. There are various crack monitoring methods such as sensors and fiber Bragg gratings. There are various modes of sensor monitoring, and among them, the strain gauge type is widely favored due to its simple structure. However, the existing method of pasting strain gauges on a double-cantilever beam structure can identify the width of existing cracks, but cannot predict the width and direction (angle) of newly generated cracks.

[0004] Therefore, how to provide a method and system for predicting crack angles of a three-cantilever beam structure based on multi-classification problems is an urgent problem to be solved at present. Summary of the Invention

[0005] Embodiments of the present invention provide a method and system for predicting crack angles of a three-cantilever beam structure based on multi-classification problems to solve the problems in the prior art.

[0006] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a preamble to the subsequent detailed description.

[0007] According to the first aspect of the embodiments of the present invention, a method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem is provided.

[0008] In one embodiment, the method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem includes the following steps: Perform static simulation on the three-cantilever beam recognition body structure using the finite element method, and obtain a simulation data set of the three-cantilever beam recognition body structure under different crack conditions; the simulation data set includes crack angle data and cantilever beam strain data; According to the simulation data set, through multi-variable visualization and correlation analysis, identify the multi-collinearity between the crack angle data and the cantilever beam strain data, and delete redundant variables to obtain an optimized data set; Based on the optimized data set, use multiple algorithms for multi-classification problems to construct a crack angle prediction model; Obtain the cantilever beam strain data and input it into the crack angle prediction model, and predict the corresponding crack angle data through the crack angle prediction model.

[0009] In one embodiment, the step of performing static simulation on the three-cantilever beam recognition body structure using the finite element method and obtaining a simulation data set of the three-cantilever beam recognition body structure under different crack conditions includes the following steps: Construct a simulation measurement environment for the three-cantilever beam recognition body structure and the matching calibration structure, and determine the constraint conditions of the three-cantilever beam recognition body structure; Combined with the preset simulation purpose, determine the boundary conditions of the three-cantilever beam recognition body structure and the matching calibration structure; Perform static simulation in the finite element analysis software, and collect the strain data of the three-cantilever beam recognition body structure under different crack conditions to obtain a simulation data set.

[0010] In one embodiment, the step of performing static simulation in the finite element analysis software, collecting the strain data of the three-cantilever beam recognition body structure under different crack conditions, and obtaining a simulation data set includes the following steps: Create a three-dimensional geometric model of the three-cantilever beam recognition body structure and the matching calibration structure in the finite element analysis software, and perform mesh division processing on the geometric model; Based on the constraint conditions of the three-cantilever beam recognition body structure, apply a load to the three-cantilever beam recognition body structure, and obtain the strain data at the cantilever of the three-cantilever beam recognition body structure to obtain a simulation data set.

[0011] In one embodiment, the load applied to the three-cantilever beam recognition body structure is a forced displacement load.

[0012] In one embodiment, the constraint condition of the three-cantilever beam recognition body structure is to fix the width of the crack and change the size of the crack angle.

[0013] In one embodiment, according to the simulation data set, through multivariate visualization and correlation analysis, identifying the multicollinearity between the crack angle data and the cantilever beam strain data, and deleting redundant variables, obtaining the optimized data set includes the following steps: For the simulation data set, use visualization software to draw the corresponding relationship diagram between variables, by observing the distribution relationship and trend between variables, and combining with the multiple regression model to calculate the coefficient of determination; the variables include the response variable vector and the regression variables; Calculate the variance inflation factor of the regression variables according to the coefficient of determination, and judge whether there is a multicollinearity problem between the regression variables based on a preset threshold. If so, delete the regression variables. Otherwise, retain the regression variables; Integrate the deleted or retained regression variables with the response variable vector to obtain the optimized data set.

[0014] In one embodiment, based on the optimized data set, adopting multiple algorithms for multi-classification problems, constructing a crack angle prediction model includes the following steps: Treat the crack angle in the optimized data set as a discrete variable, and divide the crack angle range into multiple subclasses according to a preset step size; Adopt multiple algorithms for multi-classification problems to construct a classification model, and according to the optimized data set divided into multiple subclasses by the crack angle, train and evaluate the performance of the classification model to obtain performance evaluation indicators; Based on the performance evaluation indicators, analyze the performance of each classification model in the crack angle prediction task, and according to the analysis results, select the model with the best performance as the final crack angle prediction model.

[0015] In one embodiment, adopting multiple algorithms for multi-classification problems to construct a classification model, and according to the optimized data set divided into multiple subclasses by the crack angle, train and evaluate the performance of the classification model to obtain performance evaluation indicators includes the following steps: Divide the optimized data set divided into multiple subclasses by the crack angle into a training set and a test set according to a preset division ratio; Using the training set, respectively use the extreme gradient boosting classification model, the K-nearest neighbor classification model, the decision tree classification model, the random forest classification model and the support vector machine classification model; Using the test set, test the trained extreme gradient boosting classifier, K-nearest neighbor classifier, decision tree classifier, random forest classifier and support vector machine classifier, and evaluate the performance of each classifier according to the test results to obtain performance evaluation indicators.

[0016] In one embodiment, the performance evaluation indicators include: precision rate, recall rate and F1 score.

[0017] According to the second aspect of the embodiments of the present invention, a three-cantilever beam structure crack angle prediction system based on a multi-classification problem is provided.

[0018] In one embodiment, the three-cantilever beam structure crack angle prediction system based on a multi-classification problem includes: A data acquisition unit, configured to perform static simulation on the three-cantilever beam identification body structure by using the finite element method, and acquire a simulation data set of the three-cantilever beam identification body structure under different crack conditions; the simulation data set includes crack angle data and cantilever beam strain data; A data optimization unit, configured to identify the multi-collinearity between the crack angle data and the cantilever beam strain data according to the simulation data set through multi-variable visualization and correlation analysis, and delete redundant variables to obtain an optimized data set; A model construction unit, configured to construct a crack angle prediction model based on the optimized data set by using various algorithms for multi-classification problems; An angle prediction unit, configured to acquire the cantilever beam strain data and input it into the crack angle prediction model, and predict the corresponding crack angle data through the crack angle prediction model.

[0019] According to the third aspect of the embodiments of the present invention, a computer device is provided.

[0020] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0021] According to the fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided.

[0022] In one embodiment, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0023] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: With the application background of building structure health monitoring, the present invention has carried out technical theoretical research on multi-dimensional identification and situation prediction of tiny gaps in the structure based on the sensor monitoring method. Different from other methods of crack monitoring, the sensor monitoring method based on the strain principle of strain gauges has simple deployment, stable and reliable operation, low cost, high sensitivity and accuracy, and balanced performance indicators. Aiming at the limitations of the double-cantilever beam single-dimensional identification method, a three-cantilever beam multi-dimensional identification method is proposed, which increases the measurement dimension and can not only monitor the dynamic changes of existing cracks under load, but also identify the information of the new crack direction.

[0024] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present invention. Description of the Drawings

[0025] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments in accordance with the present invention, and are used together with the specification to explain the principles of the present invention.

[0026] Figure 1 is a flowchart of a method for predicting crack angles of a three-cantilever beam structure based on a multi-classification problem shown according to an exemplary embodiment; Figure 2 is a schematic block diagram of a system for predicting crack angles of a three-cantilever beam structure based on a multi-classification problem shown according to an exemplary embodiment; Figure 3 is a schematic structural diagram of a computer device shown according to an exemplary embodiment; Figure 4 is a line graph of evaluation indexes of a three-cantilever beam angle prediction model based on a multi-classification problem in a method for predicting crack angles of a three-cantilever beam structure shown according to an exemplary embodiment; Figure 5 is a line graph of the number of correctly classified samples of a three-cantilever beam angle prediction model based on a multi-classification problem in a method for predicting crack angles of a three-cantilever beam structure shown according to an exemplary embodiment. Detailed Embodiments

[0027] The following description and the drawings fully illustrate the specific embodiments herein so that those skilled in the art can practice them. Parts and features of some embodiments can be included in or replaced with parts and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims and all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another element, and do not require or imply any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a structure, device or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such structure, device or equipment. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of another identical element in the structure, device or equipment including the element. The embodiments herein are described in a progressive manner, and the key points of each embodiment are the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other.

[0028] The terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. in this text indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. These are only for the convenience of describing this text and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In the description of this text, unless otherwise specified and defined, the terms "installed", "connected", and "coupled" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the communication inside two elements. It can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0029] In this text, unless otherwise stated, the term "plurality" means two or more.

[0030] In this text, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0031] In this text, the term "and / or" is an associative relationship describing an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, the three relationships of A and B.

[0032] It should be understood that although each step in the flowchart is displayed in sequence according to the indication of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless there is a clear description in this text, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the figure can include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0033] Each module in the device or system of this application can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0034] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0035] Figure 1 An embodiment of the crack angle prediction method for a three - cantilever beam structure based on a multi - classification problem of the present invention is shown.

[0036] In this alternative embodiment, the crack angle prediction method for a three - cantilever beam structure based on a multi - classification problem includes the following steps: Step S101: Perform a static simulation on the three - cantilever beam identification body structure using the finite element method, and obtain a simulation data set of the three - cantilever beam identification body structure under different crack conditions; the simulation data set includes crack angle data and cantilever beam strain data; Step S102: According to the simulation data set, through multivariate visualization and correlation analysis, identify the multicollinearity between the crack angle data and the cantilever beam strain data, and delete redundant variables to obtain an optimized data set; Step S103: Based on the optimized data set, use various algorithms for multi - classification problems to construct a crack angle prediction model; Step S104: Obtain the cantilever beam strain data and input it into the crack angle prediction model, and predict the corresponding crack angle data through the crack angle prediction model.

[0037] It should be noted that the finite element analysis software used in the present invention includes Solid Works and Ansys. No matter which one is used for static simulation, as long as the premise assumptions and set parameters are reasonably consistent, the simulation results are basically the same. The traditional finite element analysis objects are mainly based on structural mechanics models. However, with the increasing wide application of multi - physical - field simulations, simulations based on fluid mechanics, thermodynamics, electromagnetic fields, etc. have also been widely used. It should be pointed out that the finite element analysis process in different application fields is basically the same, that is, establishing the geometric structure of the model, clarifying the constraint relationships between the components of the geometric structure, defining materials and loads, mesh generation, and solving and outputting according to the type of simulation parameters.

[0038] In this alternative embodiment, the step of performing a static simulation on the three - cantilever beam identification body structure using the finite element method and obtaining a simulation data set of the three - cantilever beam identification body structure under different crack conditions includes the following steps: Construct a simulation measurement environment for the three - cantilever beam identification body structure and the matching calibration structure, and determine the constraint conditions of the three - cantilever beam identification body structure; Combined with the preset simulation purpose, determine the boundary conditions of the three - cantilever beam identification body structure and the matching calibration structure; Perform a static simulation in the finite element analysis software, and collect the strain data of the three - cantilever beam identification body structure under different crack conditions to obtain a simulation data set.

[0039] Among them, the three-cantilever beam recognition body structure is the main body of the three-cantilever beam multi-dimensional recognition body mechanical structure, which is composed of a bottom plate, spring steel sheets, pressing blocks, PCB bearing studs, mounting feet, etc. The simplified structure material of the three-cantilever beam recognition body is ordinary carbon steel.

[0040] Among them, the matching and calibration structure includes two calibration platforms arranged symmetrically and a calibration thread hole array evenly distributed with the distance between the installation thread holes of the simplified structure as the diameter. The change in the crack direction is achieved by changing the matching relationship between the installation holes of the simplified structure and the calibration thread hole array; the change in the crack width is achieved by changing the displacement between the calibration platforms. The change of the matching parameters and displacement parameters during the simulation process is collectively referred to as the change of the test conditions. The simplified structure is constrained by the installation thread holes at the feet and a certain symmetric thread of the calibration thread hole array; the bottom plane of the simplified structure is respectively constrained by the contact surface with the calibration platform; the calibration platforms are constrained by the contact surface. Once the constraint relationship is established, it means that the cooperation is rigidly connected during the simulation process, that is, there is no relative displacement.

[0041] In this alternative embodiment, the static simulation is performed in the finite element analysis software, and the strain data of the three-cantilever beam recognition body structure under different crack conditions are collected, and the simulation data set is obtained through the following steps: Create a three-dimensional geometric model of the three-cantilever beam recognition body structure and the matching and calibration structure in the finite element analysis software, and perform mesh division processing on the geometric model; Based on the constraint conditions of the three-cantilever beam recognition body structure, apply a load to the three-cantilever beam recognition body structure, and obtain the strain data at the upper cantilever of the three-cantilever beam recognition body structure to obtain the simulation data set.

[0042] In one embodiment, the load applied to the three-cantilever beam recognition body structure is a forced displacement load.

[0043] In this alternative embodiment, the constraint condition of the three-cantilever beam recognition body structure is to fix the crack width and change the crack angle.

[0044] Specifically, under the condition of constant crack width, the adjustment of the crack direction is achieved by changing the matching relationship between the installation holes of the simplified structure and the calibration thread hole array. The description of the crack direction requires the use of a reference cantilever beam and a reference zero degree. Cantilever beams A, B, as well as 0° and 180° are all reference points for the description of the crack direction. The crack direction is parallel to the width direction of the cross beam, perpendicular to the length direction of the cross beam, and the intersection point is located at the center point of the intersection of the width direction and the length direction of the cross beam.

[0045] In this alternative embodiment, according to the simulation data set, through multi-variable visualization and correlation analysis, the multi-collinearity between the crack angle data and the cantilever beam strain data is identified, and the redundant variables are deleted, and the optimized data set is obtained through the following steps: For the simulation data set, use visualization software to plot the corresponding relationship diagram between variables. By observing the distribution relationship and trend among variables, and combining with the multiple regression model, calculate the coefficient of determination; the variables include the response variable vector and the regression variables. Calculate the variance inflation factor of the regression variables according to the coefficient of determination, and judge whether there is a problem of multicollinearity among the regression variables based on a preset threshold. If so, delete the regression variables; otherwise, retain the regression variables. Integrate the deleted or retained regression variables with the response variable vector to obtain an optimized data set.

[0046] The calculation formula for the variance inflation factor of the regression variables according to the coefficient of determination is: ; In the formula, represents the variance inflation factor of the regression variable j , represents the coefficient of determination of the regression variable j .

[0047] In addition, if the regression variables participating in the establishment of the prediction model are orthogonal, an inaccurate inference can be obtained, that is, the regression variables have little influence on each other and are suitable for the prediction model. In most cases, the regression variables are not orthogonal, and the lack of orthogonality is not a serious problem restricting the quality of the prediction model; if there is a near-linear relationship among the regression variables, there may be a problem of multicollinearity, which may lead to the prediction model being misled and giving wrong prediction conclusions.

[0048] To check for multicollinearity in variable data, first introduce the multiple regression model: ; In the formula, y is the response variable vector, X is the regression variable matrix, β is the coefficient vector, is the random error, where follows a normal distribution with a mean of 0 and a variance of . If there exists a set t 1 , t 2 ，t 3 ,.......,, t p that are not all zero and satisfy the equation: ; In the formula, p represents the upper limit of the summation operation ( j = 1~ p ), represents the regression coefficient.

[0049] Then the regression variable X can be considered linearly correlated. If a subset of X satisfies the above equation, the rank of the correlation coefficient matrix is less than p, and at the same time does not exist. Assuming that it is approximately true for a partial subset of X, then there will be linear correlation, and the problem of multicollinearity can be considered to exist.

[0050] The variance inflation factor is usually used to test for multicollinearity. For the correlation coefficient matrix, we have: ; The j-th diagonal element of the correlation coefficient matrix C can be written as: ; where is the coefficient of determination obtained when is regressed on the other (p - 1) regression variables. If the regression variables are nearly orthogonal, then is small and is close to 1; if there is a nearly linear relationship between the regression variables, then is close to 1 and instead becomes larger. Since the variance of the j-th regression coefficient is , where can be regarded as the influence factor for the increase in the variance of the least squares estimate of the slope , is taken as the variance inflation factor to test for multicollinearity. According to the multicollinearity diagnosis criterion, if the variance inflation factor is less than 10, it can be considered that there is no multicollinearity problem among the regression variables, and the smaller this index, the better; on the contrary, if it is greater than 10, it indicates that there is a multicollinearity problem among the regression variables and the severity of the problem increases with the increase of this index.

[0051] In addition, the following are several common methods to solve multicollinearity: (1) Increasing the amount of data of the regression variables: The biggest problem of multicollinearity is that it increases the variance of the least squares estimate of the slope . Increasing the amount of data of the regression variables can generally reduce the variance of the parameter estimates, thereby reducing the impact of multicollinearity; on the other hand, the increase in the amount of data is restricted by many practical factors, such as cost or the scope of the design model, etc.

[0052] (2)Reducing the types of regression variables: When there are 3 or more types of regression variables, deleting one of the two regression variables with multicollinearity problems may solve the problems caused by multicollinearity. However, deleting variables will also result in the loss of variable information in the prediction model. Once important variables are removed, the quality of the prediction model will be immediately affected.

[0053] (3)Performing data dimensionality reduction on regression variables: Data dimensionality reduction refers to generating new regression variables through a certain operation using two or more original regression variables to replace the original regression variables. Performing data dimensionality reduction requires minimizing information loss after the emergence of new variables and the deletion of original variables. The common data dimensionality reduction method is principal component analysis.

[0054] (4)Adding penalty terms: For linear regression models, adding penalty terms (regularization terms) to the loss function (cost function) to eliminate multicollinearity is a commonly used method. For penalty terms: The L0 norm penalty term starts from non-zero parameters for restriction, that is, restricting the number of non-zero parameters within a certain range to achieve the purpose of restricting the model; The L1 norm penalty term requires the sum of parameter values to be restricted within a certain range, that is, the sum of parameters needs to be less than a certain value. The L1 norm penalty is also called parameter sparsity penalty; The L2 norm penalty term adds a square term to avoid the problem of positive and negative cancellation. The L2 norm penalty is also called weight decay penalty. Among the multiple regression algorithms selected by the invention, the LASSO regression uses the L1 norm penalty term; The Ridge regression uses the L2 norm penalty term.

[0055] (5)Ostrich policy: The essence of the ostrich policy is to ignore the multicollinearity problem. If the prediction model is not affected by the multicollinearity of the known data, the multicollinearity problem can be ignored. The rationality of the ostrich policy also shows from another angle that the multicollinearity problem among regression variables cannot be used as a necessary and sufficient condition for the inapplicability of the prediction model.

[0056] In this alternative embodiment, the method of constructing a crack angle prediction model by using multiple algorithms for multi-classification problems based on the optimized data set includes the following steps: Treat the crack angles in the optimized data set as discrete variables, and divide the crack angle range into multiple subclasses according to a preset step size; Use multiple algorithms for multi-classification problems to construct a classification model, and train and evaluate the performance of the classification model according to the optimized data set divided into multiple subclasses by crack angles to obtain performance evaluation indicators; Based on the performance evaluation indicators, analyze the performance of each classification model in the crack angle prediction task, and select the model with the best performance as the final crack angle prediction model according to the analysis results.

[0057] In this alternative embodiment, the steps of constructing a classification model using multiple algorithms for multi-classification problems, dividing the optimized data set into multiple sub-classes according to the crack angle, training and evaluating the performance of the classification model, and obtaining performance evaluation metrics include the following: Divide the optimized data set with the crack angle divided into multiple sub-classes according to a preset division ratio into a training set and a test set; Using the training set, respectively use the Extreme Gradient Boosting classification model, K-Nearest Neighbor classification model, Decision Tree classification model, Random Forest classification model, and Support Vector Machine classification model; Using the test set, test the trained Extreme Gradient Boosting classifier, K-Nearest Neighbor classifier, Decision Tree classifier, Random Forest classifier, and Support Vector Machine classifier, and evaluate the performance of each classifier according to the test results to obtain performance evaluation metrics.

[0058] In this alternative embodiment, the performance evaluation metrics include: precision, recall, and F1 score.

[0059] It should be noted that five algorithms for multi-classification problems, including the Extreme Gradient Boosting classifier, are used in the establishment of the angle prediction model of the three-cantilever beam multi-dimensional recognition method.

[0060] Without considering cross-validation, directly establish a prediction model for the above five classifiers, train and validate it, and obtain the corresponding accuracy Accuracy 、precision Precision 、recall Recall 、and the number of samples correctly classified by each classifier for the test set data, Figure 4 - Figure 5 Respectively give a line chart of the evaluation metrics and the number of correctly classified samples.

[0061] Among the angle prediction models established by using five classifiers based on multi-classification problems, the K-Nearest Neighbor classifier has the highest precision, about 98.6%, and the Support Vector Machine classifier has the lowest precision, about 1.4%; the recall conclusion is the same as the precision; the K-Nearest Neighbor classifier has the highest accuracy, about 98.8%, and the Support Vector Machine classifier has the lowest accuracy, about 0.1%; the maximum number of correctly classified samples is 479 cases (K-Nearest Neighbor classifier, Decision Tree classifier, and Random Forest classifier), and the minimum is only 7 cases (Support Vector Machine classifier). In summary, it is feasible to establish an angle prediction model for the three-cantilever beam multi-dimensional recognition method using the K-Nearest Neighbor classifier based on multi-classification problems, and the evaluation metrics meet the error requirements of engineering practice for crack angle measurement. The Decision Tree classifier and Random Forest classifier can both be used as alternative solutions for establishing this prediction model.

[0062] Figure 2 An embodiment of the crack angle prediction system for a three-cantilever beam structure based on multi-classification problems of the present invention is shown.

[0063] In this alternative embodiment, the three-cantilever beam structure crack angle prediction system based on multi-classification problems includes: A data acquisition unit 201, configured to perform static simulation on the three-cantilever beam identification body structure using the finite element method, and obtain a simulation data set of the three-cantilever beam identification body structure under different crack conditions; the simulation data set includes crack angle data and cantilever beam strain data; A data optimization unit 202, configured to identify the multicollinearity between the crack angle data and the cantilever beam strain data according to the simulation data set through multivariate visualization and correlation analysis, and delete redundant variables to obtain an optimized data set; A model construction unit 203, configured to construct a crack angle prediction model based on the optimized data set using multiple algorithms for multi-classification problems; An angle prediction unit 204, configured to obtain the cantilever beam strain data and input it into the crack angle prediction model, and predict the corresponding crack angle data through the crack angle prediction model.

[0064] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in Figure 3 The figure. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0065] Those skilled in the art can understand that Figure 3 The structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0066] In addition, the present invention also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiment are implemented.

[0067] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0068] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided by the present invention can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0069] The present invention is not limited to the structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem, characterized in that Including the following steps: Using the finite element method to conduct static simulation on the three-cantilever beam identification body structure, and obtaining the simulation data set of the three-cantilever beam identification body structure under different crack conditions; the simulation data set includes crack angle data and cantilever beam strain data; According to the simulation data set, through multivariate visualization and correlation analysis, identifying the multicollinearity between the crack angle data and the cantilever beam strain data, and deleting redundant variables to obtain an optimized data set; Based on the optimized data set, using multiple algorithms for multi-classification problems to construct a crack angle prediction model; Obtaining the cantilever beam strain data and inputting it into the crack angle prediction model, and predicting the corresponding crack angle data through the crack angle prediction model.

2. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 1, wherein The step of using the finite element method to conduct static simulation on the three-cantilever beam identification body structure and obtaining the simulation data set of the three-cantilever beam identification body structure under different crack conditions includes the following steps: Constructing the simulation measurement environment of the three-cantilever beam identification body structure and the matching calibration structure, and determining the constraint conditions of the three-cantilever beam identification body structure; Combined with the preset simulation purpose, determining the boundary conditions of the three-cantilever beam identification body structure and the matching calibration structure; Conducting static simulation in the finite element analysis software, and collecting the strain data of the three-cantilever beam identification body structure under different crack conditions to obtain a simulation data set.

3. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 2, wherein The step of conducting static simulation in the finite element analysis software and collecting the strain data of the three-cantilever beam identification body structure under different crack conditions to obtain a simulation data set includes the following steps: Creating a three-dimensional geometric model of the three-cantilever beam identification body structure and the matching calibration structure in the finite element analysis software, and performing mesh division processing on the geometric model; Based on the constraint conditions of the three-cantilever beam identification body structure, applying loads to the three-cantilever beam identification body structure, and obtaining the strain data at the cantilever of the three-cantilever beam identification body structure to obtain a simulation data set.

4. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 3, wherein, The load applied to the three-cantilever beam identification body structure is a forced displacement load.

5. The method for predicting crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 2, wherein The constraint conditions of the three-cantilever beam identification body structure are to fix the width of the crack and change the size of the crack angle.

6. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 1, wherein The step of, according to the simulation data set, through multivariate visualization and correlation analysis, identifying the multicollinearity between the crack angle data and the cantilever beam strain data, and deleting redundant variables to obtain an optimized data set includes the following steps: For the simulation data set, using visualization software to draw the corresponding relationship diagram between variables, observing the distribution relationship and trend between variables, and calculating the determination coefficient in combination with the multiple regression model; the variables include the response variable vector and the regression variables; Calculating the variance inflation factor of the regression variables according to the determination coefficient, and judging whether there is a multicollinearity problem between the regression variables based on a preset threshold. If so, deleting the regression variables, otherwise, retaining the regression variables; Integrating the deleted or retained regression variables with the response variable vector to obtain an optimized data set.

7. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 1, wherein The step of, based on the optimized data set, using multiple algorithms for multi-classification problems to construct a crack angle prediction model includes the following steps: Treating the crack angle in the optimized data set as a discrete variable, and dividing the crack angle range into multiple subclasses according to a preset step size; Construct a classification model using multiple algorithms for multi-classification problems, and divide the optimized dataset into multiple subclasses according to the crack angle, train and evaluate the performance of the classification model to obtain performance evaluation metrics; Based on the performance evaluation metrics, analyze the performance of each classification model in the crack angle prediction task, and according to the analysis results, select the model with the best performance as the final crack angle prediction model.

8. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 7, wherein, The steps of constructing a classification model using multiple algorithms for multi-classification problems, dividing the optimized dataset into multiple subclasses according to the crack angle, training and evaluating the performance of the classification model, and obtaining the performance evaluation metrics include the following: Divide the optimized dataset with the crack angle divided into multiple subclasses according to the preset division ratio into a training set and a test set; Using the training set, use the Extreme Gradient Boosting classification model, K-Nearest Neighbor classification model, Decision Tree classification model, Random Forest classification model, and Support Vector Machine classification model respectively; Using the test set, test the trained Extreme Gradient Boosting classifier, K-Nearest Neighbor classifier, Decision Tree classifier, Random Forest classifier, and Support Vector Machine classifier, and evaluate the performance of each classifier according to the test results to obtain performance evaluation metrics.

9. The method for predicting the crack angle of a three-cantilever beam structure based on a multi-classification problem according to claim 8, wherein The performance evaluation metrics include: precision, recall, and F1 score.

10. A three-cantilever beam structure crack angle prediction system based on a multi-classification problem, characterized in that, Include: A data acquisition unit for performing static simulation on the three-cantilever beam identification body structure using the finite element method and obtaining a simulation dataset of the three-cantilever beam identification body structure under different crack conditions; the simulation dataset includes crack angle data and cantilever beam strain data; A data optimization unit for identifying the multicollinearity between the crack angle data and the cantilever beam strain data through multivariate visualization and correlation analysis according to the simulation dataset, and deleting redundant variables to obtain an optimized dataset; A model construction unit for constructing a crack angle prediction model based on the optimized dataset using multiple algorithms for multi-classification problems; An angle prediction unit for obtaining the cantilever beam strain data and inputting it into the crack angle prediction model to predict the corresponding crack angle data through the crack angle prediction model.

Images