Method and device for evaluating comprehensive performance of steel template material

Abstract

The invention relates to the technical field of steel formwork detection, in particular to a comprehensive performance evaluation method and device for a steel formwork material. The method comprises the steps that geometric parameters and material parameters of a steel formwork are obtained, a three-dimensional geometric model of the steel formwork is determined based on the geometric parameters and the material parameters, grid division is conducted on the three-dimensional geometric model of the steel formwork, and the three-dimensional geometric model of the steel formwork after grid division is obtained; inputting the corresponding comprehensive performance evaluation parameters into each node in the geometric model of the steel template subjected to grid division to obtain a simulation model of a steel template material, performing feature extraction on the simulation model of the steel template material to obtain a multi-dimensional feature matrix, and calculating the comprehensive performance of the steel template material according to the multi-dimensional feature matrix. And inputting the multi-dimensional feature matrix into a preset comprehensive performance evaluation model of the steel template material to obtain a comprehensive performance evaluation result of the steel template material. By means of the configuration mode, the comprehensive performance of the steel formwork material can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of steel formwork detection, and particularly to a comprehensive performance evaluation method and device for steel formwork materials. Background Art

[0002] In the construction field, steel formworks are widely used. With the advancement of urbanization and the acceleration of infrastructure construction, their market demand continues to climb, and the types and specifications are becoming increasingly diverse. In addition to traditional flat formworks, special-shaped and large formworks are emerging continuously, and the manufacturing processes and materials are constantly innovating.

[0003] However, the traditional evaluation methods for steel formworks have obvious limitations. Most use a single index for evaluation, such as only focusing on strength or stiffness, which is difficult to comprehensively reflect the comprehensive performance; lack of systematicness, each index is independent of each other, and the correlation between indexes is not considered; strong subjectivity, the evaluation criteria are not unified, and it is greatly affected by the subjective factors of evaluators; and it cannot adapt to the development of construction technology and the new engineering quality requirements.

[0004] Based on this, the present invention proposes a comprehensive performance evaluation method and device for steel formwork materials to solve the above technical problems. Summary of the Invention

[0005] The present invention describes a comprehensive performance evaluation method and device for steel formwork materials, which can accurately evaluate the comprehensive performance of steel formwork materials.

[0006] According to the first aspect, the present invention provides a comprehensive performance evaluation method for steel formwork materials, the method comprising:

[0007] Obtain the geometric parameters and material parameters of the steel formwork;

[0008] Based on the geometric parameters and the material parameters, determine the three-dimensional geometric model of the steel formwork;

[0009] Perform mesh division on the three-dimensional geometric model of the steel formwork to obtain the three-dimensional geometric model of the steel formwork after mesh division; wherein, the three-dimensional geometric model of the steel formwork after mesh division includes a plurality of mesh nodes;

[0010] Input the corresponding comprehensive performance evaluation parameters into each node of the geometric model of the steel formwork after mesh division to obtain the simulation model of the steel formwork material; wherein, the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus and toughness;

[0011] Extract features from the simulation model of the steel formwork material to obtain a multi-dimensional feature matrix; wherein, the multi-dimensional feature matrix is used to characterize the comprehensive performance of the steel formwork material in three-dimensional space;

[0012] Input the multi-dimensional feature matrix into a preset comprehensive performance evaluation model for steel formwork materials to obtain the comprehensive performance evaluation result of the steel formwork materials.

[0013] According to a second aspect, the present invention provides a comprehensive performance evaluation device for steel formwork materials, including:

[0014] An acquisition unit configured to acquire the geometric parameters and material parameters of the steel formwork;

[0015] A first data processing unit configured to determine a three-dimensional geometric model of the steel formwork based on the geometric parameters and the material parameters;

[0016] A second data processing unit configured to perform mesh division on the three-dimensional geometric model of the steel formwork to obtain a three-dimensional geometric model of the steel formwork after mesh division; wherein, the three-dimensional geometric model of the steel formwork after mesh division includes a plurality of mesh nodes;

[0017] A third data processing unit configured to input corresponding comprehensive performance evaluation parameters into each node of the geometric model of the steel formwork after mesh division to obtain a simulation model of the steel formwork materials; wherein, the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus, and toughness;

[0018] A fourth data processing unit configured to perform feature extraction on the simulation model of the steel formwork materials to obtain a multi-dimensional feature matrix; wherein, the multi-dimensional feature matrix is used to characterize the comprehensive performance of the steel formwork materials in three-dimensional space;

[0019] A fifth data processing unit configured to input the multi-dimensional feature matrix into a preset comprehensive performance evaluation model for steel formwork materials to obtain the comprehensive performance evaluation result of the steel formwork materials.

[0020] In a third aspect, an embodiment of this specification further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0021] In a fourth aspect, an embodiment of this specification further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is made to execute the method described in any embodiment of this specification.

[0022] According to the comprehensive performance evaluation method and device for steel formwork materials provided by the present invention, first, the geometric parameters and material parameters of the steel formwork are obtained. The geometric parameters include the size specifications and shape characteristics of the steel formwork; the material parameters include the composition and microstructure of the material. Based on these parameters, using three-dimensional modeling technology, a three-dimensional geometric model of the steel formwork is constructed, which can accurately reflect the geometric shape of the steel formwork in the actual space. Subsequently, a meshing operation is performed on the constructed three-dimensional geometric model of the steel formwork. With the help of the meshing algorithm, the model is discretized into multiple regular or irregular units, thus obtaining the three-dimensional geometric model of the steel formwork after meshing. This model is composed of a large number of mesh nodes, which are the basic units for subsequent analysis. Then, a series of evaluation parameters closely related to the comprehensive performance of the steel formwork are assigned to each node in the meshed model, and thus a simulation model of the steel formwork material is constructed. These comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus, and toughness, which can comprehensively reflect the mechanical properties and deformation characteristics of the steel formwork material under different stress states. After that, by calculating and processing the physical quantities of each node in the model, a multi-dimensional feature matrix that can characterize the comprehensive performance of the steel formwork material in three-dimensional space is extracted. This feature matrix includes the stress distribution, strain state, and energy dissipation at different positions, reflecting the performance characteristics of the steel formwork material from multiple angles. Finally, the extracted multi-dimensional feature matrix is input into the pre-constructed and verified comprehensive performance evaluation model of the steel formwork material. This evaluation model is based on advanced machine learning algorithms or numerical analysis methods, and through training and optimization with a large amount of experimental data, it can accurately analyze and judge the input feature matrix, thereby outputting an accurate comprehensive performance evaluation result of the steel formwork material. Through the above configuration method, the present invention can accurately evaluate the comprehensive performance of the steel formwork material. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 Shows a schematic flowchart of the comprehensive performance evaluation method for steel formwork materials according to an embodiment;

[0025] Figure 2 Shows a schematic block diagram of the comprehensive performance evaluation device for steel formwork materials according to an embodiment. Detailed Embodiments

[0026] The following describes the solution provided by the present invention in conjunction with the drawings.

[0027] Figure 1 A flowchart showing a comprehensive performance evaluation method for steel formwork materials according to an embodiment is shown. It can be understood that this method can be executed by any device, equipment, platform, or equipment cluster with computing and processing capabilities. As Figure 1 shown, this method includes:

[0028] Step 100: Obtain the geometric parameters and material parameters of the steel formwork;

[0029] Step 102: Based on the geometric parameters and material parameters, determine the three-dimensional geometric model of the steel formwork;

[0030] Step 104: Perform mesh division on the three-dimensional geometric model of the steel formwork to obtain the three-dimensional geometric model of the steel formwork after mesh division; wherein, the three-dimensional geometric model of the steel formwork after mesh division includes multiple mesh nodes;

[0031] Step 106: Input the corresponding comprehensive performance evaluation parameters into each node in the geometric model of the steel formwork after mesh division to obtain the simulation model of the steel formwork material; wherein, the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus, and toughness;

[0032] Step 108: Extract features from the simulation model of the steel formwork material to obtain a multi-dimensional feature matrix; wherein, the multi-dimensional feature matrix is used to characterize the comprehensive performance of the steel formwork material in three-dimensional space;

[0033] Step 110: Input the multi-dimensional feature matrix into the preset comprehensive performance evaluation model of the steel formwork material to obtain the comprehensive performance evaluation result of the steel formwork material.

[0034] In this embodiment, first, the geometric parameters and material parameters of the steel formwork are obtained. The geometric parameters include the size specifications and shape characteristics of the steel formwork; the material parameters include the composition and organizational structure of the material. Based on these parameters, using 3D modeling technology, a 3D geometric model of the steel formwork is constructed, which can accurately reflect the geometric shape of the steel formwork in the actual space. Subsequently, a meshing operation is performed on the constructed 3D geometric model of the steel formwork. With the help of a meshing algorithm, the model is discretized into multiple regular or irregular units, thus obtaining the 3D geometric model of the steel formwork after meshing. This model is composed of a large number of mesh nodes, which are the basic units for subsequent analysis. Then, a series of evaluation parameters closely related to the comprehensive performance of the steel formwork are assigned to each node in the meshed model, and then a simulation model of the steel formwork material is constructed. These comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus, and toughness, which can comprehensively reflect the mechanical properties and deformation characteristics of the steel formwork material under different stress states. After that, by calculating and processing the physical quantities of each node in the model, a multi-dimensional feature matrix that can characterize the comprehensive performance of the steel formwork material in 3D space is extracted. This feature matrix includes stress distributions, strain states, and energy dissipations at different positions, reflecting the performance characteristics of the steel formwork material from multiple perspectives. Finally, the extracted multi-dimensional feature matrix is input into a pre-constructed and verified comprehensive performance evaluation model of the steel formwork material. This evaluation model is based on advanced machine learning algorithms or numerical analysis methods, and after being trained and optimized with a large amount of experimental data, it can accurately analyze and judge the input feature matrix, thereby outputting an accurate comprehensive performance evaluation result of the steel formwork material. Through the above configuration method, the present invention can accurately evaluate the comprehensive performance of the steel formwork material.

[0035] In an embodiment of the present invention, after inputting the multi-dimensional feature matrix into the preset comprehensive performance evaluation model of the steel formwork material to obtain the comprehensive performance evaluation result of the steel formwork material, it further includes:

[0036] Obtain the image data of the steel formwork;

[0037] Input the image data of the steel formwork into the preset steel formwork defect detection model to obtain the quantity and types of defects on the surface of the steel formwork;

[0038] Input the quantity and types of defects on the surface of the steel formwork into the evaluation result equations of the steel formwork surface to obtain the evaluation result of the steel formwork surface;

[0039] Based on the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material, determine the final comprehensive performance evaluation result of the steel formwork material.

[0040] In this embodiment, first, image data of the steel formwork is obtained by means of an image acquisition device such as a high-resolution industrial camera. This data contains multi-dimensional visual information such as the texture, color, and potential defects on the surface of the steel formwork. Subsequently, the image data is input into a steel formwork defect detection model that has been pre-trained and verified based on deep learning algorithms such as convolutional neural networks (CNNs). By learning a large number of labeled defect images, this model has the ability to identify and distinguish different types of defects such as cracks, holes, and sand holes. After analysis and processing by it, the number and specific types of defects on the surface of the steel formwork are output. Then, taking the number and types of defects as input parameters, they are substituted into the steel formwork surface evaluation result equation system constructed based on relevant theories and practical experience of the steel formwork surface quality. This equation system comprehensively considers the influence degree of different types of defects on the surface performance and the quantitative relationship between the number of defects and the surface quality. Through calculation and solution, the steel formwork surface evaluation result presented in quantitative indicators is obtained. Finally, based on the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material, the comprehensive performance evaluation result of the final steel formwork material is determined.

[0041] In one embodiment of the present invention, the steel formwork surface evaluation result equation system is constructed by the following formula:

[0042]

[0043] 0 < D i ≤ m, D i ≥ βE i 0 ≤ S i ≤ S max

[0044] 1 ≤ T ≤ T max T = 1 + γln(t + 1)

[0045] In the formula, S is the evaluation result of the steel formwork surface, T is the time coefficient, n is the number of defects on the steel formwork surface, w i is the weight of the i-th type of defect, wj is the weight of the j-th type of defect, C i j is the interaction coefficient matrix between defects, D i is the spatial distribution coefficient of the i-th type of defect, D j is the spatial distribution coefficient of the j-th type of defect, S i is the quantization score of the i-th type of defect, Sj is the quantization score of the j-th type of defect, a i is the lower limit of the weight of the i-th type of defect, b i the upper limit of the weight of the i-th type of defect, r ij is the weight correlation coefficient, k is the upper limit of the interaction coefficient matrix, is the initial interaction coefficient for the i-th and j-th types of defects, a is the adjustment coefficient for the dynamic adjustment of the interaction coefficient, p is the threshold for the dynamic adjustment of the interaction coefficient, m is the upper limit of the spatial distribution coefficient, E i is the cumulative spatial distribution coefficient for the i-th type of defect, β is the dynamic adjustment coefficient, S max is the upper limit value of the quantization score for the i-th type of defect, T max is the upper limit of the time coefficient, γ is the growth coefficient in the time coefficient growth model, and t is the usage time of the steel formwork.

[0046] In this embodiment, w i is the weight of the i-th type of defect, determined based on practical experience or expert judgment to ensure a certain minimum importance of this type of defect in the comprehensive evaluation. w j is the weight of the j-th type of defect, restricting the weight of this type of defect from being too high to ensure the rationality of the weight distribution. r ij is the weight correlation coefficient, used to measure the correlation between the weights of the j-th type of defect and the i-th type of defect, restricting the impact of the change in the weights of related defect categories on the weight of the target defect category. k is the upper limit of the interaction coefficient matrix, preventing the over-exaggeration of the interaction between different defects and ensuring the reasonable evaluation of the interaction effect. a is the adjustment coefficient for the dynamic adjustment of the interaction coefficient, used to control the magnitude of the increase in the interaction coefficient when the severity levels of two types of defects reach a certain level. m is the upper limit of the spatial distribution coefficient, avoiding abnormal fluctuations in the comprehensive score due to defect distribution factors, E i is the cumulative spatial distribution coefficient for the i-th type of defect, considering the accumulation of defects in different regions of the steel formwork. When the number or severity of the i-th type of defect in a local area exceeds a certain threshold, this coefficient will increase. β is the dynamic adjustment coefficient, used to restrict the relationship between the spatial distribution coefficient and the cumulative spatial distribution coefficient of the defect, reflecting the greater impact of the concentrated distribution of defects on the surface strength, S max is the upper limit value of the quantization score for the i-th type of defect, preventing the distortion of the comprehensive score due to the excessive quantization of individual defects, T max is the upper limit of the time coefficient, avoiding the unlimited growth of the time coefficient and ensuring the reasonable modeling of the impact of time on defects. γ is the growth coefficient in the time coefficient growth model, controlling the growth rate of the time coefficient with the increase in the usage time of the steel formwork. Through the evaluation result equations on the surface of the steel formwork, the evaluation results on the surface of the steel formwork can be accurately solved to improve the accuracy of the comprehensive performance evaluation results of the final steel formwork material.

[0047] In an embodiment of the present invention, based on the evaluation results on the surface of the steel formwork and the comprehensive performance evaluation results of the steel formwork material, determining the comprehensive performance evaluation results of the final steel formwork material further includes:

[0048] Fuse the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material according to a preset weight to obtain the comprehensive performance evaluation result of the final steel formwork material.

[0049] In this embodiment, since the comprehensive performance evaluation result of the steel formwork material does not consider factors such as surface defects of the steel formwork, the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material need to be fused according to a preset weight to obtain the comprehensive performance evaluation result of the final steel formwork material, which is used as the final result to accurately evaluate the comprehensive performance of the steel formwork material.

[0050] In an embodiment of the present invention, before inputting the multi-dimensional feature matrix into the comprehensive performance evaluation model of the preset steel formwork material to obtain the comprehensive performance evaluation result of the steel formwork material, it further includes:

[0051] Determine a plurality of eigenvalues and a plurality of eigenvectors according to the multi-dimensional feature matrix;

[0052] Sort the plurality of eigenvalues and the plurality of eigenvectors according to a preset rule to obtain a sorted feature matrix;

[0053] Determine a simplified feature matrix based on the sorted feature matrix;

[0054] Reduce the dimension of the simplified feature matrix to obtain a dimension-reduced feature matrix, and use the dimension-reduced feature matrix as the input of the preset comprehensive performance evaluation model of the steel formwork material.

[0055] In this embodiment, first perform an eigenvalue decomposition operation on the multi-dimensional original feature matrix, and extract the eigenvalues of each dimension and their corresponding eigenvector groups through matrix algebra methods. This operation can effectively analyze the main variation directions and variance contribution degrees of the data space, providing a mathematical basis for subsequent analysis. Establish a descending order rule based on the numerical values of the eigenvalues, and rearrange the eigenvectors in descending order according to the corresponding eigenvalues to construct an eigenvector matrix with decreasing eigenvalues. This sorting strategy follows the basic statistical principle that the larger the eigenvalue, the higher the proportion of data variance. Screen the feature dimensions based on the cumulative contribution rate of the eigenvalues. Usually, a 95% information retention threshold is preset. By successively accumulating the eigenvalue ratios, determine the smallest feature subset that can retain the core information of the original data, and form a dimension-reduced feature matrix. Finally, map the reduced feature matrix to a low-dimensional space. This process eliminates the problem of multi-collinearity between dimensions while maintaining the main information of the data, generating an optimized feature data set suitable for input into the evaluation model. To improve the calculation speed of the evaluation model.

[0056] In an embodiment of the present invention, determining a plurality of eigenvalues and a plurality of eigenvectors according to the multi-dimensional feature matrix includes:

[0057] Perform data standardization on the multi-dimensional feature matrix to obtain a standardized data matrix;

[0058] Determine the covariance matrix based on the standardized data matrix;

[0059] Perform eigen decomposition on the covariance matrix to obtain multiple eigenvalues and multiple eigenvectors.

[0060] In this embodiment, first perform dimensionless processing on the original multi-dimensional feature data. By subtracting the mean value of each feature from the eigenvalue and dividing by its standard deviation, the processed data satisfies the characteristics of a standard normal distribution with a mean of 0 and a variance of 1. Calculate the covariance matrix based on the standardized data. The diagonal elements of this matrix reflect the degree of dispersion of each feature dimension, and the non-diagonal elements reflect the correlation between different features. The specific calculation method is to multiply the transpose of the standardized data matrix by itself and then divide by the sample size minus one. Perform eigen decomposition on the covariance matrix to obtain a set of eigenvalues arranged in descending order of numerical value and their corresponding eigenvectors. Each eigenvalue represents the variance contribution of the corresponding principal component, and the eigenvectors form an orthonormal unit vector group, forming a new coordinate system for the data space. Determine the number of key principal components according to the cumulative contribution rate of the eigenvalues. Usually, the first k principal components with a cumulative contribution rate reaching 95% are selected. These principal components are composed of the eigenvectors corresponding to the largest k eigenvalues, and effective dimensionality reduction of the original data is achieved through projection transformation while retaining the main information.

[0061] In an embodiment of the present invention, the preset comprehensive performance evaluation model for the steel formwork material is a convolutional neural network model.

[0062] In this embodiment, in the technical system for the comprehensive performance evaluation of steel formwork materials, a Convolutional Neural Network (CNN) model is preset as the core evaluation tool. As an algorithm architecture with high representativeness and powerful functions in the field of deep learning, the convolutional neural network model has become an ideal choice for evaluating the comprehensive performance of steel formwork materials due to its excellent ability in processing complex pattern recognition and feature extraction. The convolutional neural network model has a unique network structure, including components such as convolutional layers, pooling layers, and fully connected layers. The convolutional layer can automatically extract local features from the input data. Through the sliding operation of the convolutional kernel on the data, it captures the key information of the steel formwork materials at different scales and dimensions, such as the microscopic structure features inside the materials and the local changes in stress distribution. The pooling layer downsamples the feature map, reducing the data dimension and improving the computational efficiency and generalization ability of the model. It is like screening out the most critical parts from numerous pieces of information, enabling the model to focus on the core features of the steel formwork material performance. The fully connected layer integrates and maps the extracted features to output the final evaluation result. During the training process of this model, based on a large amount of experimental data and actual cases, it continuously adjusts its own parameters and weights to learn the complex mapping relationship between various performance indicators of the steel formwork materials and the input features. This data-driven learning method enables the convolutional neural network model to adapt to the performance evaluation requirements of different types and specifications of steel formwork materials, with strong flexibility and adaptability. By inputting the multi-dimensional feature matrix of the steel formwork materials into this carefully trained and verified convolutional neural network model, the model can comprehensively consider various performance factors of the materials and conduct comprehensive, accurate, and efficient analysis and judgment. Compared with traditional evaluation methods, the convolutional neural network model can process large-scale and high-dimensional data, uncover the complex relationships hidden behind the data, and thus output more accurate and reliable comprehensive performance evaluation results of the steel formwork materials, providing a scientific and powerful decision-making basis for the selection and application of steel formwork materials in fields such as construction.

[0063] According to an embodiment of another aspect, the present invention provides a comprehensive performance evaluation device for steel formwork materials. Figure 2 FIG. shows a schematic block diagram of a comprehensive performance evaluation device for steel formwork materials according to an embodiment. It can be understood that this device can be implemented by any device, equipment, platform, and equipment cluster with computing and processing capabilities. As Figure 2 shown, the device includes: an acquisition unit 200, a first data processing unit 202, a second data processing unit 204, a third data processing unit 206, a fourth data processing unit 208, and a fifth data processing unit 210. The main functions of each component unit are as follows:

[0064] The acquisition unit is configured to acquire the geometric parameters and material parameters of the steel formwork.

[0065] The first data processing unit is configured to determine a three-dimensional geometric model of the steel formwork based on the geometric parameters and the material parameters;

[0066] The second data processing unit is configured to perform mesh division on the three-dimensional geometric model of the steel formwork to obtain a three-dimensional geometric model of the mesh-divided steel formwork; wherein, the three-dimensional geometric model of the mesh-divided steel formwork includes a plurality of mesh nodes;

[0067] The third data processing unit is configured to input corresponding comprehensive performance evaluation parameters into each node in the geometric model of the mesh-divided steel formwork to obtain a simulation model of the steel formwork material; wherein, the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus, and toughness;

[0068] The fourth data processing unit is configured to perform feature extraction on the simulation model of the steel formwork material to obtain a multi-dimensional feature matrix; wherein, the multi-dimensional feature matrix is used to characterize the comprehensive performance of the steel formwork material in three-dimensional space;

[0069] The fifth data processing unit is configured to input the multi-dimensional feature matrix into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material.

[0070] In an embodiment of the present invention, after inputting the multi-dimensional feature matrix into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material, it further includes:

[0071] Obtain image data of the steel formwork;

[0072] Input the image data of the steel formwork into a preset steel formwork defect detection model to obtain the quantity and types of defects on the surface of the steel formwork;

[0073] Input the quantity and types of defects on the surface of the steel formwork into an evaluation result equation system for the surface of the steel formwork to determine the evaluation result of the surface of the steel formwork;

[0074] Based on the evaluation result of the surface of the steel formwork and the comprehensive performance evaluation result of the steel formwork material, determine the comprehensive performance evaluation result of the final steel formwork material.

[0075] In an embodiment of the present invention, the evaluation result equation system for the surface of the steel formwork is constructed by the following formula:

[0076]

[0077] 0 < D i ≤ m, Di ≥βE i ,0 ≤ S i ≤ S max

[0078] 1 ≤ T ≤ T max ,T = 1 + γln(t + 1)

[0079] Wherein, S is the evaluation result of the surface of the steel formwork, T is the time coefficient, n is the number of defects on the surface of the steel formwork, w i is the weight of the i-th type of defect, w j is the weight of the j-th type of defect, C ij is the interaction coefficient matrix between defects, D i is the spatial distribution coefficient of the i-th type of defect, D j is the spatial distribution coefficient of the j-th type of defect, S i is the quantization score of the i-th type of defect, S j is the quantization score of the j-th type of defect, a i is the lower limit of the weight of the i-th type of defect, b i The upper limit of the weight of the i-th type of defect, r ij is the weight correlation coefficient, k is the upper limit of the interaction coefficient matrix, is the initial interaction coefficient between the i-th and j-th types of defects, a is the adjustment coefficient for dynamic adjustment of the interaction coefficient, p is the threshold for dynamic adjustment of the interaction coefficient, m is the upper limit of the spatial distribution coefficient, E i is the cumulative spatial distribution coefficient of the i-th type of defect, β is the dynamic adjustment coefficient, S max is the upper limit value of the quantization score of the i-th type of defect, T max is the upper limit of the time coefficient, γ is the growth coefficient in the time coefficient growth model, and t is the usage time of the steel formwork.

[0080] In an embodiment of the present invention, determining the comprehensive performance evaluation result of the final steel formwork material based on the evaluation result of the surface of the steel formwork and the comprehensive performance evaluation result of the steel formwork material further includes:

[0081] Fusing the evaluation result of the surface of the steel formwork and the comprehensive performance evaluation result of the steel formwork material according to a preset weight to obtain the comprehensive performance evaluation result of the final steel formwork material.

[0082] In an embodiment of the present invention, before inputting the multi-dimensional feature matrix into a preset comprehensive performance evaluation model of the steel formwork material to obtain the comprehensive performance evaluation result of the steel formwork material, it further includes:

[0083] Determining a plurality of eigenvalues and a plurality of eigenvectors according to the multi-dimensional feature matrix;

[0084] Sort the multiple feature values and the multiple feature vectors according to a preset rule to obtain a sorted feature matrix;

[0085] Based on the sorted feature matrix, determine a simplified feature matrix;

[0086] Reduce the dimension of the simplified feature matrix to obtain a dimension-reduced feature matrix, and use the dimension-reduced feature matrix as the input of the preset comprehensive performance evaluation model of the steel formwork material.

[0087] In an embodiment of the present invention, the determining of the multiple feature values and the multiple feature vectors according to the multi-dimensional feature matrix includes:

[0088] Perform data standardization processing on the multi-dimensional feature matrix to obtain a standardized data matrix;

[0089] Based on the standardized data matrix, determine a covariance matrix;

[0090] Perform eigen-decomposition on the covariance matrix to obtain the multiple feature values and the multiple feature vectors.

[0091] In an embodiment of the present invention, the preset comprehensive performance evaluation model of the steel formwork material is a convolutional neural network model.

[0092] According to an embodiment of another aspect, there is also provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is made to execute the method described in combination with Figure 1 ...

[0093] According to an embodiment of still another aspect, there is also provided an electronic device, including a memory and a processor. An executable code is stored in the memory. When the processor executes the executable code, the method described in combination with Figure 1 ...

[0094] The embodiments in the present invention are all described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, they are described relatively simply, and the relevant parts can refer to the partial description of the method embodiments.

[0095] Those skilled in the art should be able to realize that, in the above one or more examples, the functions described in the present invention can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0096] The specific embodiments described above further elaborate on the object, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention shall be included within the protection scope of the present invention.

Claims

1. A comprehensive performance evaluation method for steel formwork materials, characterized in that: The method comprises: Obtain the geometric parameters and material parameters of the steel formwork; Determine a three-dimensional geometric model of the steel formwork based on the geometric parameters and the material parameters; Meshing the three-dimensional geometric model of the steel template to obtain the meshed three-dimensional geometric model of the steel template; wherein the meshed three-dimensional geometric model of the steel template includes a plurality of mesh nodes; Inputting the corresponding comprehensive performance evaluation parameters into each node in the geometric model of the steel formwork after meshing to obtain a simulation model of the steel formwork material; wherein the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus and toughness; Extracting features from the simulation model of the steel formwork material to obtain a multi-dimensional feature matrix; wherein the multi-dimensional feature matrix is ​​used to characterize the comprehensive performance of the steel formwork material in three-dimensional space; The multi-dimensional characteristic matrix is ​​input into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material.

2. The method according to claim 1, characterized in that After the multi-dimensional characteristic matrix is ​​input into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material, the method further includes: Acquire image data of steel formwork; Inputting the image data of the steel template into a preset steel template defect detection model to obtain the number and types of defects on the surface of the steel template; Inputting the number and types of defects on the surface of the steel template into the evaluation result equation group of the steel template surface to obtain the evaluation result of the steel template surface; Based on the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material, the comprehensive performance evaluation result of the final steel formwork material is determined.

3. The method according to claim 2, characterized in that The evaluation result equation group of the steel template surface is constructed by the following formula: a i ≤w i ≤b i ,w i ≥0, ∑ j≠i r ij w j ≤w i 0<C ij ≤k, 0<D i ≤m,D i ≥βE i ,0≤S i ≤S max 1≤T≤T max ,T=1+γln(t+1) Wherein, S is the evaluation result of the steel template surface, T is the time coefficient, n is the number of defects on the steel template surface, and w is i is the weight of the i-th defect, w j is the weight of the j-th defect, C ij is the interaction coefficient matrix between defects, D i is the spatial distribution coefficient of the i-th defect, Dj is the spatial distribution coefficient of the j-th defect, S i is the quantitative score of the i-th defect, S j is the quantitative score of the j-th defect, a i is the lower limit of the weight of the i-th defect, b i The upper limit of the weight of the i-th defect, r ij is the weight correlation coefficient, k is the upper limit of the interaction coefficient matrix, is the initial interaction coefficient of the i-th and j-th defects, a is the adjustment coefficient of the dynamic adjustment of the interaction coefficient, p is the threshold of the dynamic adjustment of the interaction coefficient, m is the upper limit of the spatial distribution coefficient, E i is the cumulative spatial distribution coefficient of the i-th type of defect, β is the dynamic adjustment coefficient, S max is the upper limit of the quantitative score of the i-th defect, T max is the upper limit of the time coefficient, γ is the growth coefficient in the time coefficient growth model, and t is the service life of the steel formwork.

4. The method according to claim 3, characterized in that The step of determining the final comprehensive performance evaluation result of the steel formwork material based on the evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material further includes: The evaluation result of the steel formwork surface and the comprehensive performance evaluation result of the steel formwork material are integrated according to preset weights to obtain a final comprehensive performance evaluation result of the steel formwork material.

5. The method according to claim 4, characterized in that Before inputting the multi-dimensional characteristic matrix into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material, the method further includes: Determining a plurality of eigenvalues ​​and a plurality of eigenvectors according to the multi-dimensional characteristic matrix; Sorting the plurality of eigenvalues ​​and the plurality of eigenvectors according to a preset rule to obtain a sorted eigenmatrix; Based on the sorted feature matrix, determining a simplified feature matrix; The simplified characteristic matrix is ​​subjected to dimension reduction to obtain a reduced-dimensional characteristic matrix, and the reduced-dimensional characteristic matrix is ​​used as an input of the preset comprehensive performance evaluation model of the steel formwork material.

6. The method according to claim 5, characterized in that Determining a plurality of eigenvalues ​​and a plurality of eigenvectors according to the multi-dimensional feature matrix includes: Performing data standardization processing on the multi-dimensional feature matrix to obtain a standardized data matrix; determining a covariance matrix based on the standardized data matrix; Performing eigendecomposition on the covariance matrix to obtain the multiple eigenvalues ​​and the multiple eigenvectors.

7. The method according to claim 6, characterized in that The preset comprehensive performance evaluation model of the steel formwork material is a convolutional neural network model.

8. A comprehensive performance evaluation device for steel formwork materials, characterized in that: include: An acquisition unit is configured to acquire geometric parameters and material parameters of the steel formwork; A first data processing unit is configured to determine a three-dimensional geometric model of the steel formwork based on the geometric parameters and the material parameters; The second data processing unit is configured to mesh the three-dimensional geometric model of the steel template to obtain the meshed three-dimensional geometric model of the steel template; wherein the meshed three-dimensional geometric model of the steel template includes a plurality of mesh nodes; The third data processing unit is configured to input the corresponding comprehensive performance evaluation parameters into each node in the geometric model of the steel formwork after meshing to obtain a simulation model of the steel formwork material; wherein the comprehensive performance evaluation parameters include tensile strength, compressive strength, flexural strength, elastic modulus and toughness; A fourth data processing unit is configured to perform feature extraction on the simulation model of the steel formwork material to obtain a multi-dimensional feature matrix; wherein the multi-dimensional feature matrix is ​​used to characterize the comprehensive performance of the steel formwork material in three-dimensional space; The fifth data processing unit is configured to input the multi-dimensional feature matrix into a preset comprehensive performance evaluation model of the steel formwork material to obtain a comprehensive performance evaluation result of the steel formwork material.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images