A building material quality detection system

By classifying and monitoring building materials in real time, and using principal component analysis and linear regression analysis, the problem of the inability to comprehensively evaluate the quality of building materials in existing technologies has been solved. This has enabled efficient detection and risk warning of building material quality, improving detection efficiency and ensuring project quality.

CN120125083BActive Publication Date: 2025-10-28BINZHOU BEICHENG CONSTRUCTION ENGINEERING MATERIALS INSPECTION CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202510176552.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-02-18
Publication Date
2025-10-28
Estimated Expiration
2045-02-18

AI Technical Summary

Technical Problem

Existing technologies are unable to conduct comprehensive quality assessments of building materials, track quality changes between different batches of materials, detect potential quality risks in a timely manner, or issue timely warnings, leading to problems in projects due to declining material quality.

Method used

Through the material classification module, category determination module, key inspection module, and synchronous analysis module, principal component analysis and linear regression analysis are used to construct a set of material defects, monitor the material defect ratio of key inspection categories in real time, plot change curves, and determine the changing trends of the material defect ratio and the limited material ratio.

Benefits of technology

It enables multi-dimensional quality assessment of building materials, improves testing efficiency, promptly identifies potential quality risks, reduces testing costs and time waste, and ensures project quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120125083B_ABST
    Figure CN120125083B_ABST
Patent Text Reader

Abstract

This invention relates to the field of quality inspection technology, specifically disclosing a building material quality inspection system, comprising: a material classification module that categorizes building materials according to their uses and constructs a set of material defects; a category determination module that uses principal component analysis to determine key inspection categories; a key inspection module that collects defect values ​​of key monitoring categories of building materials in real time and determines whether the trend of the material defect ratio is decreasing by fitting a curve; and a synchronous analysis module that, if the material defect ratio decreases, calculates the average rate of change of adjacent batches of the defined material sequence and the material defect sequence, and determines whether the defined material ratio and the material defect ratio decrease synchronously. This invention is beneficial for monitoring the quality of building materials and reducing potential quality risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of quality testing technology, and specifically to a quality testing system for building materials. Background Technology

[0002] In today's booming construction industry, the quality of building materials plays a vital role in the safety, durability, and overall quality of construction projects. However, the uneven quality of building materials brings many potential risks to construction projects.

[0003] Chinese patent application CN113740173B discloses a testing system and method for building materials, comprising: a workbench with a support plate at its upper end, a testing air pump mounted on the support plate, a testing probe with a conical lower end at the lower end of the testing air pump, a positioning groove at the upper end of the workbench, a baffle movable along the positioning groove at the upper end of the workbench, a robotic arm with an elastic clamping component and a horizontal moving component at the upper end of the workbench, a through hole in the bottom wall of the positioning groove, an elastic abutment component inside the through hole, and a lifting and moving component at the lower end of the elastic abutment component. This system enables expansion tests on pipe ends of various specifications.

[0004] In existing technologies, only the single performance of building materials is tested, without a comprehensive evaluation of the overall quality of the materials. If the defect ratio and the limited material ratio are calculated, and the defect value is obtained, the key testing categories can be determined, and the quality of building materials can be comprehensively evaluated from multiple dimensions. For example, existing technologies cannot determine the proportion of unqualified products in a batch of pipes, or the products that can be used under limited conditions. If the quality status of various materials is grasped through quantitative analysis of building materials, it will provide a basis for the selection of building materials.

[0005] In existing technologies, there is no tracking and analysis of quality changes in different batches of materials, and it is impossible to analyze the development trend of material quality. However, if the material defect values ​​of different batches of building materials are collected in real time, and change curves are plotted, the trend of material defect ratio changes can be judged through linear regression analysis. When the material defect ratio increases abnormally, an early warning can be issued in time. Furthermore, it can be analyzed whether the material defect ratio decreases synchronously with the limit material ratio, and potential quality risks can be detected in advance. For example, if the quality of pipe materials gradually deteriorates during the construction process, existing technologies are difficult to detect the overall quality trend change in time. If an early warning is issued, the construction party can be reminded to take measures to avoid problems in the project due to the use of materials with deteriorated quality.

[0006] Therefore, the present invention provides a building material quality testing system. Summary of the Invention

[0007] The purpose of this invention is to provide a building material quality testing system to solve the problems mentioned above.

[0008] The objective of this invention can be achieved through the following technical solutions:

[0009] A building material quality testing system includes the following modules:

[0010] The material classification module is used to divide building materials into multiple categories, perform numerical analysis on the non-conforming building materials in each category, obtain the material defect ratio and the limited material ratio, and construct a set of material defects.

[0011] Category determination module: Used to analyze and distinguish different categories of building materials in the set of material defects using principal component analysis, and to determine the key inspection categories in different building material categories;

[0012] Key Inspection Module: Used to collect the material defect ratio of different batches of building materials in key inspection categories in real time, and to determine whether the material defect ratio gradually decreases with the iteration of batches;

[0013] Synchronous Analysis Module: If the material defect ratio gradually decreases with batch iterations, it obtains the limited material ratio of key monitoring categories and determines whether the material defect ratio and the limited material ratio decrease synchronously.

[0014] As a further technical solution of the present invention: the method for constructing the material defect set is as follows:

[0015] To determine the intended use of a building, building materials are categorized into multiple classes based on their different uses.

[0016] From the building materials database, obtain the number of substandard building materials of each category in the same batch to obtain the number of defective materials;

[0017] Get the quantity of building materials with restricted usage conditions in the same batch, obtain the number of restricted materials, and get the quantity of each type of building material in the same batch.

[0018] The material defect ratio is obtained by calculating the ratio of the number of defective materials to the quantity of each category of building materials.

[0019] The specified material quantity is calculated as a ratio to the quantity of each type of building material to obtain the specified material ratio;

[0020] The material defect value is obtained by weighting the material defect ratio and the limited material ratio using a formula.

[0021] Calculate the material defect value for each category of building materials, sort the material defect values ​​for each category of building materials in descending order, and construct a set of material defects.

[0022] As a further technical solution of the present invention: the method for determining the key testing categories among the different building material categories is as follows:

[0023] Based on the set of material defects, the quantity of limited materials actually used in the same batch of building materials is obtained from the building materials database, and the limited usage value is obtained.

[0024] Based on the limited usage values, a limited usage matrix is ​​constructed, and principal component analysis is used to obtain the comprehensive score of each building material.

[0025] Based on the comprehensive score of each building material, the building material categories corresponding to the set of material defects are sorted to determine the key inspection categories among all building material categories in the set of material defects.

[0026] As a further technical solution of the present invention: the method for constructing the limited usage matrix is ​​as follows:

[0027] Obtain the specified usage value for each category of building materials, and then calculate the ratio between the specified usage value and the specified number of materials to obtain the specified usage ratio.

[0028] The permitted usage ratio for each category of building materials is denoted as Xd. i , where i is the number of each type of building material in the set of material defects, and the value of i ranges from [1, m];

[0029] Retrieve the permitted usage ratios for all batches from the building materials database, and label the permitted usage ratio for each category in each batch as Xd. ij , where j is the batch number, and the value of j ranges from [1, n].

[0030] As a further technical solution of the present invention: the principal component analysis method is as follows:

[0031] Standardize the usage constraint matrix to construct a standard usage constraint matrix;

[0032] Based on the standard limited dosage matrix, the covariance matrix is ​​constructed using the covariance formula;

[0033] Eigenvalues ​​of the covariance matrix are obtained by performing eigenvalue decomposition on the covariance matrix.

[0034] Summing all eigenvalues ​​yields the total eigenvalues. Ratio of each eigenvalue to the total eigenvalues ​​yields the variance contribution rate.

[0035] The cumulative variance contribution rate of the preset number of k principal components is obtained by summation formula, and the principal component loading matrix P is constructed based on the eigenvectors corresponding to the k principal components.

[0036] The principal component loading matrix is ​​multiplied by the standard constraint matrix to obtain the score matrix of the k principal components.

[0037] Based on the score matrix of k principal components, the comprehensive score of each building material is obtained through numerical analysis.

[0038] As a further technical solution of the present invention, the numerical analysis method for the comprehensive score of each building material is as follows:

[0039] The weighting coefficients are obtained based on the ranking of each building material within the set of material defects;

[0040] Based on the weighting coefficient, cumulative variance contribution rate, and principal component score matrix of each building material, the comprehensive score of each building material is obtained through a product formula.

[0041] As a further technical solution of the present invention: the method for determining whether the material defect ratio gradually decreases with batch iteration is as follows:

[0042] Based on key monitored building materials categories, the material defect ratio of different batches of building materials is collected in real time.

[0043] Plot the batch-material defect ratio curve in a two-dimensional rectangular coordinate system with the batch as the X-axis and the material defect ratio as the Y-axis.

[0044] The material defect ratio of different batches of building materials was fitted and analyzed to obtain the fitting error value of the linear regression equation;

[0045] If the fitting error value of the linear regression equation is higher than the preset fitting error threshold, it indicates that the fitting effect of the linear regression equation on the batch-material defect variation curve is as expected.

[0046] If the linear regression equation fits the batch-material defect variation curve as expected, obtain the slope of the linear regression equation.

[0047] If the slope of the linear regression equation is negative, it means that the material defect ratio of building materials gradually decreases with each batch iteration.

[0048] As a further technical solution of the present invention, the method for fitting analysis of the material defect ratio of different batches of building materials is as follows:

[0049] Linear regression equations were used to fit the batch-material defect variation curve;

[0050] The mean absolute error and mean square error of the linear regression equation can be obtained using the formulas for mean absolute error and mean square error.

[0051] The mean absolute error and mean squared error are weighted and summed to obtain the fitting error value of the linear regression equation.

[0052] As a further technical solution of the present invention: the method for determining whether the material defect ratio and the limited material ratio decrease synchronously is as follows:

[0053] Obtain the specified material ratio for each batch of building materials in key monitoring categories, and construct a specified material sequence;

[0054] Obtain the material defect ratio for each batch and construct a material defect sequence;

[0055] The sequence change ratio is obtained by analyzing the average rate of change of the defined material sequence and the material defect sequence;

[0056] If the sequence change ratio is within the preset change ratio range, it is considered that the material defect ratio in the material defect sequence is gradually decreasing, and the material ratio is limited to decrease synchronously.

[0057] As a further technical solution of the present invention: the sequence change ratio is obtained as follows:

[0058] The average rate of change Rx between adjacent batches of a given material sequence and the average rate of change Ry between adjacent batches of a material defect sequence are obtained using the average rate of change formula.

[0059] The ratio formula is used to obtain the ratio of the average rate of change Rx between adjacent batches of a given material sequence to the average rate of change Ry between adjacent batches of a material defect sequence, i.e., the sequence change ratio.

[0060] The beneficial effects of this invention are:

[0061] (1) By classifying building materials by their uses and analyzing the defects of various building materials in combination with historical data, a set of material defects is constructed. Principal component analysis is used to determine the key testing categories among various building materials. This helps to select the most important parts from among many building material categories, allocate testing resources reasonably, improve testing efficiency, reduce unnecessary testing costs and time waste, and make the testing of building material quality more targeted and efficient.

[0062] (2) Real-time monitoring of key monitoring categories of building materials is carried out. By plotting the batch-material defect change curve and fitting the linear regression equation, the trend of material defect ratio is judged. If the material defect ratio decreases, it is judged whether the limit material ratio decreases at the same time. This can intuitively reflect the improvement of the overall quality of building materials and the reduction of potential quality risks. By analyzing the trend of material defect ratio and limit material ratio, it is beneficial to analyze the development trend of building material quality problems from multiple dimensions and improve the efficiency of building material quality testing. Attached Figure Description

[0063] The invention will now be further described with reference to the accompanying drawings.

[0064] Figure 1 This is a block diagram of a building material quality testing system according to the present invention;

[0065] Figure 2 This is a flowchart of the material analysis model provided in Embodiment 1 of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Example 1

[0068] Please see Figure 1 As shown, the present invention is a building material quality testing system, comprising the following modules:

[0069] Material Classification Module: Based on the different uses of building materials, the building materials are divided into multiple categories. Historical building material data is obtained, and numerical analysis is performed on the substandard building materials in each category to obtain the material defect value. Based on the material defect value, a material defect set is constructed.

[0070] To determine the intended use of building materials, and to classify them into multiple categories based on their different uses;

[0071] In some embodiments, building materials are classified into multiple categories according to their intended use, including: load-bearing materials, space maintenance materials, decorative and aesthetic materials, functional protection materials, and facility supporting materials.

[0072] For example, load-bearing materials used to bear the load of a building include: concrete, steel, and masonry;

[0073] Space maintenance materials are used to divide and enclose building spaces, including: bricks, blocks, wall panels, and roofing materials such as tiles and rolls;

[0074] Decorative and aesthetic materials are used to enhance the appearance of buildings, both inside and out, including paint, wallpaper, stone, and glass.

[0075] Functional protective materials are used for waterproofing, moisture-proofing, heat preservation, sound insulation and sound absorption of buildings, including: waterproof membranes, waterproof coatings, polystyrene boards, and sound-absorbing boards;

[0076] Equipment accessories include: steel pipes, plastic pipes, wires, cables, and switches;

[0077] From the building materials database, obtain the number of substandard building materials of each category in the same batch to get the number of defective materials; obtain the number of building materials in the same batch with restricted usage conditions to get the number of restricted materials; obtain the number of each category of building materials in the same batch.

[0078] It should be noted that those skilled in the art are referring to building materials that have substandard performance but can be used under limited conditions as materials with limited use. For example, if the strength of structural steel is lower than the standard requirements, it can be used in non-critical load-bearing parts.

[0079] The material defect ratio is obtained by calculating the ratio of the number of defective materials to the quantity of each category of building materials.

[0080] The specified material quantity is calculated as a ratio to the quantity of each type of building material to obtain the specified material ratio;

[0081] The material defect value is obtained by weighting the material defect ratio and the limited material ratio using a formula.

[0082] Calculate the material defect value for each category of building materials, sort the material defect values ​​for each category of building materials in descending order, and construct a set of material defects;

[0083] Category determination module: Based on the set of material defects, principal component analysis is used to analyze and distinguish different categories of building materials in the set of material defects, and to determine the key detection categories in different categories of building materials.

[0084] Based on the set of material defects, the quantity of limited materials actually used in the same batch of building materials is obtained from the building materials database, and the limited usage value is obtained.

[0085] Obtain the permitted usage value for each category of building materials, and then calculate the ratio between the permitted usage value and the permitted material quantity to obtain the permitted usage ratio. Label the permitted usage ratio for each category of building materials as Xd. i , where i is the number of each type of building material in the set of material defects, and the value of i ranges from [1, m];

[0086] Retrieve the permitted usage ratios for all batches from the building materials database, and label the permitted usage ratio for each category in each batch as Xd. ij , where j is the batch number, and the value of j ranges from [1, n];

[0087] Based on the limited usage matrix, principal component analysis was used to determine the key inspection categories among all building material categories in the set of material defects;

[0088] Specifically, such as Figure 2 As shown, the material analysis model is constructed as follows:

[0089] Through standardized formula: The constrained usage matrix is ​​standardized, where Xd ij ′ represents the standardized dosage ratio for each batch and each type. These are the mean and variance of the permitted dosage ratio for each type within the same batch;

[0090] Based on the standardized usage matrix, a standard usage matrix Xb is constructed.

[0091] Based on the standard usage constraint matrix Xb, using the formula: Obtain the covariance of the permitted dosage ratio for each batch and each type in the standard permitted dosage matrix Xb, where n represents the total number of batches involved in the calculation, Xd′ ki 、Xd′ kj These represent the permitted dosage ratios of the i-th type in the k-th batch and the permitted dosage ratios of the j-th type in the k-th batch, respectively.

[0092] The covariance Cov(Xd) of the permitted dosage ratio for each batch and each type based on the standard permitted dosage matrix Xb. i ′ j Construct the covariance matrix Cov(Xb);

[0093] The covariance matrix Cov(Xb) is decomposed into eigenvectors and corresponding eigenvalues.

[0094] Summing all eigenvalues ​​yields the total eigenvalue. The ratio of each eigenvalue to the total eigenvalue is then calculated to obtain the variance contribution rate, which is denoted as υ. q q is the eigenvalue number;

[0095] Through the formula: Obtain the cumulative variance contribution rate, where k is the number of principal components selected, and the value of k ranges from [1, m]. k This represents the sum of the variance contribution rates of the top k principal components;

[0096] Based on the eigenvectors corresponding to the k principal components, construct the principal component loading matrix P;

[0097] The principal component loading matrix is ​​multiplied by the standard constraint matrix to obtain the score matrix F of the k principal components. iqThe matrix size is n*k;

[0098] It should be noted that the standard specifies the size of the usage matrix as m*n, and the size of the score matrix F is an m*k matrix;

[0099] Through the formula: Obtain the overall score S for each building material i , where i is the number of the building material category, and α is the weighting coefficient, which is determined by the ranking of each category of building materials in the material defect set;

[0100] Based on the material analysis model, each building material has a comprehensive score S. i The building material category with the lowest overall score was selected as the key testing category.

[0101] It should be noted that the lower the overall score of a building material category, the less quantity of the restricted materials actually used. This means that the quantity of building materials that can be used under the specified conditions is small, indicating that most of these materials do not meet the standard requirements under normal circumstances, and the potential non-compliance rate is high. Therefore, they need to be closely monitored to ensure the quality of the project.

[0102] The technical solution of this embodiment is as follows: Based on the different uses of building materials, building materials are divided into multiple categories, historical building material data is obtained, numerical analysis is performed on the non-conforming building materials of each category to obtain material defect values, a material defect set is constructed based on the material defect values, and principal component analysis is used to analyze and distinguish different categories of building materials in the material defect set to determine the key detection categories in different building material categories. This is conducive to concentrating resources on key monitoring of materials with high potential quality risks and improving detection efficiency.

[0103] Example 2

[0104] like Figure 1 As shown, a building material quality testing system also includes the following modules:

[0105] Key Inspection Module: Based on key monitoring categories, it is used to collect the material defect ratio of different batches of building materials in real time and determine whether the material defect ratio gradually decreases with the iteration of batches;

[0106] Based on key monitored building materials categories, the material defect ratio of different batches of building materials is collected in real time.

[0107] In some embodiments, a material testing device is used to mark the building materials with defects, and the material defect ratio is obtained by numerical analysis of the defective building materials.

[0108] Plot the batch-material defect ratio curve in a two-dimensional rectangular coordinate system with the batch as the X-axis and the material defect ratio as the Y-axis.

[0109] Using a linear regression equation: Fit the batch-material defect variation curve;

[0110] Where a1 and b1 are the slope and intercept of the linear regression equation, respectively. The fitted value of the linear regression equation;

[0111] Through the formula: Obtain the mean absolute error (MAE) of the linear regression equation, where h is the index of each coordinate point in the linear regression equation, and z is the total number of coordinate points.

[0112] Through the formula: Obtain the mean squared error (MSE) of the linear regression equation;

[0113] The mean absolute error and mean square error are weighted and summed to obtain the fitting error value of the linear regression equation.

[0114] The fitting error value of the linear regression equation is compared with the preset fitting error threshold to determine whether the fitting effect of the linear regression equation on the batch-material defect variation curve meets expectations.

[0115] If the fitting error of the linear regression equation is lower than the preset fitting error threshold, it indicates that the fitting error of the linear regression equation is within the expected range, and the fitting effect of the linear regression equation on the batch-material defect variation curve meets expectations.

[0116] If the fitting error value of the linear regression equation is higher than the preset fitting error threshold, it indicates that the fitting error value of the linear regression equation is not within the expected range, and the fitting effect of the linear regression equation on the batch-material defect variation curve does not meet expectations.

[0117] If the linear regression equation fits the batch-material defect variation curve as expected, determine whether the material defect ratio of building materials gradually increases with batch iteration.

[0118] Specifically, the method for determining whether the material defect ratio of building materials gradually increases with batch iterations is as follows:

[0119] Obtain the slope a1 of the linear regression equation. If the slope a1 is positive, indicating whether the material defect ratio of building materials gradually increases with batch iteration, send a material defect warning to the system.

[0120] If the slope a1 is negative, it means whether the material defect ratio of the building materials gradually decreases with the iteration of batches;

[0121] It should be noted that when the linear regression equation fits as expected and the slope is positive, it indicates that the material defect ratio is gradually increasing. As an early warning signal of building material quality, it reminds quality management personnel to pay attention to the key monitoring category of building materials in a timely manner and take corresponding measures to improve them, prevent the problem from deteriorating further, and thus avoid potential safety hazards to the construction project caused by material quality problems.

[0122] Synchronous Analysis Module: Used to obtain the limited material ratio of key monitoring categories if the material defect ratio gradually decreases with batch iterations, and to determine whether the material defect ratio and the limited material ratio decrease synchronously;

[0123] If the material defect ratio decreases gradually with batch iterations for the key monitoring category of building materials, obtain the specified material ratio for each batch within the key monitoring category of building materials, and label the specified material ratio of each batch as d. j Let j be the batch number, and the value of j range from [value missing]. Construct a limited material sequence.

[0124] Obtain the material defect ratio for each batch and label the material defect ratio of each batch as c. j Construct a sequence of material defects;

[0125] Through the formula: Obtain the average rate of change Rx between adjacent batches of a defined material sequence, where t j Manufacturing time for each batch of building materials;

[0126] Through the formula: Obtain the average rate of change Ry between adjacent batches of the material defect sequence;

[0127] Through the formula: Obtain the ratio of the average rate of change Rx between adjacent batches of a defined material sequence and the average rate of change Ry between adjacent batches of a material defect sequence, i.e., the sequence change ratio R;

[0128] By comparing the sequence change ratio with the preset change ratio range, it is determined whether the material ratio decreases synchronously while the material defect ratio in the material defect sequence gradually decreases.

[0129] If the sequence change ratio is within the preset change ratio range, it is considered that the material defect ratio in the material defect sequence is gradually decreasing, and the material ratio is limited to decrease synchronously.

[0130] If the sequence change ratio is not within the preset change ratio range, it is considered that while the material defect ratio in the material defect sequence is gradually decreasing, the change trend of the limit material ratio is not synchronized.

[0131] It should be noted that the sequence variation ratio can intuitively reflect the changing trend of two variables within a certain range, making the changes in the material defect ratio and the limited material ratio of different batches comparable;

[0132] For example, if the defective material ratio decreases from 5% to 3% between adjacent batches with an average change rate of -2%, and the bound material ratio decreases from 4% to 2% with an average change rate of -2%, this indicates that both the defective material ratio and the bound material ratio decrease at the same rate between the two batches. This quantitatively reflects the degree to which the defective material ratio and the bound material ratio decrease synchronously, facilitating comparison and analysis.

[0133] It should be noted that a lower material defect ratio means that the proportion of building materials with quality problems during production or use is reduced, that is, more building materials meet the quality standards for normal use. A lower limit material ratio means that the proportion of building materials that could be used under limited conditions but were originally substandard is also decreasing, which means that building materials as a whole are closer to meeting the standard requirements, and the potential quality risks are further reduced.

[0134] The technical solution of this embodiment is as follows: Based on key monitoring categories, the material defect ratio of different batches of building materials is collected in real time. It is determined whether the material defect ratio of the key monitoring category of building materials gradually decreases with the iteration of batches. If the material defect ratio of the key monitoring category of building materials gradually decreases with the iteration of batches, the limited material ratio of the key monitoring category is obtained, and it is determined whether the material defect ratio and the limited material ratio decrease synchronously. The data on the change of building material quality is quantified from two dimensions: the material defect ratio and the limited material ratio, so that the evaluation dimensions of building material quality inspection are more comprehensive.

[0135] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A building material quality testing system, characterized in that: Includes the following modules: The material classification module is used to divide building materials into multiple categories, perform numerical analysis on the non-conforming building materials in each category, obtain the material defect ratio and the limited material ratio, and construct a set of material defects. Category determination module: Used to analyze and distinguish different categories of building materials in the set of material defects using principal component analysis, and to determine the key inspection categories in different building material categories; Key Inspection Module: Used to collect the material defect ratio of different batches of building materials in key inspection categories in real time, and to determine whether the material defect ratio gradually decreases with the iteration of batches; Synchronous Analysis Module: Used to obtain the limited material ratio of key monitoring categories if the material defect ratio gradually decreases with batch iterations, and to determine whether the material defect ratio and the limited material ratio decrease synchronously; The method for constructing the set of material defects is as follows: To determine the intended use of building materials, and to classify them into multiple categories based on their different uses; From the building materials database, obtain the number of substandard building materials of each category in the same batch to obtain the number of defective materials; Get the quantity of building materials with restricted usage conditions in the same batch, obtain the number of restricted materials, and get the quantity of each type of building material in the same batch. The material defect ratio is obtained by calculating the ratio of the number of defective materials to the quantity of each category of building materials. The specified material quantity is calculated as a ratio to the quantity of each type of building material to obtain the specified material ratio; The material defect value is obtained by weighting the material defect ratio and the limited material ratio using a formula. Calculate the material defect value for each category of building materials, sort the material defect values ​​for each category of building materials in descending order, and construct a set of material defects; The method for determining the key testing categories among the different building material categories is as follows: Based on the set of material defects, the quantity of limited materials actually used in the same batch of building materials is obtained from the building materials database, and the limited usage value is obtained. Based on the limited usage values, a limited usage matrix is ​​constructed, and principal component analysis is used to obtain the comprehensive score of each building material. Based on the comprehensive score of each building material, the building material categories corresponding to the set of material defects are sorted to determine the key inspection categories among all building material categories in the set of material defects; The principal component analysis method is as follows: Standardize the usage constraint matrix to construct a standard usage constraint matrix; Based on the standard limited dosage matrix, the covariance matrix is ​​constructed using the covariance formula; Eigenvalues ​​of the covariance matrix are obtained by performing eigenvalue decomposition on the covariance matrix. Summing all eigenvalues ​​yields the total eigenvalues. Ratio of each eigenvalue to the total eigenvalues ​​yields the variance contribution rate. The cumulative variance contribution rate of the preset number of k principal components is obtained by summation formula, and the principal component loading matrix P is constructed based on the eigenvectors corresponding to the k principal components. The principal component loading matrix is ​​multiplied by the standard constraint matrix to obtain the score matrix of the k principal components. Based on the score matrix of k principal components, the comprehensive score of each building material is obtained through numerical analysis.

2. The building material quality testing system according to claim 1, characterized in that: The method for constructing the limited usage matrix is ​​as follows: Obtain the specified usage value for each category of building materials, and then calculate the ratio between the specified usage value and the specified number of materials to obtain the specified usage ratio. The permitted usage ratio for each category of building materials is denoted as Xd. i , where i is the number of each type of building material in the set of material defects, and the value of i ranges from [1, m]; Retrieve the permitted usage ratios for all batches from the building materials database, and label the permitted usage ratio for each category in each batch as Xd. ij , where j is the batch number, and the value of j ranges from [1, n].

3. The building material quality testing system according to claim 1, characterized in that: The numerical analysis method for the comprehensive score of each building material is as follows: The weighting coefficients are obtained based on the ranking of each building material within the set of material defects; Based on the weighting coefficient, cumulative variance contribution rate, and principal component score matrix of each building material, the comprehensive score of each building material is obtained through a product formula.

4. The building material quality testing system according to claim 1, characterized in that: The method for determining whether the material defect ratio gradually decreases with batch iteration is as follows: Based on key monitored building materials categories, the material defect ratio of different batches of building materials is collected in real time. Plot the batch-material defect ratio curve in a two-dimensional rectangular coordinate system with the batch as the X-axis and the material defect ratio as the Y-axis. The material defect ratio of different batches of building materials was fitted and analyzed to obtain the fitting error value of the linear regression equation; If the fitting error value of the linear regression equation is higher than the preset fitting error threshold, it indicates that the fitting effect of the linear regression equation on the batch-material defect variation curve is as expected. If the linear regression equation fits the batch-material defect variation curve as expected, obtain the slope of the linear regression equation. If the slope of the linear regression equation is negative, it means that the material defect ratio of building materials gradually decreases with each batch iteration.

5. The building material quality testing system according to claim 4, characterized in that: The method for fitting analysis of the material defect ratio of different batches of building materials is as follows: Linear regression equations were used to fit the batch-material defect variation curve; The mean absolute error and mean square error of the linear regression equation can be obtained using the formulas for mean absolute error and mean square error. The mean absolute error and mean squared error are weighted and summed to obtain the fitting error value of the linear regression equation.

6. The building material quality testing system according to claim 1, characterized in that: The method for determining whether the material defect ratio and the limited material ratio decrease simultaneously is as follows: Obtain the specified material ratio for each batch of building materials in key monitoring categories, and construct a specified material sequence; Obtain the material defect ratio for each batch and construct a material defect sequence; The sequence change ratio is obtained by analyzing the average rate of change of the defined material sequence and the material defect sequence; If the sequence change ratio is within the preset change ratio range, it is considered that the material defect ratio in the material defect sequence is gradually decreasing, and the material ratio is limited to decrease synchronously.

7. A building material quality testing system according to claim 6, characterized in that: The sequence change ratio is obtained as follows: The average rate of change Rx between adjacent batches of a given material sequence and the average rate of change Ry between adjacent batches of a material defect sequence are obtained using the average rate of change formula. The ratio formula is used to obtain the ratio of the average rate of change Rx between adjacent batches of a given material sequence to the average rate of change Ry between adjacent batches of a material defect sequence, i.e., the sequence change ratio.

Citation Information

Patent Citations

  • A building material detection system and method

    CN113740173B

  • Building material quality detection system

    CN110796396A

  • Tobacco leaf mildew detection method adopting electronic nose for logistic regression classification

    CN115508503A