Building engineering green construction quality analysis and evaluation method

Abstract

The invention belongs to the technical field of building construction, and aims to solve the problem that more complex relationships and potential information among data are difficult to mine due to the fact that existing building engineering quality analysis and evaluation are too simple and only the linear relationship among the data is concerned. In order to achieve the purpose, the building engineering green construction quality analysis and evaluation method provided by the invention comprises the following steps: acquiring environment data, resource utilization data and construction data of a construction site; processing all the obtained data by adopting a kernel principal component analysis method; analyzing main influence factors of the environment data, the resource utilization data and the construction data based on the processed main component data, and generating an analysis result; inputting the obtained principal component data into a construction quality evaluation model; and evaluating the construction quality based on an output result of the model. According to the method, the complex nonlinear relation between the data can be effectively mined, potential information in the data can be more accurately found, a comprehensive evaluation system is constructed, and decision basis is provided for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction, and particularly relates to a method for analyzing and evaluating the quality of green construction in building engineering. Background Art

[0002] At present, with the booming development of the construction industry and the increasing attention of people to environmental protection and sustainable development, green construction has become a key direction for the development of the construction industry. However, there are still many significant deficiencies in the means of analyzing and evaluating the quality of green construction in building engineering.

[0003] Traditional statistical analysis methods, such as simple linear regression analysis, correlation analysis, etc., mainly focus on the study of linear relationships between data. During the building construction process, a large amount of complex data will be generated, and the relationships between these data are not simple linear models. Most of the existing construction quality evaluation methods only evaluate around the basic quality indicators during the construction process, such as the strength and dimensional accuracy of building structures. There is a serious lack of consideration for environmental impacts and resource utilization efficiency during the construction process. For example, when evaluating the quality of a building project, only basic indicators such as the pouring quality of concrete and the verticality of walls are often concerned, while ignoring the impacts of wastewater and waste gas generated during the construction process on the surrounding environment, as well as problems such as water resource waste and excessive energy consumption during the construction process. These methods ignore the rich non-linear relationships between environmental data, resource utilization data, and construction data, and cannot grasp the overall picture of green construction quality. This results in difficulties in identifying the key factors that truly affect the quality of green construction in practical applications, and it is difficult for construction enterprises to formulate practical and effective improvement measures, thus seriously hindering the development of the construction industry towards the green and sustainable direction.

[0004] In addition, traditional methods also have problems in the efficiency and accuracy of data processing. With the continuous expansion of the scale of building projects, the amount of data increases exponentially. Traditional analysis methods are costly and time-consuming when dealing with such a large amount of data. At the same time, due to the inability to accurately capture the complex relationships between data, the accuracy of their analysis results is greatly reduced, and they cannot provide reliable basis for the decision-making of construction enterprises.

[0005] In view of this, there is a need in this field for a method for analyzing and evaluating the quality of green construction in building engineering to solve the above problems. Summary of the Invention

[0006] In order to solve the above technical problems, that is, to solve the problem that the existing analysis and evaluation of building engineering quality are too simple, only focus on the linear relationships between data, and it is difficult to effectively analyze non-linear relationships, thereby excavating more complex relationships and potential information between data.

[0007] The present invention provides a method for analyzing and evaluating the green construction quality of a construction project, and the method includes:

[0008] Obtain the environmental data, resource utilization data, and construction data at the construction site;

[0009] Process all the obtained data by using the kernel principal component analysis method;

[0010] Based on the principal component data obtained by the kernel principal component analysis method, analyze the main influencing factors of the environmental data, resource utilization data, and construction data and generate an analysis result;

[0011] Input the principal component data obtained by the kernel principal component analysis method into the construction quality evaluation model;

[0012] Evaluate the construction quality of the construction project based on the output result of the construction quality evaluation model.

[0013] In some preferred embodiments, the environmental data includes dust data, noise data, wastewater discharge data, waste gas discharge data, and solid waste data; the resource utilization data includes material-saving data, water-saving data, and energy-saving data; the construction data includes construction material data, construction process data, construction personnel health data, and construction safety data.

[0014] In some preferred embodiments, the step of "processing all the obtained data by using the kernel principal component analysis method" specifically includes:

[0015] Perform standardization processing on all the obtained data respectively;

[0016] Calculate the kernel matrix and the centered kernel matrix in sequence;

[0017] Calculate the eigenvalues and eigenvectors of the centered kernel matrix;

[0018] Sort the eigenvalues from large to small, and select the first m eigenvalues and their corresponding eigenvectors;

[0019] For the selected m principal components, calculate the scores of each sample on the principal components.

[0020] In some preferred embodiments, the step of "performing standardization processing on all the obtained data respectively" specifically includes:

[0021] Based on all the obtained data, construct the original data matrix X=(x ij );

[0022] Perform standardization processing on all the obtained data by using the following formula (1):

[0023]

[0024] Construct a standardized data matrix \(Z=(z_{ij})\) based on all the standardized data; ij );

[0025] where \(i = 1, 2, \cdots, n\), \(n\) is the number of samples, \(j = 1, 2, \cdots, p\), \(p\) is the number of variables in each sample, \(z_{ij}\) ij is the standardized data of the \(j\)-th variable of the \(i\)-th sample, \(x_{ij}\) ij is the original data of the \(j\)-th variable of the \(i\)-th sample, is the mean of the \(j\)-th variable of all samples, \(s_j\) j is the standard deviation of the \(j\)-th variable of all samples.

[0026] In some preferred embodiments, the step of "successively calculating the kernel matrix and the centered kernel matrix" specifically includes:

[0027] Map the standardized data to a high-dimensional feature space using the following Gaussian kernel function formula (2):

[0028]

[0029] Based on the calculated \(k(z_i, z_j)\) values, construct a kernel matrix \(K=(k_{ij})\); i , \(z_j\) j ) ij );

[0030] Calculate the centered kernel matrix using the following formula (3)

[0031]

[0032] where \(k(z_i, z_j)\) is the kernel function value, \(z_i\) i , \(z_j\) j ) i is the \(i\)-th sample data, \(z_j\) j is the \(j\)-th sample data, \(\sigma\) is the bandwidth parameter of the Gaussian kernel function, \(k_{ij}\) ij = \(k(z_i, z_j)\), i , \(z_j\) j ) \(I\) is the identity matrix with dimension \(n\times n\), \(\mathbf{1}\) n is an \(n\)-dimensional vector with all elements being 1, \(\mathbf{1}^T\) is the transpose vector of \(\mathbf{1}\), and \(n\) is the number of samples. n

[0033] In some preferred embodiments, the step of "calculating the eigenvalues and eigenvectors of the centered kernel matrix" specifically includes:

[0034] Use the power method or QR decomposition method to calculate the eigenvalues \(\lambda_i\) and eigenvectors \(v_i\) of the kernel matrix k ​k , where

[0035] In some preferred embodiments, the step of "calculating the scores of each sample on the principal components for the selected m principal components" specifically includes:

[0036] Calculating the scores of each sample on the principal components using the following formula (4):

[0037]

[0038] where t ik is the score of the i-th sample on the k-th principal component, p is the number of variables in each sample, and α kj is the j-th element of the coefficient vector corresponding to the k-th principal component, v kj is the j-th element of the k-th eigenvector.

[0039] In some preferred embodiments, the construction quality evaluation model is:

[0040]

[0041] where S is the comprehensive evaluation index, and w k is the weight of the k-th principal component.

[0042] In some preferred embodiments, the weight w of the k-th principal component k is determined according to the variance contribution rate of the principal component.

[0043] In some preferred embodiments, the number m of principal components is equal to 2 or 3.

[0044] The method for analyzing and evaluating the green construction quality of building engineering of the present invention has the following beneficial effects:

[0045] The present invention uses kernel principal component analysis to process comprehensive environmental data, resource utilization data, and construction data at the construction site. This method breaks through the shackles of traditional statistical analysis that only focuses on linear relationships, and can effectively mine complex non-linear relationships between data. By mapping the original data to a high-dimensional space, it can more accurately discover potential patterns and information in the data. Based on the principal component data obtained after processing by kernel principal component analysis, it can deeply and comprehensively analyze the main influencing factors of environmental data, resource utilization data, and construction data. Different from traditional methods, the present invention can clearly identify which factors play a key role in green construction. Inputting the principal component data obtained by processing with kernel principal component analysis into the construction quality evaluation model, a comprehensive evaluation system is constructed. This system fully considers the complex relationships between multi-source data and is no longer limited to the simple index considerations of traditional evaluation methods. In this way, it can more accurately reflect the green construction quality of construction projects. Whether it is self-inspection by construction enterprises or review by regulatory departments, they can, based on the evaluation results of the present invention, conduct a detailed assessment of all aspects of the construction project, timely discover potential problems and rectify them. In addition, the green construction quality analysis and evaluation method for construction projects of the present invention provides strong support for the sustainable development of the construction industry. Construction enterprises can optimize construction plans, improve construction techniques, increase resource utilization efficiency, and reduce the negative impact on the environment according to the analysis results and evaluation indicators of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings. The drawings are schematic and should not be construed as imposing any limitation on the present invention. In the drawings:

[0047] Figure 1 is a flowchart of the green construction quality analysis and evaluation method for construction projects of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Based on the problem that the existing analysis and evaluation of construction project quality in the background technology are too simple, only focusing on the linear relationship between data and being difficult to effectively analyze the non-linear relationship, thus making it difficult to explore the more complex relationships and potential information between data, the present invention provides a method for analyzing and evaluating the green construction quality of construction projects, aiming to effectively explore the complex non-linear relationships between data, more accurately discover the potential information in the data, and construct a comprehensive evaluation system to provide a decision-making basis for enterprises.

[0050] As Figure 1 shown, the method for analyzing and evaluating the green construction quality of construction projects of the present invention includes:

[0051] Obtain the environmental data, resource utilization data and construction data at the construction site;

[0052] Use the kernel principal component analysis method (KPCA) to process all the obtained data;

[0053] Based on the principal component data obtained by the kernel principal component analysis method, analyze the main influencing factors of the environmental data, resource utilization data and construction data and generate an analysis result;

[0054] Input the principal component data obtained by the kernel principal component analysis method into the construction quality evaluation model;

[0055] Evaluate the construction quality of the construction project based on the output result of the construction quality evaluation model.

[0056] Preferably, the environmental data at least includes dust data, noise data, wastewater discharge data, waste gas discharge data and solid waste data; the resource utilization data at least includes material-saving data, water-saving data and energy-saving data; the construction data at least includes construction material data, construction process data, construction personnel health data and construction safety data. It should be noted that in the above, the contents included in the environmental data, resource utilization data and construction data are only exemplary, and those skilled in the art can flexibly set or adjust the specific contents included in the environmental data, resource utilization data and construction data according to the situation of the construction site.

[0057] Preferably, in the above, the step of "using the kernel principal component analysis method to process all the obtained data" specifically includes:

[0058] Perform standardization processing on all the obtained data respectively. Since the environmental data, resource utilization data and construction data collected from the construction site have different physical meanings and dimensions, and the numerical orders of magnitude are quite different, in order to eliminate the influence of these differences on the subsequent analysis results, it is necessary to perform standardization processing on the data.

[0059] Further preferably, the step of "performing standardized processing on all the obtained data respectively" specifically includes:

[0060] Construct an original data matrix X = (x ij ) based on all the obtained data;

[0061] Perform standardized processing on all the obtained data by using the following formula (1):

[0062]

[0063] Construct a standardized data matrix Z = (z ij ) based on all the standardized data;

[0064] where i = 1, 2,..., n, n is the number of samples, j = 1, 2,..., p, p is the number of variables in each sample, z ij is the standardized data of the j-th variable of the i-th sample, x ij is the original data of the j-th variable of the i-th sample, is the mean value of the j-th variable of all samples, and the calculation formula is s j is the standard deviation of the j-th variable of all samples, and the calculation formula is In the above, the number of samples can be collected according to different time periods, or according to different construction projects, etc. For example, environmental data, resource utilization data, and construction data are collected once a day, and continuously collected for 5 days. In this way, there are 5 sample data, and each sample data contains environmental data, resource utilization data, and construction data at the same time. Another example is to divide the construction site into multiple project groups according to the contracted project content (each project group is responsible for a different area), and collect environmental data, resource utilization data, and construction data for each project group respectively. In this way, the same number of sample data as the number of project groups is collected, and each sample data contains environmental data, resource utilization data, and construction data at the same time.

[0065] Calculate the kernel matrix and the centered kernel matrix in sequence.

[0066] Further preferably, the step of "calculating the kernel matrix and the centered kernel matrix in sequence" specifically includes:

[0067] Map the standardized data to a high-dimensional feature space by using the following Gaussian kernel function formula (2):

[0068]

[0069] Construct a kernel matrix K = (k i , z j ) based on each calculated k(z ij );

[0070] The centralized kernel matrix is calculated using the following formula (3):

[0071]

[0072] where k(z i , z j ) is the value of the kernel function, z i is the i-th sample data, z j is the j-th sample data, z i and z j can be regarded as vectors in a p-dimensional space, ||z i - z j || represents the Euclidean distance between vectors z i and z j , σ is the bandwidth parameter of the Gaussian kernel function, σ determines the shape and scope of action of the kernel function, and needs to be reasonably selected according to the actual data situation. For example, the optimal value of σ can be determined by methods such as cross-validation, k ij = k(z i , z j ), I is the identity matrix, whose main diagonal elements are all 1 and the rest are 0, with a dimension of n×n, 1 n is an n-dimensional vector with all elements being 1, is the transposed vector of 1 n , and n is the number of samples.

[0073] Calculate the eigenvalues and eigenvectors of the centralized kernel matrix.

[0074] Further preferably, the step of "calculating the eigenvalues and eigenvectors of the centralized kernel matrix" specifically includes:[[]]

[0075] Use the power method or QR decomposition method to calculate the eigenvalues λ and eigenvectors v k of the kernel matrix k , where

[0076] When using the power method to calculate the eigenvalues λ and eigenvectors v k of the kernel matrix k , first, an initial vector x0 needs to be selected. This vector should satisfy ||x0|| = 1. A random vector can be selected and normalized. For example, for an n-dimensional space (where n is the number of samples, corresponding to the dimension of the kernel matrix ), a random vector x0 = (r1, r2,..., r n ) can be generated, where r iis a random number in the interval (0,1), and then the formula Normalize (x0 on the left side of the equal sign represents the original vector, and on the right side of the equal sign represents the normalized vector), where Perform iterative calculation, the iterative formula is In each iteration, we first calculate The kernel matrix With the current iteration vector x k The product of Normalize and get the vector x for the next iteration k+1 , as the number of iterations k increases, x k will gradually converge to the eigenvector corresponding to the maximum eigenvalue. When the iteration converges (for example, when ||x k+1 -x k || is less than a pre-set threshold, the maximum eigenvalue λ max Can be Calculated, here is x k+1 The transposed vector of .

[0077] When the QR decomposition method is used to calculate the kernel matrix The eigenvalue λ k and the eigenvector v k When Perform QR decomposition and decompose it into the product of an orthogonal matrix Q and an upper triangular matrix R, that is, There are many algorithms for QR decomposition. Taking Gram-Schmidt orthogonalization as an example, assume The column vector is a1, a2, …, a n , first let For j = 2, ..., n, calculate Then The obtained q1,q2,…,q n It is the column vector of the orthogonal matrix Q. The elements of the upper triangular matrix R can be obtained by Calculate and iterate, let In each iteration, Perform QR decomposition Then calculate As the number of iterations increases, It will gradually converge to an upper triangular matrix whose main diagonal elements are the kernel matrix The eigenvalues ​​and eigenvectors can be obtained by accumulating the orthogonal matrix Q. Let Q (0) =I (identity matrix), in each iteration Q (k+1) =Q (k) Q k , when the iteration is over, Q(k) The column vectors are the corresponding eigenvectors.

[0078] Sort the eigenvalues from largest to smallest, and select the first m eigenvalues and their corresponding eigenvectors. Preferably, the number of principal components m is equal to 2 or 3.

[0079] For the selected m principal components, calculate the scores of each sample on the principal components.

[0080] More preferably, the step of "for the selected m principal components, calculate the scores of each sample on the principal components" specifically includes:

[0081] Use the following formula (4) to calculate the scores of each sample on the principal components:

[0082]

[0083] where t ik is the score of the i-th sample on the k-th principal component, p is the number of variables in each sample, and α kj is the j-th element of the coefficient vector corresponding to the k-th principal component, v kj is the j-th element of the k-th eigenvector. Through such calculations, the scores of each sample on the selected m principal components can be obtained, and these scores will serve as an important basis for subsequent analysis and evaluation.

[0084] Preferably, the construction quality evaluation model is:

[0085]

[0086] where S is the comprehensive evaluation index, and w k is the weight of the k-th principal component. The weight w of the k-th principal component k is preferably determined according to the variance contribution rate of the principal component. Through the comprehensive evaluation index S, the green construction quality of the building project can be evaluated as a whole, and the quality of the construction can be judged as excellent or poor.

[0087] For example, if the range of the obtained comprehensive evaluation index S is (0, 1), S≥0.8 is evaluated as green construction quality grade A, 0.8>S≥0.6 is evaluated as green construction quality grade B, 0.6>S≥0.4 is evaluated as green construction quality grade C, and S<0.4 is evaluated as green construction quality grade D.

[0088] Specifically, determining the weight according to the variance contribution rate of the principal component includes:

[0089] First, after performing kernel principal component analysis (KPCA) to obtain the eigenvalues λ k calculate the variance contribution rate of each principal component. The variance contribution rate CR of the k-th principal componentk The calculation formula is where p is the number of variables in the original data (including all variables in environmental data, resource utilization data, and construction data), and λ i is the i-th eigenvalue; after calculating the variance contribution rates of all principal components, normalize them to obtain the weight w k , and the normalization formula is where m is the number of principal components selected.

[0090] In the above, the main influencing factors of environmental data, resource utilization data, and construction data are analyzed based on the principal component data obtained by kernel principal component analysis, and the analysis results are specifically obtained through the scores t of each sample on the principal components ik(It can also be called the load) for analysis. In a possible scenario, if the first principal component has relatively high loads on the dust emission data and waste gas emission data, which are 0.8 and 0.75 respectively (the higher the load value, the greater the influence of the variable on the principal component), then this principal component can be interpreted as the "comprehensive influencing factor of the atmospheric environment" because dust mainly originates from earthwork excavation, material transportation and other links at the construction site, and waste gas emissions come from the operation of construction machinery and the combustion of building materials. If several construction projects have relatively high scores on this principal component, it indicates that these projects have a greater comprehensive impact on the atmospheric environment during the construction process. For another example, if the second principal component has relatively high loads on the noise data and wastewater emission data, which are 0.7 and 0.65 respectively, this principal component can be understood as the "comprehensive factor of environmental interference and water pollution" because noise mainly affects the living and working environments of residents around the construction site, and wastewater emissions may pollute the nearby water bodies. In another possible scenario, if a certain principal component has relatively large loads on the water-saving data and energy-saving data, reaching 0.85 and 0.8 respectively, it can be regarded as the "comprehensive manifestation of efficient resource utilization" because in building construction, water-saving measures include using water-saving appliances and rainwater collection and utilization, and energy conservation involves reasonable planning of construction electricity and selection of energy-efficient construction equipment. If a construction project has a relatively high score on this principal component, it indicates that the project has a relatively high utilization efficiency of water resources and energy during the construction process. For example, if another principal component has a load as high as 0.9 on the material-saving data, this principal component can be interpreted as the "dominant factor of material conservation" because material conservation is mainly reflected in optimizing the construction plan to reduce material waste and using recyclable materials. In yet another possible scenario, a principal component has relatively large loads on the construction material quality data and construction process compliance data, which are 0.82 and 0.78 respectively. It can be regarded as a comprehensive characterization of the construction process quality because the quality of construction materials is directly related to the safety and durability of the building structure, and the compliance of the construction process ensures that the construction process meets relevant standards and specifications. For example, if a principal component has loads of 0.75 and 0.7 on the construction worker health data and construction safety data respectively, this principal component can be interpreted as the "comprehensive factor of construction worker protection" because the health status of construction workers directly affects the construction progress and project quality, and construction safety is the key to ensuring the safety of personnel's lives and property.

[0091] In addition, the present invention can not only identify the complex associations among environmental data such as dust data, noise data, wastewater discharge data, waste gas emission data, and solid waste data, the complex associations among resource utilization data such as material saving data, water saving data, and energy saving data, and the complex associations among construction data such as construction material data, construction process data, construction personnel health data, and construction safety data, but also identify the complex associations among cross-category data. For example, the construction process adopted during construction may have a significant impact on the environment. If in a certain principal component, the loadings of dust data (environmental data) and construction process compliance data (construction data) are both high, this analysis is because some non-compliant construction processes, such as not operating according to the specified procedures during earth excavation, resulting in a large amount of dust generation. At this time, this principal component can be interpreted as the "associated factor between construction process and environmental dust". Another example is that the selection of construction materials not only affects the construction quality but may also affect waste gas emissions. If in a certain principal component, the loadings of waste gas emission data (environmental data) and construction material quality data (construction data) are both high, this means that using construction materials of poor quality will release more harmful gases during construction. This principal component can be understood as the "associated factor between construction material quality and environmental waste gas emissions". Through the above analysis, the complex non-linear relationships between data can be effectively mined, and the potential information in the data can be more accurately discovered, providing a decision-making basis for enterprises through analysis and evaluation. It should be noted that the kernel principal component analysis (KPCA) of the present invention is an improved method based on the principal component analysis (PCA), which can not only identify the complex non-linear relationships between data but also take into account the identification of linear relationships between data, thus making up for the blind spot of the prior art that can only identify linear relationships between data.

[0092] It should be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0093] The embodiments of the present invention are all described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0094] Those of ordinary skill in the art should understand that any discussion of the above embodiments is merely exemplary and is not intended to imply that the scope of the present disclosure is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of one or more embodiments of the present invention as described above, and they are not provided in detail for the sake of brevity.

[0095] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description.

[0096] One or more embodiments of the present invention are intended to cover all such alternatives, modifications, and variations that fall within the scope of the present invention. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of the present invention shall be included within the scope of the present disclosure.

Claims

1. A method for analyzing and evaluating the green construction quality of a building project, characterized in that: The method comprises: Obtain environmental data, resource utilization data and construction data of the construction site; The kernel principal component analysis method was used to process all the acquired data; Analyze the main influencing factors of environmental data, resource utilization data and construction data based on the principal component data obtained by kernel principal component analysis and generate analysis results; The principal component data obtained by the kernel principal component analysis method is input into the construction quality evaluation model; The construction quality of the building project is evaluated based on the output results of the construction quality evaluation model.

2. The green construction quality analysis and evaluation method for construction projects according to claim 1 is characterized in that: The environmental data includes dust data, noise data, wastewater discharge data, waste gas emission data and solid waste data; the resource utilization data includes material saving data, water saving data and energy saving data; the construction data includes construction material data, construction process data, construction personnel health data and construction safety data.

3. The green construction quality analysis and evaluation method for construction projects according to claim 2 is characterized in that: The steps of "using the kernel principal component analysis method to process all acquired data" specifically include: All acquired data are standardized respectively; Calculate the kernel matrix and the centralized kernel matrix in sequence; Calculate the eigenvalues ​​and eigenvectors of the centered kernel matrix; Sort the eigenvalues ​​from large to small, and select the first m eigenvalues ​​and their corresponding eigenvectors; For the selected m principal components, calculate the score of each sample on the principal component.

4. The green construction quality analysis and evaluation method for construction projects according to claim 3 is characterized in that: The steps of "standardizing all acquired data separately" specifically include: Construct the original data matrix X based on all the acquired data ij ); The following formula (1) is used to standardize all the acquired data: Based on all the standardized data, a standardized data matrix Z = (z ij ); Where i = 1, 2, ..., n, n is the number of samples, j = 1, 2, ..., p, p is the number of variables in each sample, z ij is the standardized data of the jth variable of the i-th sample, x ij is the original data of the jth variable of the ith sample, is the mean of the jth variable of all samples, s j is the standard deviation of the jth variable of all samples.

5. The green construction quality analysis and evaluation method for construction projects according to claim 3 is characterized in that: The steps of "calculating the kernel matrix and the centralized kernel matrix in sequence" specifically include: The following Gaussian kernel function formula (2) is used to map the standardized data into a high-dimensional feature space: Based on the calculated k(z i ,z j )Construct the kernel matrix K=(k ij ); The following formula (3) is used to calculate the centralized kernel matrix: Among them, k(z i ,z j ) is the kernel function value, z i is the i-th sample data, z j is the jth sample data, σ is the bandwidth parameter of the Gaussian kernel function, k ij = k(z i ,z j ), I is the identity matrix, with dimensions n×n, 1 n is an n-dimensional vector whose elements are all 1, is 1 n The transposed vector of , n is the number of samples.

6. The green construction quality analysis and evaluation method for construction projects according to claim 5 is characterized in that: The steps of "calculating the eigenvalues ​​and eigenvectors of the centralized kernel matrix" specifically include: Calculate the kernel matrix using the power method or QR decomposition method The eigenvalue λ k and the eigenvector v k ,in, 7. The green construction quality analysis and evaluation method for construction projects according to claim 6 is characterized in that: The steps of "for the selected m principal components, calculating the score of each sample on the principal component" specifically include: The following formula (4) is used to calculate the score of each sample on the principal component: Among them, t ik is the score of the i-th sample on the k-th principal component, p is the number of variables in each sample, α kj is the jth element of the coefficient vector corresponding to the kth principal component, v kj is the jth element of the kth eigenvector.

8. The green construction quality analysis and evaluation method for construction projects according to claim 7 is characterized in that: The construction quality evaluation model is: Among them, S is a comprehensive evaluation index, w k is the weight of the kth principal component.

9. The green construction quality analysis and evaluation method for construction projects according to claim 8 is characterized in that: The weight w of the kth principal component k Determined based on the variance contribution of the principal components.

10. The method for analyzing and evaluating the green construction quality of a construction project according to any one of claims 3 to 9, characterized in that: The number of principal components m is equal to 2 or 3.

Images