Building thermal insulation performance evaluation method based on building material big data

Abstract

The invention relates to the technical field of performance evaluation of building materials, and particularly discloses a building thermal insulation performance evaluation method based on building material big data, and the method comprises the steps: obtaining physical characteristic data of a building material, carrying out the comparative analysis of the physical characteristic data and historical data, and judging the reliability of a data source through t inspection; dividing the data into credible data and uncredible data; secondly, preprocessing the credible data, including data cleaning, denoising and normalization processing, extracting heat conduction coefficient characteristics, water absorption characteristics and density characteristics, and generating corresponding characteristic indexes; and finally, comprehensively analyzing the heat conduction coefficient characteristic index, the water absorption characteristic index and the density characteristic index, calculating a thermal insulation coefficient, and marking and classifying the thermal insulation performance of the building according to a comparison result of the thermal insulation coefficient and a preset threshold value.

Description

Technical Field

[0001] The present invention relates to the technical field of performance evaluation of building materials, and in particular to a method for evaluating thermal insulation performance of buildings based on big data of building materials. Background Art

[0002] The physical properties of building materials are directly related to the safety, durability and comfort of buildings, especially in terms of thermal insulation performance. As people's awareness of quality of life and environmental protection continues to improve, the selection and evaluation of building materials has become increasingly important. Traditional building material evaluation methods mainly rely on laboratory test reports, data manuals provided by manufacturers, and limited field test data. These methods have certain limitations in data sources and data processing.

[0003] Due to the diversity of data sources, data from different sources may differ significantly, especially between test results conducted in different laboratories or in different time periods. If these differences are not effectively handled, they will directly affect the reliability of the evaluation results. Traditional thermal insulation performance evaluation methods often only focus on data in a single dimension and cannot fully reflect the true status of the building's thermal insulation performance. Existing evaluation methods usually use simple mathematical calculations or empirical rules, lack systematic comprehensive analysis methods, and are difficult to cope with complex data sets and diversified evaluation needs.

[0004] There is a lack of systematic processing and analysis of physical property data such as thermal conductivity, water absorption and density of building materials, and the use of advanced data preprocessing technology and feature extraction methods to generate comprehensive thermal insulation performance evaluation results, thereby overcoming the limitations of traditional methods and improving the accuracy and reliability of evaluation results. Summary of the invention

[0005] The purpose of the present invention is to provide a building thermal insulation performance evaluation method based on building material big data to solve the above-mentioned background problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A building insulation performance evaluation method based on building material big data includes the following steps:

[0008] S1: Acquire physical property data of building materials, wherein the physical property data includes: thermal conductivity, water absorption and density;

[0009] S2: Compare and analyze the source of the currently collected physical property data with the source of the historical physical property data to determine whether the data source is accurate, and classify the physical property data into credible data and uncredible data based on the determination result;

[0010] S3: Based on the credible data, the physical property data is preprocessed, and features of the preprocessed physical property data are extracted to extract features of thermal conductivity, water absorption and density;

[0011] S4: generating a thermal conductivity characteristic index, a water absorption characteristic index and a density characteristic index according to the thermal conductivity characteristic, water absorption characteristic and density characteristic extracted from the physical property data characteristics;

[0012] S5: Comprehensively analyze the thermal conductivity characteristic index, water absorption characteristic index and density characteristic index to determine whether the building's thermal insulation performance is good, and mark and classify the building's thermal insulation performance.

[0013] As a further solution of the present invention, it is characterized in that the comparative analysis of the currently collected physical property data source and the historical physical property data source is performed, and the credible deviation coefficient of the physical property data source is calculated according to the analysis result, which specifically includes:

[0014] Get a set of currently collected physical property data, denoted as X = {x1, x2, ..., x n}, a set of historically collected physical property data, denoted as Y = {y1, y2, ..., y m};

[0015] Calculate the credibility deviation coefficient of the physical property data source through the t-test statistical calculation formula;

[0016] The statistical calculation formula of the t-test is:

[0017]

[0018] In the formula, Z t Represents the credibility deviation coefficient of the source of physical property data, μ x Represents the average value of the current physical property data set, μ y represents the average value of the historical physical property data set, σ x Represents the standard deviation of the current physical property data set, σ y represents the standard deviation of the historical physical property data set, n represents the number of observations in the current physical property data set, and m represents the number of observations in the historical physical property data set.

[0019] As a further solution of the present invention: the comparative analysis of the currently collected physical property data source and the historical physical property data source to determine whether the data source is accurate, and based on the determination result, the physical property data is divided into credible data and uncredible data, specifically includes:

[0020] Compare the credible deviation coefficient of the physical property data source with the credible deviation coefficient threshold of the preset physical property data source:

[0021] Determine whether the credible deviation coefficient of the physical property data source is greater than or equal to the preset credible deviation coefficient threshold of the physical property data source. If so, record it as credible data; if not, record it as untrustworthy data.

[0022] As a further solution of the present invention: based on the credible data, the physical property data is preprocessed, the features of the preprocessed physical property data are extracted, the thermal conductivity coefficient features are extracted, and the thermal conductivity coefficient feature index is generated;

[0023] Among them, the process of obtaining the characteristic index of thermal conductivity is:

[0024] Get a set of preprocessed thermal conductivity data K = {k1, k2, ..., k n};

[0025] Perform fast Fourier transform on the thermal conductivity data to obtain the spectrum F k ;

[0026] Extract the frequency f of the maximum amplitude of the spectrum max and the corresponding amplitude A max ;

[0027] Get the maximum value of the thermal conductivity k max and the minimum value k min ;

[0028] The maximum value of the thermal conductivity k max and the minimum value k min The peak-to-valley ratio ρ of the thermal conductivity is obtained by ratio calculation;

[0029] The amplitude of the thermal conductivity coefficient A max The peak-to-valley ratio ρ of the thermal conductivity is calculated to calculate the thermal conductivity characteristic index Q A .

[0030] As a further solution of the present invention: based on the trusted data, the physical property data is preprocessed, the features of the preprocessed physical property data are extracted, the water absorption rate features are extracted, and the water absorption rate feature index is generated;

[0031] The process of obtaining the water absorption characteristic index is as follows:

[0032] Obtain a set of preprocessed water absorption data;

[0033] Get the maximum and minimum water absorption in the water absorption data, connect the local maximum and minimum water absorption by spline interpolation, construct the upper and lower envelopes respectively, calculate the mean m(t) of the upper and lower envelopes, and extract the intrinsic mode function c1(t) from the original signal.

[0034] Repeat the calculation of the remaining signal to extract all the intrinsic mode functions until the remaining signal does not contain any valid information;

[0035] Perform Hilbert transform on each intrinsic mode function to obtain the analytical signal zi(t);

[0036] Calculate instantaneous amplitude, instantaneous phase and instantaneous frequency;

[0037] The water absorption characteristic index Q is calculated by calculating the ratio of the instantaneous frequency standard deviation to the instantaneous frequency mean. B .

[0038] As a further solution of the present invention: based on the trusted data, the physical property data is preprocessed, the features of the preprocessed physical property data are extracted, the density features are extracted, and the density feature index is generated;

[0039] The density characteristic index acquisition process is as follows:

[0040] Get a set of density data, standardize and normalize the density data, and calculate the normalized value d s ;

[0041] Select the number of clusters M and initialize M centroids;

[0042] Calculate the center point of each cluster, calculate the number of data points in each cluster, and calculate the compactness of each cluster;

[0043] The density characteristic index Q is obtained by calculating the ratio of the compactness of each cluster to the center point of each cluster. C .

[0044] As a further solution of the present invention: the thermal conductivity characteristic index, the water absorption characteristic index and the density characteristic index are comprehensively analyzed to obtain the thermal insulation coefficient;

[0045] The thermal insulation coefficient acquisition process is as follows:

[0046] Get the characteristic index Q of thermal conductivity A , water absorption characteristic index Q B and density characteristic index Q c ;

[0047] Characteristic index Q for thermal conductivity A, water absorption characteristic index Q B and density characteristic index Q c Normalize and calculate the insulation coefficient H ma .

[0048] As a further solution of the present invention: the comprehensive analysis of the thermal conductivity characteristic index, the water absorption characteristic index and the density characteristic index to determine whether the thermal insulation performance of the building is good, and marking and classifying the thermal insulation performance of the building, specifically includes:

[0049] The insulation coefficient H ma Compare with preset insulation factor threshold;

[0050] Determine the thermal insulation coefficient H ma Whether it is greater than or equal to the preset insulation coefficient threshold, if so, the corresponding building is marked as a material with qualified insulation performance, if not, the corresponding building is marked as a material with unqualified insulation performance;

[0051] All unqualified buildings will be marked separately, and building materials with unqualified thermal insulation performance will be distinguished.

[0052] Beneficial effects of the present invention:

[0053] (1) Through comparative analysis, the present invention can effectively identify data sources with significant differences, avoiding misjudgment caused by unreliable data sources. For example, if the currently collected thermal conductivity data has a large deviation from the historical data, it means that there may be measurement errors or inaccurate data records. In this case, the data will be marked as unreliable data and will not be used in subsequent evaluation processes. Traditional evaluation methods often lack means to verify the reliability of data sources. The present invention introduces statistical methods, such as t-tests, to objectively evaluate data based on mathematical models, thereby enhancing the scientificity and rigor of the evaluation results.

[0054] (2) The present invention achieves a comprehensive evaluation of the thermal insulation performance of a building by comprehensively analyzing the characteristic index of thermal conductivity, water absorption and density, and calculating the thermal insulation coefficient. Traditional evaluation methods often only focus on one or several physical properties, ignoring the mutual influence between different properties, resulting in incomplete evaluation results; the present invention provides a more comprehensive and scientific method for evaluating the thermal insulation performance of a building by extracting multiple characteristic indexes and conducting a comprehensive analysis. This multi-dimensional evaluation method not only considers the influence of a single physical property, but also takes into account the interaction between different properties, making the evaluation results more comprehensive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The present invention will be further described below in conjunction with the accompanying drawings.

[0056] Figure 1 It is a flowchart of the specific steps of a building thermal insulation performance evaluation method based on building material big data of the present invention;

[0057] Figure 2 It is a flowchart of the standard process of credible data judgment in the present invention;

[0058] Figure 3 It is a standard flow chart for judging the thermal insulation performance of building materials in the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Example 1

[0061] See also Figure 1 As shown, the present invention is a method for evaluating building thermal insulation performance based on building material big data, comprising the following steps:

[0062] S1: Acquire physical property data of building materials, wherein the physical property data include: thermal conductivity, water absorption and density;

[0063] S2: Compare and analyze the source of the currently collected physical property data with the source of the historical physical property data to determine whether the data source is accurate, and classify the physical property data into credible data and uncredible data based on the determination result;

[0064] S3: Based on the credible data, the physical property data is preprocessed, and features of the preprocessed physical property data are extracted to extract features of thermal conductivity, water absorption and density;

[0065] S4: generating a thermal conductivity characteristic index, a water absorption characteristic index and a density characteristic index according to the thermal conductivity characteristic, water absorption characteristic and density characteristic extracted from the physical property data characteristics;

[0066] S5: Comprehensively analyze the thermal conductivity characteristic index, water absorption characteristic index and density characteristic index to determine whether the building's thermal insulation performance is good, and mark and classify the building's thermal insulation performance.

[0067] Example 2

[0068] See also Figure 2As shown, on the basis of Example 1, the physical property data of the building material is obtained, wherein the physical property data includes: thermal conductivity, water absorption and density. Due to the diversity of the sources of the physical property data, the credibility of the data will be affected. The source of the currently collected physical property data is compared and analyzed with the source of the historical physical property data to determine whether the data source is accurate, and the physical property data is divided into credible data and uncredible data according to the determination result, specifically including:

[0069] Obtain data on the physical properties of building materials, including thermal conductivity, water absorption, and density, from a variety of sources (e.g., laboratory test reports, manufacturer data sheets, field tests, etc.);

[0070] Standardize the physical property data of all building materials to ensure consistency of comparison, and use statistical test methods (such as t-test) to determine whether there are significant differences between current data and historical data;

[0071] The specific process of the t-test method is as follows:

[0072] Assume that we have a set of currently collected physical property data, denoted as X = {x1, x2, ..., x n}, a set of historically collected physical property data, denoted as Y = {y1, y2, ..., y m};

[0073] Where n represents the number of observations in the current physical property data set, n is a positive integer greater than 0, m represents the number of observations in the historical physical property data, m is a positive integer greater than 0;

[0074] The average value of the current physical property data set is calculated by the mean calculation formula, denoted as μ x ;

[0075] The average value of the historical physical property data set is calculated by the mean calculation formula, denoted as μ y ;

[0076] The standard deviation of the current physical property data set is calculated using the standard deviation calculation formula, denoted as σ x ;

[0077] The standard deviation of the historical physical property data set is calculated by the standard deviation calculation formula, denoted as σ y ;

[0078] Calculate the credibility deviation coefficient of the physical property data source through the t-test statistical calculation formula;

[0079] The statistical calculation formula of the t-test is:

[0080]

[0081] In the formula, Z t Represents the credibility deviation coefficient of the source of physical property data, μ x Represents the average value of the current physical property data set, μ y represents the average value of the historical physical property data set, σ x Represents the standard deviation of the current physical property data set, σ y represents the standard deviation of the historical physical property data set, n represents the number of observations in the current physical property data set, and m represents the number of observations in the historical physical property data set;

[0082] The credibility deviation coefficient Z of the physical property data source t Compare with the preset credible deviation coefficient threshold of the physical property data source to determine whether the physical property data source is accurate, including:

[0083] If the credible deviation coefficient Z of the physical property data source t If the value is greater than or equal to the threshold of the credible deviation coefficient of the preset physical property data source, it means that the corresponding data source is unreliable and there is abnormal data, which is recorded as unreliable data;

[0084] If the credible deviation coefficient Z of the physical property data source t If the value is greater than or equal to the threshold of the credible deviation coefficient of the preset physical property data source, it means that the corresponding data source is reliable and recorded as credible data;

[0085] It should be noted that the credibility deviation coefficient Z of the source of physical property data t The larger the value is, the greater the deviation of the current characteristic data source is, and the less reliable it is. It is necessary to check the source and method of data collection in time. The credible deviation coefficient Z of the source of physical characteristic data is t By comparing with the credible deviation coefficient threshold of the preset physical property data source, unreliable data can be effectively identified. In this way, unreliable data can be discovered and excluded in a timely manner, ensuring that the physical property data used for evaluation is reliable.

[0086] Example 3

[0087] On the basis of Example 2, based on the credible data, the physical property data is preprocessed, and the features of the preprocessed physical property data are extracted to extract the thermal conductivity coefficient features, water absorption rate features and density features. Since the accuracy of the data will affect the evaluation of the thermal insulation performance of the building, the thermal conductivity coefficient features, water absorption rate features and density features extracted from the physical property data features are used to generate the thermal conductivity coefficient feature index, water absorption rate feature index and density feature index, which specifically include:

[0088] The collected physical property data are cleaned, denoised and normalized. The data cleaning step eliminates errors or outliers to ensure the accuracy of the data; the denoising step reduces environmental interference and measurement errors through filtering and other methods; the normalization step standardizes the data to make data from different sources comparable, thus laying the foundation for subsequent analysis;

[0089] Perform feature extraction on the preprocessed physical property data to extract thermal conductivity features, water absorption features and density features;

[0090] According to the characteristics of the thermal conductivity coefficient, a thermal conductivity characteristic index is generated, including:

[0091] Get a set of preprocessed thermal conductivity data K = {k1, k2, ..., k n};

[0092] Perform fast Fourier transform on the thermal conductivity data to obtain the spectrum F k ;

[0093] Extract the frequency f of the maximum amplitude of the spectrum max and the corresponding amplitude A max ;

[0094] Get the maximum value of the thermal conductivity k max and the minimum value k min ;

[0095] The maximum value of the thermal conductivity k max and the minimum value k min The peak-to-valley ratio ρ of the thermal conductivity is obtained by ratio calculation;

[0096] The amplitude of the thermal conductivity coefficient A max The peak-to-valley ratio ρ of the thermal conductivity is calculated to calculate the thermal conductivity characteristic index Q A ;

[0097] Among them, the thermal conductivity characteristic index Q A The calculation expression is:

[0098]

[0099] In the formula, Q A Indicates the characteristic index of thermal conductivity, A max represents the maximum amplitude of the thermal conductivity coefficient, ρ represents the peak-to-valley ratio of the thermal conductivity coefficient, a1 and a2 represent preset proportional coefficients, and a1 and a2 are both greater than 0;

[0100] It should be noted that the characteristic index of thermal conductivity Q A , which indicates the thermal conductivity of the building's thermal insulation performance, and when the thermal conductivity characteristic index QA The larger it is, the worse the thermal insulation performance of the corresponding building is, indicating that the thermal insulation performance of the corresponding building materials is poor.

[0101] According to the water absorption characteristics, a water absorption characteristic index is generated, including:

[0102] Obtain a set of preprocessed water absorption data;

[0103] Get the maximum and minimum water absorption in the water absorption data, connect the local maximum and minimum water absorption by spline interpolation, construct the upper and lower envelopes respectively, calculate the mean m(t) of the upper and lower envelopes, and extract the intrinsic mode function c1(t) from the original signal.

[0104] Wherein, the intrinsic mode function expression is:

[0105] c1(t)=x(t)-m(t);

[0106] Repeat the calculation of the residual signal r(t)=x(t)-c1(t) to extract all the intrinsic mode functions until the residual signal does not contain any valid information;

[0107] Perform Hilbert transform on each intrinsic mode function to obtain the analytical signal zi(t);

[0108] Wherein, the Hilbert transform expression is:

[0109] zi(t)=ci(t)+jH[ci(t)];

[0110] Where H[ci(t)] is the Hilbert transform of ci(t), j is the imaginary unit;

[0111] Calculate instantaneous amplitude and instantaneous phase;

[0112] Wherein, the instantaneous amplitude expression is:

[0113]

[0114] Among them, the instantaneous phase expression is:

[0115]

[0116] In the formula, Ai(t) is the instantaneous amplitude, which indicates the amplitude change of the signal at time t, and θi(t) is the instantaneous phase, which indicates the phase change of the signal at time t;

[0117] Calculate instantaneous frequency;

[0118] Wherein, the instantaneous frequency expression is:

[0119]

[0120] Where ωi(t) is the instantaneous frequency, which represents the frequency change of the signal at time t;

[0121] The water absorption characteristic index Q is calculated by calculating the ratio of the instantaneous frequency standard deviation to the instantaneous frequency mean. B ;

[0122] It should be noted that the water absorption characteristic index Q B , reflects the water absorption performance of building materials, and when the water absorption characteristic index Q B The larger it is, the worse the thermal insulation performance of the building material.

[0123] According to the density characteristics, a density characteristic index is generated, including:

[0124] Get a set of density data D = {d1, d2, ..., d n};

[0125] Standardize and normalize the density data and calculate the normalized value d s ;

[0126] Select the number of clusters M, initialize M centroids {c1, c2, ... c M};

[0127] Calculate the center point of each cluster, the calculation expression is:

[0128]

[0129] Calculate the number of data points in each cluster. The calculation expression is:

[0130] n j =|C j |;

[0131] Calculate the compactness of each cluster, the calculation expression is:

[0132]

[0133] The density characteristic index Q is obtained by calculating the ratio of the compactness of each cluster to the center point of each cluster. C ;

[0134] Where j represents the jth cluster, j is a positive integer greater than 0, ∈ j is the center point of the jth cluster, d s is the normalized value of the density data after the density data is normalized and processed, n j represents the number of data points in the jth cluster, C jrepresents the compactness of the jth cluster, and M is the number of clusters;

[0135] It should be noted that the density characteristic index Q C , reflects the thermal insulation properties of building materials, and when the density characteristic index Q C The smaller it is, the better the thermal insulation properties of the building material.

[0136] Example 4

[0137] See also Figure 3 As shown, on the basis of Example 3, the thermal conductivity characteristic index, the water absorption characteristic index and the density characteristic index are comprehensively analyzed to calculate the thermal insulation coefficient, judge whether the thermal insulation performance of the building is good, and mark and classify the thermal insulation performance of the building, specifically including:

[0138] Get the characteristic index Q of thermal conductivity A , water absorption characteristic index Q B and density characteristic index Q c ;

[0139] Characteristic index Q for thermal conductivity A , water absorption characteristic index Q B and density characteristic index Q c Perform normalization and calculate the thermal insulation coefficient H ma ;

[0140] Wherein, the thermal insulation coefficient H ma The calculation expression is:

[0141]

[0142] In the formula, H ma is the thermal insulation coefficient of the building material, e1, e2 and e3 are preset proportional factors, and e1, e2 and e3 are all greater than 0;

[0143] It should be noted that: it can be seen that the characteristic index of the thermal conductivity coefficient Q A , water absorption characteristic index Q B and density characteristic index Q c And the insulation coefficient H ma Inversely proportional, and when the conductivity characteristic index Q A , water absorption characteristic index Q B and density characteristic index Q c And the insulation coefficient H ma The smaller it is, the better the thermal insulation performance of the corresponding building material;

[0144] The insulation coefficient H ma Compare with the preset insulation coefficient threshold to determine whether the current building's insulation performance is good, including:

[0145] If the insulation coefficient H ma If it is greater than or equal to the preset insulation coefficient threshold, it means that the insulation performance of the corresponding building is good, and the corresponding building is marked as a qualified insulation material;

[0146] If the insulation coefficient H ma If it is less than the preset insulation coefficient threshold, it means that the insulation performance of the corresponding building is poor, and the corresponding building will be marked as unqualified insulation material;

[0147] All buildings will be marked separately and building materials with unqualified thermal insulation performance will be distinguished to enable the evaluation of the thermal insulation performance of the buildings.

[0148] The working principle of the present invention is to systematically process and analyze the physical property data of building materials such as thermal conductivity, water absorption and density to accurately evaluate the thermal insulation performance of the building. Firstly, by acquiring the physical property data of building materials and standardizing them, statistical test methods (such as t-test) are used to compare and analyze the currently collected data with historical data, the reliability of the data source is judged, and the data is divided into reliable data and unreliable data; then, based on the reliable data, the physical property data is preprocessed, including data cleaning, denoising and normalization, to ensure the accuracy and consistency of the data; then, the thermal conductivity coefficient characteristics, water absorption characteristics and density characteristics are extracted, and the corresponding characteristic indexes are generated; specifically, the thermal conductivity coefficient characteristic index is generated by spectrum analysis, the water absorption characteristic index is generated by Hilbert transform, and the density characteristic index is generated by cluster analysis; finally, the thermal conductivity coefficient characteristic index, water absorption characteristic index and density characteristic index are comprehensively analyzed to calculate the thermal insulation coefficient, and according to the comparison result between the thermal insulation coefficient and the preset threshold, the thermal insulation performance of the building is marked and classified, so as to identify materials with qualified and unqualified thermal insulation performance; this technical solution not only improves the accuracy and reliability of data processing, but also realizes the effective monitoring and performance evaluation of the thermal insulation performance of the building through the method of multi-feature comprehensive evaluation.

[0149] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0150] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0151] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0152] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0153] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A building insulation performance evaluation method based on building material big data, characterized in that: The following steps are involved: S1: Acquire physical property data of building materials, wherein the physical property data includes: thermal conductivity, water absorption and density; S2: Compare and analyze the source of the currently collected physical property data with the source of the historical physical property data to determine whether the data source is accurate, and classify the physical property data into credible data and uncredible data based on the determination result; S3: Based on the credible data, the physical property data is preprocessed, and features of the preprocessed physical property data are extracted to extract features of thermal conductivity, water absorption and density; S4: generating a thermal conductivity characteristic index, a water absorption characteristic index and a density characteristic index according to the thermal conductivity characteristic, water absorption characteristic and density characteristic extracted from the physical property data characteristics; S5: Comprehensively analyze the thermal conductivity characteristic index, water absorption characteristic index and density characteristic index to determine whether the building's thermal insulation performance is good, and mark and classify the building's thermal insulation performance.

2. A building insulation performance evaluation method based on building material big data according to claim 1, characterized in that: The comparative analysis of the currently collected physical property data source and the historical physical property data source, and the calculation of the credible deviation coefficient of the physical property data source according to the analysis result, specifically includes: Get a set of currently collected physical property data, denoted as X = {x1, x2, ..., x n }, a set of historically collected physical property data, denoted as Y = {y1, y2, ..., y m }; Calculate the credibility deviation coefficient of the physical property data source through the t-test statistical calculation formula; The statistical calculation formula of the t-test is: In the formula, Z t Represents the credibility deviation coefficient of the source of physical property data, μ x Represents the average value of the current physical property data set, μ y represents the average value of the historical physical property data set, σ x Represents the standard deviation of the current physical property data set, σ y represents the standard deviation of the historical physical property data set, n represents the number of observations in the current physical property data set, and m represents the number of observations in the historical physical property data set.

3. The building insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: The comparative analysis of the currently collected physical property data source and the historical physical property data source to determine whether the data source is accurate, and based on the determination result, the physical property data is divided into credible data and uncredible data, specifically includes: Compare the credible deviation coefficient of the physical property data source with the credible deviation coefficient threshold of the preset physical property data source: Determine whether the credible deviation coefficient of the physical property data source is greater than or equal to the preset credible deviation coefficient threshold of the physical property data source. If so, record it as credible data; if not, record it as untrustworthy data.

4. The building insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: Based on the credible data, the physical property data is preprocessed, the features of the preprocessed physical property data are extracted, the thermal conductivity coefficient features are extracted, and the thermal conductivity coefficient feature index is generated; Among them, the process of obtaining the characteristic index of thermal conductivity is: Get a set of preprocessed thermal conductivity data K = {k1, k2, ..., k n }; Perform fast Fourier transform on the thermal conductivity data to obtain the spectrum F k ; Extract the frequency f of the maximum amplitude of the spectrum max and the corresponding amplitude A max ; Get the maximum value of the thermal conductivity k max and the minimum value k min ; The maximum value of the thermal conductivity k max and the minimum value k min The peak-to-valley ratio ρ of the thermal conductivity is obtained by ratio calculation; The amplitude of the thermal conductivity coefficient A max The peak-to-valley ratio ρ of the thermal conductivity is calculated to calculate the thermal conductivity characteristic index Q A .

5. The building insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: The method preprocesses the physical property data based on the trusted data, extracts the characteristics of the preprocessed physical property data, extracts the water absorption characteristics, and generates a water absorption characteristic index; The process of obtaining the water absorption characteristic index is as follows: Obtain a set of preprocessed water absorption data; Get the maximum and minimum water absorption in the water absorption data, connect the local maximum and minimum water absorption by spline interpolation, construct the upper and lower envelopes respectively, calculate the mean m(t) of the upper and lower envelopes, and extract the intrinsic mode function c1(t) from the original signal. Repeat the calculation of the remaining signal to extract all the intrinsic mode functions until the remaining signal does not contain any valid information; Perform Hilbert transform on each intrinsic mode function to obtain the analytical signal zi(t); Calculate instantaneous amplitude, instantaneous phase and instantaneous frequency; The water absorption characteristic index Q is calculated by calculating the ratio of the instantaneous frequency standard deviation to the instantaneous frequency mean. B .

6. The building insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: Based on the trusted data, the physical property data is preprocessed, features of the preprocessed physical property data are extracted, density features are extracted, and a density feature index is generated; The density characteristic index acquisition process is as follows: Get a set of density data, standardize and normalize the density data, and calculate the normalized value d s ; Select the number of clusters M and initialize M centroids; Calculate the center point of each cluster, calculate the number of data points in each cluster, and calculate the compactness of each cluster; The density characteristic index Q is obtained by calculating the ratio of the compactness of each cluster to the center point of each cluster. C .

7. The building thermal insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: The thermal conductivity characteristic index, the water absorption characteristic index and the density characteristic index are comprehensively analyzed to obtain the thermal insulation coefficient; The thermal insulation coefficient acquisition process is as follows: Get the heat transfer coefficient characteristic index Q A , water absorption characteristic index Q B and density characteristic index Q c ; Characteristic index Q for thermal conductivity A , water absorption characteristic index Q B and density characteristic index Q c Normalize and calculate the insulation coefficient H ma .

8. The building thermal insulation performance evaluation method based on building material big data according to claim 1 is characterized in that: The comprehensive analysis of the thermal conductivity characteristic index, the water absorption characteristic index and the density characteristic index is performed to determine whether the thermal insulation performance of the building is good, and the thermal insulation performance of the building is marked and classified, specifically including: The insulation coefficient H ma Compare with preset insulation factor threshold; Determine the thermal insulation coefficient H ma Whether it is greater than or equal to the preset insulation coefficient threshold, if so, the corresponding building is marked as a material with qualified insulation performance, if not, the corresponding building is marked as a material with unqualified insulation performance; All unqualified buildings will be marked separately, and building materials with unqualified thermal insulation performance will be distinguished.

Images