Method and system for evaluating the light reflection effect of a building material

Abstract

The application discloses a building material light reflection effect evaluation method and system, relates to the technical field of building material measurement, adds description information to the ceramic tile material after collecting different kinds of ceramic tile materials, generates a difference degree from a ceramic tile description information set, screens the ceramic tile material according to the difference degree, and collects reflectivity data of the obtained ceramic tile material in different test scenes; key factors affecting the reflectivity of the ceramic tile material are identified by using multiple linear regression analysis, and reflectivity data and corresponding image data of the ceramic tile material in an actual use environment are collected; corresponding measured reflectivity is output from the output of the trained reflectivity measurement model, building energy consumption data is output from a building energy consumption digital twin model, and if the predicted energy consumption exceeds the expectation, optimization is made on the selection of the ceramic tile material of the building. The application can reduce the difficulty of evaluating the reflection effect of the ceramic tile material for the building, improve the evaluation efficiency, and ensure the authenticity and reliability of the evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building material measurement, in particular to a method and system for evaluating the light reflection effect of building materials. BACKGROUND

[0002] Light reflectance, also known as reflectivity, refers to the degree of reflection of light on a surface. The higher the light reflectance, the better the material's ability to reflect light. High light reflectance building materials can reduce the absorption of solar radiation, thereby reducing the thermal load of buildings and achieving energy-saving effects. This is particularly important in hot summer, as it can reduce the use of air conditioning and lower energy consumption. Light reflectance also affects the appearance of buildings. For example, the light reflectance of building materials such as glass curtain walls and aluminum plates has a significant impact on their visual effects. High reflectance materials can present a brighter and clearer appearance. In the construction field, light reflectance evaluation is widely used in the selection and performance evaluation of building materials. For example, when selecting building curtain wall materials, the influence of light reflectance on the appearance and energy-saving effect of buildings is considered; when evaluating the performance of thermal insulation coatings, the influence of reflectance on the thermal insulation effect is also considered.

[0003] In Chinese patent CN109298013A, a building insulation material equivalent thermal resistance measurement system and method are provided. The measurement system includes at least two identical detection rooms; each detection room includes at least one pair of temperature sensors symmetrically arranged on the inside and outside of the surrounding wall or roof in a detachable manner; at least one heat flow sensor is arranged near the inside temperature sensor in a detachable manner; a wireless data transmission device is used to transmit the data of the temperature sensor and the heat flow sensor; the sample to be tested and the contrast sample are installed in different detection rooms; and reliable reference data is provided for the application and promotion of thermal insulation coatings.

[0004] In Chinese patent CN106767454A, a water surface oil film thickness measurement system and method based on spectral reflectance characteristics are disclosed, which includes: a spectral data acquisition unit for pre-acquiring spectral sample data and real-time acquiring spectral measurement data; a spectral data preprocessing unit for preprocessing the spectral sample data or the spectral measurement data; a spectral feature extraction unit for extracting the reflectance spectral feature of the spectral sample data or the spectral measurement data based on the spectral feature threshold; a reflectance height curve fitting unit for creating a first oil film thickness measurement data sample curve and determining a first oil film thickness measurement result based on the curve; an absorption depth curve fitting unit for creating a second oil film thickness measurement data sample curve and determining a second oil film thickness measurement result based on the curve; and a joint operation and result display unit for calculating and displaying the oil film thickness.

[0005] When a building is initially designed or constructed, the energy consumption of the building usually needs to be planned. If the energy consumption of the building is high, the building needs to be redesigned or reconstructed, for example, the layout of the building ventilation system is adjusted, and building materials that can effectively reduce energy consumption are selected, and the like. Meanwhile, considering that the building energy consumption and the weather conditions outside the building have a large correlation, for example, when the external light intensity is large and the temperature is high, the building material with high reflectivity can more effectively reflect solar radiation, reduce the absorption of solar radiation by the building surface, which helps to reduce the temperature of the building surface, and further reduces the heat entering the building interior through the building envelope (such as walls and roofs), thereby reducing the cooling energy consumption of the building.

[0006] Therefore, from the perspective of reducing the energy consumption of the building, it is necessary to consider the light reflectivity of the ceramic tile material when selecting the building material, such as the ceramic tile material, for the building. When the existing building material is tested for reflectivity, a plurality of measuring instruments need to be applied, such as a spectral reflectance meter, a luminometer, and an angle adjustment support, and the like. Although the measurement data obtained by this measurement method has high accuracy, the actual measurement process is complex, time-consuming, and may also produce abnormal measurement values due to improper operation or changes in the measurement scene during measurement, and therefore the efficiency is also low.

[0007] Therefore, the present application provides a method and system for evaluating the light reflection effect of building materials. SUMMARY

[0008] (1) Technical problems to be solved

[0009] In view of the deficiencies in the prior art, the present application provides a method and system for evaluating the light reflection effect of building materials. The difference degree is generated from the ceramic tile description information set, the ceramic tile material is selected according to the difference degree, and the reflectivity data of the obtained ceramic tile material in different test scenes are summarized. The key factors affecting the reflectivity of the ceramic tile material are identified using multiple linear regression analysis, and the reflectivity data and the corresponding image data of the ceramic tile material in the actual use environment are collected. The measured reflectivity is output from the output of the trained reflectivity measurement model, and the building energy consumption data is output from the building energy consumption digital twin model. If the predicted energy consumption exceeds the expected value, the selection of the ceramic tile material of the building is optimized. The difficulty of evaluating the reflection effect of the ceramic tile material for the building can be reduced, and the efficiency of the evaluation can be improved, thereby solving the technical problems proposed in the background art.

[0010] (2) Technical solutions

[0011] To achieve the above purpose, the present application is realized by the following technical solutions:

[0012] The method for evaluating the light reflection effect of building materials comprises: generating an energy consumption degree Nxt from a set of energy consumption data of a building when the correlation between the weather environment and the building energy consumption exceeds the expectation, and issuing a data collection instruction to the outside if the energy consumption degree Nxt exceeds an energy consumption threshold;

[0013] After collecting different kinds of ceramic tile materials, description information is added to the ceramic tile materials, and a difference degree Cyx is generated from a set of ceramic tile description information i , the ceramic tile materials are screened according to the difference degree Cyx i , and a measurement scene construction instruction is issued to the outside;

[0014] The measurement conditions are combined to obtain a corresponding measurement scene, the ceramic tile materials are measured in the selected measurement scene, and the reflectivity data of the ceramic tile materials obtained in different test scenes are summarized to generate a set of ceramic tile measurement data;

[0015] After obtaining the optimized reflectivity measurement data and the ceramic tile image data in the corresponding test scene, a multiple linear regression analysis is used to identify the key factors affecting the reflectivity of the ceramic tile materials, and reflectivity data and corresponding image data of the ceramic tile materials in the actual use environment are collected;

[0016] The obtained ceramic tile image is used as input, the corresponding measurement reflectivity is output from the trained reflectivity measurement model, and then the building energy consumption data is output from the building energy consumption digital twin model, and if the predicted energy consumption exceeds the expectation, the selection of the ceramic tile materials of the building is optimized.

[0017] Further, weather environment data and building energy consumption data are collected within a sub-period, and a set of building energy consumption data is generated by summarizing the collected energy consumption data;

[0018] The correlation coefficient between the weather environment data and the building energy consumption data is obtained through correlation analysis, and an energy consumption analysis instruction is issued to the outside if the obtained correlation coefficient exceeds the expectation.

[0019] Further, after receiving the energy consumption analysis instruction, an energy consumption degree Nxt is generated from a set of building energy consumption data, wherein the energy consumption Ns of the building is linearly normalized to map the corresponding data value to the interval [0, 1], in the following manner:

[0020]

[0021] Weight coefficient: 0≤k1≤1, 0≤k2≤1; Ns i is the energy consumption of the i-th monitoring node, is the acceptable value of the energy consumption on the corresponding monitoring node, Ns a is the mean value of the energy consumption; n is the number of monitoring nodes.

[0022] Further, after receiving the data collection instruction, different types of ceramic tile materials are collected, attribute information and related data of the ceramic tile materials are collected, description information is added to the ceramic tile materials, and a ceramic tile description information set is generated after a plurality of description information is summarized;

[0023] The difference degree Cyx is generated from the ceramic tile description information set i The difference degree Cyx i The ceramic tile material with a difference degree lower than the difference threshold is regarded as unqualified material, and the screened ceramic tile materials are summarized to obtain a measurement material library.

[0024] Further, under the dimensionless condition, the difference degree Cyx is generated from the ceramic tile description information set i The method is as follows,

[0025]

[0026] Wherein, n is the number of description information, Xs ij is the similarity between the i th description information and the j th description information, Xs a is the average value of the similarity; the weight coefficients are 0≤F1≤1 and 0≤F2≤1, and F1+F2=1.

[0027] Further, after receiving the measurement scene construction instruction, the preset measurement conditions are combined to obtain the corresponding measurement scene; after selecting the measurement scene, a measurement scheme is formulated for the reflectivity of the ceramic tile material, and the corresponding measurement instrument is selected;

[0028] In the selected measurement scene, different ceramic tile materials are measured for several times, the light wavelength and the corresponding reflectivity data at each measurement are recorded, the reflectivity data of different ceramic tile materials in different test scenes are measured and obtained, and a ceramic tile measurement data set is generated by summarizing.

[0029] Further, after the ceramic tile reflectivity data in different test scenes are classified, a screening threshold [Qa, Qb] is set for each test scene, and if the measured reflectivity is not within the screening threshold [Qa, Qb], it is regarded as an abnormal measurement value;

[0030] According to the interpolation method, the abnormal measurement value is replaced to obtain the optimized reflectivity measurement data and the ceramic tile image data in the corresponding test scene.

[0031] Further, the screening threshold [Qa, Qb] for the reflectivity measurement data in the test scene is set as follows:

[0032]

[0033] Wherein, i=1, 2, …, k, k is the number of reflectivity measurement data, This represents the mean of the reflectance measurement data; This represents the i-th reflectance measurement data in the current test scenario.

[0034] Furthermore, the relationship between the reflectivity of different tile materials and test conditions is visualized, and multiple linear regression analysis is performed on the reflectivity of tile materials and test conditions, and the corresponding linear regression equation is constructed.

[0035] The regression coefficient corresponding to the test conditions is used as the influence. If the influence exceeds the expectation, the corresponding test conditions are used as the key factors.

[0036] Furthermore, when the ceramic tile material is in the usage environment, the reflectivity data of the ceramic tile material is periodically collected, and the reflectivity data and corresponding image data of the ceramic tile material under different lighting conditions are recorded due to ceramic tile surface pollution, air pollution or ceramic tile aging. After filtering out abnormal data, the above recorded data are used to generate a ceramic tile monitoring data set.

[0037] Furthermore, after collecting image information of the building's exterior ceramic tile material, this information is used as ceramic tile images. Data from the ceramic tile monitoring data set and the ceramic tile measurement data set are used as sample data. After training a convolutional neural network with the sample data, a trained reflectivity measurement model is obtained.

[0038] Furthermore, using the acquired tile images as input, the trained reflectance measurement model outputs the corresponding measured reflectance; after acquiring the measured reflectance of the tile materials in various areas of the building, the measured reflectance is used as input, and the building energy consumption digital twin model outputs building energy consumption data, which is then used as the predicted energy consumption.

[0039] Furthermore, if the predicted energy consumption exceeds expectations, the building area is divided into several sub-areas, and the energy consumption Nxt in each sub-area is generated from the predicted energy consumption. If the energy consumption Nxt exceeds expectations, the corresponding sub-area is taken as the area to be optimized.

[0040] With the goal of reducing energy consumption, a multi-objective optimization algorithm is used to optimize the selection of tile materials within the optimization area, and tile materials that meet the conditions are used to replace the tile materials within the optimization area.

[0041] A method and system for evaluating the light reflection effect of building materials, including an energy consumption analysis unit, which generates an energy consumption level Nxt from the building's energy consumption data set when the correlation between weather environment and building energy consumption exceeds expectations; if the energy consumption level Nxt exceeds the energy consumption threshold, it sends a data collection command to the outside.

[0042] The difference analysis unit collects information on different types of tile materials, adds descriptive information to each material, and generates a difference score (Cyx) from the set of tile description information.i Based on the difference Cyx i The ceramic tile materials are screened, and instructions for constructing a measurement scene are sent to the outside.

[0043] The sample measurement unit combines measurement conditions to obtain corresponding measurement scenarios, measures the tile material under the selected measurement scenarios, and summarizes the reflectivity data of the tile material under different test scenarios to generate a tile measurement data set.

[0044] The sample data acquisition unit acquires optimized reflectance measurement data and tile image data under corresponding test scenarios. Then, it uses multiple linear regression analysis to identify key factors affecting the reflectance of tile materials and collects reflectance data and corresponding image data of tile materials in actual use environments.

[0045] The data recognition unit takes the acquired tile image as input, outputs the corresponding measured reflectance from the trained reflectance measurement model, and then outputs the building energy consumption data from the building energy consumption digital twin model. If the predicted energy consumption exceeds expectations, the selection of tile materials for the building is optimized.

[0046] (III) Beneficial Effects

[0047] This invention provides a method and system for evaluating the light reflection effect of building materials, which has the following beneficial effects:

[0048] 1. By judging the correlation between weather conditions and building energy consumption, the building's energy consumption plan can be adjusted according to external weather conditions. By periodically collecting building energy consumption data and generating energy consumption Nxt, the abnormality of building energy consumption can be assessed. If the building energy consumption is abnormal, it can be dealt with in a timely manner to reduce building energy consumption.

[0049] 2. Based on the degree of difference (Cyx) i By screening the ceramic tile materials and removing those that are highly similar to other ceramic tile materials, we can avoid interference from highly similar ceramic tile materials in the actual measurements. By increasing the diversity of the sample data, we can also improve the reliability of subsequent measurement data.

[0050] 3. By acquiring reflectance data under different application scenarios, the measured data is closer to the data in actual application, and the reliability of the acquired reflectance data is higher. By increasing the diversity of measurement scenarios, the reliability of the acquired measurement data can also be ensured when the weather conditions outside the building change.

[0051] 4. By filtering and replacing the measured values, the reliability of the acquired measurement data can be ensured, and the interference of abnormal data can be reduced, making the evaluation of the light reflection effect of building materials more reliable. By filtering out the factors that have the greatest impact on the reflectivity of tiles, targeted processing can be carried out when it is necessary to adjust and optimize the reflectivity of tile materials, which is beneficial to the subsequent feedback processing of building energy consumption.

[0052] 5. By recording and statistically analyzing the actual usage data of ceramic tile materials on the exterior of buildings, we can supplement the measurement data, increase the diversity of sample data, and provide feedback for judging the current state of ceramic tile materials.

[0053] 6. The reflectivity is measured by the output of the reflectivity measurement model, thus completing the measurement and evaluation process of light reflection of ceramic tile materials. This can reduce the difficulty of evaluating the reflectivity of ceramic tile materials used in construction, improve the efficiency of the evaluation, and ensure the authenticity and reliability of the evaluation by using a large amount of collected data as an aid.

[0054] 7. The building's predicted energy consumption is output from the digital twin model of building energy consumption. It is determined whether the energy consumption Nxt in each area of ​​the building exceeds the expectation. Areas with abnormal energy consumption are selected for optimization. By cleaning, adjusting or optimizing the tile materials in the areas to be optimized, the building's energy consumption can be reduced. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the light reflection effect evaluation method of the present invention;

[0056] Figure 2 This is a schematic diagram of the light reflection effect evaluation method system of the present invention. Detailed Implementation

[0057] 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.

[0058] Please see Figure 1 This invention provides a method for evaluating the light reflection effect of building materials, including,

[0059] Step 1: When the correlation between weather conditions and building energy consumption exceeds expectations, an energy consumption level Nxt is generated from the building's energy consumption data set. If the energy consumption level Nxt exceeds the energy consumption threshold, a data collection command is sent to the outside.

[0060] Step one includes the following:

[0061] Step 101: Set a data collection cycle containing several sub-cycles, collect weather and environmental data such as temperature and humidity within the sub-cycles, collect building energy consumption data, and summarize the collected energy consumption data to generate a building energy consumption data set.

[0062] The correlation coefficient between weather and building energy consumption data is obtained through correlation analysis. If the obtained correlation coefficient exceeds the expectation, an energy consumption analysis command is sent to the outside.

[0063] When in use, by collecting weather and energy consumption data outside the building, it is possible to determine the correlation between weather conditions, such as lighting conditions and building energy consumption. The building's energy consumption plan can be adjusted based on external weather conditions. At the same time, in order to reduce energy consumption, the building materials can also be adjusted.

[0064] Step 102: After receiving the energy consumption analysis command, the energy consumption Nxt is generated from the building's energy consumption data set. The building's energy consumption Ns is linearly normalized, mapping the corresponding data values ​​to the interval [0,1], as follows:

[0065]

[0066] Weight coefficients: 0≤k1≤1, 0≤k2≤1. Weight coefficients can be obtained using the analytic hierarchy process (AHP). Ns i Let i be the energy consumption of the i-th monitoring node. Ns represents the acceptable energy consumption value at the corresponding monitoring node. a is the average energy consumption; n is the number of monitoring nodes;

[0067] Based on historical data and expectations for building energy management, energy consumption thresholds are set in advance;

[0068] If the energy consumption Nxt exceeds the energy consumption threshold, it indicates that the building's current energy consumption level is high and there is a need for energy consumption optimization. The building will then send a data collection command to the outside.

[0069] When using it, refer to the content in steps 101 and 102:

[0070] After completing the planning of building energy consumption, building energy consumption data is collected periodically and an energy consumption index Nxt is generated. The energy consumption index can be used to assess whether the building energy consumption is abnormal. If the building energy consumption is abnormal, it can be dealt with in a timely manner to reduce the building energy consumption.

[0071] Based on the above content and existing technologies:

[0072] When testing the reflectivity of existing building materials, multiple measuring instruments are usually required, such as full-wavelength reflectance meters, spectrophotometers, photometers, and angle adjustment brackets. Although the measurement data obtained by this method is highly accurate, the actual measurement process is complex and time-consuming. In addition, abnormal measurement values ​​may be generated due to improper operation or changes in the measurement scene, so the efficiency is also low.

[0073] Step 2: After collecting different types of tile materials, add descriptive information to each tile material, and generate a difference index (Cyx) from the set of tile description information. i Based on the difference Cyx i The ceramic tile materials are screened, and instructions for constructing a measurement scene are sent to the outside.

[0074] Step two includes the following:

[0075] Step 201: After receiving the data acquisition instruction, collect different types of tile materials, such as tile samples with different colors, textures and surface treatments, collect the attribute information and related data of the tile materials, such as the size, thickness and material of the tile, and add descriptive information to the tile materials based on this. After summarizing several descriptive information, generate a set of tile description information.

[0076] When using it, you can add tile description information to describe the tile material, and you can filter several different tile materials based on the description information;

[0077] Step 202: Under dimensionless conditions, generate the difference degree Cyx from the set of tile description information. i To obtain the degree of difference assessment for the differences between different tile materials, among which,

[0078]

[0079] Where n is the number of descriptive information items, Xs ij Xs is the similarity between the i-th and j-th description information. a The average similarity; weighting coefficients: 0≤F1≤1, 0≤F2≤1, and F1+F2=1;

[0080] Based on historical data and anticipated similarities between different tile materials, a difference threshold is pre-set; tile materials are then screened based on the degree of difference, with the difference level (Cyx) being used as the criterion. i Tiles with a difference threshold below the threshold are considered unqualified and are removed, thus screening the tiles. The screened tiles are then compiled into a measurement material library, and a measurement scenario construction command is sent to the outside.

[0081] When using it, refer to steps 201 and 202:

[0082] Cyx is generated from a set of tile description information. i Based on the difference Cyx i Screening tile materials and removing those that are highly similar to other tile materials with little difference can prevent highly similar tile materials from interfering with actual measurements and causing invalid measurement data. Increasing the diversity of sample data can also improve the reliability of subsequent measurement data.

[0083] Step 3: Combine measurement conditions to obtain the corresponding measurement scenarios, measure the tile material under the selected measurement scenarios, and summarize the obtained reflectivity data of the tile material under different test scenarios to generate a tile measurement data set.

[0084] Step three includes the following:

[0085] Step 301: After receiving the measurement scene construction instruction, for example, select different light conditions and different temperatures, and combine the preset measurement conditions to obtain the corresponding measurement scene; after selecting the measurement scene, formulate a measurement plan for the reflectivity of the tile material and select the corresponding measurement instruments, such as a spectrophotometer, a photometer, and an angle adjustment bracket.

[0086] Step 302: Perform several measurements on different tile materials under the selected measurement scenario, record the light wavelength and corresponding reflectivity data for each measurement, organize the measured reflectivity data into a table, and classify them according to wavelength and reflectivity;

[0087] The reflectance data of different tile materials under different test scenarios are measured and collected to generate a set of tile measurement data.

[0088] When using this method, refer to steps 301 and 302:

[0089] After selecting the application scenarios for the tile material, obtaining reflectivity data under different application scenarios can make the obtained measurement data closer to the data in actual application, thus increasing the reliability of the obtained reflectivity data. At the same time, by increasing the diversity of measurement scenarios, the reliability of the obtained measurement data can also be ensured when the external weather conditions of the building change.

[0090] Step 4: After obtaining the optimized reflectance measurement data and the tile image data in the corresponding test scenario, use multiple linear regression analysis to identify the key factors affecting the reflectance of the tile material, and collect the reflectance data and corresponding image data of the tile material in the actual use environment.

[0091] Step four includes the following:

[0092] Step 401: After classifying the tile reflectivity data under different test scenarios, set a filtering threshold [Qa, Qb] for each test scenario, as follows:

[0093]

[0094] Where i = 1, 2, ..., k, and k is the number of reflectance measurement data. This represents the mean of the reflectance measurement data; This is the i-th reflectance measurement data in the current test scenario;

[0095] If the measured reflectance is not within the screening threshold [Qa, Qb], it is regarded as an abnormal measurement value. The abnormal measurement value is replaced by interpolation to obtain the optimized reflectance measurement data and the tile image data under the corresponding test scenario.

[0096] When in use, by filtering and replacing the measured values, the reliability of the acquired measurement data can be ensured and the interference of abnormal data can be reduced, thus making the evaluation of the light reflection effect of building materials more reliable.

[0097] Step 402: Visualize the relationship between the reflectivity of different tile materials and the test conditions, perform multiple linear regression analysis on the reflectivity of tile materials and the test conditions, and construct the corresponding linear regression equation;

[0098] The regression coefficient corresponding to the test conditions is used as the influence. If the influence exceeds the expectation, the corresponding test conditions are taken as the key factors. This allows for comparison of the reflectivity of different materials, taking into account the influence of color, surface treatment and material type on reflectivity.

[0099] When in use, after continuously acquiring several sets of measurement data under different measurement scenarios, multiple linear regression analysis is performed to screen out the factors with the greatest impact on the reflectivity of the tiles. When it is necessary to adjust and optimize the reflectivity of the tile material, targeted processing can be achieved, which is beneficial for subsequent feedback processing of building energy consumption.

[0100] Step 403: When the tile material is in the use environment, periodically collect the reflectivity data of the tile material, and record the reflectivity data of the tile material under different light conditions due to tile surface pollution, air pollution or tile material aging, as well as the corresponding image data. After filtering out abnormal data, generate a tile monitoring data set by combining the above recorded data.

[0101] When using this method, refer to steps 401 to 403:

[0102] In addition to measuring under different usage scenarios, the actual usage data of the tile material on the exterior of the building can be recorded and statistically analyzed to supplement the measurement data. Furthermore, the similar reflectivity data under similar scenarios can increase the diversity of the sample data and serve as feedback. After recording and statistically analyzing the actual reflectivity data, the current state of the tile material can also be judged, such as whether the building needs to be cleaned, thus playing a feedback role.

[0103] Step 5: Using the obtained tile image as input, the corresponding measured reflectance is output by the trained reflectance measurement model, and then the building energy consumption digital twin model outputs building energy consumption data. If the predicted energy consumption exceeds expectations, the selection of tile materials for the building is optimized.

[0104] Step five includes the following:

[0105] Step 501: After acquiring the image information of the exterior ceramic tile material of the building, use it as the ceramic tile image;

[0106] The data from the tile monitoring dataset and the tile measurement dataset are used as sample data. After training a convolutional neural network with the sample data, a trained reflectance measurement model is obtained. The obtained tile images are used as input, and the corresponding reflectance is measured by outputting the trained reflectance measurement model.

[0107] When in use, after acquiring image data of the building's ceramic tile material, the previously acquired relevant data is used as sample data to train and acquire a reflectivity measurement model. The reflectivity is then measured by the output of the reflectivity measurement model, thus completing the measurement and evaluation process of light reflection of the ceramic tile material.

[0108] Image recognition and analysis can reduce the difficulty of assessing the reflectivity of ceramic tile materials used in construction, improve the efficiency of the assessment, and ensure the authenticity and reliability of the assessment by using a large amount of collected data as an aid.

[0109] Step 502: After acquiring building-related data, such as structural data, energy consumption data, environmental conditions and lighting conditions data, use them as sample data to train and generate a digital twin model of building energy consumption; after acquiring the measured reflectivity of the tile material in each area of ​​the building, use the measured reflectivity as input, and output the building energy consumption data from the digital twin model of building energy consumption, and use it as the predicted energy consumption; if the predicted energy consumption exceeds the expectation, a filtering instruction is issued.

[0110] Step 503: After receiving the filtering instruction, the building area is divided into several sub-areas. The energy consumption Nxt in each sub-area is generated from the predicted energy consumption. If the energy consumption Nxt exceeds the expectation, the corresponding sub-area is taken as the area to be optimized.

[0111] With the goal of reducing energy consumption, a multi-objective optimization algorithm is used to optimize the selection of tile materials in the optimization area, and the tile materials in the optimization area are replaced with qualified tile materials.

[0112] When using this method, refer to steps 501 to 503:

[0113] After evaluating the tile materials, the building's energy consumption is predicted by the digital twin model of the building's energy consumption, using the identified reflection effect as input. This allows the model to determine whether the energy consumption Nxt in each area of ​​the building exceeds expectations or whether there are any anomalies. Furthermore, by filtering out areas with abnormal energy consumption and cleaning, adjusting, or optimizing the tile materials in these areas, and taking into account weather conditions such as lighting conditions, the model can reduce the building's energy consumption.

[0114] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into hierarchical levels such as objectives, criteria, and alternatives, and then performs qualitative and quantitative analysis based on these levels. It is particularly suitable for handling objective systems with hierarchical and interleaved evaluation indicators, and is an effective decision-making tool when objective values ​​are difficult to describe quantitatively.

[0115] The core of the Analytic Hierarchy Process (AHP) lies in decomposing the decision problem into multiple levels, forming a hierarchical structure. This structure typically includes an objective level, a criterion level, a sub-criterion level, and an alternative level. By solving for the eigenvectors of the judgment matrix, the priority weight of each element at each level relative to an element at the previous level is obtained. Finally, a weighted summation method is used to hierarchically merge the final weights of each alternative with respect to the overall objective, thereby finding the optimal solution.

[0116] Please see Figure 2 This invention provides a system for evaluating the light reflection effect of building materials, including,

[0117] The energy consumption analysis unit generates an energy consumption level Nxt from the building's energy consumption data set when the correlation between weather conditions and building energy consumption exceeds expectations. If the energy consumption level Nxt exceeds the energy consumption threshold, it sends a data collection command to the outside.

[0118] The difference analysis unit collects information on different types of tile materials, adds descriptive information to each material, and generates a difference score (Cyx) from the set of tile description information. i Based on the difference Cyx i The ceramic tile materials are screened, and instructions for constructing a measurement scene are sent to the outside.

[0119] The sample measurement unit combines measurement conditions to obtain corresponding measurement scenarios, measures the tile material under the selected measurement scenarios, and summarizes the reflectivity data of the tile material under different test scenarios to generate a tile measurement data set.

[0120] The sample data acquisition unit acquires optimized reflectance measurement data and tile image data under corresponding test scenarios. Then, it uses multiple linear regression analysis to identify key factors affecting the reflectance of tile materials and collects reflectance data and corresponding image data of tile materials in actual use environments.

[0121] The data recognition unit takes the acquired tile image as input, outputs the corresponding measured reflectance from the trained reflectance measurement model, and then outputs the building energy consumption data from the building energy consumption digital twin model. If the predicted energy consumption exceeds expectations, the selection of tile materials for the building is optimized.

[0122] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as 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, all or part of the processes or functions described in the embodiments of this application are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. 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 includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0123] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0128] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for evaluating the light reflection effect of building materials, characterized in that: include, When the correlation between weather conditions and building energy consumption exceeds expectations, an energy consumption index is generated from the building's energy consumption data set. If energy consumption If the energy consumption threshold is exceeded, a data acquisition command is sent to the outside. After collecting different types of tile materials, descriptive information is added to each tile material, and a difference score is generated from the set of tile description information. Based on the degree of difference The ceramic tile materials are screened, and instructions for constructing a measurement scene are sent to the outside. The measurement conditions are combined to obtain the corresponding measurement scenarios. The tile material is measured under the selected measurement scenarios. The reflectivity data of the tile material under different test scenarios are summarized to generate a set of tile measurement data. After obtaining the optimized reflectance measurement data and the tile image data in the corresponding test scenario, multiple linear regression analysis was used to identify the key factors affecting the reflectance of the tile material, and reflectance data and corresponding image data of the tile material in the actual use environment were collected. The acquired tile images are used as input, and the trained reflectance measurement model outputs the corresponding measured reflectance. Then, the building energy consumption digital twin model outputs the building energy consumption data. If the predicted energy consumption exceeds expectations, the selection of tile materials for the building is optimized.

2. The method for evaluating the light reflection effect of building materials according to claim 1, characterized in that: Weather and building energy consumption data are collected within the sub-cycle, and the collected energy consumption data are aggregated to generate a building energy consumption data set. Correlation analysis is used to obtain the correlation coefficient between weather and environmental data and building energy consumption data. If the obtained correlation coefficient exceeds expectations, an energy consumption analysis command is sent to the outside.

3. The method for evaluating the light reflection effect of building materials according to claim 2, characterized in that: Upon receiving the energy consumption analysis command, an energy consumption index is generated from the building's energy consumption data set. Among them, the energy consumption of buildings Perform linear normalization to map the corresponding data values ​​to an interval. Inside, in the following manner: ； Weighting coefficients: , ; Let i be the energy consumption of the i-th monitoring node. This represents the acceptable energy consumption value at the corresponding monitoring node. is the average energy consumption; n is the number of monitoring nodes.

4. The method for evaluating the light reflection effect of building materials according to claim 3, characterized in that: After receiving the data acquisition instruction, it collects different types of tile materials, collects the attribute information and related data of the tile materials, adds descriptive information to the tile materials, and generates a set of tile description information by summarizing several descriptive information sets. Differences are generated from the set of tile description information. , to the degree of difference Tile materials that are below the difference threshold are considered unqualified materials, and the screened tile materials are compiled into a measurement material library.

5. The method for evaluating the light reflection effect of building materials according to claim 4, characterized in that: Under dimensionless conditions, the difference degree is generated from the set of tile description information. The method is as follows: ； Where m is the number of descriptive information items. It is the similarity between the i-th and j-th description information. The average similarity; weighting coefficients: , ,and .

6. The method for evaluating the light reflection effect of building materials according to claim 5, characterized in that: After receiving the measurement scene construction instruction, the preset measurement conditions are combined to obtain the corresponding measurement scene; after selecting the measurement scene, a measurement plan is formulated for the reflectivity of the ceramic tile material, and the corresponding measurement instrument is selected; Several measurements were performed on different tile materials under the selected measurement scenario. The light wavelength and corresponding reflectance data were recorded at each measurement. The reflectance data of different tile materials under different test scenarios were obtained and the data were compiled to generate a set of tile measurement data.

7. The method for evaluating the light reflection effect of building materials according to claim 6, characterized in that: After categorizing the tile reflectivity data under different test scenarios, a filtering threshold was set for each test scenario. If the measured reflectance is not within the screening threshold Within this range, it is treated as an abnormal measurement value; Abnormal measurement values ​​were replaced using interpolation to obtain optimized reflectivity measurement data and tile image data for the corresponding test scenario.

8. The method for evaluating the light reflection effect of building materials according to claim 7, characterized in that: Set a filtering threshold for reflectivity measurement data in the test scenario. The method is as follows: ； in, k is the number of reflectance measurement data. This represents the mean of the reflectance measurement data; This represents the i-th reflectance measurement data in the current test scenario.

9. The method for evaluating the light reflection effect of building materials according to claim 8, characterized in that: The relationship between the reflectivity of different tile materials and test conditions is visualized. Multiple linear regression analysis is performed on the reflectivity of tile materials and test conditions to construct the corresponding linear regression equation. The regression coefficient corresponding to the test conditions is used as the influence. If the influence exceeds the expectation, the corresponding test conditions are used as the key factors.

10. The method for evaluating the light reflection effect of building materials according to claim 9, characterized in that: When the ceramic tile material is in the usage environment, the reflectivity data of the ceramic tile material is periodically collected, and the reflectivity data and corresponding image data of the ceramic tile material under different lighting conditions are recorded due to ceramic tile surface pollution, air pollution or ceramic tile aging. After filtering out abnormal data, the above recorded data are used to generate a ceramic tile monitoring data set.

11. The method for evaluating the light reflection effect of building materials according to claim 10, characterized in that: After collecting image information of the building's exterior ceramic tile material, it is used as the ceramic tile image; the data in the ceramic tile monitoring data set and the ceramic tile measurement data set are used as sample data, and the convolutional neural network is trained using the sample data to obtain the trained reflectivity measurement model; The acquired tile image is used as input, and the trained reflectance measurement model outputs the corresponding measured reflectance. After obtaining the measured reflectivity of the ceramic tile material in various areas of the building, the measured reflectivity is used as input, and the building energy consumption digital twin model outputs building energy consumption data, which is then used as the predicted energy consumption.

12. The method for evaluating the light reflection effect of building materials according to claim 11, characterized in that: If the predicted energy consumption exceeds expectations, the building area will be divided into several sub-areas, and the energy consumption level for each sub-area will be generated based on the predicted energy consumption. If energy consumption If the result exceeds expectations, the corresponding sub-region will be designated as the region to be optimized. With the goal of reducing energy consumption, a multi-objective optimization algorithm is used to optimize the selection of tile materials within the optimization area, and tile materials that meet the conditions are used to replace the tile materials within the optimization area.

13. A system for evaluating the light reflection effect of building materials, using the method described in any one of claims 1 to 12, characterized in that: include, The energy consumption analysis unit generates an energy consumption rate from the building's energy consumption data set when the correlation between weather conditions and building energy consumption exceeds expectations. If energy consumption If the energy consumption threshold is exceeded, a data acquisition command is sent to the outside. The difference analysis unit collects information on different types of tile materials, adds descriptive information to each material, and generates a difference score from the set of tile description information. Based on the degree of difference The ceramic tile materials are screened, and instructions for constructing a measurement scene are sent to the outside. The sample measurement unit combines measurement conditions to obtain corresponding measurement scenarios, measures the tile material under the selected measurement scenarios, and summarizes the reflectivity data of the tile material under different test scenarios to generate a tile measurement data set. The sample data acquisition unit acquires optimized reflectance measurement data and tile image data under corresponding test scenarios. Then, it uses multiple linear regression analysis to identify key factors affecting the reflectance of tile materials and collects reflectance data and corresponding image data of tile materials in actual use environments. The data recognition unit takes the acquired tile image as input, outputs the corresponding measured reflectance from the trained reflectance measurement model, and then outputs the building energy consumption data from the building energy consumption digital twin model. If the predicted energy consumption exceeds expectations, the selection of tile materials for the building is optimized.

Images