A method for optimizing thermal parameters of existing building envelope structures based on genetic algorithm

Abstract

The present invention relates to the technical field of energy-saving transformation of existing buildings, solves the technical problem of low reliability of optimization of thermal parameters of existing building envelope structures in the prior art, and improves the accuracy of optimization of thermal parameters of existing building envelope structures. In particular, it relates to a method for optimizing thermal parameters of existing building envelope structures based on a genetic algorithm, the method comprising: obtaining thermophysical property parameters, performing fitness evaluation on the thermophysical property parameters, calculating predicted values ​​of the thermophysical property parameters, measuring the predicted values ​​of the thermophysical property parameters, generating a response data set, and finally performing iterative optimization based on a genetic algorithm to obtain an optimal solution set of thermal parameters. The present invention achieves more accurate acquisition of predicted values ​​of thermophysical property parameters, improves the accuracy of optimization of thermal parameters of existing building envelope structures, and effectively solves the problem of low reliability of optimization of thermal parameters of existing building envelope structures in the prior art.

Description

Technical Field

[0001] The invention relates to the technical field of energy-saving transformation of existing buildings, and in particular to a method for optimizing thermal parameters of an existing building envelope structure based on a genetic algorithm. Background Art

[0002] With the intensification of global climate change and the increasingly serious energy crisis, building energy conservation has become a hot issue of global concern. As the main part of building energy consumption, the thermal performance of building envelope has an important impact on the energy consumption and indoor environment of the building. Genetic Algorithm (GA) is a type of random global optimization algorithm based on natural selection and genetic genetics. The algorithm searches for the optimal solution or approximate optimal solution in the solution space by simulating the selection, crossover and mutation mechanisms in the biological evolution process. At present, the existing building area in my country has reached 65 billion square meters, and the energy consumption generated accounts for a large proportion of China's total building energy consumption. The strategy of relying solely on new buildings to meet energy-saving standards cannot achieve the goal of energy conservation and carbon reduction in the entire construction industry. Therefore, optimizing the thermal parameters of building envelopes based on genetic algorithms and improving the energy efficiency of buildings are of great significance to achieving the goal of building energy conservation.

[0003] The existing thermal parameter optimization method of the envelope structure of existing buildings determines the optimization target of the envelope structure according to the energy-saving requirements of the existing buildings, and at the same time establishes an optimization model of the thermal parameters of the envelope structure according to the optimization target, then encodes the thermal parameters of the envelope structure to generate an initial population, and finally calculates the fitness of the individual according to the optimization model until the optimal individual is obtained. For example, the invention patent with the announcement number CN116720247B discloses a multi-objective optimization design method for the envelope structure of office buildings based on random operation, and the patent application with the publication number CN116628819A discloses a low-carbon-oriented optimization design method for the outer envelope structure of a substation building.

[0004] However, in the prior art, the thermal parameters of building envelope structures are often affected by a variety of uncertain factors, such as changes in meteorological conditions and differences in the performance of building materials. These factors usually cause the optimization results of the thermal parameters to deviate from the expected values. In addition, the existing genetic algorithms often use random generation to generate the initial population, which leads to uneven individual distribution and insufficient diversity of the initial population, resulting in low reliability in the optimization of thermal parameters of existing building envelope structures. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for optimizing the thermal parameters of existing building envelope structures based on genetic algorithms, which solves the technical problem of low reliability in the prior art of optimizing the thermal parameters of existing building envelope structures and improves the accuracy of optimizing the thermal parameters of existing building envelope structures.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for optimizing thermal parameters of existing building envelope structures based on genetic algorithms, the method comprising the following steps:

[0007] S1. Obtaining thermal physical parameters of an existing building envelope structure located in any preset area within a preset time period, wherein the thermal physical parameters include an exterior wall heat transfer coefficient, a roof heat transfer coefficient, and an exterior window heat transfer coefficient;

[0008] S2, performing fitness evaluation on the acquired thermophysical property parameters to evaluate whether the thermophysical property parameters converge within a preset time period, if so, proceeding to step S3; if not, returning to step S1;

[0009] S3, calculating the predicted value of the thermal physical parameter of the existing building envelope structure in the preset area according to the thermal physical parameter;

[0010] S4, judging whether the predicted value of the thermophysical property parameter is within the preset range of the design parameter value, if so, obtaining the actual design parameters of the existing building envelope structure in the preset area, and forming a response data set between the actual design parameters and the existing building performance index; otherwise, returning to step S1;

[0011] S5. Based on the genetic algorithm combined with the response data set, the envelope structure of the existing building is iteratively optimized to obtain the optimal solution set of thermal parameters. The optimal solution set of thermal parameters represents the envelope structure design scheme in which the envelope structure of the existing building converges between the reference performance indicators of the existing building after iterative optimization.

[0012] Furthermore, in step S2, the specific process includes:

[0013] Real-time monitoring of the change of the heat transfer coefficient of the exterior wall within a preset time period to obtain the heat gain, and at the same time determine whether the heat gain is equal to the preset heat gain;

[0014] If it is equal, the heat transfer coefficient of the external wall converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external wall within the preset time period is continuously monitored in the preset area until the heat gain obtained is equal to the preset heat gain;

[0015] Real-time monitoring of the roof heat transfer coefficient changes within a preset time period to obtain the solar radiation temperature, and at the same time determine whether the solar radiation temperature is equal to the preset solar radiation temperature;

[0016] If it is equal to, the roof heat transfer coefficient converges within the preset time period; otherwise, the change of the roof heat transfer coefficient within the preset time period is continuously monitored in the preset area until the obtained solar radiation temperature is equal to the preset solar radiation temperature;

[0017] Real-time monitoring of the changes in the heat transfer coefficient of the exterior wall within a preset time period to obtain the insulation value, and at the same time determine whether the insulation value is equal to the preset insulation value;

[0018] If it is equal, the heat transfer coefficient of the external window converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external window within the preset time period is continuously monitored in the preset area until the obtained insulation amount is equal to the preset insulation amount.

[0019] Furthermore, in step S3, the specific process includes:

[0020] Determine the shading coefficient and ventilation coefficient that affect the predicted value of the thermophysical property parameter within a preset time period;

[0021] Combined with the thermophysical parameters, the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area, the predicted value of the roof heat transfer coefficient of the preset roof area, and the predicted value of the exterior window heat transfer coefficient of the preset exterior window area are calculated, where:

[0022] The calculation expression of the predicted value of the exterior wall heat transfer coefficient is:

[0023] ;

[0024] In the formula, is the number of the preset exterior wall area, , is the total number of preset exterior wall areas; t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; represents the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area in the tth preset time period; Indicates the shading coefficient of the preset roof area in the tth preset time period; Indicates the ventilation coefficient of the preset external window area in the tth preset time period; Indicates The external wall heat transfer coefficient of a preset external wall area in the tth preset time period;

[0025] The calculation expression of the predicted value of the roof heat transfer coefficient is:

[0026] ;

[0027] In the formula, is the number of the preset roof area, , is the total number of preset roof areas; represents the predicted value of the roof heat transfer coefficient of the preset roof area in the tth preset time period; Indicates The roof heat transfer coefficient of a preset roof area in the tth preset time period;

[0028] The calculation expression of the predicted value of the heat transfer coefficient of the exterior window is:

[0029] ;

[0030] In the formula, is the number of the preset roof area, , is the total number of preset exterior window areas; represents the predicted value of the heat transfer coefficient of the external window in the preset external window area in the tth preset time period; Indicates The heat transfer coefficient of the external window of a preset external window area in the tth preset time period.

[0031] Further, in step S4, the existing building performance index is obtained by the unit volume energy consumption index, carbon emission index and thermal comfort index of the existing building within a preset time period. The specific process includes:

[0032] Obtain energy consumption data of existing buildings within a preset time period, and obtain energy consumption per unit volume in combination with the plane size information of existing buildings. The energy consumption data includes electricity consumption and fuel consumption. The energy consumption per unit volume is the ratio of energy consumption data to the volume of existing buildings.

[0033] Real-time monitoring of the carbon dioxide emissions of existing buildings within a preset time period, and obtaining a preset carbon emission factor from a preset database, based on which the carbon emission index is obtained. The carbon emission factor is used to reflect the amount of carbon dioxide generated per unit volume of the existing building, and the carbon emission index is the product of the carbon dioxide emissions and the carbon emission factor;

[0034] The environmental parameters of existing buildings within a preset time period are measured in real time to obtain thermal comfort indicators. At the same time, the performance indicators of existing buildings are obtained by combining the obtained unit volume energy consumption indicators and carbon emission indicators. The environmental parameters include humidity, wind speed and solar radiation temperature.

[0035] Furthermore, the calculation process of the existing building performance index is:

[0036] Calculate the thermal comfort index of existing buildings in the tth preset time period , the calculation formula is:

[0037] ;

[0038] In the formula, is the number of the preset area type, ; represents humidity impact factor; Indicates the humidity of the f-th type preset area in the t-th preset time period; Indicates the reference humidity of the f-type preset area; represents the wind speed influence factor; Indicates the wind speed in the f-th preset area during the t-th preset time period; Indicates the reference wind speed for the f-th type preset area; represents the solar radiation temperature impact factor; Indicates the solar radiation temperature of the f-th type preset area in the t-th preset time period; Indicates the reference solar radiation temperature of the f-th type preset area;

[0039] According to thermal comfort index Calculate the performance index of existing buildings in the tth preset time period , the calculation formula is:

[0040] ;

[0041] Where t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; It represents the energy consumption index per unit volume of the existing building in the tth preset time period; represents the carbon emission factor; Represents the carbon dioxide emissions of existing buildings in the tth preset time period.

[0042] Furthermore, in step S4, the specific steps of forming a response data set between the actual design parameters and the existing building performance indicators are:

[0043] The actual design parameters are arranged and combined with the existing building performance indicators, and the arrangement and combination process is visualized in the form of a scatter plot to form a response data set.

[0044] Further, in step S5, the combination of the response data set and the genetic algorithm is used to iteratively optimize the existing building envelope structure, wherein the iterative optimization is used to evaluate the average fitness of the existing building envelope structure within a preset time period, and the specific process is as follows:

[0045] Based on the NSGA-Ⅲ algorithm, the row data is encoded as the first individual, the column data is encoded as the second individual, and the response data set is encoded as a population. The first individual represents an existing building envelope design, and the second individual represents an existing building performance indicator.

[0046] A crossover operation is performed on the first individual and the second individual to generate a new population, and the fitness between the new population and the population is evaluated until the fitness between the new population and the population converges to obtain the average fitness.

[0047] Furthermore, after step S3, the method further includes:

[0048] Measuring the predicted values ​​of the thermophysical property parameters and judging whether the predicted values ​​of the thermophysical property parameters meet the measurement indicators, which include correlation indicators, root mean square error indicators and mean absolute error indicators;

[0049] If yes, go to the next step; if no, return to the previous step.

[0050] Furthermore, the specific process of measuring the predicted value of the thermophysical property parameter includes:

[0051] The correlation index is obtained by measuring the linear relationship between the thermophysical parameter and the average value of the thermophysical parameter, and the ratio of the linear relationship between the thermophysical parameter and the predicted value of the thermophysical parameter. When the correlation index is close to 1, it means that there is a good linear relationship between the thermophysical parameter and the average value of the thermophysical parameter. When the correlation index is close to 0, it means that there is no linear relationship between the thermophysical parameter and the average value of the thermophysical parameter. When the correlation index is close to -1, it means that there is a negative linear relationship between the thermophysical parameter and the average value of the thermophysical parameter.

[0052] By measuring the linear relationship between the thermophysical parameter and the predicted value of the thermophysical parameter, the root mean square error index is obtained. The smaller the root mean square error index is, the smaller the difference between the thermophysical parameter and the predicted value of the thermophysical parameter is, and the more accurate the corresponding predicted value of the thermophysical parameter is.

[0053] By measuring the linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters, the mean absolute error index is obtained. The smaller the mean absolute error index is, the smaller the difference between the thermophysical property parameters and the average value of the thermophysical property parameters is.

[0054] Furthermore, the calculation of the measurement index is specifically as follows:

[0055] The correlation index is calculated using the following formula:

[0056] ;

[0057] In the formula, Represents the correlation index of existing buildings in the tth preset time period; They are the total number of preset exterior wall areas, preset roof areas and preset exterior window areas respectively; Respectively represent the predicted value of the heat transfer coefficient of the exterior wall, the predicted value of the heat transfer coefficient of the roof, and the predicted value of the heat transfer coefficient of the exterior window in the preset exterior wall area, the preset roof area, and the preset exterior window area in the tth preset time period; Indicates The external wall heat transfer coefficient of a preset external wall area in the tth preset time period; Indicates The roof heat transfer coefficient of a preset roof area in the tth preset time period; Indicates The heat transfer coefficient of the external window of a preset external window area in the tth preset time period; Indicates The average value of the external wall heat transfer coefficient of a preset external wall area in the tth preset time period; Indicates The average value of the roof heat transfer coefficient of a preset roof area in the tth preset time period; Indicates The average value of the heat transfer coefficient of the external windows of a preset external window area in the tth preset time period;

[0058] The root mean square error metric is calculated using the following formula:

[0059] ;

[0060] In the formula, It represents the root mean square error index of the existing building in the tth preset time period;

[0061] The mean absolute error metric is calculated using the following formula:

[0062] ;

[0063] In the formula, It represents the mean absolute error index of the existing building in the tth preset time period.

[0064] By means of the above technical solution, the present invention provides a method for optimizing thermal parameters of existing building envelope structures based on genetic algorithm, which has at least the following beneficial effects:

[0065] 1. The present invention achieves more accurate acquisition of predicted values ​​of thermophysical property parameters, improves the accuracy of thermal parameter optimization of existing building envelope structures, and effectively solves the problem of low reliability of thermal parameter optimization of existing building envelope structures in the prior art.

[0066] 2. The present invention takes into account the effects of the shading coefficient and the ventilation coefficient when calculating the predicted values ​​of the thermal physical property parameters, which helps to more clearly understand the heat dissipation performance of the existing building envelope structure, improves the accuracy and reliability of the predicted values ​​of the thermal physical property parameters, and thus enhances the accuracy of the optimization of the thermal parameters of the existing building envelope structure.

[0067] 3. The present invention can not only accurately obtain the thermal comfort index of existing buildings, but also evaluate the environmental protection performance of existing buildings by real-time monitoring of the environmental parameters of existing buildings within a preset time period, and combining the carbon emissions of existing buildings within the preset time period and the influence of carbon emission factors on thermal comfort indexes, thereby achieving more accurate acquisition of existing building performance indicators.

[0068] 4. The present invention improves the accuracy of existing building performance indicators by comprehensively considering the impact of energy consumption indicators and thermal comfort indicators on existing building performance indicators, eliminates the impact on the response data set, and further improves the correspondence between actual design parameters and existing building performance indicators, ensuring that each actual design parameter combination corresponds to a set of existing building performance indicators, which helps to directly observe the performance of existing buildings under different design parameter combinations.

[0069] 5. The present invention measures the predicted values ​​of thermal physical property parameters by measuring indicators, which can more comprehensively evaluate the prediction accuracy of thermal physical property parameters of existing building envelope structures, achieve more accurate acquisition of predicted values ​​of thermal physical property parameters, and at the same time improve the accuracy and reliability of predicted values ​​of thermal physical property parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0071] Figure 1 It is a flow chart of the method for optimizing thermal parameters of existing building envelope structure in the first embodiment of the present invention;

[0072] Figure 2 A three-dimensional coordinate analysis diagram of the existing building performance index in the first embodiment of the present invention;

[0073] Figure 3 The figure is a flow chart of a method for optimizing thermal parameters of an existing building envelope structure in the second embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0075] Embodiment 1

[0076] To solve the problem of low reliability in the optimization of thermal parameters of existing building envelope structures, please refer to Figure 1-Figure 2This embodiment proposes a method for optimizing thermal parameters of existing building envelope structures based on a genetic algorithm. The method measures the plane size information of the existing building and the thermal physical parameters of the existing building envelope structure in a preset area within a preset time period, and performs fitness evaluation on the thermal physical parameters. Then, the predicted values ​​of the thermal physical parameters are calculated and it is determined whether the predicted values ​​of the thermal physical parameters are within the preset design parameter value range. Finally, the response data set and the genetic algorithm are combined to iteratively optimize the existing building envelope structure to obtain the optimal solution set of thermal parameters, thereby achieving the effect of improving the accuracy of thermal parameter optimization of the existing building envelope structure.

[0077] In order to better understand the method proposed in this embodiment, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown, the method comprises the following steps:

[0078] S1. Obtain the thermal physical parameters of the existing building envelope structure located in any preset area within a preset time period, the thermal physical parameters include the heat transfer coefficient of the exterior wall, the heat transfer coefficient of the roof and the heat transfer coefficient of the exterior window, and the thermal physical parameters are used to reflect the heat dissipation performance of the existing building envelope structure in the preset area within the preset time period. In this embodiment, the preset time period is at least one week, and the envelope structures in different areas usually have different thermal physical properties due to factors such as materials, structures and orientations. Therefore, by limiting the exterior walls, roofs and exterior windows of the existing buildings in the preset area, the measurement error introduced by the overall complexity of the existing buildings can be reduced, which helps to improve the accuracy of the thermal physical parameter measurement, wherein the preset area includes the preset exterior wall area, the preset roof area and the preset exterior window area.

[0079] In this embodiment, a heat flow meter and a temperature sensor can be used to measure the thermal physical parameters of the existing building envelope. Specifically, the heat flow meter can measure the heat flow through a unit area per unit time, and the temperature sensor is used to record the temperature difference between the inside and outside of the existing building envelope. Through these data, the heat transfer coefficient of the existing building envelope can be calculated. Thus, the required exterior wall heat transfer coefficient of the preset exterior wall area, the roof heat transfer coefficient of the preset roof area, and the exterior window heat transfer coefficient of the preset exterior window area can be obtained.

[0080] S2. Perform fitness evaluation on the acquired thermophysical property parameters to evaluate whether the thermophysical property parameters converge within a preset time period. If so, proceed to step S3; if not, return to step S1.

[0081] In this embodiment, the change of the heat transfer coefficient of the external wall within a preset time period is monitored in real time to obtain the heat gain, and at the same time, it is determined whether the heat gain is equal to the preset heat gain; if it is equal, the heat transfer coefficient of the external wall converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external wall within the preset time period is continuously monitored in the preset area until the obtained heat gain is equal to the preset heat gain. Among them, the preset heat gain is usually represented by the result of summing and averaging the historical heat gains in the preset database, and the heat gain is obtained by measuring the initial temperature of the external wall in the preset area through the temperature sensor, and measuring the temperature of the external wall in the preset area within the preset time period through the temperature sensor, and obtaining the heat gain of the external wall within the preset time period through the difference between the temperature and the initial temperature.

[0082] Similarly, the change of the roof heat transfer coefficient within the preset time period is monitored in real time to obtain the solar radiation temperature, and at the same time, it is determined whether the solar radiation temperature is equal to the preset solar radiation temperature; if it is equal, the roof heat transfer coefficient converges within the preset time period; otherwise, the change of the roof heat transfer coefficient within the preset time period is continuously monitored in the preset area until the obtained solar radiation temperature is equal to the preset solar radiation temperature. Among them, the preset solar radiation temperature is usually represented by the result of summing and averaging the historical solar radiation temperatures in the preset database. The steps for obtaining the solar radiation temperature are: measuring the temperature of the roof in the preset area before solar irradiation through a temperature sensor, and measuring the temperature of the roof in the preset area after solar irradiation within the preset time period through a temperature sensor, and obtaining the solar radiation temperature of the roof within the preset time period through the difference between the temperature after solar irradiation and the temperature before solar irradiation.

[0083] Similarly, the change of the heat transfer coefficient of the external wall within the preset time period is monitored in real time to obtain the insulation amount, and at the same time, it is determined whether the insulation amount is equal to the preset insulation amount; if it is, the heat transfer coefficient of the external window converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external window within the preset time period is continuously monitored in the preset area until the obtained insulation amount is equal to the preset insulation amount. Among them, the preset insulation amount is usually represented by the result of summing and averaging the historical insulation amounts in the preset database, and the steps for obtaining the insulation amount are: using a temperature sensor to measure the temperature of the outer surface of the external window in the preset area after being irradiated by the sun, and at the same time, using a temperature sensor to measure the temperature of the inner surface of the external window in the preset area after the preset time period ends, and the insulation amount of the external window in the preset time period is obtained by the difference between the temperature of the external surface irradiated by the sun and the temperature of the inner surface of the external wall.

[0084] Convergence evaluation of thermal physical parameters in a preset area through the heat gain of the exterior wall, the solar radiation temperature of the roof, and the insulation of the exterior windows can help improve the energy efficiency of existing buildings. For example, understanding the heat gain of the exterior wall can help choose more efficient insulation materials or adjust the wall structure to reduce heat loss, thereby improving the accuracy and reliability of the thermal physical parameters obtained in the preset area.

[0085] S3, calculating the predicted values ​​of the thermal property parameters of the existing building envelope in the preset area according to the thermal property parameters, wherein the predicted values ​​of the thermal property parameters include the predicted values ​​of the heat transfer coefficient of the exterior wall, the predicted values ​​of the heat transfer coefficient of the roof, and the predicted values ​​of the heat transfer coefficient of the exterior window. As a preferred implementation of this embodiment, the specific process includes:

[0086] Determine the shading coefficient and ventilation coefficient that affect the predicted value of the thermophysical property parameter within a preset time period. In this embodiment, the shading coefficient is used to reflect the ability of the roof in the preset roof area to block solar radiation heat within a preset time period. The shading coefficient is obtained by measuring the ratio of the heat passing through the roof glass to the heat passing through the standard roof glass with a thickness of 3mm in real time through a thermometer. The lower the heat passing through the roof glass, the smaller the shading coefficient, and the better the performance of the corresponding roof in blocking the radiation of sunlight heat into the room.

[0087] The ventilation coefficient is used to reflect the ventilation performance of the external windows in the preset external window area within the preset time period. Usually, an anemometer is used to measure the air flow rate through the external windows in the preset external window area, and the atmospheric air flow rate outside the external windows at the current moment is measured at the same time. The air flow rate through the external windows is divided by the atmospheric air flow rate outside the external windows at the current moment to obtain the ventilation coefficient. The larger the ventilation coefficient, the better the ventilation performance of the external windows.

[0088] It needs to be understood that changes in the shading coefficient and ventilation coefficient will change the thermal environment of the building, thereby affecting the values ​​of the thermal physical parameters. Taking the roof heat transfer coefficient and the predicted value of the roof heat transfer coefficient as an example, a reduction in the shading coefficient (i.e., an increase in shading performance) will usually reduce the solar radiation heat absorbed by the roof, thereby reducing the roof heat transfer coefficient, while an increase in the ventilation coefficient will enhance air flow and help dissipate heat, thereby increasing the predicted value of the roof heat transfer coefficient; similarly, the shading coefficient and ventilation coefficient have an effect on the predicted value of the exterior wall heat transfer coefficient and the predicted value of the exterior window heat transfer coefficient.

[0089] As mentioned above, by taking into account the effects of the shading coefficient and the ventilation coefficient when calculating the predicted values ​​of the thermophysical property parameters, it is helpful to have a clearer understanding of the heat dissipation performance of the existing building envelope structure, improve the accuracy and reliability of the predicted values ​​of the thermophysical property parameters, thereby enhancing the accuracy of the optimization of the thermal parameters of the existing building envelope structure, and effectively solving the problem of low reliability of the optimization of the thermal parameters of the existing building envelope structure in the prior art.

[0090] Combined with the thermophysical parameters, the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area, the predicted value of the roof heat transfer coefficient of the preset roof area, and the predicted value of the exterior window heat transfer coefficient of the preset exterior window area are calculated, where:

[0091] The calculation expression of the predicted value of the exterior wall heat transfer coefficient is:

[0092] ;

[0093] In the formula, is the number of the preset exterior wall area, , is the total number of preset exterior wall areas; t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; represents the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area in the tth preset time period; Indicates the shading coefficient of the preset roof area in the tth preset time period; Indicates the ventilation coefficient of the preset external window area in the tth preset time period; Indicates The external wall heat transfer coefficient of a preset external wall area in the tth preset time period;

[0094] The calculation expression of the predicted value of the roof heat transfer coefficient is:

[0095] ;

[0096] In the formula, is the number of the preset roof area, , is the total number of preset roof areas; represents the predicted value of the roof heat transfer coefficient of the preset roof area in the tth preset time period; Indicates The roof heat transfer coefficient of a preset roof area in the tth preset time period;

[0097] The calculation expression of the predicted value of the heat transfer coefficient of the exterior window is:

[0098] ;

[0099] In the formula, is the number of the preset roof area, , is the total number of preset exterior window areas; represents the predicted value of the heat transfer coefficient of the external window in the preset external window area in the tth preset time period; Indicates The heat transfer coefficient of the external window of a preset external window area in the tth preset time period.

[0100] This embodiment achieves more accurate acquisition of predicted values ​​of thermophysical property parameters, thereby improving the accuracy of optimization of thermal parameters of existing building envelope structures, and effectively solves the problem of low reliability of optimization of thermal parameters of existing building envelope structures in the prior art.

[0101] S4. Determine whether the predicted value of the thermal physical property parameter is within the preset design parameter value range. If so, obtain the actual design parameters of the existing building envelope structure in the preset area, and form a response data set between the actual design parameters and the existing building performance indicators; otherwise, return to S1, and the actual design parameters include the material of the exterior wall, the thickness of the roof, and the shading material of the exterior window.

[0102] In this embodiment, the design parameter value range includes the value range of the external wall heat transfer coefficient, the value range of the roof heat transfer coefficient, and the value range of the external window heat transfer coefficient. In actual applications, the difference between the historical maximum external wall heat transfer coefficient and the historical minimum external wall heat transfer coefficient in the preset database is usually set as the value range of the external wall heat transfer coefficient; the difference between the historical maximum roof heat transfer coefficient and the historical minimum roof heat transfer coefficient in the preset database is set as the value range of the roof heat transfer coefficient; the difference between the historical maximum external window heat transfer coefficient and the historical minimum external window heat transfer coefficient in the preset database is set as the value range of the external window heat transfer coefficient. The specific design parameter value range can be set in combination with actual needs, and no limitation is made here.

[0103] In this embodiment, the performance index of the existing building is obtained through the unit volume energy consumption index, carbon emission index and thermal comfort index of the existing building in a preset time period. The unit volume energy consumption index is used to reflect the energy consumption of the existing building in the preset time period, the carbon emission index is used to reflect the carbon dioxide emissions of the existing building in the preset time period, and the thermal comfort index is used to reflect the comfort of the internal environment of the existing building. The specific process includes:

[0104] The energy consumption data of the existing building in a preset time period is obtained, and the energy consumption index per unit volume is obtained in combination with the plane size information of the existing building. The energy consumption data includes electricity consumption and fuel consumption. The energy consumption index per unit volume is the ratio of the energy consumption data to the volume of the existing building, wherein the volume of the existing building is the product of the length, width, and height of the existing building in a preset area (preset external wall area, preset roof area, and preset external window area), and the plane size information is the length, width, and height data of the existing building, and a laser rangefinder can be used to measure the length, width, and height of the existing building. In this embodiment, the energy consumption data is the sum of the electricity consumption per unit volume and the fuel consumption per unit volume, wherein the electricity consumption per unit volume is the ratio of the total electricity consumption of the existing building in the preset time period to the volume of the existing building, and the fuel consumption per unit volume is the ratio of the total fuel consumption of the existing building in the preset time period to the volume of the existing building.

[0105] Real-time monitoring of carbon dioxide emissions from existing buildings within a preset time period, and obtaining a preset carbon emission factor from a preset database to obtain a carbon emission index based on this. The carbon emission factor is used to reflect the amount of carbon dioxide generated per unit volume by the existing building, and the carbon emission index is the product of carbon dioxide emissions and the carbon emission factor.

[0106] The environmental parameters of the existing building are measured in real time within a preset time period to obtain the thermal comfort index, and the performance index of the existing building is obtained by combining the obtained unit volume energy consumption index and carbon emission index. The environmental parameters include humidity, wind speed and solar radiation temperature. In practical applications, the thermal comfort index is the sum of the humidity index, wind speed index and solar radiation temperature index. The solar radiation temperature of the roof of the preset roof area in the preset time period is usually measured in real time by a temperature sensor, and divided by the average solar radiation temperature to obtain the solar radiation temperature index; the humidity of the roof of the preset roof area in the preset time period is measured in real time by a humidity sensor, and divided by the average humidity to obtain the humidity index; the wind speed of the roof of the preset roof area in the preset time period is measured in real time by a speed sensor, and divided by the average wind speed to obtain the wind speed index. Among them, the average solar radiation temperature is usually represented by the sum and average of the historical roof solar radiation temperatures in the preset database; the average humidity is usually represented by the sum and average of the historical roof humidity in the preset database; the average wind speed is usually represented by the sum and average of the historical roof wind speeds in the preset database.

[0107] By real-time monitoring of the environmental parameters of existing buildings within a preset time period, and combining the carbon emissions of existing buildings within the preset time period and the impact of carbon emission factors on thermal comfort indicators, not only can the thermal comfort indicators of existing buildings be accurately obtained, but also the environmental protection performance of existing buildings can be evaluated, thereby achieving more accurate acquisition of existing building performance indicators.

[0108] Furthermore, the existing building performance index is calculated by the following formula:

[0109] ;

[0110] Where t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; represents the performance index of the existing building in the tth preset time period; It represents the energy consumption index per unit volume of the existing building in the tth preset time period; represents the carbon emission factor; It represents the carbon dioxide emission of the existing building in the tth preset time period; It represents the thermal comfort index of the existing building in the tth preset time period.

[0111] In this embodiment, in order to simplify the analysis, we define , where It represents the energy consumption index of the existing building in the tth preset time period. The simplified calculation formula of the performance index of the existing building is: .like Figure 2 As shown, it is a three-dimensional coordinate analysis diagram of the existing building performance index provided by the embodiment of the present application, which is composed of Figure 2 It can be seen that the existing building performance index decreases with the increase of the energy consumption index and increases with the increase of the thermal comfort index, wherein the carbon emission factor is obtained from a preset database. In a specific embodiment, a mapping set of carbon dioxide emissions and their corresponding carbon emission factors is constructed according to the relationship between the historical carbon dioxide emissions in the preset database and the existing building performance index, and the real-time carbon dioxide emissions are input into the mapping set to obtain the corresponding carbon emission factor.

[0112] It should be understood that the algorithm of this embodiment combines the energy consumption index and the thermal comfort index factors, and comprehensively analyzes to obtain the existing building performance index. The energy consumption index and the thermal comfort index in this formula not only unilaterally affect the value of the existing building performance index, but the thermal comfort index also indirectly affects the value of the energy consumption index. When the thermal comfort increases, it means that more energy is needed to maintain the indoor temperature and humidity, which leads to an increase in the energy consumption index, and then affects the value of the existing building performance index. For example, when the building manager needs to improve the indoor comfort, it is usually necessary to increase the operating time or power of the heating or cooling system, which will lead to an increase in the energy consumption index. By comprehensively considering the impact of the energy consumption index and the thermal comfort index factors on the existing building performance indicators, the accuracy of the existing building performance indicators is improved, the impact on the response data set is eliminated, and the correspondence between the actual design parameters and the existing building performance indicators is further improved.

[0113] Furthermore, the specific calculation formula of thermal comfort index is:

[0114] ;

[0115] In the formula, is the number of the preset area type, ; represents humidity impact factor; Indicates the humidity of the f-th type preset area in the t-th preset time period; Indicates the reference humidity of the f-type preset area; represents the wind speed influence factor; Indicates the wind speed in the f-th preset area during the t-th preset time period; Indicates the reference wind speed for the f-th type preset area; represents the solar radiation temperature impact factor; Indicates the solar radiation temperature of the f-th type preset area in the t-th preset time period; Represents the reference solar radiation temperature of the f-th type preset area.

[0116] Specifically, f=1 is the preset exterior wall area, f=2 is the preset roof area, and f=3 is the preset exterior window area. It represents the humidity of the exterior wall in the preset exterior wall area during the tth preset time period. Indicates the reference exterior wall humidity, It represents the humidity of the roof in the preset roof area during the tth preset time period. represents the reference roof humidity, It represents the humidity of the external window in the preset external window area during the tth preset time period, represents the reference external window humidity, represents the wind speed of the external wall in the preset external wall area in the tth preset time period, represents the reference exterior wall wind speed, It represents the wind speed of the roof in the preset roof area during the tth preset time period, represents the reference roof wind speed, represents the wind speed of the external window in the preset external window area during the tth preset time period, represents the reference external window wind speed, represents the solar radiation temperature of the external wall in the preset external wall area in the tth preset time period, represents the reference exterior wall solar radiation temperature, It represents the solar radiation temperature of the roof in the preset roof area during the tth preset time period. represents the reference roof solar radiation temperature, represents the solar radiation temperature of the external window in the preset external window area during the tth preset time period, Represents the reference external window solar radiation temperature.

[0117] Among them, the humidity influence factor, wind speed influence factor and solar radiation temperature influence factor are obtained from the preset database. The humidity influence factor is used to measure the influence of humidity on the existing building envelope structure within a preset time period, the wind speed influence factor is used to measure the influence of wind speed on the existing building envelope structure within a preset time period, and the solar radiation temperature influence factor is used to measure the influence of solar radiation temperature on the existing building envelope structure within a preset time period.

[0118] In this embodiment, the reference exterior wall humidity is represented by the sum and average of the historical exterior wall humidity in the preset database, the reference roof humidity is represented by the sum and average of the historical roof humidity in the preset database, and the reference exterior window humidity is represented by the sum and average of the historical exterior window humidity in the preset database.

[0119] The reference exterior wall wind speed is represented by the sum and average of the historical exterior wall wind speeds in the preset database, the reference roof wind speed is represented by the sum and average of the historical roof wind speeds in the preset database, and the reference exterior window wind speed is represented by the sum and average of the historical exterior window wind speeds in the preset database.

[0120] The reference exterior wall solar radiation temperature is represented by the sum and average of the historical exterior wall solar radiation temperatures in the preset database, the reference roof solar radiation temperature is represented by the sum and average of the historical roof solar radiation temperatures in the preset database, and the reference exterior window solar radiation temperature is represented by the sum and average of the historical exterior window solar radiation temperatures in the preset database.

[0121] Specifically, taking the roof of a preset roof area as an example, the humidity impact factor is obtained from a preset database. In a specific embodiment, a mapping set of roof humidity and its corresponding humidity impact factor is constructed according to the relationship between the historical roof humidity and the thermal comfort index in the preset database, and the real-time roof humidity is input into the mapping set to obtain the corresponding humidity impact factor.

[0122] The wind speed influence factor is obtained from a preset database. In a specific embodiment, taking the roof of a preset roof area as an example, a mapping set of roof wind speed and its corresponding wind speed influence factor is constructed according to the relationship between the historical roof wind speed and the thermal comfort index in the preset database, and the real-time roof wind speed is input into the mapping set to obtain the corresponding wind speed influence factor.

[0123] The solar radiation temperature impact factor is obtained from a preset database. In a specific embodiment, taking the roof of a preset roof area as an example, a mapping set of the roof solar radiation temperature and its corresponding solar radiation temperature impact factor is constructed according to the relationship between the historical roof solar radiation temperature and the thermal comfort index in the preset database, and the real-time roof solar radiation temperature is input into the mapping set to obtain the corresponding solar radiation temperature impact factor.

[0124] Specifically, when , and When , the corresponding thermal comfort index is equal to 1. At this time, the thermal comfort effect of the existing building is the best. In order to simplify the analysis, the definition , , .

[0125] In the formula, It represents the humidity index of the existing building in the tth preset time period. It represents the wind speed index of the existing building in the tth preset time period. It represents the solar radiation temperature index of the existing building in the tth preset time period. The simplified calculation formula of the thermal comfort index is: .

[0126] It should be understood that the algorithm of this embodiment combines the humidity index, wind speed index and solar radiation temperature index factors to obtain the thermal comfort index through comprehensive analysis. The wind speed index and solar radiation temperature index in this formula not only unilaterally affect the value of the thermal comfort index, but the solar radiation temperature index also indirectly affects the value of the wind speed index. Suppose there is an office building with windows facing south and no sunshade facilities installed. On a clear afternoon in summer, the solar radiation intensity is very high, causing the temperature near the building's exterior walls and windows to rise sharply. Due to the increase in temperature near the exterior walls and windows, a temperature gradient is formed with other indoor areas, driving the natural convection of indoor air. This convection may increase the wind speed near the window area. If the building is equipped with an air conditioning system, in order to cope with the indoor temperature rise caused by solar radiation, the air conditioning system may increase the air supply to maintain the set indoor temperature, which will cause the wind speed index of the entire indoor area to increase.

[0127] In summary, the solar radiation temperature index indirectly affects the value of the wind speed index by changing the temperature distribution and air flow inside and outside the building, so as to more accurately evaluate the thermal comfort level of existing buildings and improve the accuracy and reliability of the thermal comfort index.

[0128] In this embodiment, the specific steps of forming a response data set between actual design parameters and existing building performance indicators are:

[0129] The actual design parameters are arranged and combined with the existing building performance indicators, and the arrangement and combination process is visualized in the form of a scatter plot to form a response data set, which is used to visualize the one-to-one correspondence between the actual design parameters and the existing building performance indicators. The arrangement and combination usually uses the actual design parameters as row data and the existing building performance indicators as column data. The scatter plot is used to reflect the influence of the actual design parameters on the existing building envelope structure in the preset area.

[0130] Specifically, the actual design parameters (materials of the exterior walls, thickness of the roof, and shading materials of the exterior windows) and existing building performance indicators (energy consumption per unit volume, carbon emission indicators, and thermal comfort indicators) are encoded and organized into data tables to be presented in the form of response data sets, ensuring that each actual design parameter combination corresponds to a set of existing building performance indicators, which helps to directly observe the performance of existing buildings under different design parameter combinations.

[0131] In this embodiment, the row data in the response data set represent different actual design parameter combinations (which can be different values ​​of the same design parameter or a combination of multiple design parameters), and the column data represent the existing building performance index. At the same time, the actual design parameter is used as the x-axis, and the existing building performance index is used as the y-axis. A scatter plot is drawn using drawing software (such as the Seaborn library), and different colors are used to represent different design parameter combinations. The distribution of the scatter plot and the influence of different design parameter combinations on the existing building performance index are observed in real time, such as the changes in the existing building performance index corresponding to different design parameter combinations, thereby improving the accuracy of the visual analysis of the response data set.

[0132] S5. Iteratively optimize the existing building envelope structure based on the genetic algorithm combined with the response data set to obtain the optimal solution set of thermal parameters. The iterative optimization is used to evaluate the average fitness of the existing building envelope structure within a preset time period. The optimal solution set of thermal parameters represents the envelope structure design scheme that converges between the existing building reference performance indicators after iterative optimization.

[0133] Furthermore, the specific process of iterative optimization of the existing building envelope structure by combining the response data set and the genetic algorithm is as follows:

[0134] According to the NSGA-Ⅲ algorithm, the row data is encoded as the first individual, the column data is encoded as the second individual, and the response data set is encoded as a population. The first individual represents an existing building envelope structure design, and the second individual represents an existing building performance indicator. The first individual and the second individual are cross-operated to generate a new population, and the fitness between the new population and the population is evaluated until the fitness between the new population and the population converges to obtain the average fitness. The cross-operation includes single-point cross-over and uniform cross-over. Fitness convergence means that the fitness between the new population and the population is equal to the preset population fitness.

[0135] In this embodiment, the actual design parameters are variable in the genetic operations (such as crossover and mutation) in the NSGA-Ⅲ (Non-dominated Sorting Genetic Algorithm III) algorithm. When the first individual and the second individual perform a crossover operation, a population (i.e., a response data set) will be formed. With different crossovers of the first individual (actual design parameters) and different permutations and combinations of the first individual and the second individual, that is, a permutation and combination will be performed after each crossover, and new populations (i.e., new existing building performance indicators: new population fitness) will be continuously generated. When the fitness of the new population is equal to the fitness of the initial population, it indicates that the fitness between the new population and the population has converged. Among them, the NSGA-Ⅲ algorithm is a kind of genetic algorithm, which is usually applicable to a single individual (the first individual and the second individual). The preset population fitness is the initial population fitness when the second individual (existing building performance indicator) is not crossover-operated. The average fitness is usually the ratio of the sum of the fitness of the new population to the number of crossover operations, thereby improving the accuracy and efficiency of fitness convergence.

[0136] Specifically, the reference performance indicators of existing buildings usually include reference unit volume energy consumption indicators, reference carbon emission indicators and reference thermal comfort indicators. Among them, the reference unit volume energy consumption indicators are usually expressed by summing and averaging the historical unit volume energy consumption data in the preset database, the reference carbon emission indicators are usually expressed by summing and averaging the historical carbon emission data in the preset database, and the reference thermal comfort indicators are usually expressed by summing and averaging the historical thermal comfort data in the preset database. It should be noted that the historical unit volume energy consumption data are usually the single unit volume energy consumption data of the existing buildings in the historical time period (such as year, season, month). The historical carbon emission data is usually the total amount of energy (such as electricity, gas and heat) consumed per unit volume (such as per square meter, per cubic meter). The historical carbon emission data is usually the total amount of greenhouse gas emissions generated by existing buildings in the historical time period. The historical thermal comfort data is usually the sum of indoor temperature and humidity of existing buildings in the historical time period. When the reference unit volume energy consumption index is equal to the unit volume energy consumption index, the reference carbon emission index is equal to the carbon emission index and the reference thermal comfort index is equal to the thermal comfort index, it means that the performance indicators of the existing building have converged, which is the optimal solution set of thermal parameters, thereby improving the accuracy of optimization of thermal parameters of the existing building envelope structure.

[0137] In summary, the embodiment of the present application obtains the thermophysical property parameters of the existing building envelope structure in a preset area, obtains the predicted values ​​of the thermophysical property parameters by calculation and determines whether the predicted values ​​of the thermophysical property parameters are within the preset design parameter value range, and then combines the response data set and the genetic algorithm to iteratively optimize the existing building envelope structure to obtain the optimal solution set of thermal parameters, thereby achieving more accurate acquisition of the predicted values ​​of the thermophysical property parameters, improving the accuracy of the optimization of the thermal parameters of the existing building envelope structure, and effectively solving the problem of low reliability of the optimization of the thermal parameters of the existing building envelope structure in the prior art.

[0138] Embodiment 2

[0139] See also Figure 3 Based on the first embodiment, this embodiment also proposes another implementation method. It should be noted that the same parts as the first embodiment can be referred to each other, and only the differences are described here. Specifically, a method for optimizing thermal parameters of existing building envelope structures based on genetic algorithms includes the following steps:

[0140] S1. Obtaining thermal physical parameters of an existing building envelope structure located in any preset area within a preset time period, wherein the thermal physical parameters include an exterior wall heat transfer coefficient, a roof heat transfer coefficient, and an exterior window heat transfer coefficient;

[0141] S2, performing fitness evaluation on the acquired thermophysical property parameters to evaluate whether the thermophysical property parameters converge within a preset time period, if so, proceeding to step S3; if not, returning to step S1;

[0142] S3, calculating the predicted value of the thermal physical parameter of the existing building envelope structure in the preset area according to the thermal physical parameter;

[0143] S4, measure the predicted value of the thermophysical property parameter, and determine whether the predicted value of the thermophysical property parameter meets the measurement index, which includes the correlation index, the root mean square error index and the mean absolute error index; if so, proceed to the next step; if not, return to S1.

[0144] Specifically, the correlation index, root mean square error index and mean absolute error index are obtained by combining the thermophysical parameters of the existing building envelope and the corresponding average values ​​of the thermophysical parameters. The average values ​​of the thermophysical parameters include the average values ​​of the heat transfer coefficients of the exterior walls, the roofs and the exterior windows. The correlation index is used to measure the accuracy of the predicted values ​​of the thermophysical parameters; the root mean square error index is used to measure the degree of overlap between the thermophysical parameters and the predicted values ​​of the thermophysical parameters; and the mean absolute error index is used to measure the degree of overlap between the thermophysical parameters and the average values ​​of the thermophysical parameters.

[0145] In practical applications, the Pearson correlation coefficient is usually used as a correlation indicator to measure the strength and direction of the linear relationship between two variables. The Pearson correlation coefficient not only has an intuitive numerical representation, but is also accompanied by corresponding statistical test methods (such as t-test), which can determine whether the correlation coefficient is significantly different from 0, that is, whether there is a significant linear relationship between the two variables. It has a clear range of values ​​and an intuitive explanation, so even non-statistical technicians can easily understand its meaning.

[0146] The root mean square error metric is a common way to measure the difference between the predicted and actual values. It calculates the square root of the average of the squares of the differences between the predicted and actual values. The mean absolute error metric is another way to measure the accuracy of the forecast. It calculates the average of the absolute values ​​of the differences between the predicted and actual values.

[0147] In this embodiment, the correlation index is obtained by measuring the linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters, and the ratio of the linear relationship between the thermophysical property parameters and the predicted values ​​of the thermophysical property parameters. When the correlation index is close to 1, it means that there is a good linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters. When the correlation index is close to 0, it means that there is no linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters. When the correlation index is close to -1, it means that there is a negative linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters.

[0148] By measuring the linear relationship between the thermophysical parameter and the predicted value of the thermophysical parameter, the root mean square error index is obtained. The smaller the root mean square error index is, the smaller the difference between the thermophysical parameter and the predicted value of the thermophysical parameter is, and the more accurate the corresponding predicted value of the thermophysical parameter is.

[0149] By measuring the linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters, the mean absolute error index is obtained. The smaller the mean absolute error index is, the smaller the difference between the thermophysical property parameters and the average value of the thermophysical property parameters is.

[0150] Furthermore, the correlation index is calculated by the following formula:

[0151] ;

[0152] In the formula, Represents the correlation index of existing buildings in the tth preset time period; Indicates The average value of the external wall heat transfer coefficient of a preset external wall area in the tth preset time period; Indicates The average value of the roof heat transfer coefficient of a preset roof area in the tth preset time period; Indicates The average value of the heat transfer coefficient of the external windows in the preset external window area in the tth preset time period.

[0153] In order to simplify the analysis in this embodiment, we define , , , where It represents the external wall heat transfer correlation index of the external wall in the preset external wall area in the tth preset time period, It represents the roof heat transfer correlation index of the roof in the preset roof area in the tth preset time period, It represents the external window heat transfer correlation index of the external windows in the preset external window area in the tth preset time period.

[0154] The simplified calculation formula of the correlation index is: , the statistical table of changes in correlation indicators is shown in Table 1:

[0155] Table 1 Statistics of changes in correlation indicators

[0156]

[0157] It should be understood that the external wall heat transfer correlation index is usually obtained by measuring the ratio of the square of the difference between the external wall heat transfer coefficient and the predicted value of the external wall heat transfer coefficient to the square of the difference between the average value of the external wall heat transfer coefficient. When the external wall heat transfer coefficient is equal to the predicted value of the external wall heat transfer coefficient and the external wall heat transfer coefficient is equal to the average value of the external wall heat transfer coefficient, the equivalent exchange principle is used to obtain the predicted value of the external window heat transfer coefficient equal to the average value of the external wall heat transfer coefficient, that is, when the external wall heat transfer correlation index is equal to 1 , the predicted value of the exterior wall heat transfer coefficient is the most accurate.

[0158] Similarly, when the roof heat transfer correlation index is equal to 1 , the roof heat transfer coefficient prediction value is most accurate when the external window heat transfer correlation index is equal to 1 , the predicted value of the heat transfer coefficient of the exterior window is the most accurate. In summary, when , and When , the corresponding correlation index is equal to 0, that is, the accuracy of the predicted value of the thermophysical property parameters is the highest.

[0159] Specifically, the root mean square error index is calculated by the following formula:

[0160] ;

[0161] In the formula, It represents the root mean square error index of the existing building in the tth preset time period;

[0162] The mean absolute error metric is calculated using the following formula:

[0163] ;

[0164] In the formula, It represents the mean absolute error index of the existing building in the tth preset time period.

[0165] In the calculation formula of the root mean square error indicator, in order to simplify the analysis, the definition , , , where It represents the external wall heat transfer root mean square error index of the external wall in the preset external wall area in the tth preset time period, It represents the root mean square error index of the roof heat transfer of the roof in the preset roof area during the tth preset time period. It represents the external window heat transfer root mean square error index of the external window in the preset external window area in the tth preset time period. The simplified calculation formula of the root mean square error index is: .

[0166] It should be understood that the external wall heat transfer root mean square error index is usually obtained by measuring the square of the difference between the external wall heat transfer coefficient and the predicted value of the external wall heat transfer coefficient. When the external wall heat transfer coefficient is equal to the predicted value of the external wall heat transfer coefficient, that is, the external wall heat transfer root mean square error index is equal to 0 , the predicted value of the heat transfer coefficient of the exterior wall is the most accurate. Similarly, when the root mean square error index of the roof heat transfer is equal to 0 , the roof heat transfer coefficient prediction value is the most accurate when the external window heat transfer root mean square error index is equal to 0 , the predicted value of the heat transfer coefficient of the exterior window is the most accurate. In summary, when , and When , the corresponding root mean square error index is equal to 0, that is, the accuracy of the predicted value of the thermophysical property parameters is the highest.

[0167] In the calculation formula of the mean absolute error indicator, in order to simplify the analysis, the definition , , , where It represents the mean absolute error index of the heat transfer of the exterior wall in the preset exterior wall area during the tth preset time period. It represents the mean absolute error index of roof heat transfer in the preset roof area during the t-th preset time period. It represents the average absolute error index of the heat transfer of the external windows in the preset external window area in the tth preset time period. The simplified calculation formula of the average absolute error index is: .

[0168] It should be understood that the average absolute error index of external wall heat transfer is usually obtained by measuring the absolute value of the difference between the external wall heat transfer coefficient and the average value of the external wall heat transfer coefficient. When the external wall heat transfer coefficient is equal to the average value of the external wall heat transfer coefficient, that is, the average absolute error index of external wall heat transfer is equal to 0 , the average value of the heat transfer coefficient of the exterior wall is the most accurate. Similarly, when the roof heat transfer mean absolute error index is equal to 0 , the average value of the roof heat transfer coefficient is the most accurate, and when the average absolute error index of the external window heat transfer is equal to 0 , the average value of the heat transfer coefficient of the exterior window has the highest accuracy. In summary, when , and When , the corresponding mean absolute error index is equal to 0, that is, the accuracy of the average value of the thermophysical property parameters is the highest.

[0169] S5. Determine whether the predicted value of the thermophysical property parameter is within the preset range of the design parameter value. If so, obtain the actual design parameters of the existing building envelope structure in the preset area, and form a response data set between the actual design parameters and the existing building performance index; otherwise, return to S1;

[0170] S6. Based on the genetic algorithm combined with the response data set, the existing building envelope structure is iteratively optimized to obtain the optimal solution set of thermal parameters.

[0171] In this embodiment, by applying measurement indicators to the calculation of the predicted values ​​of thermal physical property parameters, the prediction accuracy of the thermal physical property parameters of the existing building envelope structure can be more comprehensively evaluated, and more accurate acquisition of the predicted values ​​of the thermal physical property parameters can be achieved, while improving the accuracy and reliability of the predicted values ​​of the thermal physical property parameters.

[0172] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0173] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0174] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for optimizing thermal parameters of existing building envelope structures based on genetic algorithm, characterized in that: The method comprises the following steps: S1. Obtaining thermal physical parameters of an existing building envelope structure located in any preset area within a preset time period, wherein the thermal physical parameters include an exterior wall heat transfer coefficient, a roof heat transfer coefficient, and an exterior window heat transfer coefficient; S2, performing fitness evaluation on the acquired thermophysical property parameters to evaluate whether the thermophysical property parameters converge within a preset time period, if so, proceeding to step S3; if not, returning to step S1; S3. Calculate the predicted value of the thermal physical parameter of the existing building envelope structure in the preset area according to the thermal physical parameter. The specific process includes: Determine the shading coefficient and ventilation coefficient that affect the predicted value of the thermophysical property parameter within a preset time period; Combined with the thermophysical parameters, the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area, the predicted value of the roof heat transfer coefficient of the preset roof area, and the predicted value of the exterior window heat transfer coefficient of the preset exterior window area are calculated, where: The calculation expression of the predicted value of the exterior wall heat transfer coefficient is: ； In the formula, is the number of the preset exterior wall area, , is the total number of preset exterior wall areas; t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; represents the predicted value of the exterior wall heat transfer coefficient of the preset exterior wall area in the tth preset time period; Indicates the shading coefficient of the preset roof area in the tth preset time period; Indicates the ventilation coefficient of the preset external window area in the tth preset time period; Indicates The external wall heat transfer coefficient of a preset external wall area in the tth preset time period; The calculation expression of the predicted value of the roof heat transfer coefficient is: ； In the formula, is the number of the preset roof area, , is the total number of preset roof areas; represents the predicted value of the roof heat transfer coefficient of the preset roof area in the tth preset time period; Indicates The roof heat transfer coefficient of a preset roof area in the tth preset time period; The calculation expression of the predicted value of the heat transfer coefficient of the exterior window is: ； In the formula, is the number of the preset roof area, , is the total number of preset exterior window areas; represents the predicted value of the heat transfer coefficient of the external window in the preset external window area in the tth preset time period; Indicates The heat transfer coefficient of the external window of a preset external window area in the tth preset time period; S4, judging whether the predicted value of the thermophysical property parameter is within the preset range of the design parameter value, if so, obtaining the actual design parameters of the existing building envelope structure in the preset area, and forming a response data set between the actual design parameters and the existing building performance index; otherwise, returning to step S1; In step S4, the existing building performance index is obtained through the unit volume energy consumption index, carbon emission index and thermal comfort index of the existing building within a preset time period. The specific process includes: Obtain energy consumption data of existing buildings within a preset time period, and obtain energy consumption per unit volume in combination with the plane size information of existing buildings. The energy consumption data includes electricity consumption and fuel consumption. The energy consumption per unit volume is the ratio of energy consumption data to the volume of existing buildings. Real-time monitoring of the carbon dioxide emissions of existing buildings within a preset time period, and obtaining a preset carbon emission factor from a preset database, based on which the carbon emission index is obtained. The carbon emission factor is used to reflect the amount of carbon dioxide generated per unit volume of the existing building, and the carbon emission index is the product of the carbon dioxide emissions and the carbon emission factor; Real-time measurement of environmental parameters of existing buildings within a preset time period to obtain thermal comfort indicators, and at the same time, combined with the obtained unit volume energy consumption indicators and carbon emission indicators to obtain the performance indicators of existing buildings. Environmental parameters include humidity, wind speed and solar radiation temperature; The calculation process of the existing building performance index is as follows: Calculate the thermal comfort index of existing buildings in the tth preset time period , the calculation formula is: ； In the formula, is the number of the preset area type, ; represents humidity impact factor; Indicates the humidity of the f-th type preset area in the t-th preset time period; Indicates the reference humidity of the f-type preset area; represents the wind speed influence factor; Indicates the wind speed in the f-th preset area during the t-th preset time period; Indicates the reference wind speed for the f-th type preset area; represents the solar radiation temperature impact factor; Indicates the solar radiation temperature of the f-th type preset area in the t-th preset time period; Indicates the reference solar radiation temperature of the f-th type preset area; According to thermal comfort index Calculate the performance index of existing buildings in the tth preset time period , the calculation formula is: ； Where t is the number of the preset time period, , T is the total number of preset time periods; e is a natural constant; It represents the energy consumption index per unit volume of the existing building in the tth preset time period; represents the carbon emission factor; It represents the carbon dioxide emission of the existing building in the tth preset time period; S5. Based on the genetic algorithm combined with the response data set, the envelope structure of the existing building is iteratively optimized to obtain the optimal solution set of thermal parameters. The optimal solution set of thermal parameters represents the envelope structure design scheme in which the envelope structure of the existing building converges between the reference performance indicators of the existing building after iterative optimization.

2. The method for optimizing thermal parameters of existing building envelope structures according to claim 1, characterized in that: In step S2, the specific process includes: Real-time monitoring of the change of the heat transfer coefficient of the exterior wall within a preset time period to obtain the heat gain, and at the same time determine whether the heat gain is equal to the preset heat gain; If it is equal, the heat transfer coefficient of the external wall converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external wall within the preset time period is continuously monitored in the preset area until the heat gain obtained is equal to the preset heat gain; Real-time monitoring of the roof heat transfer coefficient changes within a preset time period to obtain the solar radiation temperature, and at the same time determine whether the solar radiation temperature is equal to the preset solar radiation temperature; If it is equal to, the roof heat transfer coefficient converges within the preset time period; otherwise, the change of the roof heat transfer coefficient within the preset time period is continuously monitored in the preset area until the obtained solar radiation temperature is equal to the preset solar radiation temperature; Real-time monitoring of the changes in the heat transfer coefficient of the exterior wall within a preset time period to obtain the insulation value, and at the same time determine whether the insulation value is equal to the preset insulation value; If it is equal, the heat transfer coefficient of the external window converges within the preset time period; otherwise, the change of the heat transfer coefficient of the external window within the preset time period is continuously monitored in the preset area until the obtained insulation amount is equal to the preset insulation amount.

3. The method for optimizing thermal parameters of existing building envelope structures according to claim 1, characterized in that: In step S4, the specific steps of forming a response data set between actual design parameters and existing building performance indicators are: The actual design parameters are arranged and combined with the existing building performance indicators, and the arrangement and combination process is visualized in the form of a scatter plot to form a response data set.

4. The method for optimizing thermal parameters of existing building envelope structures according to claim 1, characterized in that: In step S5, the existing building envelope structure is iteratively optimized by combining the response data set and the genetic algorithm, wherein the iterative optimization is used to evaluate the average fitness of the existing building envelope structure within a preset time period. The specific process is as follows: Based on the NSGA-Ⅲ algorithm, the row data is encoded as the first individual, the column data is encoded as the second individual, and the response data set is encoded as a population. The first individual represents an existing building envelope design, and the second individual represents an existing building performance indicator. A crossover operation is performed on the first individual and the second individual to generate a new population, and the fitness between the new population and the population is evaluated until the fitness between the new population and the population converges to obtain the average fitness.

5. The method for optimizing thermal parameters of existing building envelope structures according to claim 1, characterized in that: After step S3, the method further includes: Measuring the predicted values ​​of the thermophysical property parameters and judging whether the predicted values ​​of the thermophysical property parameters meet the measurement indicators, which include correlation indicators, root mean square error indicators and mean absolute error indicators; If yes, go to the next step; if no, return to the previous step.

6. The method for optimizing thermal parameters of existing building envelope structures according to claim 5, characterized in that: The specific process of measuring the predicted value of the thermophysical property parameter includes: The correlation index is obtained by measuring the linear relationship between the thermophysical parameter and the average value of the thermophysical parameter, and the ratio of the linear relationship between the thermophysical parameter and the predicted value of the thermophysical parameter. When the correlation index is close to 1, it means that there is a good linear relationship between the thermophysical parameter and the average value of the thermophysical parameter. When the correlation index is close to 0, it means that there is no linear relationship between the thermophysical parameter and the average value of the thermophysical parameter. When the correlation index is close to -1, it means that there is a negative linear relationship between the thermophysical parameter and the average value of the thermophysical parameter. By measuring the linear relationship between the thermophysical parameter and the predicted value of the thermophysical parameter, the root mean square error index is obtained. The smaller the root mean square error index is, the smaller the difference between the thermophysical parameter and the predicted value of the thermophysical parameter is, and the more accurate the corresponding predicted value of the thermophysical parameter is. By measuring the linear relationship between the thermophysical property parameters and the average value of the thermophysical property parameters, the mean absolute error index is obtained. The smaller the mean absolute error index is, the smaller the difference between the thermophysical property parameters and the average value of the thermophysical property parameters is.

7. The method for optimizing thermal parameters of existing building envelope structures according to claim 5 or 6, characterized in that: The calculation of the measurement index is specifically as follows: The correlation index is calculated using the following formula: ； In the formula, Represents the correlation index of existing buildings in the tth preset time period; , , They are the total number of preset exterior wall areas, preset roof areas and preset exterior window areas respectively; , , Respectively represent the predicted value of the heat transfer coefficient of the exterior wall, the predicted value of the heat transfer coefficient of the roof, and the predicted value of the heat transfer coefficient of the exterior window in the preset exterior wall area, the preset roof area, and the preset exterior window area in the tth preset time period; Indicates The external wall heat transfer coefficient of a preset external wall area in the tth preset time period; Indicates The roof heat transfer coefficient of a preset roof area in the tth preset time period; Indicates The heat transfer coefficient of the external window of a preset external window area in the tth preset time period; Indicates The average value of the external wall heat transfer coefficient of a preset external wall area in the tth preset time period; Indicates The average value of the roof heat transfer coefficient of a preset roof area in the tth preset time period; Indicates The average value of the heat transfer coefficient of the external windows of a preset external window area in the tth preset time period; The root mean square error metric is calculated using the following formula: ； In the formula, It represents the root mean square error index of the existing building in the tth preset time period; The mean absolute error metric is calculated using the following formula: ； In the formula, It represents the mean absolute error index of the existing building in the tth preset time period.

Images