Carbon reduction optimization method for BIPV curved roof gymnasium based on CNN and genetic algorithm

Abstract

The embodiment of the invention provides a carbon reduction optimization method for a BIPV curved roof gymnasium based on a CNN and a genetic algorithm. Relates to the field of building design and artificial intelligence combination. The method comprises the following steps: constructing a BIPV curved roof gymnasium model, converting a roof surface in the model into grids, extracting three-dimensional data from grid intersection points, converting the three-dimensional data into scatter data, and carrying out linear plane regression to obtain a form judgment plane; coding roof height information in the model into a gray level image, and inputting the gray level image into a trained CNN, so that the trained CNN outputs annual average carbon emission prediction intensity corresponding to the model; performing regression analysis on the relationship between the plane parameters in the judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; and according to a regression analysis result, combining a genetic algorithm to optimize the roof shape in the BIPV curved roof gymnasium model. By optimizing the shape of the roof of the BIPV curved roof gymnasium, carbon emission in the building operation period is reduced, and the purposes of energy conservation and environmental protection are achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of integration of architectural design and artificial intelligence, and in particular to a carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm. Background Art

[0002] BIPV curved roof gymnasium is a gymnasium that combines photovoltaic technology with a curved roof structure. Integrating photovoltaic modules on the roof can achieve solar power generation and reduce carbon emissions. Existing methods for reducing carbon emissions from BIPV curved roof gymnasiums focus on optimizing the layout of the BIPV array without considering optimizing the roof shape; moreover, existing research on the roof shape of gymnasiums with integrated BIPV mostly focuses on non-curved roofs, and there is no relevant research on the impact of curved roofs on carbon emissions. Therefore, it is of great significance to study the carbon reduction optimization method of BIPV roofs with free-form surface structures. Summary of the invention

[0003] The present invention discloses a carbon reduction optimization method and device for a BIPV curved roof gymnasium based on CNN and genetic algorithm, equipment, and storage medium.

[0004] According to the first aspect of the present disclosure, a carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm is provided. The method comprises:

[0005] Construct a BIPV curved roof gymnasium model, convert the roof surface in the BIPV curved roof gymnasium model into a grid, extract three-dimensional data from the grid intersection and convert it into scattered point data for linear plane regression to obtain the morphological judgment plane;

[0006] Encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model;

[0007] A regression analysis was performed on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN;

[0008] According to the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with genetic algorithm.

[0009] In some implementations of the first aspect, the plane parameters include:

[0010] The angle between the morphological judgment plane and the horizontal plane, the direction of the morphological judgment plane, and the average distance between the grid intersection and the morphological judgment plane.

[0011] In some implementations of the first aspect, based on the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm, including:

[0012] Create a population of various roof shapes and encode each roof shape in the population as an individual;

[0013] Based on the current individuals, a new roof shape is generated by using the crossover and mutation operations in the genetic algorithm, and the new roof shape is encoded into the corresponding new individual;

[0014] CNN is used to calculate the annual average carbon emission prediction intensity corresponding to the new individual, and a regression analysis is performed on the relationship between the plane parameters corresponding to the new individual and the annual average carbon emission prediction intensity. The fitness of the new individual is calculated based on the regression analysis results.

[0015] According to the fitness, some new individuals are selected as the fathers and mothers of the next generation for reproduction to generate a new population, and each roof shape in the new population is encoded as an individual;

[0016] Repeat the process of generating new roof shapes, calculating fitness, and generating new populations until all fitness values ​​in the current population reach the preset fitness threshold;

[0017] The highest fitness is selected from the fitness that reaches the preset fitness threshold, and the roof shape in the BIPV curved roof gymnasium model is optimized according to the individual corresponding to the highest fitness.

[0018] In some implementations of the first aspect, the CNN is trained by the following method:

[0019] Simulate the energy consumption and photovoltaic power generation of existing BIPV curved roof gymnasium models to obtain the annual average carbon emission calculation intensity corresponding to the existing BIPV curved roof gymnasium models;

[0020] The roof height information in each existing BIPV curved roof gymnasium model is encoded into a grayscale image and input into a pre-trained CNN, so that the pre-trained CNN outputs the predicted annual average carbon emission intensity corresponding to the existing BIPV curved roof gymnasium model;

[0021] According to the coefficient of determination and root mean square error, the difference between the annual average carbon emission calculation intensity and the annual average carbon emission prediction intensity of the same BIPV curved roof gymnasium model output by the pre-trained CNN is calculated;

[0022] Adjust the model parameters of the pre-trained CNN according to the gap value, and re-input the adjusted model parameters into the pre-trained CNN;

[0023] Repeatedly input grayscale images, calculate gap values, adjust model parameters, and re-input model parameters until each gap value reaches a preset threshold to obtain a trained CNN.

[0024] In some implementations of the first aspect, the annual average carbon emission calculation intensity includes thermal carbon emissions and electricity carbon emissions; wherein,

[0025] Thermal carbon emissions are calculated using the following formula:

[0026]

[0027] C H is thermal carbon emissions, Q H is the cumulative heat consumption value for one year, A is the total building area corresponding to the BIPV curved roof gymnasium model, η is the heating system efficiency of the coal-fired boiler as the heat source, and f h is the thermal carbon emission coefficient;

[0028] Electricity carbon emissions are calculated using the following formula:

[0029] C E =(E C +E L +E E -SEGI)×f e

[0030] C E is the carbon emissions from electricity, E C 、E L 、E E , SEGI and f e They are cooling energy consumption, lighting energy consumption, other electrical energy consumption of equipment in the BIPV curved roof gymnasium model, solar power generation intensity and electricity carbon emission coefficient.

[0031] In some implementations of the first aspect, the solar power generation intensity is calculated by the following formula:

[0032]

[0033] Where I represents the annual solar radiation on the surface of the photovoltaic cells in the photovoltaic system in the BIPV curved roof stadium model, K E is the conversion efficiency of the photovoltaic cell, K S is the loss efficiency of the photovoltaic system, A P is the net area of ​​PV panels in the PV system.

[0034] In some implementations of the first aspect, the method further includes:

[0035] The roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into the trained CNN, so that the trained CNN outputs the annual average carbon emission comprehensive intensity corresponding to the BIPV curved roof gymnasium model;

[0036] A regression analysis was conducted on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission comprehensive intensity output by the trained CNN, and the roof shape in the BIPV curved roof gymnasium model was optimized using a genetic algorithm.

[0037] The annual average carbon emission comprehensive intensity includes cooling carbon emission, heating carbon emission, lighting carbon emission, equipment carbon emission and carbon emission saved by BIPV power generation. According to the second aspect of the present disclosure, a BIPV curved roof gymnasium carbon reduction optimization device based on CNN and genetic algorithm is provided. The device includes:

[0038] A morphological judgment plane acquisition module is used to construct a BIPV curved roof gymnasium model, convert the roof surface in the BIPV curved roof gymnasium model into a grid, extract three-dimensional data from the grid intersection and convert it into scattered point data for linear plane regression to obtain a morphological judgment plane;

[0039] The module for obtaining the predicted annual average carbon emission intensity is used to encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model;

[0040] The regression analysis module is used to perform regression analysis on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN;

[0041] The roof shape optimization module is used to optimize the roof shape in the BIPV curved roof gymnasium model based on the regression analysis results combined with the genetic algorithm.

[0042] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method described above.

[0043] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method as described above.

[0044] In the present disclosure, by constructing a BIPV curved roof gymnasium model, the roof surface in the BIPV curved roof gymnasium model is converted into a grid, three-dimensional data is extracted from the grid intersection and converted into scattered data for linear plane regression to obtain a morphological judgment plane; the roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into a trained CNN so that the trained CNN outputs the annual average carbon emission prediction intensity corresponding to the BIPV curved roof gymnasium model; a regression analysis is performed on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; according to the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm. In this way, carbon emissions are reduced and the purpose of energy conservation and environmental protection is achieved.

[0045] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0047] Figure 1 A flow chart of a carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm provided by an embodiment of the present disclosure is shown;

[0048] Figure 2 A structural diagram of a carbon reduction optimization device for a BIPV curved roof gymnasium based on CNN and genetic algorithm provided by an embodiment of the present disclosure is shown;

[0049] Figure 3 A block diagram of an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0051] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0052] In response to the problems arising in the background technology, the embodiments of the present disclosure provide a carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm. By constructing a BIPV curved roof gymnasium model, the roof surface in the BIPV curved roof gymnasium model is converted into a grid, three-dimensional data is extracted from the grid intersection and converted into scattered data for linear plane regression to obtain a morphological judgment plane; the roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into a trained CNN so that the trained CNN outputs the annual average carbon emission prediction intensity corresponding to the BIPV curved roof gymnasium model; a regression analysis is performed on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; based on the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm. In this way, carbon emissions during building operation are reduced, and the purpose of energy conservation and environmental protection is achieved.

[0053] The carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm provided by the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings through specific embodiments.

[0054] Figure 1 A flowchart of a carbon reduction optimization method for a BIPV curved roof gymnasium based on CNN and genetic algorithm provided by an embodiment of the present disclosure is shown. The method 100 includes the following steps:

[0055] S110, constructing a BIPV curved roof gymnasium model, converting the roof surface in the BIPV curved roof gymnasium model into a grid, extracting three-dimensional data from the grid intersections and converting them into scattered point data for linear plane regression, and obtaining a morphological judgment plane.

[0056] In some embodiments, the roof structure of the BIPV curved roof gymnasium is modeled using Grasshopper, and the roof shape is controlled by moving along the z-axis using 25 evenly distributed control points with a moving step of 0.1 m. Considering factors such as the thickness of the roof structure, the actual height limit of the roof, the activity requirements in the gymnasium, and the design requirements of the roof curvature, the lowest point of the roof in the model is set to 18 meters, and the range of the highest point is set to 22-25 meters;

[0057] Furthermore, the roof in the BIPV curved roof gymnasium model is integrated with a photovoltaic system, through which solar power generation can be achieved.

[0058] In some embodiments, the roof surface in the BIPV curved roof gymnasium model is converted into a grid, and the intersection points of each grid constitute a point cloud set of the curved roof. Three-dimensional data is extracted from the point cloud set and converted into scattered data for linear plane regression to obtain a morphological judgment plane. The morphological judgment plane has geometric information of all subdivided areas on the curved roof, and these geometric information are represented by plane parameters in the morphological judgment plane.

[0059] S120, encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model.

[0060] In some embodiments, the CNN is trained by:

[0061] Simulate the energy consumption and photovoltaic power generation of existing BIPV curved roof gymnasium models to obtain the annual average carbon emission calculation intensity corresponding to the existing BIPV curved roof gymnasium models;

[0062] The roof height information in each existing BIPV curved roof gymnasium model is encoded into a grayscale image and input into a pre-trained CNN, so that the pre-trained CNN outputs the predicted annual average carbon emission intensity corresponding to the existing BIPV curved roof gymnasium model;

[0063] According to the coefficient of determination and root mean square error, the difference between the annual average carbon emission calculation intensity and the annual average carbon emission prediction intensity of the same BIPV curved roof gymnasium model output by the pre-trained CNN is calculated;

[0064] Adjust the model parameters of the pre-trained CNN according to the gap value, and re-input the adjusted model parameters into the pre-trained CNN;

[0065] Repeatedly input grayscale images, calculate gap values, adjust model parameters, and re-input model parameters until each gap value reaches a preset threshold to obtain a trained CNN.

[0066] In some embodiments, the annual average carbon emission calculation intensity CEI includes thermal carbon emissions and electricity carbon emissions;

[0067] Thermal carbon emissions are calculated using the following formula:

[0068]

[0069] C H is thermal carbon emissions, QH is the cumulative heat consumption value for one year, A is the total building area corresponding to the BIPV curved roof gymnasium model, η is the heating system efficiency of the coal-fired boiler as the heat source, and f h is the thermal carbon emission coefficient;

[0070] Electricity carbon emissions are calculated using the following formula:

[0071] C E =(E C +E L +E E -SEGI)×f e

[0072] C E is the carbon emissions from electricity, E C 、E L 、E E , SEGI and f e They are cooling energy consumption, lighting energy consumption, other electrical energy consumption of equipment in the BIPV curved roof gymnasium model, solar power generation intensity and electricity carbon emission coefficient.

[0073] In some embodiments, the solar power generation intensity is calculated by the following formula:

[0074]

[0075] Where I represents the annual solar radiation on the surface of the photovoltaic cells in the photovoltaic system in the BIPV curved roof stadium model, K E is the conversion efficiency of the photovoltaic cell, K S is the loss efficiency of the photovoltaic system, A P is the net area of ​​PV panels in the PV system.

[0076] In some embodiments, the method 100 further includes:

[0077] The roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into the trained CNN, so that the trained CNN outputs the annual average carbon emission comprehensive intensity corresponding to the BIPV curved roof gymnasium model;

[0078] A regression analysis was conducted on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission comprehensive intensity output by the trained CNN, and the roof shape in the BIPV curved roof gymnasium model was optimized using a genetic algorithm.

[0079] The annual average comprehensive carbon emission intensity includes carbon emissions from cooling, heating, lighting, equipment and carbon emissions saved by BIPV power generation.

[0080] In some embodiments, the heating carbon emissions E H Calculated by the following formula:

[0081]

[0082] Among them, q1 and q2 are the calorific value of standard coal and comprehensive coal consumption for power generation respectively.

[0083] In some embodiments, the coefficient of determination R 2 The calculation formula is as follows:

[0084]

[0085] Among them, y i Y is the annual average carbon emission intensity corresponding to the i-th existing BIPV curved roof gymnasium model, i is the predicted annual average carbon emission intensity corresponding to the i-th existing BIPV curved roof gymnasium model, y′ i is the average value of the calculated annual carbon emission intensity of the existing BIPV curved roof gymnasium models, and n is the number of existing BIPV curved roof gymnasium models;

[0086] The calculation formula of root mean square error RMSE is as follows:

[0087]

[0088] In some embodiments, the method 100 further includes:

[0089] The distances of each control point in the BIPV curved roof gymnasium model moved along the z-axis are input into the ANN model so that the ANN model can output the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model;

[0090] When the number of existing BIPV curved roof gymnasium models is the same, the determination coefficients and root mean square errors of the CNN and ANN models are calculated respectively. By comparing the determination coefficients and root mean square errors of the CNN and ANN models, it can be found that when the number of existing BIPV curved roof gymnasium models is less than 3000, the annual average carbon emission prediction intensity output by CNN is more accurate. Therefore, CNN is used to predict the annual average carbon emission intensity of the BIPV curved roof gymnasium model.

[0091] S130, performing regression analysis on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN.

[0092] In some embodiments, the plane parameters include:

[0093] The angle between the morphological judgment plane and the horizontal plane (i.e., the inclination angle S), the direction of the morphological judgment plane (i.e., the slope aspect SA), and the average distance between the grid intersection and the morphological judgment plane (i.e., the fluctuation distance V).

[0094] In some embodiments, for BIPV curved roofs with convex, concave and hyperbolic shapes, the annual average carbon emission prediction intensity output by the trained CNN decreases with the increase of the inclination angle S and the fluctuation distance V, and first increases and then decreases with the increase of the slope SA.

[0095] S140, based on the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm.

[0096] In some embodiments, based on the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm, including:

[0097] Create a population of various roof shapes and encode each roof shape in the population as an individual;

[0098] Based on the current individuals, a new roof shape is generated by using the crossover and mutation operations in the genetic algorithm, and the new roof shape is encoded into the corresponding new individual;

[0099] CNN is used to calculate the annual average carbon emission prediction intensity corresponding to the new individual, and a regression analysis is performed on the relationship between the plane parameters corresponding to the new individual and the annual average carbon emission prediction intensity. The fitness of the new individual is calculated based on the regression analysis results.

[0100] According to the fitness, some new individuals are selected as the fathers and mothers of the next generation for reproduction to generate a new population, and each roof shape in the new population is encoded as an individual;

[0101] Repeat the process of generating new roof shapes, calculating fitness, and generating new populations until all fitness values ​​in the current population reach the preset fitness threshold;

[0102] The highest fitness is selected from the fitness that reaches the preset fitness threshold, and the roof shape in the BIPV curved roof gymnasium model is optimized according to the individual corresponding to the highest fitness.

[0103] In some embodiments, for BIPV curved roofs with convex, concave and hyperbolic shapes, the range of the inclination angle S of the convex BIPV curved roof that meets the preset requirements of the annual average carbon emission intensity is 0.35-1.53°, the range of the slope SA is 141.73-225.25°, and the range of the fluctuation distance V is 0.15-0.33m; the range of the inclination angle S of the concave BIPV curved roof that meets the preset requirements of the annual average carbon emission intensity is 0.17-0.33°, the range of the slope SA is 148.79-209.94°, and the range of the fluctuation distance V is 0.17-0.26m; the range of the inclination angle S of the hyperbolic BIPV curved roof that meets the preset requirements of the annual average carbon emission intensity is 0.14-1.14°, the range of the slope SA is 137.76-313.67°, and the range of the fluctuation distance V is 0.11-0.22m.

[0104] In some embodiments, appropriately improving the loss efficiency of the photovoltaic system can also reduce the annual average carbon emission intensity.

[0105] According to the embodiments of the present disclosure, by constructing a BIPV curved roof gymnasium model, the roof surface in the BIPV curved roof gymnasium model is converted into a grid, three-dimensional data is extracted from the grid intersection and converted into scattered data for linear plane regression to obtain a morphological judgment plane; the roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into a trained CNN so that the trained CNN outputs the annual average carbon emission prediction intensity corresponding to the BIPV curved roof gymnasium model; a regression analysis is performed on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; according to the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with a genetic algorithm. In this way, carbon emissions are reduced and the purpose of energy conservation and environmental protection is achieved.

[0106] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0107] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0108] Figure 2The structure diagram of a BIPV curved roof gymnasium carbon reduction optimization device based on CNN and genetic algorithm provided by an embodiment of the present disclosure is shown. The device 200 includes:

[0109] The morphology judgment plane acquisition module 210 is used to construct a BIPV curved roof gymnasium model, convert the roof surface in the BIPV curved roof gymnasium model into a grid, extract three-dimensional data from the grid intersection and convert it into scattered point data for linear plane regression to obtain the morphology judgment plane.

[0110] The annual average carbon emission predicted intensity acquisition module 220 is used to encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the annual average carbon emission predicted intensity corresponding to the BIPV curved roof gymnasium model.

[0111] In some embodiments, the annual average carbon emission forecast intensity acquisition module 220 is specifically used to:

[0112] CNN is trained by:

[0113] Conduct energy simulation on existing BIPV curved roof gymnasium models to obtain the annual average carbon emission calculation intensity corresponding to the existing BIPV curved roof gymnasium models;

[0114] The roof height information in each existing BIPV curved roof gymnasium model is encoded into a grayscale image and input into a pre-trained CNN, so that the pre-trained CNN outputs the predicted annual average carbon emission intensity corresponding to the existing BIPV curved roof gymnasium model;

[0115] According to the coefficient of determination and root mean square error, the difference between the annual average carbon emission calculation intensity and the annual average carbon emission prediction intensity of the same BIPV curved roof gymnasium model output by the pre-trained CNN is calculated;

[0116] Adjust the model parameters of the pre-trained CNN according to the gap value, and re-input the adjusted model parameters into the pre-trained CNN;

[0117] Repeatedly input grayscale images, calculate gap values, adjust model parameters, and re-input model parameters until each gap value reaches a preset threshold to obtain a trained CNN.

[0118] In some embodiments, the annual average carbon emission forecast intensity acquisition module 220 is further used to:

[0119] The annual average carbon emission calculation intensity includes thermal carbon emissions and electricity carbon emissions;

[0120] Thermal carbon emissions are calculated using the following formula:

[0121]

[0122] C H is thermal carbon emissions, Q H is the cumulative heat consumption value for one year, A is the total building area corresponding to the BIPV curved roof gymnasium model, η is the heating system efficiency of the coal-fired boiler as the heat source, and f h is the thermal carbon emission coefficient;

[0123] Electricity carbon emissions are calculated using the following formula:

[0124] C E =(E C +E L +E E -SEGI)×f e

[0125] C E is the carbon emissions from electricity, E C 、E L 、E E , SEGI and f e They are cooling energy consumption, lighting energy consumption, other electrical energy consumption of equipment in the BIPV curved roof gymnasium model, solar power generation intensity and electricity carbon emission coefficient.

[0126] In some embodiments, the annual average carbon emission forecast intensity acquisition module 220 is further used to:

[0127] The solar power generation intensity is calculated by the following formula:

[0128]

[0129] Where I represents the annual solar radiation on the surface of the photovoltaic cells in the photovoltaic system in the BIPV curved roof stadium model, K E is the conversion efficiency of the photovoltaic cell, K S is the loss efficiency of the photovoltaic system, A P is the net area of ​​PV panels in the PV system.

[0130] In some embodiments, the apparatus 200 is further configured to:

[0131] The roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into the trained CNN, so that the trained CNN outputs the annual average carbon emission comprehensive intensity corresponding to the BIPV curved roof gymnasium model;

[0132] A regression analysis was conducted on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission comprehensive intensity output by the trained CNN, and the roof shape in the BIPV curved roof gymnasium model was optimized using a genetic algorithm.

[0133] The annual average comprehensive carbon emission intensity includes carbon emissions from cooling, heating, lighting energy consumption, equipment, and carbon emissions that can be saved from BIPV power generation.

[0134] The regression analysis module 230 is used to perform regression analysis on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN.

[0135] In some embodiments, the regression analysis module 230 is specifically used to:

[0136] Plane parameters, including:

[0137] The angle between the morphological judgment plane and the horizontal plane, the direction of the morphological judgment plane, and the average distance between the grid intersection and the morphological judgment plane.

[0138] The roof shape optimization module 240 is used to optimize the roof shape in the BIPV curved roof gymnasium model based on the regression analysis results in combination with the genetic algorithm.

[0139] In some embodiments, the roof shape optimization module 240 is specifically configured to:

[0140] According to the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized by combining genetic algorithm, including:

[0141] Create a population of various roof shapes and encode each roof shape in the population as an individual;

[0142] Based on the current individuals, a new roof shape is generated by using the crossover and mutation operations in the genetic algorithm, and the new roof shape is encoded into the corresponding new individual;

[0143] CNN is used to calculate the annual average carbon emission prediction intensity corresponding to the new individual, and a regression analysis is performed on the relationship between the plane parameters corresponding to the new individual and the annual average carbon emission prediction intensity. The fitness of the new individual is calculated based on the regression analysis results.

[0144] According to the fitness, some new individuals are selected as the fathers and mothers of the next generation for reproduction to generate a new population, and each roof shape in the new population is encoded as an individual;

[0145] Repeat the process of generating new roof shapes, calculating fitness, and generating new populations until all fitness values ​​in the current population reach the preset fitness threshold;

[0146] The highest fitness is selected from the fitness that reaches the preset fitness threshold, and the roof shape in the BIPV curved roof gymnasium model is optimized according to the individual corresponding to the highest fitness.

[0147] Understandably, Figure 2 Each module / unit in the illustrated device 200 has the function of implementing each step in the method 100 provided in the embodiment of the present disclosure and can achieve its corresponding technical effect. For the sake of brevity, they will not be described in detail here.

[0148] Figure 3 A block diagram of an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. The electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0149] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0150] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0151] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0152] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in the embodiment of the present disclosure. For the sake of concise description, they are not repeated here.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0157] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0158] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0159] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0160] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A carbon reduction optimization method for BIPV curved roof gymnasium based on CNN and genetic algorithm, characterized in that: include: Construct a BIPV curved roof gymnasium model, convert the roof surface in the BIPV curved roof gymnasium model into a grid, extract three-dimensional data from the grid intersection and convert it into scattered point data for linear plane regression to obtain the morphological judgment plane; Encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model; A regression analysis was performed on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; According to the regression analysis results, the roof shape in the BIPV curved roof gymnasium model is optimized in combination with the genetic algorithm.

2. The method according to claim 1, characterized in that The plane parameters include: The angle between the morphological judgment plane and the horizontal plane, the direction of the morphological judgment plane, and the average distance between the grid intersection and the morphological judgment plane.

3. The method according to claim 1, characterized in that The method of optimizing the roof shape in the BIPV curved roof gymnasium model based on the regression analysis results and combining the genetic algorithm includes: Create a population of various roof shapes and encode each roof shape in the population as an individual; Based on the current individuals, a new roof shape is generated by using the crossover and mutation operations in the genetic algorithm, and the new roof shape is encoded into the corresponding new individual; CNN is used to calculate the predicted annual average carbon emission intensity corresponding to the new individuals, and regression analysis is performed on the relationship between the plane parameters corresponding to the new individuals and the predicted annual average carbon emission intensity. The fitness of the new individuals is calculated based on the regression analysis results. According to the fitness, some new individuals are selected as the fathers and mothers of the next generation for reproduction to generate a new population, and each roof shape in the new population is encoded as an individual; Repeat the process of generating new roof shapes, calculating fitness, and generating new populations until all fitness values ​​in the current population reach the preset fitness threshold; The highest fitness is selected from the fitness that reaches the preset fitness threshold, and the roof shape in the BIPV curved roof gymnasium model is optimized according to the individual corresponding to the highest fitness.

4. The method according to claim 1, characterized in that: The CNN is trained by: Simulate the energy consumption and photovoltaic power generation of existing BIPV curved roof gymnasium models to obtain the annual average carbon emission calculation intensity corresponding to the existing BIPV curved roof gymnasium models; The roof height information in each existing BIPV curved roof gymnasium model is encoded into a grayscale image and input into a pre-trained CNN, so that the pre-trained CNN outputs the predicted annual average carbon emission intensity corresponding to the existing BIPV curved roof gymnasium model; According to the coefficient of determination and root mean square error, the difference between the annual average carbon emission calculation intensity and the annual average carbon emission prediction intensity of the same BIPV curved roof gymnasium model output by the pre-trained CNN is calculated; Adjust the model parameters of the pre-trained CNN according to the gap value, and re-input the adjusted model parameters into the pre-trained CNN; Repeatedly input grayscale images, calculate gap values, adjust model parameters, and re-input model parameters until each gap value reaches a preset threshold to obtain a trained CNN.

5. The method according to claim 4, characterized in that The annual average carbon emission calculation intensity includes thermal carbon emissions and electricity carbon emissions; The thermal carbon emissions are calculated using the following formula: C H is thermal carbon emissions, Q H is the cumulative heat consumption value for one year, A is the total building area corresponding to the BIPV curved roof gymnasium model, η is the heating system efficiency of the coal-fired boiler as the heat source, and f h is the thermal carbon emission coefficient; The electricity carbon emissions are calculated using the following formula: C E =(E C +E L +E E -SEGI)×f e C E is the carbon emissions from electricity, E C 、E L 、E E , SEGI and f e They are cooling energy consumption, lighting energy consumption, other electrical energy consumption of equipment in the BIPV curved roof gymnasium model, solar power generation intensity and electricity carbon emission coefficient.

6. The method according to claim 5, characterized in that The solar power generation intensity is calculated by the following formula: Where I represents the annual solar radiation on the surface of the photovoltaic cells in the photovoltaic system in the BIPV curved roof stadium model, K E is the conversion efficiency of the photovoltaic cell, K S is the loss efficiency of the photovoltaic system, A P is the net area of ​​PV panels in the PV system.

7. The method according to claim 5, characterized in that The method further comprises: The roof height information in the BIPV curved roof gymnasium model is encoded into a grayscale image and input into the trained CNN, so that the trained CNN outputs the annual average carbon emission comprehensive intensity corresponding to the BIPV curved roof gymnasium model; A regression analysis was conducted on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission comprehensive intensity output by the trained CNN, and the roof shape in the BIPV curved roof gymnasium model was optimized using a genetic algorithm. The annual average comprehensive carbon emission intensity includes carbon emissions from cooling, heating, lighting, equipment and carbon emissions saved by BIPV power generation.

8. A device for implementing the method of claim 1, characterized in that: include: A morphological judgment plane acquisition module is used to construct a BIPV curved roof gymnasium model, convert the roof surface in the BIPV curved roof gymnasium model into a grid, extract three-dimensional data from the grid intersection and convert it into scattered point data for linear plane regression to obtain a morphological judgment plane; The module for obtaining the predicted annual average carbon emission intensity is used to encode the roof height information in the BIPV curved roof gymnasium model into a grayscale image and input it into the trained CNN, so that the trained CNN outputs the predicted annual average carbon emission intensity corresponding to the BIPV curved roof gymnasium model; The regression analysis module is used to perform regression analysis on the relationship between the plane parameters in the morphological judgment plane and the annual average carbon emission prediction intensity output by the trained CNN; The roof shape optimization module is used to optimize the roof shape in the BIPV curved roof gymnasium model based on the regression analysis results combined with the genetic algorithm.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images