Opening and closing roof sports building photo-thermal balance optimization method based on generative adversarial network and genetic algorithm

Abstract

The invention relates to the technical field of sports building photo-thermal optimization, in particular to a retractable roof sports building photo-thermal environment balance optimization method based on a generative adversarial network and a genetic algorithm. The method comprises the following steps: obtaining form data of the retractable roof; performing parametric modeling on the form data of the retractable roof to generate a two-dimensional grayscale image of the retractable roof; performing fluid dynamics and photo-thermal environment numerical simulation on the form data of the retractable roof to obtain environment simulation data of the retractable roof; carrying out image pairing on the two-dimensional grayscale image of the retractable roof and the simulation data of the lower space environment of the retractable roof to obtain an input-output image pair; and performing wind speed distribution prediction on the input-output image pair by using a generative adversarial network, and generating a wind speed distribution prediction value of the retractable roof. According to the method, the generative adversarial network and the genetic algorithm are combined, intelligent optimization of photo-thermal balance of the retractable roof sports building is achieved, and the defects of flexibility, optimization precision and calculation efficiency of a traditional method are overcome.

Description

Technical Field

[0001] The present invention relates to the field of photothermal optimization technology, and in particular to a photothermal balance optimization method for a retractable roof sports building based on a generative adversarial network and a genetic algorithm. Background Art

[0002] Retractable roofs, as adaptive building structures, regulate indoor temperature and air circulation by changing the degree of roof opening and closing, thereby achieving a building's solar and thermal balance under varying climatic conditions. Traditional roof control strategies rely on fixed empirical rules and physical models. However, with the diversification of building environments and climatic conditions, these methods face challenges such as insufficient flexibility and precision errors. To improve the intelligence and adaptability of control strategies, researchers have begun exploring intelligent control of retractable roofs based on advanced optimization methods such as generative adversarial networks (GANs) and genetic algorithms (GAs). GANs effectively simulate complex environmental changes by training a generative model against a discriminative model. Genetic algorithms, as optimization algorithms that mimic natural selection, can efficiently find optimal solutions in large search spaces. However, existing optimization methods generally lack tools for intuitively determining wind, light, and thermal comfort environments, resulting in low complexity and accuracy in optimizing the solar and thermal balance of retractable roof sports buildings. Summary of the Invention

[0003] Based on this, it is necessary to provide a light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a method for optimizing the light and heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm is provided. The method comprises the following steps:

[0005] Step S1: Acquire the retractable roof morphology data; perform parametric modeling on the retractable roof morphology data to generate a two-dimensional grayscale image of the retractable roof; perform fluid dynamics and light and heat environment simulation on the sports building space covered by the retractable roof to obtain wind, light and heat environment simulation data of the space covered by the retractable roof;

[0006] Step S2: Pairing the two-dimensional grayscale image of the retractable roof with the wind, solar, and thermal environment simulation data to obtain an input-output image pair; using a generative adversarial network to predict the wind speed distribution of the input-output image pair to generate a predicted value of the spatial wind speed distribution of the retractable roof; and constructing a wind-solar-thermal environment gene library based on the predicted value of the spatial wind speed distribution and the solar thermal environment simulation data.

[0007] Step S3: Acquire environmental demand data for large sports spaces; set wind, solar, and thermal environment balance targets for the retractable roof space based on the environmental demand data for the large sports space, and obtain wind, solar, and thermal balance target parameters; iteratively optimize the wind, solar, and thermal balance target parameters using a genetic algorithm based on the wind-solar-thermal environment gene library to generate a Pareto optimal solution for the retractable roof morphological parameters under typical meteorological conditions; perform a regression analysis on the opening ratio of the roof morphological parameters based on the Pareto optimal solution and the corresponding indoor environment to generate a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve;

[0008] Step S4: Conduct climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort light environment impact curve to generate sensitivity analysis results; dynamically adjust the opening ratio of the retractable roof based on the sensitivity analysis results to perform wind, light and heat balance optimization and control operations for the retractable roof sports building.

[0009] The present invention performs parameterized modeling on the retractable roof morphology data and simulates the fluid dynamics and thermal environment of the large space below it. This allows accurate analysis of the ventilation, lighting, and thermal environment of the building space below the retractable roof. By combining wind speed distribution prediction with thermal environment simulation data, the wind-solar-thermal balance is optimized, the comfort and energy efficiency of the sports space below the roof are improved, and the comfort level of the building's internal environment is ensured. By using a generative adversarial network to predict the wind speed distribution of input-output image pairs, the impact of changes in the roof opening ratio on the wind speed distribution can be efficiently and accurately simulated, providing a scientific basis for the wind speed regulation of the roof and further optimizing the natural ventilation effect of the building. By constructing a wind-solar-thermal environment gene library, the coordinated optimization of wind speed, lighting, and thermal environment is achieved. The genetic algorithm iteratively optimizes the wind-solar-thermal balance target parameters, allowing the wind-solar-thermal regulation of the retractable roof to be precisely adjusted according to different climate zones, building usage requirements, and environmental changes, ensuring the maximization of the building's wind-solar-thermal comfort and energy efficiency. Based on the Pareto optimal solution, a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve is generated, providing designers with a detailed relationship between the roof opening ratio and ventilation, thermal comfort, and light environment, helping them make more scientific design decisions and optimize the ventilation, lighting, and thermal comfort of the retractable roof. Through climate zone sensitivity analysis, the morphological design of the retractable roof can be adjusted according to the characteristics of different climate zones, ensuring that the roof can be personalized under various climatic conditions to achieve the best wind, light, and heat balance effect. This targeted design not only improves the adaptability of the roof, but also provides a guarantee for the energy-saving effect of the building. According to the results of the sensitivity analysis, the opening ratio of the retractable roof is dynamically adjusted, so that the retractable roof can flexibly adjust the opening ratio under different meteorological conditions, optimize the balance of wind, light, and heat environment, and further improve the energy efficiency and comfort of the building. Therefore, the present invention realizes the intelligent optimization of the light and heat balance of the retractable roof sports building by combining generative adversarial networks and genetic algorithms, solving the shortcomings of traditional methods in flexibility, optimization accuracy, and computational efficiency.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Acquire the shape data of the retractable roof;

[0012] Step S12: performing parametric modeling on the retractable roof morphological data, defining the dynamic adjustment range of the roof opening and closing direction and the opening ratio, and obtaining a retractable roof geometric model;

[0013] Step S13: converting the retractable roof geometric model into a grayscale image to generate a two-dimensional grayscale image of the retractable roof;

[0014] Step S14: extracting the roof shape of the retractable roof from the two-dimensional grayscale image, and using simulation software to perform CFD simulation and light and heat environment simulation on the building space below the retractable roof, calculating the indoor and outdoor wind speed distribution and thermal comfort index, and obtaining indoor and outdoor wind speed distribution data and thermal comfort index data;

[0015] Step S15: performing daylight analysis on the building space below the retractable roof to generate daylight coefficient distribution data; converting the indoor and outdoor wind speed distribution data, daylight coefficient distribution data, and thermal comfort index data into graphs to generate a wind speed distribution map, a daylight coefficient distribution map, and a thermal comfort index heat map;

[0016] Step S16: Integrate the wind speed distribution map, the daylight coefficient distribution map, and the thermal comfort index thermodynamic map into wind, light, and thermal environment simulation data of the space covered by the retractable roof.

[0017] By accurately acquiring and parametrically modeling the retractable roof's morphological data, this method clearly defines the roof's opening and closing direction and the dynamic adjustment range of the opening ratio, ensuring the model's high flexibility and adjustability, and providing accurate baseline data for subsequent simulation and optimization. By constructing a geometric model of the retractable roof, the roof's opening ratio can be dynamically adjusted to meet varying climate, environmental, and functional requirements, ensuring the roof optimizes ventilation and thermal conditions under various conditions, further improving building comfort and energy efficiency. Through CFD simulation and thermal environment simulation, indoor and outdoor wind speed distribution and thermal comfort indicators can be accurately calculated, providing architects with detailed environmental data to help adjust the retractable roof structure, optimize ventilation, lighting, and thermal comfort, and enhance the building's living and user experience. By generating a daylight coefficient through daylight analysis, the lighting performance of the retractable roof can be effectively evaluated, ensuring that the building fully utilizes natural light and reducing energy consumption from artificial lighting. Furthermore, the analysis of the daylight coefficient helps to more accurately optimize the roof's opening ratio, improving the building's energy efficiency. The chart conversion steps generate wind speed distribution maps and thermal comfort index heat maps, helping designers intuitively understand the ventilation and thermal comfort of retractable roofs under different conditions, facilitating accurate design decisions. These heat maps and distribution maps also provide a scientific basis for subsequent building maintenance and adjustments.

[0018] Preferably, the daylight analysis of the building space below the retractable roof includes:

[0019] Extract the daylighting area of ​​the building space under the retractable roof to obtain an image of the daylighting area of ​​the space under the retractable roof; calculate the solar altitude angle and azimuth angle of the daylighting area image of the space under the retractable roof to obtain the solar altitude angle and solar azimuth angle;

[0020] Based on the solar altitude angle and solar azimuth angle, light propagation simulation is performed on the daylighting area of ​​the retractable roof to generate sunlight propagation path simulation data. The illumination intensity of each pixel in the daylighting area image of the space below the retractable roof is calculated based on the sunlight propagation path simulation data to obtain a local sunlight intensity map.

[0021] The local sunlight intensity map is used to calculate the actual illumination area ratio of the lighting area image under the retractable roof to obtain the daylighting coefficient.

[0022] By extracting images of the daylighting areas of retractable roofs, the present invention can accurately identify which areas have good daylighting conditions under sunlight, thereby optimizing the design of the roof opening and closing, and improving the efficiency of natural lighting. By calculating the sun's altitude and azimuth, it is possible to dynamically simulate the changes in the daylighting area according to different seasons and times, ensuring that the daylighting analysis takes into account the changes in the sun's angle and generating more accurate daylighting simulation data. Based on the calculation of the sun's angle, the simulation of the light propagation path can provide a comprehensive understanding of how sunlight propagates within the roof opening area, helping designers to better control the direction and intensity of daylighting. Based on the sunlight propagation path simulation data, the illumination intensity of each pixel is calculated to obtain a local sunlight intensity map, which can comprehensively evaluate the daylighting conditions in different areas and provide accurate data support for space utilization and lighting design. The local sunlight intensity map is used to calculate the actual illumination area ratio and generate the daylighting coefficient. This data can quantify the daylighting efficiency and help designers adjust the design of the roof opening to maximize the natural lighting effect, improve the indoor lighting quality, and reduce energy consumption.

[0023] Preferably, step S2 includes the following steps:

[0024] Step S21: Pairing the two-dimensional grayscale image of the retractable roof and the wind speed distribution map of the space below the roof to obtain an input-output image pair; dividing the input-output image pair into a data set to generate a model training set, a model test set, and a model validation set;

[0025] Step S22: Constructing a Pix2Pix network framework; inputting the model training set, model test set, and model validation set into the Pix2Pix network framework for training, testing, and validation to obtain a Pix2Pix algorithm model; inputting a preset two-dimensional image of the retractable roof design into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, thereby generating a predicted indoor wind speed map of the space under the retractable roof;

[0026] Step S23: performing a numerical matrix conversion on the indoor predicted wind speed map of the space below the retractable roof to obtain a predicted value of the spatial wind speed distribution of the retractable roof, and extracting the average wind speed value of the key area of ​​the sports building based on the predicted value of the spatial wind speed distribution of the retractable roof to obtain the average wind speed value of the key area;

[0027] Step S24: Parameter association is performed on the opening ratio of the retractable roof according to the average wind speed value in the key area, and a gene library is constructed using the associated parameters and the light-heat environment simulation data to obtain a wind-light-heat environment gene library.

[0028] By pairing the two-dimensional grayscale image of the retractable roof with the wind speed distribution map, the present invention can ensure that the input and output data of the wind speed prediction match and generate accurate training data. Further, by dividing the data set, the balance of training, testing and validation sets is ensured, which helps to improve the reliability and accuracy of model training and provide strong data support for subsequent predictions. By constructing the Pix2Pix network framework and combining the image data of the retractable roof with the wind speed distribution map, accurate wind speed prediction can be achieved. The Pix2Pix network uses generative adversarial network (GAN) technology to generate high-quality wind speed prediction results by learning the relationship between the input image and the target wind speed map, ensuring the accuracy and usability of the prediction map. The prediction results are converted into a numerical matrix, and the average wind speed value of the key area is extracted. By converting the wind speed distribution map into a numerical matrix, the wind speed data of the key areas of the sports building can be obtained more accurately, helping to optimize the ventilation effect of the retractable roof and providing a data basis for the subsequent wind, light and heat balance optimization. By parameter-associating the average wind speed value of the key area with the opening ratio, dynamic optimization and adjustment of the roof structure can be achieved. This process establishes a wind-light-heat environment gene library by utilizing the correlation between wind speed and light-heat environment data, providing architectural designers with an effective tool to ensure that buildings can optimize the balance of ventilation and light-heat environment under different climatic conditions.

[0029] Preferably, step S22 includes:

[0030] Build a Pix2Pix network framework, which includes a generator and a discriminator;

[0031] Set the training parameters for the Pix2Pix network framework and generate training parameter setting values, where the training parameter settings include learning rate settings, number of convolutional layers settings, epoch settings, and optimizer settings;

[0032] The model training set is input into the Pix2Pix network framework to predict wind speed through the generator in the Pix2Pix network framework, generating an initial predicted wind speed map for retractable roofs. The model test set is then used to compare the initial predicted wind speed map for retractable roofs with the real result image through the discriminator in the Pix2Pix network framework.

[0033] The structural similarity and root mean square error of the initial retractable roof wind speed prediction map are calculated to obtain the accuracy of the wind speed prediction map;

[0034] The wind speed prediction map accuracy was tested on the model validation set to obtain the Pix2Pix algorithm model;

[0035] The preset two-dimensional image of the retractable roof design is input into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, and a predicted indoor wind speed map of the space under the retractable roof is generated.

[0036] The present invention uses the generator in the Pix2Pix network framework to predict wind speeds and combines it with a discriminator to perform preliminary image comparison, thereby generating an accurate wind speed prediction map. This method can not only handle complex wind speed prediction tasks, but also perform efficient predictions under multiple retractable roof states. By setting training parameters (such as learning rate, number of convolutional layers, epochs, and optimizer), parameter optimization during the model training process is ensured, thereby improving the learning effect and accuracy of the network model, reducing the risk of overfitting, and enhancing the model's generalization ability. By calculating the structural similarity (SSIM) and root mean square error (RMSE) of the initial prediction result map, the difference between the predicted wind speed map and the actual result can be accurately assessed, thereby providing a basis for further optimization of the model. This accuracy assessment method ensures the high quality of the prediction results and further improves the reliability of building wind environment analysis. By adjusting the training parameters to optimize the prediction accuracy and further optimizing the wind speed prediction map through convergence checks, it can be ensured that the final retractable roof wind speed prediction map has high accuracy and stability, which can provide more accurate wind environment data for architectural design. The use of the discriminator ensures that the difference between the generated wind speed prediction map and the real wind speed map is minimized, thereby improving the realism of the generated image and enabling the model to better imitate the actual wind speed distribution map, making it suitable for complex building wind environment analysis.

[0037] Preferably, step S3 includes the following steps:

[0038] Step S31: Acquire the environmental demand data of the large sports space; set the wind-solar-heat balance target for the retractable roof space according to the environmental demand data of the large sports space, and obtain the wind-solar-heat balance target parameters;

[0039] Step S32: performing a diversity assessment on the wind-solar heat balance target parameters using the NSGA-III algorithm, and dynamically adjusting the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters;

[0040] Step S33: Based on the wind-solar-thermal environment gene library, the wind-solar-thermal balance target parameters are iteratively optimized using the NSGA-III algorithm, and extreme solutions are eliminated to generate a Pareto optimal solution.

[0041] Step S34: Based on the opening ratio of the roof morphological parameter change of the Pareto optimal solution, a multivariate linear regression equation is established for different opening ratios of the opening and closing roof and the corresponding indoor environment performance, and the roof opening and closing ratio-ventilation impact curve, the roof opening and closing ratio-natural lighting impact curve, and the roof opening and closing ratio-thermal comfort impact curve are generated respectively, and are unified into a roof opening and closing ratio-ventilation thermal comfort and light environment impact curve.

[0042] By utilizing a wind-solar-thermal environmental gene library, this invention can set wind-solar-thermal balance targets based on the predicted wind speed distribution under the retractable roof, generating a set of wind-solar-thermal balance target parameters for the roof design. This step provides a scientific theoretical basis for subsequent optimization, ensuring that the design meets comfort and energy efficiency requirements under different environmental conditions. The NSGA-III algorithm evaluates the diversity of the wind-solar-thermal balance target parameters and dynamically adjusts them based on the evaluation results. This approach, by considering diversity and feasibility, allows flexible adjustment of design parameters based on actual environmental requirements, ensuring greater adaptability and stability in design optimization. By iteratively optimizing the wind-solar-thermal balance target parameters and eliminating extreme solutions, the feasibility and stability of the optimization process are ensured. This process, utilizing intelligent algorithms (such as NSGA-III), not only optimizes the wind-solar-thermal balance of the roof but also eliminates unreasonable extreme solutions, ensuring that the final design has optimal performance indicators. Based on Pareto optimal solutions, a multivariate linear regression equation is established for different opening ratios of the retractable roof and the corresponding indoor environmental performance, generating impact curves between the roof opening ratio and ventilation, natural lighting, and thermal comfort. This process clearly demonstrates the relationship between design factors and actual effects, providing a precise theoretical basis for subsequent decision-making. By integrating these impact curves, a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve was generated, providing a comprehensive evaluation tool for actual building design.

[0043] Preferably, step S31 includes:

[0044] Obtain data on the environmental requirements of large sports spaces;

[0045] Optimization objectives are defined based on the environmental demand data of large sports spaces, including maximizing the daylight factor, maximizing the natural ventilation rate, and minimizing the thermal comfort index;

[0046] Decision variable constraints are set for maximizing the daylight coefficient, maximizing the natural ventilation speed, and minimizing the thermal comfort index, and limiting the spatial three-dimensional coefficient of the opening ratio;

[0047] Based on the optimization objectives and decision variables, the predicted values ​​of wind speed distribution of retractable roof are combined to obtain the target parameters of wind-solar heat balance.

[0048] The present invention can ensure that the roof design takes into account indoor lighting, ventilation effects and comfort by setting the optimization goals of maximizing the daylight coefficient, maximizing the natural ventilation speed and minimizing the thermal comfort index. This comprehensive optimization enables the building to achieve the best balance in energy consumption, living comfort and environmental benefits, and is particularly suitable for green buildings and energy-saving designs. By constraining decision variables (such as the spatial three-dimensional coefficient of the opening ratio), the maximum and minimum ranges of the roof openings can be controlled to ensure that the design does not deviate from actual feasibility. For example, an opening ratio that is too large will increase radiant heat and affect thermal comfort, while an opening ratio that is too small will not be able to effectively ventilate or light. The setting of constraint conditions helps to find the best solution within the feasibility range. Based on the combination of optimization objectives and decision variables, the wind-solar-heat balance target parameters can be accurately generated. This parameter set provides a theoretical basis for subsequent light-heat balance calculations, wind speed distribution predictions and lighting analysis, making the entire design process more refined and scientific. By simultaneously considering daylighting, natural ventilation, and thermal comfort, a comprehensive design solution can be developed early in the building design process. This multi-objective optimization not only improves the functionality of the building design but also reduces energy consumption during future operations and reduces reliance on facilities like air conditioning. This optimization method can be flexibly applied to different types of buildings, adjusting optimization objectives based on specific needs. For example, ventilation speed is more critical for sports buildings, while daylight factor and thermal comfort become more important for residential buildings. The adaptability of this method allows it to meet the needs of different projects.

[0049] Preferably, step S32 includes the following steps:

[0050] Step S321: setting the population size, crossover rate, and mutation rate of the NSGA-III algorithm, and performing non-dominated sorting on the wind-solar-heat balance target parameters according to the population size, crossover rate, and mutation rate to obtain a wind-solar-heat balance sorting result;

[0051] Step S322: Calculate the congestion distance of the wind-solar-heat balance sorting results to obtain wind-solar-heat balance sample distance data;

[0052] Step S323: Perform a diversity assessment on the wind-solar heat balance target parameters using the wind-solar heat balance sorting results and the wind-solar heat balance sample distance data, and dynamically adjust the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters. The diversity assessment formula is as follows:

[0053]

[0054] Where D totalis the diversity evaluation result, α is the influence coefficient of adjusting the diversity metric of the target space on the total diversity evaluation, β is the influence coefficient of adjusting the physical space sample distance metric of the target space on the total diversity evaluation, D is the diversity metric of the population in the target space, s i For the first wind-solar heat balance sample, s j For the second wind-solar heat balance sample, dist(s i ,s j ) is s i and s j The physical distance between them, N is the number of samples.

[0055] By calculating the crowding distance of the wind-solar thermal balance ranking results and further evaluating them based on a diversity assessment formula, this method accurately measures the diversity of wind-solar thermal balance target parameters. This precise assessment helps ensure balanced development of design solutions across multiple target spaces, thereby avoiding local optimal solutions and promoting global optimization. Dynamic adjustment of wind-solar thermal balance target parameters enables real-time updating and optimization of design solutions within a constantly changing design space. The diversity assessment results serve as the basis for dynamic adjustment, allowing wind-solar thermal balance target parameters to promptly adapt to new design requirements and environmental conditions, effectively avoiding local optimal solutions during the optimization process and ensuring the superiority of the final solution. Leveraging the diversity assessment and dynamic adjustment capabilities of the NSGA-III algorithm, wind-solar thermal balance target parameters can flexibly adapt to varying design requirements and environmental changes. This flexibility is particularly important for navigating complex and uncertain building environments, ensuring the applicability and efficiency of the design solution. In the diversity assessment formula, the α and β coefficients, respectively, control the diversity metric in the target space and the sample distance metric in the physical space. This allows for a reasonable balance of the impact of different optimization objectives during the optimization process, thereby improving the overall performance of the design solution. In this way, the algorithm effectively balances different design objectives (such as daylighting, ventilation, and thermal comfort), avoiding the overemphasis of one objective at the expense of others. By calculating crowding distance and assessing diversity, it can better screen suitable design solutions and accelerate the optimization process through dynamic adjustments. This not only improves the quality of design solutions, but also reduces unnecessary design iterations, saving computing resources and time, and improving design efficiency.

[0056] Preferably, step S4 includes the following steps:

[0057] Step S41: performing climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort and light environment impact curve to generate sensitivity analysis results;

[0058] Step S42: performing climate zone testing on the retractable roof morphology data based on the sensitivity analysis results to generate applicable scope assessment data;

[0059] Step S43: Dynamically control and adjust the opening ratio through the applicable scope evaluation data to perform the wind, light and heat balance optimization operation of the retractable roof sports building.

[0060] By performing a climate zone sensitivity analysis on the roof-ventilation thermal comfort and light environment impact curve, the present invention can gain an in-depth understanding of the ventilation and light and heat comfort performance of the roof under different climate conditions, thereby enabling the design to adapt to the needs of different regions. The design is adjusted according to the differences in climate zones to ensure that the building can achieve optimal thermal comfort and ventilation effects under various climate conditions. By generating applicable scope assessment data, the opening and closing roof structure data can be accurately tested, thereby dynamically controlling the adjustment of the opening ratio. This adjustment ensures that the roof can perform optimally in different climate zones, especially in areas with changeable climates, and can better control the temperature, humidity and air flow in the house, thereby improving the overall living experience. Dynamically controlling the adjustment of the opening ratio helps to optimize the natural ventilation and lighting efficiency of the building, reduce dependence on air conditioning and artificial lighting, and thus improve the energy efficiency of the building. This optimization solution helps to reduce the energy consumption of the building, support more environmentally friendly and low-carbon building design, and promote sustainable development. Sensitivity analysis and scope of application assessment can accurately identify the strengths and weaknesses of building designs in different climate zones. This analysis not only improves design accuracy but also reduces uncertainty during the actual construction process, avoiding over-adjustments or errors, and ensuring that the final design achieves consistent thermal comfort and ventilation performance across all climate zones. Based on the results of sensitivity analysis, the design team can be provided with scientific decision-making support, helping them more rationally select the roof opening ratio and structural solution most suitable for the target region. This decision-making basis helps to make the best design choices under complex and changing climate conditions, ensuring the building's comfort and energy efficiency.

[0061] Preferably, step S42 includes the following steps:

[0062] Step S421: Identify key parameters of the retractable roof morphology data based on the sensitivity analysis results, thereby obtaining sensitive parameter data; perform dynamic response analysis on the sensitive parameter data, thereby obtaining response characteristic data;

[0063] Step S422: performing climate zoning mapping on the retractable roof morphology data based on the response characteristic data, thereby obtaining zoning data; performing climate element simulation on the retractable roof morphology data based on the zoning data, thereby obtaining climate simulation data;

[0064] Step S423: Performing a performance test on the retractable roof morphology data based on the climate simulation data to obtain test data; performing an environmental adaptability range analysis on the retractable roof morphology data using the test data, thereby generating applicable range assessment data.

[0065] By identifying key parameters of the retractable roof and analyzing its dynamic response, the present invention accurately captures sensitive parameters and morphological response characteristics within the design. This data provides a scientific basis for subsequent climate adaptability testing, ensuring that the roof design can be optimized and adjusted for different environmental conditions, thereby achieving optimal ventilation, lighting, and thermal comfort. Through climate zoning mapping and climate factor simulation, step S42 conducts detailed climate adaptability testing of the retractable roof structure. This simulation data provides the design team with quantitative performance predictions under different climate conditions, helping to ensure that the design maintains stable performance across different climate zones, especially in extreme climates. Multi-dimensional analysis methods such as response characteristic data analysis, climate zoning mapping, and climate factor simulation provide a deeper understanding of the multi-level performance of the retractable roof structure in different climates and environments, further optimizing the design and ensuring consistent performance across different climates. Based on the structural performance testing, step S42 provides an in-depth analysis of the environmental adaptability range of the retractable roof structure, ensuring that it maintains excellent performance across different climate zones. Through scope assessment, the design can optimize the roof opening ratio and structural form, ensuring energy conservation and comfort in various climates, thereby improving the building's sustainability. Through sensitivity analysis and climate simulation, designers are provided with precise design parameters and decision-making support. This data helps them better understand the building's performance in different climates, enabling them to make more scientific and accurate design decisions and avoid design errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of the steps of a method for optimizing the light and heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm.

[0067] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0068] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0069] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0070] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0071] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0072] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0073] To achieve this, please refer to Figures 1 to 3 A method for optimizing the light and heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm is provided. The method comprises the following steps:

[0074] Step S1: Acquire the retractable roof morphology data; perform parametric modeling on the retractable roof morphology data to generate a two-dimensional grayscale image of the retractable roof; perform fluid dynamics and light and heat environment simulation on the sports building space covered by the retractable roof to obtain wind, light and heat environment simulation data of the space covered by the retractable roof;

[0075] Step S2: Pairing the two-dimensional grayscale image of the retractable roof with the wind, solar, and thermal environment simulation data to obtain an input-output image pair; using a generative adversarial network to predict the wind speed distribution of the input-output image pair to generate a predicted value of the spatial wind speed distribution of the retractable roof; and constructing a wind-solar-thermal environment gene library based on the predicted value of the spatial wind speed distribution and the solar thermal environment simulation data.

[0076] Step S3: Acquire environmental demand data for large sports spaces; set wind, solar, and thermal environment balance targets for the retractable roof space based on the environmental demand data for the large sports space, and obtain wind, solar, and thermal balance target parameters; iteratively optimize the wind, solar, and thermal balance target parameters using a genetic algorithm based on the wind-solar-thermal environment gene library to generate a Pareto optimal solution for the retractable roof morphological parameters under typical meteorological conditions; perform a regression analysis on the opening ratio of the roof morphological parameters based on the Pareto optimal solution and the corresponding indoor environment to generate a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve;

[0077] Step S4: Conduct climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort light environment impact curve to generate sensitivity analysis results; dynamically adjust the opening ratio of the retractable roof based on the sensitivity analysis results to perform wind, light and heat balance optimization and control operations for the retractable roof sports building.

[0078] The present invention can accurately analyze the ventilation, lighting and thermal environment of the roof by performing parametric modeling, fluid dynamics and photothermal environment simulation on the retractable roof morphological data. By combining wind speed distribution prediction with photothermal environment simulation data, it can optimize the wind-solar-thermal balance, improve the comfort and energy efficiency of the space below the roof, and ensure the comfort of the building's internal environment. By using a generative adversarial network to predict the wind speed distribution of input-output image pairs, it can efficiently and accurately simulate the impact of changes in the roof opening ratio on the wind speed distribution, provide a scientific basis for the wind speed control of the roof, and further optimize the natural ventilation effect of the building. By constructing a wind-solar-thermal environment gene library, the coordinated optimization of wind speed, lighting and thermal environment is achieved. The genetic algorithm iteratively optimizes the wind-solar-thermal balance target parameters, so that the wind-solar-thermal regulation of the retractable roof can be accurately adjusted according to different climate zones, building usage requirements and environmental changes, ensuring the maximization of the building's wind-solar-thermal comfort and energy efficiency. Based on the Pareto optimal solution, a roof opening and closing ratio-ventilation, thermal comfort and light environment impact curve is generated to provide designers with a detailed relationship between the roof opening ratio and ventilation, thermal comfort and light environment, helping to make more scientific design decisions and optimize the ventilation and thermal comfort of the retractable roof. Through climate zone sensitivity analysis, the structural design of the retractable roof can be adjusted according to the characteristics of different climate zones to ensure that the roof can achieve the best wind, light and heat balance effect under various climatic conditions. This targeted design not only improves the adaptability of the roof, but also provides a guarantee for the energy-saving effect of the building. According to the results of the sensitivity analysis, the opening ratio of the retractable roof structure is dynamically adjusted, so that the retractable roof can flexibly adjust the opening ratio under different climatic conditions, optimize the balance of wind, light and heat environment, and further improve the energy efficiency and comfort of the building. Therefore, the present invention realizes the intelligent optimization of the light and heat balance of the retractable roof sports building by combining generative adversarial networks and genetic algorithms, solving the shortcomings of traditional methods in flexibility, optimization accuracy and computational efficiency.

[0079] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart showing the steps of a method for optimizing the light-heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm according to the present invention. In this example, the method for optimizing the light-heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm includes the following steps:

[0080] Step S1: Acquire the retractable roof morphology data; perform parametric modeling on the retractable roof morphology data to generate a two-dimensional grayscale image of the retractable roof; perform fluid dynamics and light and heat environment simulation on the sports building space covered by the retractable roof to obtain wind, light and heat environment simulation data of the space covered by the retractable roof;

[0081] In an embodiment of the present invention, design data for a retractable roof is obtained, including structural information such as the roof's geometry, dimensions, material, opening ratio, and opening and closing pattern. This data can be obtained from architectural design drawings, structural design documents, or 3D scan data of existing buildings. Laser scanning technology, optical imaging, and measurement tools can be used to collect various physical parameters of the roof. The acquired retractable roof morphological data is integrated to ensure its integrity and accuracy. This data includes the roof's spatial coordinate system, geometric features, opening locations, and dimensional information. CAD (Computer-Aided Design) software or a BIM (Building Information Modeling) platform ensures that the data can serve as a foundation for subsequent modeling. Based on the retractable roof structural data, parametric modeling techniques are used to generate a two-dimensional or three-dimensional model of the retractable roof. This step can be performed using modeling software (such as AutoCAD, Rhino, or SolidWorks). Parametric design allows for dynamic adjustment of the roof's opening and closing ratio, dimensions, and angles, thereby rapidly generating different roof configurations. Each design parameter (such as opening ratio, roof tilt angle, and number of floors) can be used as an input to the model. Using the modeled roof data, a rendering tool is used to generate a two-dimensional grayscale image of the retractable roof. This image should visualize the roof geometry and opening locations. During the rendering process, ray tracing techniques can be used to simulate lighting and shadows on the roof, producing a realistic grayscale image where grayscale values ​​reflect the light intensity or opening / closing state of different areas. A three-dimensional geometric model of the retractable roof is constructed using CAD software (such as AutoCAD, SolidWorks) or BIM tools (such as Revit). This model should include the roof's opening and closing mechanism, supporting structure, and environmental factors. For fluid dynamics simulations, CFD software (such as ANSYS Fluent, OpenFOAM) is used to mesh the space beneath the roof and the surrounding air domain. For thermal and solar simulations, finite element methods (such as ANSYS, COMSOL) are used to refine the mesh to ensure accuracy. Fluid boundary conditions such as wind speed, air pressure, and temperature are set based on actual conditions. Simulations of different retractable roof angles and varying meteorological conditions (such as wind speed, air temperature, and humidity) can be performed. CFD software was used to determine the air flow, wind speed distribution, wind pressure distribution, and dynamic pressure of the retractable roof under different opening and closing conditions. The roof's stability, air permeability, and potential airflow impact were analyzed. Fluid dynamics simulations were used to generate wind speed, pressure, and streamline diagrams, analyzing the retractable roof's ventilation performance, heat exchange, and the impact of wind on the roof structure. Thermal and light environmental conditions, such as light intensity, solar radiation, air temperature, and humidity, were set. By simulating light and heat flux distribution in different seasons and time periods, more representative environmental data was obtained. Finite element simulations were used to simulate heat transfer under different opening and closing angles of the roof.Considering heat exchange modes such as radiation, convection, and conduction, analyze temperature changes on the roof surface, structure, and surrounding environment. Develop roof surface temperature distribution, thermal radiation patterns, and the impact of roof opening and closing on indoor and outdoor temperatures. Further analysis can be conducted on the impact of roof opening and closing on energy efficiency, indoor temperature control, and comfort.

[0082] Step S2: Pairing the two-dimensional grayscale image of the retractable roof with the wind, solar, and thermal environment simulation data to obtain an input-output image pair; using a generative adversarial network to predict the wind speed distribution of the input-output image pair to generate a predicted value of the spatial wind speed distribution of the retractable roof; and constructing a wind-solar-thermal environment gene library based on the predicted value of the spatial wind speed distribution and the solar thermal environment simulation data.

[0083] In an embodiment of the present invention, corresponding simulation data is searched for each two-dimensional grayscale image. This data is typically generated based on the roof's geometric structure and environmental conditions. For example, the opening angle and wind speed distribution corresponding to different roof positions require precise matching. During matching, the size and resolution of the grayscale image must be consistent with the simulation data, and the matching relationship between the two must be accurate. Each grayscale image should correspond to a set of wind speed distribution data, forming an input-output image pair. Image matching techniques (such as image registration) can be used to ensure a one-to-one correspondence between the input image and the output simulation data. A generative adversarial network (GAN) model is used to predict wind speed distribution. The GAN consists of two parts: a generator and a discriminator. The generator accepts a two-dimensional grayscale image of the open and close roof as input and generates a predicted wind speed distribution image using a deep neural network. The discriminator determines the similarity between the generated predicted wind speed distribution image and the actual wind speed distribution image, and uses feedback signals to help the generator gradually improve the quality of the generated image. A convolutional neural network (CNN) is designed to extract features from the input two-dimensional grayscale image and generate a predicted wind speed distribution image through deconvolution. A CNN architecture is also used to distinguish generated wind speed distribution images from real images. By learning to identify the features of real wind speed images, the discrimination capability is continuously improved. The generator's performance is optimized by calculating the differences between the generated wind speed images and the real images (such as structural similarity and root mean square error). The discriminator's performance is optimized by calculating the error between the generated and real images. The GAN model is trained using input-output image pairs (a 2D grayscale image of a retractable roof and simulated wind speed distribution data). During training, the generator continuously generates predicted wind speed distribution images, while the discriminator evaluates the authenticity of these images. By alternately optimizing the generator and discriminator, the accuracy of wind speed distribution predictions is gradually improved. When the adversarial process between the generator and discriminator reaches equilibrium, the model is able to accurately generate predicted wind speed distribution images. The trained GAN model is fed with a new 2D grayscale image of a retractable roof to generate a corresponding predicted wind speed distribution image. The generated image contains information such as the wind speed distribution within the roof, airflow path, and wind speed intensity. Wind speed distribution data for a variety of retractable roof structures are collected from the generated wind speed distribution prediction values. These data include wind speed distribution images under different opening ratios, angles, and wind speed conditions, which serve as the basis for subsequent analysis. The wind speed distribution prediction image under each structure is associated with specific retractable roof structural parameters (such as opening ratio, inclination angle, and airflow path). The generated wind speed distribution prediction values ​​are combined with the retractable roof structural data, environmental conditions, and solar thermal environment simulation data to create a wind-solar-thermal environment gene library containing a variety of roof configurations and wind speed distribution characteristics and solar thermal characteristics.

[0084] Step S3: Acquire environmental demand data for large sports spaces; set wind, solar, and thermal environment balance targets for the retractable roof space based on the environmental demand data for the large sports space, and obtain wind, solar, and thermal balance target parameters; iteratively optimize the wind, solar, and thermal balance target parameters using a genetic algorithm based on the wind-solar-thermal environment gene library to generate a Pareto optimal solution for the retractable roof morphological parameters under typical meteorological conditions; perform a regression analysis on the opening ratio of the roof morphological parameters based on the Pareto optimal solution and the corresponding indoor environment to generate a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve;

[0085] In this embodiment of the present invention, multiple wind-solar thermal balance targets are set based on predicted wind speed distribution values ​​from a wind-solar thermal environment gene library, combined with the roof's morphological characteristics and external environmental conditions. The primary targets include maximizing the daylight factor, maximizing natural ventilation speed, and minimizing the thermal comfort index. Based on these wind-solar thermal balance targets, constraints are imposed on the structural parameters of the retractable roof (such as the opening ratio, roof tilt angle, and wind speed distribution) to ensure these targets are feasible within the design range. Three-dimensional spatial coefficients for the opening ratio are set as constraints on the decision variables. For example, the size and shape of the openings are optimized to ensure an optimal balance between wind speed distribution, daylighting conditions, and temperature control. Based on these optimization targets and decision variables, parameter combination analysis is performed to generate wind-solar thermal balance target parameters. These parameters can include values ​​for relevant indicators such as daylighting, ventilation speed, and thermal comfort index. A genetic algorithm (GA) is used to optimize these wind-solar thermal balance target parameters. The GA simulates natural selection and genetic mechanisms to search for optimal design parameters. Multiple solutions (i.e., different combinations of roof design parameters) are randomly generated and serve as initial individuals in the population. Depending on the objectives set, a fitness function is designed to measure the quality of each solution. For example, the fitness function can be used to score each solution based on its achievement of the wind-solar-heat balance objective. The optimal solution corresponds to a design that minimizes the thermal comfort index, maximizes the daylight factor, and maximizes the natural ventilation rate. A selection mechanism selects individuals with higher fitness from the current population, undergoes crossover (combining the characteristics of two individuals) and mutation (introducing small random variations), and generates new offspring. In each generation, individuals with lower fitness are eliminated, while individuals with higher fitness continue to reproduce. Through multiple generations of evolution, the optimal solution is gradually approached. Through multiple iterations of optimization, a set of optimal parameters is ultimately generated. These parameters represent the specific solution that achieves the optimal wind-solar-heat balance for the retractable roof design. The output of the genetic algorithm is a set of Pareto optimal solutions, representing different design options that achieve the best balance between multiple objectives. For example, one solution may perform best in terms of daylighting and ventilation, while another may be superior in terms of thermal comfort. A Pareto optimal solution is not a single optimal solution, but rather a set of solutions that cannot be further improved by addressing any one objective without compromising the performance of the others. Based on the Pareto optimal solution, a regression analysis was performed. This regression analysis modeled the relationship between the roof's opening ratio, a morphological parameter, and wind speed distribution, daylighting, and thermal comfort. This regression model quantified the impact of the opening ratio parameter on wind speed distribution, daylighting, and thermal comfort, thereby establishing an impact curve. Based on the regression analysis results, a curve was plotted that correlated the roof's opening ratio with ventilation, thermal comfort, and light environment.

[0086] Step S4: Perform a climate zone sensitivity analysis on the roof opening / closing ratio-ventilation, thermal comfort, and light environment impact curve to generate sensitivity analysis results. Based on the sensitivity analysis results, dynamically adjust the opening ratio of the retractable roof to optimize the wind, light, and heat balance of the retractable roof sports building. In this embodiment of the present invention, the world is divided into multiple climate zones based on regional climatic conditions, such as tropical, temperate, and frigid zones. The climatic characteristics of each climate zone (such as temperature, humidity, precipitation, and wind speed) will have different impacts on the design parameters of the retractable roof. Based on the roof opening / closing ratio-ventilation, thermal comfort, and light environment impact curve, the sensitivity of the roof configuration (such as opening ratio, vent distribution, roof angle, etc.) to the light and heat balance objectives (lighting, ventilation, and thermal comfort) in different climate zones is analyzed. Parameters for each climate zone are simulated and adjusted to evaluate the impact of the roof opening / closing design on various performance characteristics (such as lighting, ventilation speed, and thermal comfort index), and sensitivity analysis results are generated. For example, some climate zones rely more on natural ventilation, while others rely more on daylighting. Therefore, the analysis aims to determine which roof parameters have the greatest impact on wind-solar heat balance under different climatic conditions. By varying each design parameter (such as opening ratio and vent location) and observing its impact on the wind-solar heat balance target, the sensitivity of each parameter is assessed. By combining multiple factors and conducting multivariate analysis using a system model, the optimal parameter combination for global performance is determined. Based on the results of the climate zone sensitivity analysis, key roof design parameters are dynamically adjusted. Specifically, the opening ratio, a key factor determining ventilation and daylighting, is optimized. The goal is to ensure optimal wind-solar heat balance across different climatic conditions, tailored to the needs of each climatic zone. For example, in tropical climates, a larger opening ratio is required to increase natural ventilation, while in cold climates, a smaller opening ratio is required to maintain indoor warmth. Based on real-time monitored environmental data (such as temperature, humidity, and wind speed), the system automatically adjusts the opening ratio. This adaptive adjustment can respond to climate changes or changing building requirements. By incorporating intelligent control algorithms (such as fuzzy control and neural network control), the opening ratio is precisely controlled according to environmental changes, optimizing the roof's ventilation and daylighting performance. During the dynamic adjustment of the opening ratio, comprehensive optimization is performed based on factors such as lighting, ventilation, and thermal comfort to ensure the achievement of wind, solar, and heat balance. Sensors and data acquisition systems are installed to monitor the roof's lighting, ventilation, and thermal comfort in real time, and further adjustments are made based on feedback to ensure the roof design always maintains an optimal solar and thermal balance.

[0087] Preferably, step S1 includes the following steps:

[0088] Step S11: Acquire the shape data of the retractable roof;

[0089] Step S12: performing parametric modeling on the retractable roof morphological data, defining the dynamic adjustment range of the roof opening and closing direction and the opening ratio, and obtaining a retractable roof geometric model;

[0090] Step S13: converting the retractable roof geometric model into a grayscale image to generate a two-dimensional grayscale image of the retractable roof;

[0091] Step S14: extracting the roof shape of the retractable roof from the two-dimensional grayscale image, and using simulation software to perform CFD simulation and light and heat environment simulation on the building space below the retractable roof, calculating the indoor and outdoor wind speed distribution and thermal comfort index, and obtaining indoor and outdoor wind speed distribution data and thermal comfort index data;

[0092] Step S15: performing daylight analysis on the building space below the retractable roof to generate daylight coefficient distribution data; converting the indoor and outdoor wind speed distribution data, daylight coefficient distribution data, and thermal comfort index data into graphs to generate a wind speed distribution map, a daylight coefficient distribution map, and a thermal comfort index heat map;

[0093] Step S16: Integrate the wind speed distribution map, the daylight coefficient distribution map, and the thermal comfort index thermodynamic map into wind, light, and thermal environment simulation data of the space covered by the retractable roof.

[0094] In an embodiment of the present invention, data on the retractable roof's morphology is obtained from architectural design drawings, BIM models, or other building information sources. This data typically includes the roof's dimensions, shape, support structure, material, and opening and closing mechanism. If existing data is unavailable, 3D scanning or laser scanning can be used to obtain the roof's geometric morphology. Modeling software (such as AutoCAD, Rhino, or Revit) is used to perform geometric modeling of the roof. The roof's opening and closing directions (e.g., horizontal, vertical, etc.) and the opening ratio (e.g., percentage of opening) are defined, allowing for dynamic adjustment based on actual needs. A dynamic model of the roof is created using parametric design tools (such as the Grasshopper plug-in) to ensure that the roof's opening and closing process reflects the flexibility and adjustability of real-world opening and closing. The model is converted into a software format suitable for simulation analysis (e.g., STL or OBJ format) to provide geometric input for subsequent steps. The roof's geometric model is converted into a two-dimensional image using Python software. The grayscale of the image represents the roof's morphological characteristics, with white representing areas without the roof (e.g., openings), red representing the roof, and gray and black representing the building's solid components (e.g., walls and surrounding buildings). When generating a two-dimensional grayscale image, ensure a sufficiently high resolution to preserve the details of the roof's form. The roof model is imported into CFD simulation software (such as ANSYS Fluent or OpenFOAM) for fluid dynamics simulation. During the simulation, boundary conditions such as wind speed and air pressure are set to calculate the wind speed distribution, wind pressure, and other fluid dynamic characteristics of the retractable roof in different opening and closing states. Thermal environment simulation software (such as COMSOL or EnergyPlus) is used to simulate illumination, thermal radiation, convection, and conduction. The impact of roof form on thermal comfort is calculated, and thermal comfort indicators (such as temperature, humidity, and heat load) are obtained. Lighting analysis tools (such as DIALux or Radiance) are used to perform daylight analysis on the lower space of the retractable roof. The effects of the roof opening ratio and opening angle on indoor daylighting are analyzed to generate the daylight coefficient, which is the light intensity per unit area when the roof is open. The daylight coefficient is an important indicator of light uniformity and reflects the effect of the roof's opening and closing states on indoor daylighting. Based on CFD simulation results, wind speed data is converted into charts or heat maps, showing the indoor and outdoor wind speed distribution under different roof opening and closing conditions. Based on the solar and thermal environment simulation results, a thermal comfort index heat map is generated to visually demonstrate the impact of the retractable roof in different opening and closing conditions on indoor and outdoor thermal comfort. Daylight analysis results are presented in tables or charts, showing the daylight factor under different opening and closing angles and opening ratios. The wind speed distribution map, thermal comfort index heat map, and daylight factor are integrated to generate CFD simulation data and solar and thermal environment simulation data for the retractable roof.

[0095] Preferably, the daylight analysis of the building space below the retractable roof includes:

[0096] Extract the daylighting area of ​​the building space under the retractable roof to obtain an image of the daylighting area of ​​the space under the retractable roof; calculate the solar altitude angle and azimuth angle of the daylighting area image of the space under the retractable roof to obtain the solar altitude angle and solar azimuth angle;

[0097] Based on the solar altitude angle and solar azimuth angle, light propagation simulation is performed on the daylighting area of ​​the retractable roof to generate sunlight propagation path simulation data. The illumination intensity of each pixel in the daylighting area image of the space below the retractable roof is calculated based on the sunlight propagation path simulation data to obtain a local sunlight intensity map.

[0098] The local sunlight intensity map is used to calculate the actual illumination area ratio of the lighting area image under the retractable roof to obtain the daylighting coefficient.

[0099] In an embodiment of the present invention, a two-dimensional grayscale image of a retractable roof is processed by using image processing software or programming tools (such as MATLAB, Python's OpenCV). The grayscale image is binarized, and the open area is distinguished from the non-open area based on the set color value (for example, the roof covered area is red, the open area is white, and the walls and surrounding buildings are gray and black). Automatic segmentation is performed using a suitable threshold segmentation method (such as the Otsu method), or the threshold is manually adjusted to ensure accurate extraction of the lighting area. The solar altitude angle (α) represents the angle between the sun's rays and the ground, and the calculation formula is: α = arcsin (sin (δ) · sin (φ) + cos (δ) · cos (φ) · cos (H)); wherein δ is the sun's declination angle, φ is the latitude of the observation point, and H is the hour angle (i.e., the time difference between the sun at the current moment and the local noon). The solar azimuth angle (Az) represents the angle of the sun relative to the south direction, and the calculation formula is: Where H is the hour angle, δ is the declination angle, and φ is the latitude of the observation point. You can use a solar position calculation tool such as SolarCalc or a custom program to calculate the solar altitude and azimuth angles at different times and dates. Based on the solar altitude and azimuth angles, simulate the propagation of light from the sun to the roof opening. Use a ray tracing algorithm (such as Monte Carlo Ray Tracing) to simulate the propagation of light from the sun to the roof opening. Professional illumination simulation software (such as Radiance, Daysim, and LDT Tools) can be used for ray propagation simulation. These tools accurately simulate the light propagation path based on the sun's position and the geometry of the roof opening. Treat the sun as a point light source, set its altitude and azimuth angles, and calculate the light propagation path based on the roof geometry. During light propagation, factors such as air scattering, reflection, and absorption are taken into account to attenuate the light. Based on the simulated sunlight propagation path, calculate the illumination intensity at each pixel in the image of the daylighting area of ​​the retractable roof. For each pixel, calculate the number and intensity of sunlight passing through that point. Illumination intensity is generally related to the angle of incidence, reflection, refraction, and attenuation of sunlight. Illumination intensity (I) can be calculated using the following formula: I = I0·cos(θ); where I0 is the sunlight intensity and θ is the angle between the light and the surface normal. Using the calculated illumination intensity value, a corresponding light intensity value is assigned to each pixel to generate a local sunlight intensity map. By performing threshold processing on the local sunlight intensity map, effective illumination areas are screened out. Areas where the illumination intensity exceeds a certain threshold are considered effective daylighting areas. The actual illumination area is calculated by calculating the area of ​​the effective illumination area in the local sunlight intensity map. The area of ​​all roof openings in the daylighting area image is used as the total daylighting area. The daylighting factor (IF) is defined as the ratio of the actual illumination area to the total daylighting area. The generated daylighting factor serves as a lighting performance indicator for roof design and can be further used for architectural design optimization.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: Pairing the two-dimensional grayscale image of the retractable roof and the wind speed distribution map of the space below the roof to obtain an input-output image pair; dividing the input-output image pair into a data set to generate a model training set, a model test set, and a model validation set;

[0102] Step S22: Constructing a Pix2Pix network framework; inputting the model training set, model test set, and model validation set into the Pix2Pix network framework for training, testing, and validation to obtain a Pix2Pix algorithm model; inputting a preset two-dimensional image of the retractable roof design into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, thereby generating a predicted indoor wind speed map of the space under the retractable roof;

[0103] Step S23: performing a numerical matrix conversion on the indoor predicted wind speed map of the space below the retractable roof to obtain a predicted value of the spatial wind speed distribution of the retractable roof, and extracting the average wind speed value of the key area of ​​the sports building based on the predicted value of the spatial wind speed distribution of the retractable roof to obtain the average wind speed value of the key area;

[0104] Step S24: Parameter association is performed on the opening ratio of the retractable roof according to the average wind speed value in the key area, and a gene library is constructed using the associated parameters and the light-heat environment simulation data to obtain a wind-light-heat environment gene library.

[0105] In an embodiment of the present invention, two-dimensional grayscale images of retractable roofs are paired with corresponding wind speed distribution maps. Each two-dimensional grayscale image corresponds to a wind speed distribution map, with the two-dimensional grayscale image serving as input and the wind speed distribution map serving as output. The image sizes must be consistent, and each pair of images represents the simulation results for the same retractable roof state. The dataset is divided into 70% for training, 15% for testing, and 15% for validation. This dataset can be randomly partitioned to ensure the representativeness and diversity of the training, testing, and validation sets. The training set is used as image pair data for model training, the testing set is used as image pair data for model evaluation, and the validation set is used as image pair data for model verification and adjustment during training. Pix2Pix is ​​an image-to-image translation model suitable for image generation and wind speed prediction tasks. Its framework comprises a generator and a discriminator: the generator accepts a two-dimensional grayscale image of a retractable roof as input and generates a predicted wind speed distribution map. The discriminator distinguishes the generated wind speed distribution map from the actual wind speed distribution map, assessing the authenticity of the generated image and providing feedback to the generator for optimization. A Pix2Pix network is constructed using a deep learning framework (such as TensorFlow or PyTorch). The network consists of an input layer: a two-dimensional grayscale image of the retractable roof; a convolutional layer: extracting feature information from the input image; skip connections: concatenating the shallow and deep outputs of the generator to preserve detail; and an output layer: generating the wind speed distribution map. The divided training data is input into the Pix2Pix model for training. The accuracy of the generated wind speed distribution map is continuously optimized by minimizing the loss functions of the generator and discriminator. The predicted wind speed map for the retractable roof generated by the Pix2Pix network is converted into a numerical matrix. This is achieved by mapping image pixel values ​​to wind speed distribution, extracting the wind speed value corresponding to each pixel into a numerical matrix. The numerical matrix represents the wind speed distribution of the retractable roof in different opening and closing states, including wind speed magnitudes in different areas. Identify the key areas in the sports building (for example, sports fields, spectator seats, entrances, etc.). Extract the wind speed matrix portion of each key area and calculate the average wind speed value of the area. Perform correlation analysis on the opening ratio and the average wind speed value of the key area through statistical methods (such as regression analysis) or machine learning methods (such as support vector machine, decision tree, etc.). This analysis can reveal the influence of the opening ratio on the wind speed of the key areas of the sports building. For example, analyze the wind speed change trend under different opening ratios when the opening ratio of the retractable roof ranges from 0% to 100%. Integrate the light and heat environment data related to the opening ratio (such as temperature, humidity, thermal comfort, etc.) into the parameter association model. Based on environmental factors such as wind speed, light, thermal comfort, etc., establish a multi-dimensional wind-light-heat environment gene library. Each data point in the gene library includes a mapping of the retractable roof state (opening ratio) and the corresponding environmental characteristics.

[0106] Preferably, step S22 includes:

[0107] Build a Pix2Pix network framework, which includes a generator and a discriminator;

[0108] Set the training parameters for the Pix2Pix network framework and generate training parameter setting values, where the training parameter settings include learning rate settings, number of convolutional layers settings, epoch settings, and optimizer settings;

[0109] The model training set is input into the Pix2Pix network framework to predict wind speed through the generator in the Pix2Pix network framework, generating an initial predicted wind speed map for retractable roofs. The model test set is then used to compare the initial predicted wind speed map for retractable roofs with the real result image through the discriminator in the Pix2Pix network framework.

[0110] The structural similarity and root mean square error of the initial retractable roof wind speed prediction map are calculated to obtain the accuracy of the wind speed prediction map;

[0111] The wind speed prediction map accuracy was tested on the model validation set to obtain the Pix2Pix algorithm model;

[0112] The preset two-dimensional image of the retractable roof design is input into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, and a predicted indoor wind speed map of the space under the retractable roof is generated.

[0113] In an embodiment of the present invention, the Pix2Pix network framework is based on the generator and discriminator in a generative adversarial network (GAN). The generator is responsible for generating a target image (i.e., a predicted wind speed map) from an input image, while the discriminator is responsible for evaluating whether the generated wind speed map is realistic, comparing the difference with the actual wind speed map, and optimizing the generator. The generator typically adopts a U-Net architecture, which is a symmetrical encoder-decoder structure that can effectively process spatial information in the image and transmit detailed features at jump connections to improve the accuracy of the prediction results. Input information such as a two-dimensional grayscale image of a retractable roof, a wind speed distribution map, and a thermal comfort map are input. All input images are subjected to a convolution operation and feature extraction, and the output is a predicted wind speed distribution map. Selecting an appropriate learning rate has a significant impact on the convergence speed and performance of the network. Generally, setting a low learning rate (e.g., 0.0002) can prevent gradient explosion or vanishing. The number of convolutional layers in the generator and discriminator should be set according to the complexity of the network. Generally speaking, the number of convolutional layers in the generator can range from 4 to 8, and the number of convolutional layers in the discriminator is similar. The greater the number of layers, the stronger the network's expressiveness and processing capabilities. The number of training iterations is generally recommended to be 20-50 epochs, which can be adjusted based on the model's training progress. More epochs provide the network with more opportunities for optimization. The Adam optimizer is used because it effectively adjusts network parameters, especially when handling sparse gradients. The parameters are set to be: beta_1 = 0.5, beta_2 = 0.999, and the learning rate is typically set to 0.0002. Image data from the training set is fed into the generator within the Pix2Pix network framework. Each input-output image pair is processed by the generator to generate an initial predicted wind speed map for the retractable roof based on information such as the retractable roof's geometric image, wind speed distribution map, and thermal comfort map. The generator learns from the image pairs in the training set and generates the predicted wind speed map. The initial predicted wind speed map for the retractable roof deviates from the actual wind speed map. Using data from the model test set, the discriminator compares the generated initial wind speed map with the true wind speed map. The discriminator evaluates the authenticity of the generated wind speed map and provides feedback to the generator, prompting the generator to optimize. The following two common accuracy evaluation methods are used for the generated initial retractable roof predicted wind speed map: The Structural Similarity Index (SSIM) is a metric that measures the similarity between two images, focusing particularly on structural similarity, and can effectively reflect the perceptual quality of the image. SSIM can be used to compare the similarity between the generated wind speed map and the true wind speed map, obtaining a value in the range [0,1]. The closer the value is to 1, the more similar the two images are. The root mean square error is a commonly used method to calculate the difference between the predicted value and the true value, which can quantify the degree of error in the generated image. The generated wind speed map is verified for accuracy using data from the model validation set.By comparing the wind speed maps in the validation set with the generated wind speed maps, we confirm whether the model has converged and whether the generated wind speed maps meet expectations. If the model's accuracy (such as SSIM and RMSE) in the validation set meets expectations and converges, it indicates that the wind speed prediction model is sufficiently stable. The final Pix2Pix algorithm model can be generated. The preset two-dimensional image of the retractable roof design is then input into the Pix2Pix algorithm model to predict the indoor wind speed in the space below the roof, generating a predicted indoor wind speed map for the space below the retractable roof.

[0114] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0115] Step S31: Acquire the environmental demand data of the large sports space; set the wind-solar-heat balance target for the retractable roof space according to the environmental demand data of the large sports space, and obtain the wind-solar-heat balance target parameters;

[0116] Step S32: performing a diversity assessment on the wind-solar heat balance target parameters using the NSGA-III algorithm, and dynamically adjusting the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters;

[0117] Step S33: Based on the wind-solar-thermal environment gene library, the wind-solar-thermal balance target parameters are iteratively optimized using the NSGA-III algorithm, and extreme solutions are eliminated to generate a Pareto optimal solution.

[0118] In an embodiment of the present invention, wind-solar thermal balance targets are set based on the daylight factor, using data on large sports space environmental requirements and wind speed, light intensity, and thermal comfort under different roof opening and closing conditions. Setting wind-solar thermal balance target parameters includes determining an ideal wind speed range to ensure air circulation and comfort within the sports building. Setting an appropriate daylight factor to ensure that natural lighting within the building meets design requirements. Setting an appropriate thermal comfort target based on thermal comfort standards (e.g., UTCI and PMV-PPD). Wind-solar thermal balance target parameters include specific numerical ranges for the aforementioned targets, which are multivariate and interrelated. NSGA-III (Non-dominated Sorting Genetic Algorithm III) is a multi-objective optimization algorithm specifically designed for multi-objective problems, particularly suitable for high-dimensional optimization tasks. This algorithm evaluates solution quality using non-dominated sorting and crowding distance, effectively finding Pareto front solutions. Wind-solar thermal balance target parameters are input, and the NSGA-III algorithm is used to evaluate the diversity of these target parameters. The results of the diversity assessment reveal the trade-offs and distributions between wind speed, daylighting, and thermal comfort under different retractable roof design parameters. Based on the diversity assessment results, the wind-solar thermal balance target parameters are dynamically adjusted. For example, if wind speed is too high and daylighting is insufficient, the algorithm adjusts the parameters to reduce wind speed and increase the daylight factor to achieve a balance. The adjusted parameters serve as the new wind-solar thermal balance target adjustment parameters, which can be optimized through multiple iterations to approach the optimal target. Using the adjusted wind-solar thermal balance target parameters, the NSGA-III algorithm performs multiple rounds of iterative optimization, gradually adjusting the parameter combination. With each iteration, a new set of solutions is generated, and the quality of the solutions is evaluated (for example, by the distribution of the Pareto front). In each iteration, extreme solutions that do not meet the design objectives (for example, extremely low daylight factors or extremely high wind speeds) are eliminated to ensure that the optimization results remain within an acceptable range. This elimination of extreme solutions can be achieved by setting thresholds or performing post-processing analysis. After multiple iterations, a set of Pareto-optimal solutions is selected as the optimal design. These solutions represent the optimal trade-off between wind speed, daylighting, and thermal comfort. Based on the Pareto optimal solution and the morphological data of the retractable roof, a regression model was used to establish the relationship between wind speed, daylighting, thermal comfort, and the roof opening and closing ratio parameters. The regression equation is: Y = β0 + β1X1 + β2X2 + … + β n X n , where Y is the target variable (wind speed, daylighting, thermal comfort), X1, X2, ..., X n are design parameters (e.g. roof opening ratio), β0, β1, …, β nis the regression coefficient. The following three curves are generated based on the regression equation: The roof opening ratio-ventilation influence curve represents the influence of the opening ratio on wind speed. The roof opening ratio-natural lighting influence curve represents the influence of the roof opening ratio parameters on indoor natural lighting. The roof opening ratio-thermal comfort influence curve represents the influence of the roof opening ratio parameters on thermal comfort (such as temperature, humidity, UTCI value, etc.). The above three curves are integrated to generate the roof opening ratio-ventilation thermal comfort light environment influence curve. This curve combines the influence of wind speed, lighting and thermal comfort, and provides a comprehensive design reference. It can be represented by a multidimensional function: E = f(v, l, t); where E is the comprehensive environmental influence, v is the wind speed, l is the lighting coefficient, and t is the thermal comfort.

[0119] Preferably, step S31 includes:

[0120] Obtain data on the environmental requirements of large sports spaces;

[0121] Optimization objectives are defined based on the environmental demand data of large sports spaces, including maximizing the daylight factor, maximizing the natural ventilation rate, and minimizing the thermal comfort index;

[0122] Decision variable constraints are set for maximizing the daylight coefficient, maximizing the natural ventilation speed, and minimizing the thermal comfort index, and limiting the spatial three-dimensional coefficient of the opening ratio;

[0123] Based on the optimization objectives and decision variables, the predicted values ​​of wind speed distribution of retractable roof are combined to obtain the target parameters of wind-solar heat balance.

[0124] In this embodiment of the present invention, by acquiring environmental demand data for large sports spaces, the wind, light, and heat environment gene library and the daylight factor can be combined to determine optimization objectives: maximizing the daylight factor, maximizing the natural ventilation rate, and minimizing the thermal comfort index. This ensures a balance between these objectives during the optimization process and ensures that the roof structure complies with practical design specifications. Decision variable constraints are set for each objective. These decision variables include parameters that affect daylighting, ventilation, and thermal comfort, such as the roof opening ratio, opening direction, roof shape, and roof inclination angle. The maximum and minimum values ​​of the roof opening ratio are constrained. Based on building structure and safety requirements, the opening ratio should not exceed a certain percentage to avoid compromising building stability or energy efficiency. A three-dimensional spatial coefficient for the opening ratio is set to define the range of the roof opening ratio, thereby controlling the design space during the optimization process. There is a trade-off between ventilation rate and daylight factor. For example, excessively large openings can affect wind speed or thermal comfort, so a balance between ventilation and daylighting must be maintained. Constraints are set for maximizing the daylight factor objective: Cmax ≤ 1, where Cmax represents the maximum daylight factor. Constraints are set for maximizing the ventilation rate objective: Vmax ≥ 0, where Vmax is the maximum ventilation rate. A constraint to minimize the thermal comfort index is set: Hmin ≤ 3, where Hmin is the minimum thermal comfort index (e.g., PMV value). Using previously predicted wind speed distribution (through methods such as CFD simulation), wind speed distribution data is obtained for different roof opening ratios. This wind speed distribution data takes into account the impact of factors such as opening configuration and roof angle on indoor and outdoor wind speeds. The predicted wind speed distribution values ​​are combined with the optimization objectives of the daylight factor and thermal comfort index to form the target parameters for solar-thermal balance. This parameter combination takes into account the following aspects: the interaction between wind speed and temperature, ensuring that the retractable roof structure design maximizes ventilation while reducing heat accumulation; the interaction between the daylight factor and the sunlight path, ensuring that natural light is increased without affecting indoor thermal radiation levels; the correlation between the thermal comfort index and the ratio and configuration of roof openings. By calculating the thermal comfort value for each design option, it is ensured that the final solution meets comfort requirements. During the optimization process, the final wind-solar-thermal balance target parameters are obtained based on the combination of objective functions. This parameter set is used in the execution of subsequent optimization algorithms (such as the NSGA-III algorithm) to ensure a balance between different optimization objectives to obtain the optimal retractable roof design.

[0125] Preferably, step S32 includes the following steps:

[0126] Step S321: setting the population size, crossover rate, and mutation rate of the NSGA-III algorithm, and performing non-dominated sorting on the wind-solar-heat balance target parameters according to the population size, crossover rate, and mutation rate to obtain a wind-solar-heat balance sorting result;

[0127] Step S322: Calculate the congestion distance of the wind-solar-heat balance sorting results to obtain wind-solar-heat balance sample distance data;

[0128] Step S323: Perform a diversity assessment on the wind-solar heat balance target parameters using the wind-solar heat balance sorting results and the wind-solar heat balance sample distance data, and dynamically adjust the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters. The diversity assessment formula is as follows:

[0129]

[0130] Where D total is the diversity evaluation result, α is the influence coefficient of adjusting the diversity metric of the target space on the total diversity evaluation, β is the influence coefficient of adjusting the physical space sample distance metric of the target space on the total diversity evaluation, D is the diversity metric of the population in the target space, s i For the first wind-solar heat balance sample, s j For the second wind-solar heat balance sample, dist(s i ,s j ) is s i and s j The physical distance between them, N is the number of samples.

[0131] In this embodiment of the present invention, an appropriate population size N is set, which determines the number of individuals in each generation. The selected population size should enable exploration of the optimization space within a suitable timeframe while also avoiding excessive computational complexity. The crossover rate Cr refers to the probability of performing a crossover operation within the population. An appropriate crossover rate helps the algorithm search a wider range of solution spaces. The mutation rate Mr refers to the probability of performing a mutation operation on an individual. Mutation operations help increase population diversity and avoid the occurrence of local optimal solutions. Based on the optimization objective of the wind, solar, and heat balance target parameters, the population is sorted using the non-dominated sorting method. Non-dominated sorting is a multi-objective optimization method that distinguishes optimal solutions (Pareto optimal solutions) from other solutions through sorting. During this process, individuals in the population are divided into different levels (tiers): the first level is non-dominated solutions, the second level is solutions dominated by the first level, and so on. The crowding distance calculation is used to assess the distribution of solutions in the target space to prevent the population from concentrating in a specific location. Solutions with larger crowding distances are generally considered more diverse and have a greater chance of surviving in the next generation. For each non-dominated solution, calculate the distance between it and the adjacent solution to obtain the crowding distance Di. The calculation method is as follows: For each target, sort the individuals in ascending or descending order of the target value. For each individual, calculate the distance between it and its left and right neighbors. Individuals with farther distances will have a larger crowding distance. The crowding distance Di of each individual is obtained as a key factor in diversity assessment. Based on the wind-solar heat balance sorting results and crowding distance data, the following formula is used for diversity assessment: Where D total is the diversity evaluation result, α is the influence coefficient of adjusting the diversity metric of the target space on the total diversity evaluation, β is the influence coefficient of adjusting the physical space sample distance metric of the target space on the total diversity evaluation, D is the diversity metric of the population in the target space, dist(s i ,s j ) is the wind and solar thermal balance sample s i and s j The physical distance between i For the first wind-solar heat balance sample, s j This is the second wind-solar-heat balance sample. The physical distance between each sample and other samples is calculated, and the crowding distance is used to enhance the evaluation. The diversity of the target space is weighted and added to the distance in the physical space to obtain the diversity evaluation results of the target parameters for the solar-heat balance. Based on the diversity evaluation results, the target parameters for the solar-heat balance are dynamically adjusted. By adjusting the sample distances between the target space and the physical space, excessive concentration or duplication of solutions can be effectively avoided, maintaining the diversity of the solution space.

[0132] Preferably, step S4 includes the following steps:

[0133] Step S41: performing climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort and light environment impact curve to generate sensitivity analysis results;

[0134] Step S42: performing climate zone testing on the retractable roof morphology data based on the sensitivity analysis results to generate applicable scope assessment data;

[0135] Step S43: Dynamically control and adjust the opening ratio through the applicable scope evaluation data to perform the wind, light and heat balance optimization operation of the retractable roof sports building.

[0136] In an embodiment of the present invention, different climate zones (such as tropical, temperate, and frigid zones) are defined based on climatological data. The characteristics of each climate zone include environmental factors such as temperature, humidity, wind speed, and sunshine. Meteorological data for each climate zone is collected and used as the basic data source for analysis. A roof opening / closing ratio-ventilation-thermal comfort and light environment impact curve demonstrates the impact of roof configuration on indoor thermal comfort, particularly ventilation and lighting efficiency under different climate conditions. Sensitivity analysis methods (such as local sensitivity analysis or global sensitivity analysis) are used to assess the extent to which climate change affects the thermal comfort and light environment impact curve. The sensitivity analysis results are generated by focusing on the impact of opening ratio, roof material, ventilation design, and other factors on comfort. By quantifying the changes in thermal comfort in each climate zone, they provide a basis for optimizing roof structures for each climate zone. Repeated experiments are conducted across different climate zones to analyze the changes in the roof-ventilation-thermal comfort and light environment impact curve under various climate conditions. Statistical methods are used to calculate the volatility of the curve and assess its stability and sensitivity. Based on the sensitivity analysis results obtained in S41, a test plan for roof structures in different climate zones is developed, covering multiple parameters such as the opening ratio. By constructing typical test cases for different climate zones, the ventilation and lighting performance of the roof under different climate conditions is simulated. A three-dimensional model of the retractable roof is built on the numerical simulation platform, and wind-solar heat balance calculations are performed under different climate conditions to generate suitability data for the roof form. Actual simulations are conducted to obtain performance indicators such as ventilation, lighting, and thermal comfort for the retractable roof in different climate zones. Key factors considered include thermal comfort index (such as the PMV index), ventilation rate, and lighting efficiency. Comprehensive analysis of the test results from different climate zones generates applicability assessment data to evaluate the applicability of the retractable roof structure in different climate zones. This data includes the performance of the retractable roof in terms of thermal comfort, energy efficiency, and ventilation under specific climate conditions. Based on the applicability assessment data generated in S42, a dynamic control strategy is developed. The opening ratio of the retractable roof is adjusted to optimize ventilation, lighting, and thermal comfort for each climate zone and different thermal comfort requirements. The opening ratio can be adjusted dynamically based on real-time climate data, for example, increasing the opening ratio in hot weather to enhance ventilation and decreasing it in cold weather to reduce heat loss. Using control theory and optimization algorithms (such as PID control and fuzzy control), the roof opening ratio is dynamically adjusted based on external environmental conditions (such as temperature, humidity, and wind speed). Based on the needs of different climate zones, dynamic control schemes tailored to different seasons and weather conditions are developed to ensure the optimal wind, solar, and heat balance of the roof under various environmental conditions. Implementing dynamic control systems in actual buildings collects real-time climate and indoor environmental data, adjusts the opening ratio of the retractable roof, and optimizes the wind, solar, and heat balance inside and outside the building.

[0137] Preferably, step S42 includes the following steps:

[0138] Step S421: Identify key parameters of the retractable roof morphology data based on the sensitivity analysis results, thereby obtaining sensitive parameter data; perform dynamic response analysis on the sensitive parameter data, thereby obtaining response characteristic data;

[0139] Step S422: performing climate zoning mapping on the retractable roof morphology data based on the response characteristic data, thereby obtaining zoning data; performing climate element simulation on the retractable roof morphology data based on the zoning data, thereby obtaining climate simulation data;

[0140] Step S423: Performing a performance test on the retractable roof morphology data based on the climate simulation data to obtain test data; performing an environmental adaptability range analysis on the retractable roof morphology data using the test data, thereby generating applicable range assessment data.

[0141] In this embodiment of the present invention, based on the sensitivity analysis results of step S41, key parameters affecting the solar and thermal balance of a retractable roof in different climate zones are determined. These parameters include opening ratio, roof material, wind speed, solar radiation intensity, and indoor temperature. Sensitivity analysis methods (such as local sensitivity analysis and global sensitivity analysis) are used to assess the sensitivity of each parameter and identify the key parameters that have the greatest impact on roof performance. Dynamic response analysis is performed on these sensitive parameter data to simulate the dynamic response of the retractable roof under different climate conditions. Dynamic simulation analyzes the response characteristics of the retractable roof, such as the response of the roof ventilation rate to changes in the opening ratio and the impact of changes in material thermal conductivity on indoor temperature. Response characteristic data is generated, such as the changing trends of roof ventilation efficiency and thermal comfort under different wind speeds and opening ratios. Based on the characteristics of different climate zones, the retractable roof morphology data is mapped to corresponding climate zones. The characteristics of each climate zone, such as temperature, humidity, precipitation, and wind speed, will have different impacts on the roof's ventilation efficiency and thermal comfort. The key parameters of the retractable roof are combined with the characteristics of the climate zones to generate climate zoning mapping data. Data for each zone should include the region's climate factors, wind speed, lighting requirements, temperature and humidity conditions, and other factors. Based on the climate zone mapping data, climate factor simulations are conducted, using climate simulation tools to simulate the performance of roof structures in different climate zones. The simulations include the impact of factors such as wind speed, solar radiation, and air humidity under different climate conditions. The generated climate simulation data will reveal how retractable roofs respond to these factors in different climates, helping to better understand the compatibility of roof designs with these climates. Using this climate simulation data, various performance tests are conducted on retractable roofs, including thermal comfort, ventilation efficiency, and daylighting. Numerical simulations and wind tunnel tests are used to test the actual performance of the roofs under different climate conditions. For example, in a simulated tropical climate, the relationship between the roof opening ratio and ventilation efficiency is tested; in cold climates, the impact of the thermal conductivity of the roof material on thermal comfort is tested. Based on the test results, an environmental adaptability range analysis is conducted to assess the adaptability of the retractable roofs under different climate conditions. For example, we can analyze whether the ventilation and lighting efficiency of retractable roofs in temperate climates are sufficient, and whether the thermal comfort in cold climates meets the requirements, and generate scope of application assessment data. This will provide guidance for the design of retractable roofs, determine their scope of use in different climate zones, and help select the most appropriate design solution.

[0142] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0143] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing the light and heat balance of a retractable roof sports building based on a generative adversarial network and a genetic algorithm, characterized by: The following steps are involved: Step S1: Obtaining the shape data of the retractable roof; Perform parametric modeling on the retractable roof morphology data to generate a two-dimensional grayscale image of the retractable roof; Conduct fluid dynamics and solar thermal environment simulations on the sports building space covered by the retractable roof to obtain wind, solar and thermal environment simulation data for the space covered by the retractable roof; Step S2: Pairing the two-dimensional grayscale image of the retractable roof with the wind, solar, and thermal environment simulation data to obtain an input-output image pair; using a generative adversarial network to predict the wind speed distribution of the input-output image pair to generate a predicted value of the spatial wind speed distribution of the retractable roof; Constructing a wind-light-heat environment gene library based on the predicted value of the spatial wind speed distribution and the light-heat environment simulation data; Step S3: Acquire environmental demand data for large sports spaces; set wind, solar, and thermal environment balance targets for the retractable roof space based on the environmental demand data for the large sports space, and obtain wind, solar, and thermal balance target parameters; iteratively optimize the wind, solar, and thermal balance target parameters using a genetic algorithm based on the wind-solar-thermal environment gene library to generate a Pareto optimal solution for the retractable roof morphological parameters under typical meteorological conditions; perform a regression analysis on the opening ratio of the roof morphological parameters based on the Pareto optimal solution and the corresponding indoor environment to generate a roof opening and closing ratio-ventilation, thermal comfort, and light environment impact curve; Step S4: Conduct climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort light environment impact curve to generate sensitivity analysis results; dynamically adjust the opening ratio of the retractable roof based on the sensitivity analysis results to perform wind, light and heat balance optimization and control operations for the retractable roof sports building.

2. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire the shape data of the retractable roof; Step S12: performing parametric modeling on the retractable roof morphological data, defining the dynamic adjustment range of the roof opening and closing direction and the opening ratio, and obtaining a retractable roof geometric model; Step S13: converting the retractable roof geometric model into a grayscale image to generate a two-dimensional grayscale image of the retractable roof; Step S14: extracting the roof shape of the retractable roof from the two-dimensional grayscale image, and using simulation software to perform CFD simulation and light and heat environment simulation on the building space below the retractable roof, calculating the indoor and outdoor wind speed distribution and thermal comfort index, and obtaining indoor and outdoor wind speed distribution data and thermal comfort index data; Step S15: performing daylight analysis on the building space below the retractable roof to generate daylight coefficient distribution data; converting the indoor and outdoor wind speed distribution data, daylight coefficient distribution data, and thermal comfort index data into graphs to generate a wind speed distribution map, a daylight coefficient distribution map, and a thermal comfort index heat map; Step S16: Integrate the wind speed distribution map, the daylight coefficient distribution map, and the thermal comfort index thermodynamic map into wind, light, and thermal environment simulation data of the space covered by the retractable roof.

3. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 2 is characterized in that: The daylight analysis of the building space below the retractable roof includes: Extract the daylighting area of ​​the building space under the retractable roof to obtain an image of the daylighting area of ​​the space under the retractable roof; calculate the solar altitude angle and azimuth angle of the daylighting area image of the space under the retractable roof to obtain the solar altitude angle and solar azimuth angle; Based on the solar altitude angle and solar azimuth angle, light propagation simulation is performed on the daylighting area of ​​the retractable roof to generate sunlight propagation path simulation data. The illumination intensity of each pixel in the daylighting area image of the space below the retractable roof is calculated based on the sunlight propagation path simulation data to obtain a local sunlight intensity map. The local sunlight intensity map is used to calculate the actual illumination area ratio of the lighting area image under the retractable roof to obtain the daylighting coefficient.

4. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Pairing the two-dimensional grayscale image of the retractable roof and the wind speed distribution map of the space below the roof to obtain an input-output image pair; dividing the input-output image pair into a data set to generate a model training set, a model test set, and a model validation set; Step S22: Constructing a Pix2Pix network framework; inputting the model training set, model test set, and model validation set into the Pix2Pix network framework for training, testing, and validation to obtain a Pix2Pix algorithm model; inputting a preset two-dimensional image of the retractable roof design into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, thereby generating a predicted indoor wind speed map of the space under the retractable roof; Step S23: performing a numerical matrix conversion on the indoor predicted wind speed map of the space below the retractable roof to obtain a predicted value of the spatial wind speed distribution of the retractable roof, and extracting the average wind speed value of the key area of ​​the sports building based on the predicted value of the spatial wind speed distribution of the retractable roof to obtain the average wind speed value of the key area; Step S24: Parameter association is performed on the opening ratio of the retractable roof according to the average wind speed value in the key area, and a gene library is constructed using the associated parameters and the light-heat environment simulation data to obtain a wind-light-heat environment gene library.

5. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 4 is characterized in that: Step S22 includes: Build a Pix2Pix network framework, which includes a generator and a discriminator; Set the training parameters for the Pix2Pix network framework and generate training parameter setting values, where the training parameter settings include learning rate settings, number of convolutional layers settings, epoch settings, and optimizer settings; The model training set is input into the Pix2Pix network framework, and the generator in the Pix2Pix network framework is used to predict wind speeds and generate an initial predicted wind speed map for retractable roofs. The model test set is then used to compare the initial predicted wind speed map with the actual result image through the discriminator in the Pix2Pix network framework. The structural similarity and root mean square error of the initial retractable roof prediction wind speed map are calculated to obtain the accuracy of the wind speed prediction map. The wind speed prediction map accuracy is then converged using the model validation set to obtain the Pix2Pix algorithm model. The preset two-dimensional image of the retractable roof design is input into the Pix2Pix algorithm model to predict the indoor wind speed of the space under the roof, and a predicted indoor wind speed map of the space under the retractable roof is generated.

6. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Acquire the environmental demand data of the large sports space; set the wind, solar and heat balance target for the retractable roof space according to the environmental demand data of the large sports space, and obtain the wind, solar and heat balance target parameters; Step S32: performing a diversity assessment on the wind-solar heat balance target parameters using the NSGA-III algorithm, and dynamically adjusting the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters; Step S33: Based on the wind-solar-thermal environment gene library, the wind-solar-thermal balance target parameters are iteratively optimized using the NSGA-III algorithm, and extreme solutions are eliminated to generate a Pareto optimal solution. Step S34: Based on the opening ratio of the roof morphological parameter change of the Pareto optimal solution, a multivariate linear regression equation is established for different opening ratios of the opening and closing roof and the corresponding indoor environment performance, and the roof opening and closing ratio-ventilation impact curve, the roof opening and closing ratio-natural lighting impact curve, and the roof opening and closing ratio-thermal comfort impact curve are generated respectively, and are unified into a roof opening and closing ratio-ventilation thermal comfort and light environment impact curve.

7. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 6 is characterized in that: Step S31 includes: Obtain data on the environmental requirements of large sports spaces; Optimization objectives are defined based on the environmental demand data of large sports spaces, including maximizing the daylight factor, maximizing the natural ventilation rate, and minimizing the thermal comfort index; Decision variable constraints are set for maximizing the daylight coefficient, maximizing the natural ventilation speed, and minimizing the thermal comfort index, and limiting the spatial three-dimensional coefficient of the opening ratio; Based on the optimization objectives and decision variables, the predicted values ​​of wind speed distribution of retractable roof are combined to obtain the target parameters of wind-solar heat balance.

8. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 6 is characterized in that: Step S32 includes the following steps: Step S321: setting the population size, crossover rate, and mutation rate of the NSGA-III algorithm, and performing non-dominated sorting on the wind-solar-heat balance target parameters according to the population size, crossover rate, and mutation rate to obtain a wind-solar-heat balance sorting result; Step S322: Calculate the congestion distance of the wind-solar-heat balance sorting results to obtain wind-solar-heat balance sample distance data; Step S323: Perform a diversity assessment on the wind-solar heat balance target parameters using the wind-solar heat balance sorting results and the wind-solar heat balance sample distance data, and dynamically adjust the wind-solar heat balance target parameters based on the diversity assessment results to generate wind-solar heat balance target adjustment parameters. The diversity assessment formula is as follows: Where D total is the diversity evaluation result, α is the influence coefficient of adjusting the diversity metric of the target space on the total diversity evaluation, β is the influence coefficient of adjusting the physical space sample distance metric of the target space on the total diversity evaluation, D is the diversity metric of the population in the target space, s i For the first wind-solar heat balance sample, s j For the second wind-solar heat balance sample, dist(s i ,s j ) is s i and s j The physical distance between them, N is the number of samples.

9. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing climate zone sensitivity analysis on the roof opening and closing ratio-ventilation thermal comfort and light environment impact curve to generate sensitivity analysis results; Step S42: performing climate zone testing on the retractable roof morphology data based on the sensitivity analysis results to generate applicable scope assessment data; Step S43: Dynamically control and adjust the opening ratio through the applicable scope evaluation data to perform the wind, light and heat balance optimization operation of the retractable roof sports building.

10. The light and heat balance optimization method for retractable roof sports buildings based on generative adversarial networks and genetic algorithms according to claim 9 is characterized in that: Step S42 includes the following steps: Step S421: Identify key parameters of the retractable roof morphology data based on the sensitivity analysis results, thereby obtaining sensitive parameter data; perform dynamic response analysis on the sensitive parameter data, thereby obtaining response characteristic data; Step S422: performing climate zoning mapping on the retractable roof morphology data based on the response characteristic data, thereby obtaining zoning data; performing climate element simulation on the retractable roof morphology data based on the zoning data, thereby obtaining climate simulation data; Step S423: Performing a performance test on the retractable roof morphology data based on the climate simulation data to obtain test data; performing an environmental adaptability range analysis on the retractable roof morphology data using the test data, thereby generating applicable range assessment data.

Images