基于物理风洞与神经网络算法的建筑群体形态生成设计方法研究
|
摘要
近年来,随着我国城市高层、高密度建筑群的发展,城市通风、热岛效应、空气污染以及行人热舒适度等已经成为研究城市高层建筑群体设计的重要课题。同时,环境性能化模拟与实验工具的不断发展,针对城市风环境影响进行初期概念设计决策的作用愈加凸显。本文首先介绍了以物理风洞为模拟工具的实验平台,包括数据采集、性能可视化设计方法探索;然后开发了一套针对高密度城市高层建筑群体的机械生形装置,打通建筑几何生成与城市风环境数据参数的关联;在此基础上,提出了一种将神经网络算法应用于高层建筑群场景的建筑几何生成设计优化算法。由此,实现城市设计导向的、基于城市高密度风环境性能化的、高层建筑形体预测与生成方法研究。
In recent years, with the rapid development of urban high-rise and high-density buildings in China, urban ventilation, heat island effect, air pollution and thermal comfort at pedestrian level is becoming an important topic in the study of high-density and high-rise urban design. Since the environmental assessment in the design stage can have a direct and significant impact on the final quality of the city, it is particularly important to rethink the relationship between architectural form and urban micro climate, especially the internal logic between urbanmorphology and natural ventilation, and to explore the design method driven by wind environment optimization in the early design stage. Therefore, with the continuous development of environmental performance simulation and experimental tools, the past "trial-and-error"passive design method is gradually replaced by logical generation design, and the role of early conceptual design decision-making for urban wind environment impact is becoming increasingly prominent. However, at present, a large number of performance simulation tools are subject to the tradeoff between simulation accuracy and time consumption, which makes it difficult to bring timely feedback in the early stage of design. In fact, the iterative generation method based on digital simulation tools only chooses the best among the limited random solutions, not from the environmental performance to the inverse solution of the scheme form. This "post-evaluation" paradigm cannot really satisfy the architect's comprehensive requirements for the environmental performance design.Firstly, this paper introduces the experimental platform using physical wind tunnel as simulation tool, including data acquisition and performance visualization design method exploration. It has the advantages of easy operation, controllable cost, and stable flow field and so on, guided by the initial shape generation design of the scheme. Its perception and real-time acquisition of environmental data make the wind environment simulation change from the postdesign verification to the front-end design exploration.After that, this study summarizes several commonly appliedurban morphologydesign strategies for wind environment performance optimization of high-rise buildings in high-density cities, including rotation, twisting, concaveconvex, hollowing, lifting-up, and develops a set of dynamic model devices for high-rise buildingsfor physical wind tunnel test. In the experiment of urban morphology generation in physical wind tunnel, firstly, the method of optimizing the layout of ventilated buildings is adopted, and then the angle between building orientation and wind direction is determined by wind tunnel experiment under the condition that the building layout is initially determined by sunshine. Finally, the specific form is determined to achieve the optimal control of the overall wind environment of the block. The dynamic model controls the parameters of different servos directly by the program, and uses the servos and gears to drive each building model to move. It constantly changes the orientation and shape of the building, including the size of the hollow facade, the external shape of distortion or indentation, and the height of the overhead. The dynamic model has the possibility of generating a large number of different morphology data instantaneously, which meets the needs of machine learning for massive sample data, and opens up the relationship between building geometry generation and urban wind environment data.On this basis, an optimization algorithm of building geometry generation and design based on neural network algorithm is proposed in this paper. The generation system based on neural network includes four parts: morphology optimization strategy, mechanical dynamic system, simulation evaluation system and intelligent prediction system. The parameter logic can be described as the data circulation process of "geometric parameter group-mechanical parameter group-environmental parameter group". In this study, the twisting form in high-rise buildings are selected for wind tunnel experiments under different plane and elevation strategies, and the mechanical parameters of each morphology scheme and the corresponding environmental data obtained from experiments are taken as sample data to construct a neural network regression model to predict the optimal morphology of twisted buildings under the control of various wind environment independently.Thus, this paper presents a design-oriented, performance-based, high-rise building group morphology generation, prediction and optimization design method based on natural wind environment in high-density urban districts. The application of physical wind tunnel is trying to solving the problems of complex operation and feedback timeconsumption of using CFD(computational fluid dynamics) software. The introduction of dynamic model makes it possible to obtain a large number of entity building models in a short time. The combination of neural network algorithm maximizes the application of wind tunnel test data to realize the direct conversion of design-oriented from environmental performance to architectural geometry. It has found that, in the early stage of urban design, the optimal control of urban form according to the wind environment can be realized, which may avoid the economic and resource losses caused by the repeating modified design based on the local wind environment criteria and pedestrians' requirement in the later adjustment stage of design, which overturns the "post-evaluation" mode of environmental performance of contemporary architectural design.
In recent years, with the rapid development of urban high-rise and high-density buildings in China, urban ventilation, heat island effect, air pollution and thermal comfort at pedestrian level is becoming an important topic in the study of high-density and high-rise urban design. Since the environmental assessment in the design stage can have a direct and significant impact on the final quality of the city, it is particularly important to rethink the relationship between architectural form and urban micro climate, especially the internal logic between urbanmorphology and natural ventilation, and to explore the design method driven by wind environment optimization in the early design stage. Therefore, with the continuous development of environmental performance simulation and experimental tools, the past "trial-and-error"passive design method is gradually replaced by logical generation design, and the role of early conceptual design decision-making for urban wind environment impact is becoming increasingly prominent. However, at present, a large number of performance simulation tools are subject to the tradeoff between simulation accuracy and time consumption, which makes it difficult to bring timely feedback in the early stage of design. In fact, the iterative generation method based on digital simulation tools only chooses the best among the limited random solutions, not from the environmental performance to the inverse solution of the scheme form. This "post-evaluation" paradigm cannot really satisfy the architect's comprehensive requirements for the environmental performance design.Firstly, this paper introduces the experimental platform using physical wind tunnel as simulation tool, including data acquisition and performance visualization design method exploration. It has the advantages of easy operation, controllable cost, and stable flow field and so on, guided by the initial shape generation design of the scheme. Its perception and real-time acquisition of environmental data make the wind environment simulation change from the postdesign verification to the front-end design exploration.After that, this study summarizes several commonly appliedurban morphologydesign strategies for wind environment performance optimization of high-rise buildings in high-density cities, including rotation, twisting, concaveconvex, hollowing, lifting-up, and develops a set of dynamic model devices for high-rise buildingsfor physical wind tunnel test. In the experiment of urban morphology generation in physical wind tunnel, firstly, the method of optimizing the layout of ventilated buildings is adopted, and then the angle between building orientation and wind direction is determined by wind tunnel experiment under the condition that the building layout is initially determined by sunshine. Finally, the specific form is determined to achieve the optimal control of the overall wind environment of the block. The dynamic model controls the parameters of different servos directly by the program, and uses the servos and gears to drive each building model to move. It constantly changes the orientation and shape of the building, including the size of the hollow facade, the external shape of distortion or indentation, and the height of the overhead. The dynamic model has the possibility of generating a large number of different morphology data instantaneously, which meets the needs of machine learning for massive sample data, and opens up the relationship between building geometry generation and urban wind environment data.On this basis, an optimization algorithm of building geometry generation and design based on neural network algorithm is proposed in this paper. The generation system based on neural network includes four parts: morphology optimization strategy, mechanical dynamic system, simulation evaluation system and intelligent prediction system. The parameter logic can be described as the data circulation process of "geometric parameter group-mechanical parameter group-environmental parameter group". In this study, the twisting form in high-rise buildings are selected for wind tunnel experiments under different plane and elevation strategies, and the mechanical parameters of each morphology scheme and the corresponding environmental data obtained from experiments are taken as sample data to construct a neural network regression model to predict the optimal morphology of twisted buildings under the control of various wind environment independently.Thus, this paper presents a design-oriented, performance-based, high-rise building group morphology generation, prediction and optimization design method based on natural wind environment in high-density urban districts. The application of physical wind tunnel is trying to solving the problems of complex operation and feedback timeconsumption of using CFD(computational fluid dynamics) software. The introduction of dynamic model makes it possible to obtain a large number of entity building models in a short time. The combination of neural network algorithm maximizes the application of wind tunnel test data to realize the direct conversion of design-oriented from environmental performance to architectural geometry. It has found that, in the early stage of urban design, the optimal control of urban form according to the wind environment can be realized, which may avoid the economic and resource losses caused by the repeating modified design based on the local wind environment criteria and pedestrians' requirement in the later adjustment stage of design, which overturns the "post-evaluation" mode of environmental performance of contemporary architectural design.
引文
[1]冒亚龙.高层建筑美学价值研究[D].重庆:重庆大学,2006.MAO Y L. Study on aesthetics value of high-rise buildings[D]. Chongqing:Chongqing University, 2006.
[2]石邢,李艳霞.面向城市设计的行人高度城市风环境评价准则与方法[J].西部人居环境学刊,2015, 30(5):22-27.SHI X, LI Y X. Evaluation Criteria and Methodology for Pedestrian-Level Wind Environment in Urban Design[J]. Journal of Human Settlements in West China,2015, 30(5):22-27.
[3] MORRIS I. The measure of civilization:how social development decides the fate of nations[M]. New Jersey:Princeton University Press, 2013.
[4]袁烽,柴华.数字孪生关于2017年上海“数字未来”活动“可视化”与“物质化”主题的讨论[J].时代建筑,2018(1):17-23.YUAN F, CHAI H. Digital Twin On Visualization and Materialization of Digital FUTURE Shanghai 2017[J]. Time Architecture, 2018(1):17-23.
[5] LICKLIDER J C. Man-computer symbiosis[J]. IRE transactions on human factors in electronics, 1960(1):4-11.
[6] LINDINGER H. Ulm design:the morality of objects:Hochschule fur Gestaltung Ulm 1953-1968[M]. Cambridge:MIT Press, 1991.
[7] MARSH A. Generative and performative design:a challenging new role for modern architects[C]//The Oxford conference2008, 2008.
[8] LOHR S. The age of big data[J]. New York Times, 2012, 11.
[9]李麟学,叶心成,王轶群.环境智能建筑[J].时代建筑,2018(1):56-61.LI L X, YE X C, WANG Y Q. Environmental Intelligent Architecture[J]. TimeArchitecture, 2018(1):56-61.
[10] BEHLING S, BEHLING S,SCHINDLER B. Solar power:the evolution of sustainable architecture[M].Munich:Prestel, 2000.
[11] INAKI A,RENATA S,LLUIS O. Abalos+sentkiewicz:Essays on Thermodynamics[M]. Architecture and Beauty, 2015.
[12] LYNN G, KELLY T. Animate form[M].New York:Princeton Architectural Press, 1999.
[13]彭博.深度卷积网络原理与实践[M].北京:机械工业出版社,2018.PENG B. Deep Convolutional Neural Network Principle Practice[M]. Beijing:China Machine Press, 2018.
[14]袁烽.从图解思维到数字建造[M].上海:同济大学出版社,2016.YUAN F. From Diagrammatic Thinking to Digital Fabrication[M]. Shanghai:Tongji University Press, 2016.
[15] NABONI E. Environmental Simulation Tools in Architectural Practice[C].Munich:PLEA, 2013.
[16] KAIJIMA S,BOUFFANAIS R,WILLCOX K, et al. Computational Fluid Dynamics for Architectural Design[J].Architectural Design,2013, 83(2):118-123.
[17] GANE V, HAYMAKER J. Benchmarking current conceptual high-rise design processes[J]. Journal of Architectural Engineering, 2009, 16(3):100-111.
[18] LIN Y J Z,YAO J,YUAN P F. Research On Physical Wind Tunnel And Dynamic Model Based Building Morphology Generation Method[C]//CAADRIA,2018:165-174.
[19]郭芳.Geco在参数化建筑节能设计中的应用——以哈萨克斯坦阿斯塔纳国家图书馆窗洞设计为例[J].城市建筑,2013(6):222.GUO F. The Application of Geco in the Design of Parametric Building Energysaving—Case Study of the National Library of Kazakhstan Astana[J]. Urbanism andArchitecture, 2013(6):222.
[20]高菲.高层住宅自动布局研究初探——以理想地块板式高层为例[J].中华民居(下旬刊),2014(5):197.GAO F. Preliminary Study on the Automatic Layout of High-rise Residential Buildings-Taking the Ideal Block-Type High-rises as an Example[J]. Zhonghua Minju, 2014(5):197.
[21]朱一宇.城市规划设计中风环境的评价方法研究[D].南京:东南大学,2014.ZHU Y Y. The study of assessment of urban wind environment in urban planning design[D]. Nanjing:Southeast University, 2014.
[22]林钰琼,姚佳伟,郑静云,等.基于风洞可视化的环境性能建筑生形方法研究[J].南方建筑,2018(2):24-29.LIN Y Q, YAO J W, ZHENG J Y, et al.Research on the Building Morphology Generation Method Based on the Wind Tunnel Visualization of Environmental Performance[J]. South Architecture,2018(2):24-29.
[23]王成刚,罗峰,王咏薇,等高密度建筑群及超高建筑物对风环境影响的风洞试验[J].大气科学学报,2016, 39(1):133-139.WANG C G, LUO F, WANG Y W, et al. Experimental study of the impact of high-density building clusters and highrise building on the wind environment[J].Transactions of Atmospheric Sciences,2016, 39(1):133-139.
[24]郑颖生.基于改善高层高密度城市区域风环境的高层建筑布局研究[D].杭州:浙江大学,2013.ZHENG Y S. Research on high-rise building layout based on improving wind environment in high-rise and highdensity urban areas[D]. Hangzhou:Zhejiang University, 2013.
[25]姚雪牙,冷红,孙青林.高层住区风环境优化策略研究[J].工业建筑,2013(s1):9-11.YAO X S,LENG H,SUN Q L. Study on Optimization Strategy Wind Environment of High-rise Settlements[J].Industrial Construction, 2013(S1):9-11.
[26]谢振宇,杨讷.改善室外风环境的高层建筑形态优化设计策略[J].建筑学报,2013(2):76-81.XIE Z Y, YANG N. Optimization Design Tactics for High-rise Building Shape on Improvement of Outdoor Wind Environment[J]. Architectural Journal,2013(2):76-81.
[27]郭飞,李沛雨.基于风环境的建筑形态生成策略[J].住宅产业,2016(7):41-45.GUO F, LI F Y. Building morphology generation strategy based on wind environment[J]. Housing Industry,2016(7):41-45.
[28]周宇舫,范凌.模型思维[C]. 2010年全国高等学校建筑院系建筑数字技术教学研讨会,2010.ZHOU Y F, FAN L. Model Thinking[C].Proceedings of 2010 National Conference on Architecture's Digital Technoloigies in Education&Research, 2010.
[29]尼尔·里奇,袁烽.建筑数字化编程[M].上海:同济大学出版社,2012.LEACH N, YUAN F. Scriping the Future[M]. Shanghai:Tongji University Press, 2012.
[30] CONWAY J. The game of life[J].Scientific American, 1970, 223(4):4.
[31]蔡凌豪,范凌,赖文波,等.设计视角下人工智能的定义、应用及影响[J].景观设计学,2018(2):58-65.CAIL H, FAN L, LAI W B, et al.Definition, Application and Influence of Artificial Intelligence on Design Industries[J]. Landscape Architecture Frontiers, 2018(2):58-65.
[32] MAXWELL I, PIGRAM D. Algorithmic Typology:Towards an Operational Model,Scripting the Futures[D]. Shanghai:Tongji University Press, 2012:107-112.
[33] LIN Y, YAO J, ZHENG J, et al. Environmental-Performance Morphology Generation:Combining Physical Wind Tunnel and Dynamic Building Model[C]//Advances inArchitectural Geometry 2018:174-194.
[34] LEACH N. The Informational City[J]. Next Generation Building, 2015,2(1):181-196.
[35] RUMELHART D, MCCLELLAND J.Explorations in the Microstructure of Cognition(Volume 1:Foundations)[M].Cambridge:MIT press, 1988.
[36]周志华.机器学习[M].北京:清华大学出版社,2016:97-117.ZHOU Z H. Machine Learning[M]. Beijing:Tsinghua University Press, 2016:97-117.
[37] REN Z M, ZENG A, ZHANG Y C.Structure-oriented prediction in complex networks[J]. Physics Reports, 2018(750):1-51.
[38] MORFIDIS K, KOSTINAKIS K.Approaches to the rapid seismic damage prediction of r/c buildings using artificial neural networks[J]. Engineering Structures, 2018(165):120-141.
[39]林钰琼,姚佳伟,黄辰宇,等.浅层神经网络在环境性能化建筑自生形方法中的应用初探[C]//全国建筑院系建筑数字技术教学与研究学术研讨会组委会,长安大学建筑学院.数字技术·建筑全生命周期——2018年全国建筑院系建筑数字技术教学与研究学术研讨会论文集.北京:中国建筑工业出版社.2018:143-149.LIN Y Q, YAO J W, HUANG C Y, et al.[C]//Digital Technology·Building LifeCycle-Proceedings of 2018 National Conference on Architecture's Digital Technoloigies in Education&Research.Beijing:China Architecture&Building Press. 2018:143-149.
[2]石邢,李艳霞.面向城市设计的行人高度城市风环境评价准则与方法[J].西部人居环境学刊,2015, 30(5):22-27.SHI X, LI Y X. Evaluation Criteria and Methodology for Pedestrian-Level Wind Environment in Urban Design[J]. Journal of Human Settlements in West China,2015, 30(5):22-27.
[3] MORRIS I. The measure of civilization:how social development decides the fate of nations[M]. New Jersey:Princeton University Press, 2013.
[4]袁烽,柴华.数字孪生关于2017年上海“数字未来”活动“可视化”与“物质化”主题的讨论[J].时代建筑,2018(1):17-23.YUAN F, CHAI H. Digital Twin On Visualization and Materialization of Digital FUTURE Shanghai 2017[J]. Time Architecture, 2018(1):17-23.
[5] LICKLIDER J C. Man-computer symbiosis[J]. IRE transactions on human factors in electronics, 1960(1):4-11.
[6] LINDINGER H. Ulm design:the morality of objects:Hochschule fur Gestaltung Ulm 1953-1968[M]. Cambridge:MIT Press, 1991.
[7] MARSH A. Generative and performative design:a challenging new role for modern architects[C]//The Oxford conference2008, 2008.
[8] LOHR S. The age of big data[J]. New York Times, 2012, 11.
[9]李麟学,叶心成,王轶群.环境智能建筑[J].时代建筑,2018(1):56-61.LI L X, YE X C, WANG Y Q. Environmental Intelligent Architecture[J]. TimeArchitecture, 2018(1):56-61.
[10] BEHLING S, BEHLING S,SCHINDLER B. Solar power:the evolution of sustainable architecture[M].Munich:Prestel, 2000.
[11] INAKI A,RENATA S,LLUIS O. Abalos+sentkiewicz:Essays on Thermodynamics[M]. Architecture and Beauty, 2015.
[12] LYNN G, KELLY T. Animate form[M].New York:Princeton Architectural Press, 1999.
[13]彭博.深度卷积网络原理与实践[M].北京:机械工业出版社,2018.PENG B. Deep Convolutional Neural Network Principle Practice[M]. Beijing:China Machine Press, 2018.
[14]袁烽.从图解思维到数字建造[M].上海:同济大学出版社,2016.YUAN F. From Diagrammatic Thinking to Digital Fabrication[M]. Shanghai:Tongji University Press, 2016.
[15] NABONI E. Environmental Simulation Tools in Architectural Practice[C].Munich:PLEA, 2013.
[16] KAIJIMA S,BOUFFANAIS R,WILLCOX K, et al. Computational Fluid Dynamics for Architectural Design[J].Architectural Design,2013, 83(2):118-123.
[17] GANE V, HAYMAKER J. Benchmarking current conceptual high-rise design processes[J]. Journal of Architectural Engineering, 2009, 16(3):100-111.
[18] LIN Y J Z,YAO J,YUAN P F. Research On Physical Wind Tunnel And Dynamic Model Based Building Morphology Generation Method[C]//CAADRIA,2018:165-174.
[19]郭芳.Geco在参数化建筑节能设计中的应用——以哈萨克斯坦阿斯塔纳国家图书馆窗洞设计为例[J].城市建筑,2013(6):222.GUO F. The Application of Geco in the Design of Parametric Building Energysaving—Case Study of the National Library of Kazakhstan Astana[J]. Urbanism andArchitecture, 2013(6):222.
[20]高菲.高层住宅自动布局研究初探——以理想地块板式高层为例[J].中华民居(下旬刊),2014(5):197.GAO F. Preliminary Study on the Automatic Layout of High-rise Residential Buildings-Taking the Ideal Block-Type High-rises as an Example[J]. Zhonghua Minju, 2014(5):197.
[21]朱一宇.城市规划设计中风环境的评价方法研究[D].南京:东南大学,2014.ZHU Y Y. The study of assessment of urban wind environment in urban planning design[D]. Nanjing:Southeast University, 2014.
[22]林钰琼,姚佳伟,郑静云,等.基于风洞可视化的环境性能建筑生形方法研究[J].南方建筑,2018(2):24-29.LIN Y Q, YAO J W, ZHENG J Y, et al.Research on the Building Morphology Generation Method Based on the Wind Tunnel Visualization of Environmental Performance[J]. South Architecture,2018(2):24-29.
[23]王成刚,罗峰,王咏薇,等高密度建筑群及超高建筑物对风环境影响的风洞试验[J].大气科学学报,2016, 39(1):133-139.WANG C G, LUO F, WANG Y W, et al. Experimental study of the impact of high-density building clusters and highrise building on the wind environment[J].Transactions of Atmospheric Sciences,2016, 39(1):133-139.
[24]郑颖生.基于改善高层高密度城市区域风环境的高层建筑布局研究[D].杭州:浙江大学,2013.ZHENG Y S. Research on high-rise building layout based on improving wind environment in high-rise and highdensity urban areas[D]. Hangzhou:Zhejiang University, 2013.
[25]姚雪牙,冷红,孙青林.高层住区风环境优化策略研究[J].工业建筑,2013(s1):9-11.YAO X S,LENG H,SUN Q L. Study on Optimization Strategy Wind Environment of High-rise Settlements[J].Industrial Construction, 2013(S1):9-11.
[26]谢振宇,杨讷.改善室外风环境的高层建筑形态优化设计策略[J].建筑学报,2013(2):76-81.XIE Z Y, YANG N. Optimization Design Tactics for High-rise Building Shape on Improvement of Outdoor Wind Environment[J]. Architectural Journal,2013(2):76-81.
[27]郭飞,李沛雨.基于风环境的建筑形态生成策略[J].住宅产业,2016(7):41-45.GUO F, LI F Y. Building morphology generation strategy based on wind environment[J]. Housing Industry,2016(7):41-45.
[28]周宇舫,范凌.模型思维[C]. 2010年全国高等学校建筑院系建筑数字技术教学研讨会,2010.ZHOU Y F, FAN L. Model Thinking[C].Proceedings of 2010 National Conference on Architecture's Digital Technoloigies in Education&Research, 2010.
[29]尼尔·里奇,袁烽.建筑数字化编程[M].上海:同济大学出版社,2012.LEACH N, YUAN F. Scriping the Future[M]. Shanghai:Tongji University Press, 2012.
[30] CONWAY J. The game of life[J].Scientific American, 1970, 223(4):4.
[31]蔡凌豪,范凌,赖文波,等.设计视角下人工智能的定义、应用及影响[J].景观设计学,2018(2):58-65.CAIL H, FAN L, LAI W B, et al.Definition, Application and Influence of Artificial Intelligence on Design Industries[J]. Landscape Architecture Frontiers, 2018(2):58-65.
[32] MAXWELL I, PIGRAM D. Algorithmic Typology:Towards an Operational Model,Scripting the Futures[D]. Shanghai:Tongji University Press, 2012:107-112.
[33] LIN Y, YAO J, ZHENG J, et al. Environmental-Performance Morphology Generation:Combining Physical Wind Tunnel and Dynamic Building Model[C]//Advances inArchitectural Geometry 2018:174-194.
[34] LEACH N. The Informational City[J]. Next Generation Building, 2015,2(1):181-196.
[35] RUMELHART D, MCCLELLAND J.Explorations in the Microstructure of Cognition(Volume 1:Foundations)[M].Cambridge:MIT press, 1988.
[36]周志华.机器学习[M].北京:清华大学出版社,2016:97-117.ZHOU Z H. Machine Learning[M]. Beijing:Tsinghua University Press, 2016:97-117.
[37] REN Z M, ZENG A, ZHANG Y C.Structure-oriented prediction in complex networks[J]. Physics Reports, 2018(750):1-51.
[38] MORFIDIS K, KOSTINAKIS K.Approaches to the rapid seismic damage prediction of r/c buildings using artificial neural networks[J]. Engineering Structures, 2018(165):120-141.
[39]林钰琼,姚佳伟,黄辰宇,等.浅层神经网络在环境性能化建筑自生形方法中的应用初探[C]//全国建筑院系建筑数字技术教学与研究学术研讨会组委会,长安大学建筑学院.数字技术·建筑全生命周期——2018年全国建筑院系建筑数字技术教学与研究学术研讨会论文集.北京:中国建筑工业出版社.2018:143-149.LIN Y Q, YAO J W, HUANG C Y, et al.[C]//Digital Technology·Building LifeCycle-Proceedings of 2018 National Conference on Architecture's Digital Technoloigies in Education&Research.Beijing:China Architecture&Building Press. 2018:143-149.