WO2022047959A1 - 一种提升风环境的人工智能城市设计形态布局方法 - Google Patents

一种提升风环境的人工智能城市设计形态布局方法 Download PDF

Info

Publication number
WO2022047959A1
WO2022047959A1 PCT/CN2020/124322 CN2020124322W WO2022047959A1 WO 2022047959 A1 WO2022047959 A1 WO 2022047959A1 CN 2020124322 W CN2020124322 W CN 2020124322W WO 2022047959 A1 WO2022047959 A1 WO 2022047959A1
Authority
WO
WIPO (PCT)
Prior art keywords
wind
urban
urban design
data
buildings
Prior art date
Application number
PCT/CN2020/124322
Other languages
English (en)
French (fr)
Inventor
杨俊宴
邵典
史北祥
朱骁
顾杰
Original Assignee
东南大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东南大学 filed Critical 东南大学
Priority to US17/611,004 priority Critical patent/US20220309201A1/en
Publication of WO2022047959A1 publication Critical patent/WO2022047959A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]

Definitions

  • the invention relates to the field of urban planning, in particular to an artificial intelligence urban design form layout method for improving wind environment.
  • Wind environment is one of the important research contents of urban planning, which refers to the affected wind field formed by outdoor natural wind under the influence of urban topography or natural topography.
  • Good urban wind environment quality can not only improve the indoor and outdoor comfort of urban residents, reduce the energy consumption of urban buildings for heating in winter and cooling in summer, but also timely release the pollution caused by automobile exhaust near the underlying surface of the city. caused air pollution.
  • the traditional urban form design does not consider the wind environment, so it is impossible to detect whether the wind speed standard requirements are met during the layout, and it is also impossible to adjust the local layout form according to the wind speed standard requirements.
  • the emergence of artificial intelligence provides a more scientific and efficient means of urban design. By constructing a wind farm interactive sand table, simulating the wind environment, and intelligently adjusting the urban form layout, the wind environment can be effectively improved.
  • One of the common ways to improve the urban wind environment is to improve the wind environment between buildings.
  • the simulation results are compared with the "Green Building Evaluation Standards", and the plane layout is selected based on the best.
  • This method does not consider the influence of surrounding buildings on the wind environment of the plot, the simulation error is very large, and it is only suitable for the improvement of the wind environment between two buildings, and cannot improve the wind environment of the entire block; Wind tunnel tests are simulated and adjusted.
  • This method consumes a lot of manpower and material resources. The adjustment is difficult, the error coefficient is large, the judgment is arbitrary, the process is inefficient, and the results are lacking in science.
  • the purpose of the present invention is to provide an artificial intelligence urban design form layout method for improving the wind environment.
  • the present invention can intelligently adjust the urban form layout for multi-scale urban blocks and judge that the adjustment scheme is feasible. sex.
  • An artificial intelligence urban design form layout method for improving wind environment comprising the following steps:
  • Step 1 Data acquisition
  • Step 2 Construction of wind farm interactive sand table
  • Input the data obtained in step 1 into the geographic information system platform, and perform simulation operations through the input of measured wind direction and speed to generate the cloud map and vector map of wind direction and speed distribution, which are superimposed with the urban three-dimensional spatial digital model to construct the wind farm interactive sand table.
  • Set the simulated wind direction and wind speed parameters construct a simulated environment for the urban wind field, and verify the simulated wind speed and direction data in the wind field at the point selected in step 1 with the measured data. Adjust the parameter values of domain height and initial grid size until the error is less than or equal to 3%;
  • Step 3 Wind field simulation and evaluation of urban design scheme
  • step 7 Put the urban design plan into the wind farm interactive sand table, extract the simulated wind speed data in the wind farm of the block where the design plan is located, and classify the wind environment impact according to the Beaufort Wind Scale. If the wind classification results are all 0-4 If the wind is between grades, skip to step 7, and if the wind grade reaches grade 5 or above in some areas, skip to step 4;
  • Step 4 Artificial Intelligence Adjustment of Urban Design Morphological Layout
  • the calculation formula of the function M is as follows:
  • the SUM is adjusted to the sum of the floor area occupied by the buildings in the block after the rearrangement, and the SUM was originally the sum of the floor area occupied by the buildings in the original block.
  • Step 5 Determination of urban design standards and specifications
  • Step 6 Wind field simulation and evaluation of the adjustment scheme
  • Step 7 Holographic display of wind environment improvement plan
  • the equipment includes a VR panoramic display stand equipped with a wind environment simulation system, an adjustable axial fan and 3D tracking glasses.
  • the three-dimensional spatial digital model of the city is generated by unifying the three-dimensional vector data of the city into the 2000 National Geodetic Coordinate System, including the urban geographic elevation, road network, building outline, building height, urban water system and urban mountain information. .
  • wind direction adjustment refers to the computer through the formula wind direction error Calculate the point wind direction error F 1 , F 2 , F 3 ??
  • the artificial intelligence algorithm in the step 4 adopts the Random algorithm to rearrange the buildings and adjust the urban form layout, which refers to the grid processing of the blocks, the size of each grid is 1m*1m, and the grid
  • the lattice is numbered from 1-n, creating set A, numbering the geometric centers of the bottom of the building X1-XN, creating set B, the buildings are distributed on the block through (a, b), where a ⁇ A, b ⁇ B,
  • the quantitative calculation of each index is carried out according to the local "Urban Design Standards and Guidelines", which refers to the translation of the urban design standard specification data into the urban design sand table index database, and the comparison with the plan index data in the sand table, and the "Urban Design Standards and Guidelines” refers to the "Urban Design Standards and Guidelines” promulgated by the city. If the city has not promulgated, the "Urban Design Standards and Guidelines" of the province where the city is located shall be used.
  • the present invention constructs a wind farm interactive sand table by combining wind speed simulation software with a geographic information platform. It breaks through the problem of large artificial adjustment error of traditional wind environment simulation parameter adjustment, and the control error is less than 3%; reduces the complexity of traditional wind environment simulation multiple software collaborative operation; simplifies the tedious process of wind environment operation.
  • the fourth step is to automatically optimize the urban design layout by combining the rasterized urban design plane with the Random algorithm.
  • the application of the Random algorithm to the field of urban form layout adjustment breaks through the expert judgment of traditional urban design layout, adds more options for feasible solutions, and makes the entire process more intelligent and automated.
  • the wind speed and direction data, urban three-dimensional vector data, urban design plan data and urban design standard specification data are entered into the geographic information system to construct the sand table, and the computer simulates the wind environment, combined with the actual measurement verification and feedback adjustment, to realize the real scene in the city.
  • the precise simulation of the wind environment in the design scheme improves the accuracy and efficiency of the wind environment simulation to the greatest extent;
  • the present invention overcomes the limitation of the traditional method of only targeting individual buildings without considering the layout of surrounding buildings, realizes the layout optimization of the design scheme and the improvement of the overall wind environment quality at the scale of the whole city, and effectively avoids the adjustment of individual buildings. Occurrence of reducing the quality of the surrounding wind environment;
  • the present invention combines the urban form layout adjustment method based on rasterized blocks and the Random algorithm with the wind environment impact assessment, through interactive feedback and round-by-round optimization, to ensure that no wind exceeding level 4 will occur in any area of the urban design plan. Case;
  • the present invention ensures the feasibility of the adjusted urban design scheme by performing quantitative calculation according to the local "Urban Design Standards and Guidelines";
  • the present invention simulates the wind environment for the urban design scheme, and automatically adjusts and selects the method and sand table, which avoids the problems of traditional wind environment improvement with large input of manpower and material resources, involving human brain judgment, large randomness and small scale.
  • the efficient and scientific, full-process automation, precise and intelligent adjustment of urban design scheme for the improvement of the urban wind environment at scale provides a reference approach for adjusting the layout of urban design schemes to improve the urban design wind environment;
  • the present invention makes the wind environment display visualized and perceptible through the 4D holographic projection platform, and improves the display effect.
  • Fig. 1 is the flow chart of the method of the present invention
  • Figure 2 is the "Beaufort Wind Scale"
  • Figure 3 shows the local regional wind environment effect of the original scheme
  • Figure 4 shows the local regional wind environment effect of the scheme after the layout shape adjustment.
  • An artificial intelligence urban design form layout method for improving wind environment includes the following steps:
  • Data acquisition Use a 32-channel wind direction anemometer with GPS positioning to randomly acquire the wind speed and wind direction data of the city where the original urban design plan is located. Obtain the three-dimensional vector data, urban design plan data, and urban design standard specification data of the city where the block is located from the local planning department.
  • the 32-channel wind direction anemometer with GPS positioning is used to record the wind speed and direction with specific location coordinates;
  • the random and fixed-point acquisition of the wind speed and wind direction data of the city where the original urban design plan is located refers to the time when the dominant wind direction or the unfavorable wind direction and the high frequency of gale are selected according to the meteorological statistics for measurement.
  • the measurement is carried out continuously, and the measurement should be recorded every 3-5 minutes.
  • the selected area is randomly selected, but should include the dominant wind direction area, the main activity area, the most unfavorable area and the area with special requirements, such as pollutant or heat source discharge area and ventilation openings.
  • the measurement height is 1.5m above the ground or movable platform.
  • the three-dimensional vector data includes all vector blocks and vector building blocks in the city
  • the vector block and vector building block data are polygon data with closed contours, and the vector block data includes road network data (road outline or road red line), elevation data (used to simulate terrain) and water body data; vector building blocks
  • the sand table is constructed by inputting the data obtained in step 1 into the geographic information system platform.
  • the construction of the urban wind field simulation environment refers to using the CFD wind environment simulation software as a plug-in to adapt to the geographic information system platform, and performing simulation operations on the input of the measured wind direction and speed to generate the wind direction and speed distribution cloud map and vector map and the urban three-dimensional vector data.
  • Field interactive sandbox refers to using the CFD wind environment simulation software as a plug-in to adapt to the geographic information system platform, and performing simulation operations on the input of the measured wind direction and speed to generate the wind direction and speed distribution cloud map and vector map and the urban three-dimensional vector data.
  • the verification of the wind speed and direction data simulated in the wind field at the selected point in step 1 and the actual measured data refers to inputting the randomly measured wind speed and direction data into the wind environment simulation module in the geographic information system, and then setting the simulated wind direction.
  • Wind speed parameters and wind environment simulation in the wind field interactive sand table generate a wind direction and wind speed attribute table, compare the measured wind direction and wind speed data, carry out error calculation, and then calculate the wind speed, wind direction, calculation domain height, initial grid according to the error coefficient of simulation and actual measurement.
  • the parameter value of size is adjusted until the error is ⁇ 3%. This operation is used to improve the accuracy and precision of sandbox wind environment simulation.
  • wind direction adjustment refers to the computer through the formula wind direction error Calculate the point wind direction error F 1 , F 2 , F 3 ?? F n , and then use the formula Calculate the average error and automatically correct the wind direction error by the computer; if some areas cannot be simulated, the computer automatically adjusts the height of the computational domain until it covers the entire range or reduces the initial grid by 10% each time until all the measured points can get the wind speed and direction. simulation.
  • Putting the urban design plan into the interactive sand table of the wind field refers to using the geographic information platform to add data functions to establish a connection with the vector block and vector building block data of the design plan, and using the projection operation to transform the data coordinates, including projection coordinates, Switch between geographic coordinates and conversion between different coordinate systems, adjust the city's three-dimensional vector data to the 2000 national geodetic coordinate system; use the Layer3DToFeatureClass operation, combined with building height information, to stretch the building to form a three-dimensional model, combined with elevation data and water bodies
  • the data generates 3D terrain and constructs 3D model of urban design scheme.
  • the extraction of the simulated wind speed data in the wind field of the block where the design scheme is located refers to obtaining the wind speed and direction of each geographic coordinate after simulating the wind environment, generating a wind speed and direction attribute table with location information, and a wind direction and wind speed distribution cloud map and vector diagram.
  • the evaluation of the impact on the wind environment according to the "Beaufort Wind Scale” refers to translating the “Beaufort Wind Scale” into a wind speed comfort attribute table, entering it into the interactive sand table of the wind farm, and being associated with the wind speed and direction attribute table and automatically. Judgment, if the evaluation results are all between 0-4 winds, the wind environment comfort standard is met, and skip to step 7. If the evaluation results in some areas exceed the range of 0-4 winds, the wind environment comfort standard is not met. The information system recognizes its coordinates, marks them in the 3D sand table, and jumps to step 4 at the same time.
  • the rasterization of the blocks refers to dividing the blocks into grids within 1m*1m through the polygon to raster command, so as to improve the accuracy of the scheme adjustment;
  • re-arranging buildings randomly to adjust the urban form layout means that the vertices of the grid are numbered from 1-n to create a set A; the geometric centers of the bottom of the building are numbered X1-XN to create a set B.
  • the random distribution of buildings on the block is represented by (a, b), where a ⁇ A, b ⁇ B.
  • Use the Random algorithm to randomly select and combine from sets A and B, respectively, to generate a list [(a1,b1), (a2,b2)...(an, bn)], where an ⁇ A,bn ⁇ B, will The list dataset is projected onto the block space to form an adjusted urban design morphological layout.
  • the geometric center point of the building is converted into the center point of each polygon by using the feature to point command in the geographic information platform, and the center point contains coordinate data.
  • the guaranteeing that the buildings do not overlap and that the buildings cannot exceed the boundary of the block refers to judging whether the sum of the grid numbers of the buildings in the blocks belonging to the adjustment plan is equal to the sum of the grid numbers of the buildings in the blocks of the original plan.
  • the function of the difference is equal to 0, and it is processed according to the following formula:
  • SUM is adjusted to the sum of the grid numbers of the building layout in the block of the adjustment scheme, and SUM is the sum of the grid numbers of the building layout in the block of the original scheme;
  • the sum of the building layout grid numbers in the block of the original scheme refers to generating a building data attribute table, and using SUM operation to obtain the sum of the building grid numbers;
  • the sum of the number of building layout grids in the block of the adjustment plan refers to obtaining all new building grid data by using the union of inputs command from all building grid data, and then combining the block grid data with the new building grid data.
  • the building uses the Intersect command to obtain the building grid in the block, generates the building data attribute table, and uses the SUM operation to obtain the sum of the building grid numbers.
  • the quantitative calculation of various indicators according to the local "Urban Design Standards and Guidelines” refers to the translation of building spacing and building setback standards into an urban design sand table index library, and the adjustment plan in the geographic information system generates building spacing and building setbacks.
  • the attribute table is associated with the index database, and the sand table automatically determines whether it meets the requirements.
  • the "Urban Design Standards and Guidelines” refers to the “Urban Design Standards and Guidelines” promulgated by the city. If the city has not been promulgated, the city's provincial Urban Design Standards and Guidelines;
  • step 6 Wind field simulation and evaluation of the adjustment scheme, put the scheme after the layout shape adjustment and meet the local "Urban Design Standards and Guidelines" into the wind field interactive sand table, extract the simulated wind speed data in the wind field of the block where the adjustment scheme is located, and Evaluate the impact of the wind environment against the "Beaufort Wind Scale". If the evaluation results in some areas exceed the range of 0-4 winds, repeat step 4 until the evaluation results are between 0-4 winds. The specific operation is the same as step three.
  • the equipment includes a VR panoramic display stand equipped with a wind environment simulation system, an adjustable axial fan and 3D tracking glasses.
  • the VR panoramic display stand and 3D tracking glasses equipped with the wind environment simulation system are used to display the urban three-dimensional space model with wind direction and wind speed distribution cloud map and vector diagram, and the adjustable axial flow fan is used to simulate the feeling of real wind. It constitutes a visible and perceptible holographic display module of the wind environment improvement scheme.
  • the CFD wind environment simulation software is used as a plug-in to adapt to the geographic information system platform, and the measured wind direction and speed input are simulated to generate the wind direction and wind speed distribution cloud map and vector map and the urban three-dimensional vector data superimposed to construct the wind farm interactive sand table.
  • Random algorithm uses the Random algorithm to randomly select and combine from sets A and B, respectively, to generate a list [(a1, b1), (a2, b2)...(an, bn)], where an ⁇ A, bn ⁇ B, will
  • the list dataset is projected onto the block space to form an adjusted urban design morphological layout.
  • SUM is adjusted to the sum of the grid numbers of the building layout in the block of the adjustment scheme, and SUM is the sum of the grid numbers of the building layout in the block of the original scheme;
  • the requirements for the red line of the road for building concessions are shown in Table 2; the requirements for the main railway line for construction concessions are not less than 20m, and the requirements for the branch railway lines for construction concessions are not less than 15m; the requirements for building concessions with revetments are not less than 5m, and the requirements for non-revetment rivers are not less than 10m.
  • Table 2 The requirements for the red line of the road for building concessions are shown in Table 2; the requirements for the main railway line for construction concessions are not less than 20m, and the requirements for the branch railway lines for construction concessions are not less than 15m; the requirements for building concessions with revetments are not less than 5m, and the requirements for non-revetment rivers are not less than 10m.
  • the equipment includes a VR panoramic display stand equipped with a wind environment simulation system, an adjustable axial fan and 3D tracking glasses.
  • the VR panoramic display stand and 3D tracking glasses equipped with the wind environment simulation system are used to display the urban three-dimensional space model with the wind direction and wind speed distribution cloud map and vector diagram, and the adjustable axial flow fan is used to simulate the feeling of real wind.
  • description with reference to the terms “one embodiment,” “example,” “specific example,” etc. means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one aspect of the present invention. in one embodiment or example.
  • schematic representations of the above terms do not necessarily refer to the same embodiment or example.
  • the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Civil Engineering (AREA)
  • Computational Mathematics (AREA)
  • Architecture (AREA)
  • Structural Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Fluid Mechanics (AREA)
  • Mathematical Physics (AREA)
  • Processing Or Creating Images (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种提升风环境的人工智能城市设计形态布局方法，包括数据获取、风场交互沙盘建构、城市设计方案的风场模拟与评价、城市设计形态布局的人工智能调整、城市设计标准规范判定、调整方案的风场模拟与评价和风环境提升方案全息展示。通过对照《蒲福风力等级表》，采用Random算法调整城市设计形态布局来提升风环境。能够应对城市规划设计领域风环境的提升，实现基于Random算法对建筑物进行随机布点来调整城市形态布局，用精准量化的方式使提升城市设计风环境效率更高，城市设计方案质量更佳。

Description

一种提升风环境的人工智能城市设计形态布局方法 技术领域
本发明涉及城市规划领域，具体的是一种提升风环境的人工智能城市设计形态布局方法。
背景技术
风环境是城市规划学科的重要研究内容之一，指室外自然风在城市地形地貌或自然地形地貌影响下形成的受到影响之后的风场。良好的城市风环境品质，不仅可以改进城市居民室内和户外的舒适感，降低城市建筑物在冬季取暖和夏季降温所需的能耗，还可以及时缓释城市下垫面附近因汽车尾气等所造成的大气污染。传统的城市形态设计未考虑风环境，无法在布局时检测是否满足风速标准要求，也无法结合风速标准要求对局部布局形态做出调整。另一方面，人工智能的出现，提供了一种更加科学、更加高效的城市设计手段。通过建构风场交互沙盘，模拟风环境，智能调整城市形态布局从而有效提升风环境。
目前常见的城市风环境提升方法，一种是建筑之间的风环境的提升，通过在CFD软件中建模并进行风环境模拟，模拟结果对照《绿色建筑评价标准》，择优选择平面布局，这种方法不考虑周边建筑对地块风环境的影响，模拟的误差非常大，且只适用于两个建筑之间的风环境提升，无法对整个街区的风环境做出提升；另一种是通过风洞试验进行模拟调整，这种方法耗费大量的人力物力，调整困难且误差系数大、判断随意性大，过程缺乏效率性以及结果缺乏科学性。
发明内容
为解决上述背景技术中提到的不足，本发明的目的在于提供一种提升风环 境的人工智能城市设计形态布局方法，本发明能够对多尺度的城市街区智能调整城市形态布局并判断调整方案可行性。
本发明的目的可以通过以下技术方案实现：
一种提升风环境的人工智能城市设计形态布局方法，包括如下步骤：
步骤一：数据获取
使用带有GPS定位的32通道风向风速仪，定点获取城市设计原始方案所在城市的风速、风向数据,向当地规划部门获取街区所在城市的三维矢量数据、城市设计方案数据、城市设计标准规范数据；
步骤二：风场交互沙盘建构
将步骤一中获取的数据输入到地理信息系统平台中，通过实测风向风速输入进行模拟运算生成风向风速分布云图和矢量图，与城市三维空间数字模型叠加，构建风场交互沙盘。设定模拟风向风速参数，建构城市风场模拟环境，并将步骤一中所选取点在风场中模拟的风速风向数据与实测数据进行核验，根据模拟与实测的误差系数对风速、风向、计算域高度、初始网格大小的参数值进行调整，直至误差≤3％；
步骤三：城市设计方案的风场模拟与评价
将城市设计方案置入风场交互沙盘中，提取设计方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风环境影响进行分级，若风力分级结果均在0-4级风之间则跳转至步骤七，若部分区域出现风力分级达到5级及以上风级的情况则跳转至步骤四；
步骤四：城市设计形态布局的人工智能调整
提取模拟风力等级达到5级及5级以上风级的城市设计方案的区域，进行栅格化处理，以栅格中的十字交叉点为参照，通过人工智能算法将建筑底面积 的几何中心点随机移动至栅格中的十字交叉点，以此对建筑进行重新排布；进而判断重新排布后街区内建筑所占的底面积之和是否等于原方案街区内建筑所占的底面积之和，即两者之间差的函数M是否等于0，若M不等于0则对建筑进行重新排布，直到M为0，从而保证布局调整后的建筑之间不交叠、建筑始终在街区的边界范围内。其中，所述函数M的计算公式如下：
M＝SUM调整-SUM原
其中SUM调整为重新排布后街区内建筑所占的底面积之和，SUM原为原方案街区内建筑所占的底面积之和。
步骤五：城市设计标准规范判定
将调整后的布局输入风场交互沙盘中，对照当地《城市设计标准与准则》进行各项指标的定量计算，若出现不符合《城市设计标准与准侧》的情况，则重复步骤四操作，直至所有建筑布局均满足当地《城市设计标准与准则》要求；
步骤六:调整方案的风场模拟与评价
将布局形态调整后且满足当地《城市设计标准与准则》的方案置入风场交互沙盘中，提取调整方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风级进行评价，若出现风力分级达到5级及以上风级的情况则重复步骤四操作，直至风力等级模拟结果均在0-4级之间；
步骤七：风环境提升方案全息展示
使用4D全息投影对风环境提升后的城市设计方案进行全方位展示，设备包括搭载风环境模拟仿真系统的VR全景展示台、调节式轴流风机和3D追踪眼镜。
进一步地，所述城市三维空间数字模型，是通过统一城市三维矢量数据为2000国家大地坐标系后所生成，包含城市地理高程、道路路网,建筑轮廓，建筑高度，城市水系和城市山体类信息。
进一步地，所述步骤二中对风速、风向、计算域高度、初始网格大小的参数值进行调整，风速调整指计算机通过公式风速误差
Figure PCTCN2020124322-appb-000001
计算出各点风速误差W 1、W 2、W 3……W n，再利用公式
Figure PCTCN2020124322-appb-000002
计算平均误差，针对风速误差计算机自动修正；风向调整指计算机通过公式风向误差
Figure PCTCN2020124322-appb-000003
计算出个点风向误差F 1、F 2、F 3……F n，再利用公式
Figure PCTCN2020124322-appb-000004
计算平均误差，针对风向误差计算机自动修正；如果部分区域不能得到模拟，则计算机自动调整计算域高度直至覆盖整个范围或者缩小初始网格，每次缩小10％直至所有实测点均能得到风速风向的模拟。
进一步地，所述步骤四中的人工智能算法，采用Random算法，将建筑重新排布调整城市形态布局，指将街区进行栅格化处理，每个栅格的大小为1m*1m，并将栅格进行从1-n编号，创建集合A，将建筑底面的几何中心进行编号X1-XN，创建集合B，建筑物在街区上分布通过(a，b)，其中a∈A,b∈B，使用Random算法处理，分别从集合A、B中任意选择进行组合，生成列表[(a1,b1),(a2,b2)……(an，bn)]，其中an∈A,bn∈B，将列表数据集投射到街区空间上，形成调整后的城市设计形态布局。
进一步地，所述步骤五中对照当地《城市设计标准与准则》进行各项指标的定量计算，指将城市设计标准规范数据转译为城市设计沙盘指标库，与沙盘中方案指标数据对照，且该《城市设计标准与准则》指该城市所颁布的《城市设计标准与准则》，如该城市未颁布，则使用该城市所在省的《城市设计标准与准则》。
本发明的有益效果：
1、本发明通过将风速模拟软件与地理信息平台相结合，构建风场交互沙盘。 突破了传统风环境模拟参数调整的人为调整误差大的问题，控制误差在3％以内；降低了传统风环境模拟多个软件协同操作的复杂性；简化了风环境操作繁琐流程。步骤四通过Random算法结合栅格化的城市设计平面，自动优化城市设计布局。将Random算法应用到城市形态布局调整领域，突破了传统城市设计布局的专家判断，增加了更多可行方案的选择，整个过程更加智能和自动化。
2、本发明通过风速风向数据、城市三维矢量数据、城市设计方案数据以及城市设计标准规范数据录入地理信息系统构建沙盘，计算机进行风环境模拟，结合实测验证与反馈调整，实现了在城市真实场景中对设计方案的风环境精细模拟，最大程度的提升了风环境模拟的准确性和效率；
3、本发明攻克了传统只针对个别建筑而不考虑周边建筑布局的方法局限，实现了在全市尺度下对设计方案的布局优化与整体风环境质量的提升，有效避免了因为个别建筑的调整而降低周边风环境质量的情况发生；
4、本发明将基于栅格化街区和Random算法的城市形态布局调整方法与风环境影响评价相结合，通过交互反馈和逐轮优化，确保城市设计方案任何区域内都不会出现超出4级风的情况；
5、本发明通过对照当地《城市设计标准与准则》进行定量计算，确保调整后城市设计方案的可行性；
6、本发明对城市设计方案进行风环境模拟，并自动调整和筛选的方法和沙盘，避免了传统风环境提升投入人力物力大、涉及人脑判断、随意性大和尺度小的问题，实现对不同尺度城市风环境提升的高效科学、全流程自动化、精确化、智能化的城市设计方案调整，为调整城市设计方案布局来提升城市设计风环境提供了参考途径；
7、本发明通过4D全息投影平台，使风环境展示可视化、可感受，提升展 示效果。
附图说明
下面结合附图对本发明作进一步的说明。
图1是本发明方法流程图；
图2是《蒲福风力等级表》；
图3为原始方案局部区域风环境效果；
图4为布局形态调整后方案局部区域风环境效果。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
在本发明的描述中，需要理解的是，术语“开孔”、“上”、“下”、“厚度”、“顶”、“中”、“长度”、“内”、“四周”等指示方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的组件或元件必须具有特定的方位，以特定的方位构造和操作，因此不能理解为对本发明的限制。
一种提升风环境的人工智能城市设计形态布局方法，如图1-4所示，包括以下步骤：
一、数据获取，使用带有GPS定位的32通道风向风速仪，随机定点获取城市设计原始方案所在城市的风速、风向数据。向当地规划部门获取街区所在城市的三维矢量数据、城市设计方案数据、城市设计标准规范数据。
其中，所述带有GPS定位的32通道风向风速仪，用于记录带有具体位置坐标的风速风向；
所述随机定点获取城市设计原始方案所在城市的风速、风向数据，指根据气象统计资料选择主导风向或不利风向大风出现频次较高的时间进行测量，测量连续进行，测量应3-5分钟记录一次风向、瞬时最大风速和平均风速。选点区域为随机选择，但应包括主导风向区域、主要活动区域、最不利区域和有特殊要求的区域，如污染物或热源排放区和通风口。测量高度为地面或活动平台以上1.5m高度处。
所述三维矢量数据包括城市内所有的矢量街区、矢量建筑体块；
所述矢量街区、矢量建筑体块数据均为轮廓闭合的多边形数据，矢量街区数据包括路网数据(道路轮廓线或道路红线)、高程数据(用于模拟地形)和水体数据；矢量建筑体块数据应带有建筑高度信息(在没有高度的情况下，通过建筑层数推算建筑高度，建筑高度＝建筑层数*3米)，以上数据可以为DWG格式或SHP格式，且包含地理坐标数据；
二、风场交互沙盘建构，将步骤一中获取的数据输入到的地理信息系统平台中构建沙盘，所使用的计算机设备配置要求带有8个Tesla V100 GPU。设定模拟风向风速参数，建构城市风场模拟环境，并将步骤一中所选取点在风场中模拟的风速风向数据与实测数据进行核验，调整模拟参数直至误差≤3％。
所述将步骤一中获取的数据输入到的地理信息系统平台中构建沙盘。指建立数据文件夹，利用地理信息平台添加数据功能与文件夹建立联系，确保矢量街区、矢量地块数据格式为DWG格式或SHP格式，利用projection操作对数据坐标进行转换，包括投影坐标、地理坐标间的切换以及不同坐标系之间的转换，调整城市三维矢量数据统一为2000国家大地坐标系；利用Layer3DToFeatureClass操作，结合建筑高度信息，对建筑物进行拉伸形成三维模型，结合高程数据和水体数据生成三维地形；最终生成城市三维空间数字模 型。
所述建构城市风场模拟环境，指将CFD风环境模拟软件作为插件适配地理信息系统平台，将实测风向风速输入进行模拟运算生成风向风速分布云图和矢量图与城市三维矢量数据叠加，构建风场交互沙盘。
所述将步骤一中所选取点在风场中模拟的风速风向数据与实测数据进行核验，指将随机实测的风速风向数据录入到地理信息系统中的风环境模拟模块中，进而设定模拟风向风速参数并在风场交互沙盘中进行风环境模拟，生成风向风速属性表，对比实测风向风速数据，进行误差计算，再根据模拟与实测的误差系数对风速、风向、计算域高度、初始网格大小的参数值进行调整，直至误差≤3％。此操作用以提升沙盘风环境模拟的准确性和精度。
风速调整指计算机通过公式风速误差
Figure PCTCN2020124322-appb-000005
计算出各点风速误差W 1、W 2、W 3……W n，再利用公式
Figure PCTCN2020124322-appb-000006
计算平均误差，针对风速误差计算机自动修正；风向调整指计算机通过公式风向误差
Figure PCTCN2020124322-appb-000007
计算出个点风向误差F 1、F 2、F 3……F n，再利用公式
Figure PCTCN2020124322-appb-000008
计算平均误差，针对风向误差计算机自动修正；如果部分区域不能得到模拟，则计算机自动调整计算域高度直至覆盖整个范围或者缩小初始网格，每次缩小10％直至所有实测点均能得到风速风向的模拟。
三、城市设计方案的风场模拟与评价，将城市设计方案置入风场交互沙盘中，提取设计方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风环境影响进行评价，若评价结果均在0-4级风之间则跳转至步骤七，若部分区域评价结果超出0-4级风的范围则跳转至步骤四。
所述将城市设计方案置入风场交互沙盘中，指用地理信息平台添加数据功 能与设计方案的矢量街区、矢量建筑体块数据建立联系，利用projection操作对数据坐标进行转换，包括投影坐标、地理坐标间的切换以及不同坐标系之间的转换，调整城市三维矢量数据为2000国家大地坐标系；利用Layer3DToFeatureClass操作，结合建筑高度信息，对建筑物进行拉伸形成三维模型，结合高程数据和水体数据生成三维地形，构建城市设计方案三维模型。
所述提取设计方案所在街区风场中的模拟风速数据，指进行风环境模拟后，得到各地理坐标的风速风向，生成带有位置信息的风速风向属性表以及风向风速分布云图和矢量图。
所述对照《蒲福风力等级表》对风环境影响进行评价，指将《蒲福风力等级表》转译为风速舒适度属性表，录入到风场交互沙盘中，与风速风向属性表关联并自动判别，若评价结果均在0-4级风之间则满足风环境舒适标准，跳转至步骤七，若部分区域评价结果超出0-4级风的范围，则不满足风环境舒适标准，地理信息系统识别其坐标，并在三维沙盘中进行标注，同时跳转至步骤四。
四、城市设计形态布局的人工智能调整，针对不符合《蒲福风力等级表》的城市设计方案的形态布局区域，将地街区进行栅格化处理，基于Random算法，将建筑重新随机排布调整城市形态布局，并保证建筑之间不交叠、建筑不能超出街区的边界。
所述将街区进行栅格化处理，指通过polygon to raster命令，将街区划分为1m*1m以内的栅格，以提高方案调整时的精度；
所述基于Random算法，将建筑重新随机排布调整城市形态布局，指将栅格顶点进行从1-n编号，创建集合A；将建筑底面的几何中心进行编号X1-XN，创建集合B。建筑物在街区上随机分布通过(a，b)表示，其中a∈A,b∈B。使用Random算法处理，分别从集合A、B中随机选择进行组合，生成列表[(a1,b1), (a2,b2)……(an，bn)]，其中an∈A,bn∈B，将列表数据集投射到街区空间上，形成调整后的城市设计形态布局。
所述建筑几何中心点，通过在地理信息平台中运用要素转点(Feature to point)指令，将多边形街区面转换为每个面的中心点，所述中心点包含坐标数据。
所述保证建筑之间不交叠、建筑不能超出街区的边界，指判断属于调整方案街区内建筑布局栅格数的和是否等于原方案街区内建筑布局栅格数的和，即要求两者之间差的函数等于0，按照如下公式进行处理：
M＝SUM调整-SUM原
其中SUM调整为调整方案街区内建筑布局栅格数的和，SUM原为原方案街区内建筑布局栅格数的和；
所述原方案街区内建筑布局栅格数的和，指生成建筑数据属性表，利用SUM运算得出建筑栅格数的和；
所述调整方案街区内建筑布局栅格数的和，指将所有建筑栅格数据先用并集(union of inputs)命令得出所有新的建筑栅格数据，再将街区栅格数据和新的建筑用交集(Intersect)命令得出街区内的建筑栅格，生成建筑数据属性表，利用SUM运算得出建筑栅格数的和。
五、城市设计标准规范判定，将调整后的布局输入风场交互沙盘中，对照当地《城市设计标准与准则》进行各项指标的定量计算，若部分区域形态布局不满足则重复步骤四操作，直至所有形态布局均满足当地《城市设计标准与准则》要求。
所述对照当地《城市设计标准与准则》进行各项指标的定量计算，指将建筑间距、建筑退线标准规范转译为城市设计沙盘指标库，地理信息系统中调整 方案生成建筑间距、建筑退线属性表，与指标库关联，沙盘自动判别是否满足要求，该《城市设计标准与准则》指该城市所颁布的《城市设计标准与准则》，如该城市未颁布，则使用该城市所在省的《城市设计标准与准则》；
六、调整方案的风场模拟与评价，将布局形态调整后且满足当地《城市设计标准与准则》的方案置入风场交互沙盘中，提取调整方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风环境影响进行评价，若部分区域评价结果超出0-4级风的范围则则重复步骤四操作，直至评价结果均在0-4级风之间。具体操作同步骤三。
七、风环境提升方案全息展示，使用4D全息投影对风环境提升后的城市设计方案进行全方位展示。设备包括搭载风环境模拟仿真系统的VR全景展示台、可调节式轴流风机和3D追踪眼镜。
所述搭载风环境模拟仿真系统的VR全景展示台和3D追踪眼镜用于展示带有风向风速分布云图和矢量图的城市三维空间模型，可调节式轴流风机用于模拟真实风的感受，共同构成可视可感的风环境提升方案全息展示模块。
实施例
以下将以常州市某地区城市设计为例对本发明的技术方案进行详细说明。
(1)以常州市某地区为目标街区，获取常州市的三维矢量数据、城市设计方案数据、城市设计标准规范数据，随机定点获取常州市风向风速数据，具体包括：
(1.1)通过常州市规划部门，获得常州市的三维矢量数据、城市设计方案数据和城市设计标准规范数据，包含常州市的现状以及设计方案的闭合街区CAD/SHP文件、现状闭合用地地块CAD/SHP文件、现状闭合建筑及层数(高度)CAD/SHP文件、高程数据和水体数据，城市设计标准规范中的建筑间距和建筑退 线数据。
(1.2)根据气象统计资料选择主导风向或不利风向大风出现频次较高的时间，在地面或活动平台以上1.5m高度处，用带有GPS定位的32通道风向风速仪，记录带有具体位置坐标的风速风向。测量连续进行，3-5分钟记录一次风向、瞬时最大风速和平均风速。选点区域为随机选择的200个点，但应包括主导风向区域、主要活动区域、最不利区域和有特殊要求的区域，如污染物或热源排放区和通风口。
(2)将以上数据输入到地理信息系统软件中构建沙盘，具体包括：
(2.1)将现状常州市三维矢量数据中的现状闭合街区CAD文件、现状闭合用地地块CAD文件、高程数据文件和水体数据文件导入地理信息系统软件，并导出闭合多段线(Polyline)的SHP格式；将现状闭合建筑及层数(高度)CAD文件导入地理信息系统软件，并导出建筑闭合面(Polyline)的SHP格式及层数点(Point)的SHP格式；将建筑闭合面与建筑层数点进行空间关联，将每个建筑附上其层数(高度)信息。
(2.2)利用projection操作对数据坐标进行转换，包括投影坐标、地理坐标间的切换以及不同坐标系之间的转换，调整城市三维矢量数据统一为2000国家大地坐标系。
(2.3)利用Layer3DToFeatureClass操作，结合建筑高度信息，对建筑物进行拉伸，形成三维模型，结合高程数据和水体数据生成三维地形；最终生成城市三维空间数字模型。
(2.4)将CFD风环境模拟软件作为插件适配地理信息系统平台，将实测风向风速输入进行模拟运算生成风向风速分布云图和矢量图与城市三维矢量数据叠加，构建风场交互沙盘。
(2.5)将随机实测的200个点的风速风向数据录入到地理信息系统中的风环境模拟模块中，进而设定模拟风向风速参数并在风场交互沙盘中进行风环境模拟，生成风向风速属性表，对比实测风向风速数据，进行误差计算，误差系数为6.8％。再根据模拟与实测的误差系数对风速、风向、计算域高度、初始网格大小的参数值进行调整，最终误差为2.6％，符合≤3％的要求，得到了精确的风场交互沙盘。
(3)将城市设计方案置入风场交互沙盘中，进行城市设计方案的风场模拟与评价，具体包括：
(3.1)将设计方案的闭合街区CAD文件、闭合用地地块CAD文件、建筑及层数(高度)CAD文件、高程数据文件和水体数据文件导入之前构建的风场交互沙盘中，导出闭合多段线(Polyline)的SHP格式和建筑闭合面(Polyline)的SHP格式及层数点(Point)的SHP格式；将建筑闭合面与建筑层数点进行空间关联，将每个建筑附上其层数(高度)信息。
(3.2)利用projection操作对数据坐标进行转换，包括投影坐标、地理坐标间的切换以及不同坐标系之间的转换，调整城市设计方案三维矢量数据为2000国家大地坐标系。
(3.3)利用Layer3DToFeatureClass操作，结合建筑高度信息，对建筑物进行拉伸形成三维模型，结合高程数据和水体数据生成三维地形，构建城市设计方案三维模型。
(3.4)利用风场交互沙盘中的风环境模拟模块进行风环境模拟，得到带有地理位置信息的风速风向属性表以及整体风向风速分布云图和矢量图。
(3.5)将《蒲福风力等级表》转译为风速舒适度属性表，录入到风场交互沙盘中，关联风速风向属性表并自动判别。评判标准为，若评价结果均在0-4 级风之间则满足风环境舒适标准；若部分区域评价结果超出0-4级风的范围，则通过地理信息系统自动识别其坐标，并在三维沙盘中进行标注。
(4)针对不符合《蒲福风力等级表》的城市设计方案的形态布局区域，进行人工智能的调整，具体包括：
(4.1)将街区进行栅格化处理，将街区划分为13580块1m*1m精度的栅格，并将栅格顶点从1开始依次编号，创建集合A；运用要素转点(Feature to point)指令，将多边形街区面转换为每个面的中心点，所述中心点包含坐标数据，将建筑底面的几何中心进行编号X1-XN，创建集合B。建筑物在街区上随机分布通过(a，b)表示，其中a∈A,b∈B。使用Random算法处理，分别从集合A、B中随机选择进行组合，生成列表[(a1,b1),(a2,b2)……(an，bn)]，其中an∈A,bn∈B，将列表数据集投射到街区空间上，形成调整后的城市设计形态布局。
(4.2)调整后的城市形态布局要求建筑之间不交叠、建筑不能超出街区的边界。通过判断调整方案街区内建筑布局栅格数的和是否等于原方案街区内建筑布局栅格数的和。建立两者之间差的函数，公式如下：
M＝SUM调整-SUM原
其中SUM调整为调整方案街区内建筑布局栅格数的和，SUM原为原方案街区内建筑布局栅格数的和；
(4.3)针对原始方案，生成建筑数据属性表，利用SUM运算得出建筑栅格数的和为9765；针对调整方案，将所有建筑栅格数据先用并集(union of inputs)命令得出所有新的建筑栅格数据，再将街区栅格数据和新的建筑用交集(Intersect)命令得出街区内的建筑栅格，生成建筑数据属性表，利用SUM运算得出建筑栅格数的和和为8653。代入公式不符合两者差等于0的要求，因此 循环以上操作，直至M＝0，生成最终调整的城市设计形态布局。
(5)将最终调整的城市设计方案再次输入到风场交互沙盘中，并进行城市设计标准规范判定，具体包括：
(5.1)将《江苏省城市规划管理技术规定》常州市实施细则(即常州当地的城市设计标准与准则)中的建筑日照间距、建筑山墙间距、建筑退让道路红线标准、建筑退让铁路红线标准以及建筑退让河道标准规范转译为城市设计沙盘指标库，地理信息系统中调整方案生成建筑间距、建筑退线属性表，与指标库关联，进行定量计算，沙盘自动判别是否满足要求，其中居住建筑日照间距要求
Figure PCTCN2020124322-appb-000009
非居住建筑日照间距满足底层建筑最小为6m，多层建筑最小为10m，高层建筑最小为13m；山墙间距要求如表1所示：
Figure PCTCN2020124322-appb-000010
表1建筑山墙最小间距
建筑退让道路红线要求如表2所示；建筑退让铁路干线要求不小于20m、退让铁路支线要求不小于15m；建筑退让有驳岸河道要求不小于5m、无驳岸河道 要求不小于10m。结果存在部分区域不能满足相关标准规范。其中38处不能满足建筑间距要求，42处不能满足建筑退线要求，因此重新调整城市形态布局，直至所有形态布局均满足当地《江苏省城市规划管理技术规定》常州市实施细则的要求。
Figure PCTCN2020124322-appb-000011
表2建筑后退城市规划道路红线最小距离
(6)将布局形态调整后且满足《江苏省城市规划管理技术规定》常州市实施细则的方案置入风场交互沙盘中，进行调整方案的风场模拟与评价，按照(3)中的步骤，得出评价结果，所有区域均满足风速0-4级的风速要求要求。
(7)使用4D全息投影对风环境提升后的城市设计方案进行全方位展示。设备包括搭载风环境模拟仿真系统的VR全景展示台、可调节式轴流风机和3D追踪眼镜。
其中，搭载风环境模拟仿真系统的VR全景展示台和3D追踪眼镜用于展示带有风向风速分布云图和矢量图的城市三维空间模型，可调节式轴流风机用于 模拟真实风的感受。
在本说明书的描述中，参考术语“一个实施例”、“示例”、“具体示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
以上显示和描述了本发明的基本原理、主要特征和本发明的优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。

Claims (5)

  1. 一种提升风环境的人工智能城市设计形态布局方法，其特征在于，包括如下步骤：
    步骤一：数据获取
    使用带有GPS定位的32通道风向风速仪，定点获取城市设计原始方案所在城市的风速、风向数据,向当地规划部门获取街区所在城市的三维矢量数据、城市设计方案数据、城市设计标准规范数据；
    步骤二：风场交互沙盘建构
    将步骤一中获取的数据输入到地理信息系统平台中，通过实测风向风速输入进行模拟运算生成风向风速分布云图和矢量图，与城市三维空间数字模型叠加，构建风场交互沙盘，设定模拟风向风速参数，建构城市风场模拟环境，并将步骤一中所选取点在风场中模拟的风速风向数据与实测数据进行核验，根据模拟与实测的误差系数对风速、风向、计算域高度、初始网格大小的参数值进行调整，直至误差≤3％；
    步骤三：城市设计方案的风场模拟与评价
    将城市设计方案置入风场交互沙盘中，提取设计方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风环境影响进行分级，若风力分级结果均在0-4级风之间则跳转至步骤七，若部分区域出现风力分级达到5级及以上风级的情况则跳转至步骤四；
    步骤四：城市设计形态布局的人工智能调整
    提取模拟风力等级达到5级及5级以上风级的城市设计方案的区域，进行栅格化处理，以栅格中的十字交叉点为参照，通过人工智能算法将建筑底面积的几何中心点随机移动至栅格中的十字交叉点，以此对建筑进行重新排布；进 而判断重新排布后街区内建筑所占的底面积之和是否等于原方案街区内建筑所占的底面积之和，即两者之间差的函数M是否等于0，若M不等于0则对建筑进行重新排布，直到M为0，从而保证布局调整后的建筑之间不交叠、建筑始终在街区的边界范围内。其中，所述函数M的计算公式如下：
    M＝SUM调整-SUM原
    其中SUM调整为重新排布后街区内建筑所占的底面积之和，SUM原为原方案街区内建筑所占的底面积之和。
    步骤五：城市设计标准规范判定
    将调整后的布局输入风场交互沙盘中，对照当地《城市设计标准与准则》进行各项指标的定量计算，若出现不符合《城市设计标准与准侧》的情况，则重复步骤四操作，直至所有建筑布局均满足当地《城市设计标准与准则》要求；
    步骤六:调整方案的风场模拟与评价
    将布局形态调整后且满足当地《城市设计标准与准则》的方案置入风场交互沙盘中，提取调整方案所在街区风场中的模拟风速数据，并对照《蒲福风力等级表》对风级进行评价，若出现风力分级达到5级及以上风级的情况则重复步骤四操作，直至风力等级模拟结果均在0-4级之间；
    步骤七：风环境提升方案全息展示
    使用4D全息投影对风环境提升后的城市设计方案进行全方位展示，设备包括搭载风环境模拟仿真系统的VR全景展示台、调节式轴流风机和3D追踪眼镜。
  2. 根据权利要求1所述的一种提升风环境的人工智能城市设计形态布局方法，其特征在于，所述城市三维空间数字模型，是通过统一城市三维矢量数据为2000国家大地坐标系后所生成，包含城市地理高程、道路路网,建筑轮廓，建筑高度，城市水系和城市山体类信息。
  3. 根据权利要求1所述的一种提升风环境的人工智能城市设计形态布局方法，其特征在于，所述步骤二中对风速、风向、计算域高度、初始网格大小的参数值进行调整，风速调整指计算机通过公式风速误差
    Figure PCTCN2020124322-appb-100001
    计算出各点风速误差W 1、W 2、W 3……W n，再利用公式
    Figure PCTCN2020124322-appb-100002
    计算平均误差，针对风速误差计算机自动修正；风向调整指计算机通过公式风向误差
    Figure PCTCN2020124322-appb-100003
    计算出个点风向误差F 1、F 2、F 3……F n，再利用公式
    Figure PCTCN2020124322-appb-100004
    计算平均误差，针对风向误差计算机自动修正；如果部分区域不能得到模拟，则计算机自动调整计算域高度直至覆盖整个范围或者缩小初始网格，每次缩小10％直至所有实测点均能得到风速风向的模拟。
  4. 根据权利要求1所述的一种提升风环境的人工智能城市设计形态布局方法，其特征在于，所述步骤四中的人工智能算法，采用Random算法，将建筑重新排布调整城市形态布局，指将街区进行栅格化处理，每个栅格的大小为1m*1m，并将栅格进行从1-n编号，创建集合A，将建筑底面的几何中心进行编号X1-XN，创建集合B，建筑物在街区上分布通过(a，b)，其中a∈A,b∈B，使用Random算法处理，分别从集合A、B中任意选择进行组合，生成列表[(a1,b1),(a2,b2)……(an，bn)]，其中an∈A,bn∈B，将列表数据集投射到街区空间上，形成调整后的城市设计形态布局。
  5. 根据权利要求1所述的一种提升风环境的人工智能城市设计形态布局方法，其特征在于，所述步骤五中对照当地《城市设计标准与准则》进行各项指标的定量计算，指将城市设计标准规范数据转译为城市设计沙盘指标库，与沙盘中方案指标数据对照，且该《城市设计标准与准则》指该城市所颁布的《城 市设计标准与准则》，如该城市未颁布，则使用该城市所在省的《城市设计标准与准则》。
PCT/CN2020/124322 2020-09-04 2020-10-28 一种提升风环境的人工智能城市设计形态布局方法 WO2022047959A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/611,004 US20220309201A1 (en) 2020-09-04 2020-10-28 Artificial-intelligence-assisted method for providing urban design form and layout with improved wind environment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010923497.XA CN112100720B (zh) 2020-09-04 2020-09-04 一种提升风环境的人工智能城市设计形态布局方法
CN202010923497.X 2020-09-04

Publications (1)

Publication Number Publication Date
WO2022047959A1 true WO2022047959A1 (zh) 2022-03-10

Family

ID=73757376

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/124322 WO2022047959A1 (zh) 2020-09-04 2020-10-28 一种提升风环境的人工智能城市设计形态布局方法

Country Status (3)

Country Link
US (1) US20220309201A1 (zh)
CN (1) CN112100720B (zh)
WO (1) WO2022047959A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115329691A (zh) * 2022-08-01 2022-11-11 上海师范大学 一种基于cfd与gis的超大城市风环境模拟方法
CN116432285A (zh) * 2023-04-12 2023-07-14 江苏大学 一种局部微气候与舒适度优化的建筑形态评价方法
CN116842877A (zh) * 2023-09-04 2023-10-03 江苏省环境监测中心 一种基于多源数据综合利用的小尺度三维风场重构算法
CN117933491B (zh) * 2024-03-21 2024-05-28 山东农业大学 融合城市风场影响的建筑区产流预测方法、系统、装置

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113032874A (zh) * 2021-03-17 2021-06-25 三一智造(深圳)有限公司 一种提升风环境的人工智能城市设计形态布局方法
CN114091146A (zh) * 2021-11-10 2022-02-25 青岛理工大学 基于风环境模拟的街区形态设计方法、装置及存储介质
CN115618462A (zh) * 2022-10-10 2023-01-17 哈尔滨工业大学 一种基于缩尺模型物理仿真的城市街区局地风热环境耦合预测方法
CN116167148B (zh) * 2023-04-26 2023-07-07 青岛理工大学 基于局域微气候的城市街区形态优化方法及其系统
CN117010059A (zh) * 2023-07-17 2023-11-07 东南大学建筑设计研究院有限公司 高校校园规划设计中面积分配与分区测算的数字化方法
CN116977469B (zh) * 2023-08-02 2024-01-23 中国水利水电科学研究院 一种基于随机切片的社区尺度城市形态数据批量生成方法
CN117273268A (zh) * 2023-09-15 2023-12-22 东南大学建筑设计研究院有限公司 基于日照、风、热环境模拟的街区形态综合优化方法
CN117332709A (zh) * 2023-09-20 2024-01-02 长沙学院 一种建筑风压模拟等效数值方法及模拟装置
CN117197730B (zh) * 2023-11-02 2024-04-05 江苏通创现代建筑产业技术研究院有限公司 一种城市空间畸变图像的修复评估方法
CN117521424B (zh) * 2024-01-05 2024-04-09 中国电子科技集团公司第十五研究所 一种仿真训练场景生成方法和装置

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000259700A (ja) * 1999-03-11 2000-09-22 Ohbayashi Corp 風環境表示システム
CN103136432A (zh) * 2013-03-28 2013-06-05 机械工业第三设计研究院 一种基于微气候分析的建筑场地设计方法及系统
CN105513133A (zh) * 2016-02-03 2016-04-20 东南大学 一种城市风环境数字地图制作及显示方法
CN105913135A (zh) * 2016-03-22 2016-08-31 东南大学 一种基于风环境效应场模型的街区三维形态格局优化方法
CN106156516A (zh) * 2016-07-21 2016-11-23 哈尔滨工业大学 一种基于风洞试验的城市街区行人风环境评估方法
KR20170033711A (ko) * 2015-09-17 2017-03-27 한국외국어대학교 연구산학협력단 도시 개발 대상지역의 미래 기후환경 변화 예측 분석시스템 및 이를 이용한 기후 환경 변화 예측 분석 방법
CN109948214A (zh) * 2019-03-11 2019-06-28 天津城建大学 城市多尺度风环境数值模拟方法
CN110110353A (zh) * 2019-03-20 2019-08-09 广西大学 面向绿色住区设计方案初期的参数化生成优化设计方法
CN110175374A (zh) * 2019-05-13 2019-08-27 浙江大学城市学院 一种基于cfd数值模拟的双子楼建筑风环境的优化方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120020788A1 (en) * 2009-10-29 2012-01-26 The Green Electric Company, A Massachusetts Corporation Wind energy system
CN101908086A (zh) * 2010-07-09 2010-12-08 上海理工大学 一种对建筑室内风环境进行数字化动态模拟的分析方法
CN101872380B (zh) * 2010-07-09 2011-12-21 上海理工大学 一种降低区域建筑能耗流失的方法
KR101281583B1 (ko) * 2013-02-25 2013-07-03 현대산업개발 주식회사 초고층 건물에서의 소형 풍력발전 시스템의 적용방법
US9353730B2 (en) * 2013-06-10 2016-05-31 Uprise Energy, LLC Wind energy devices, systems, and methods
CN106228890B (zh) * 2016-09-30 2022-09-06 中国科学技术大学 一种环境风作用下高层建筑立体火行为模拟实验装置
CN110532666A (zh) * 2019-08-26 2019-12-03 中国石油大学(华东) 基于风环境变化的城市微气候演变分析方法
CN111444558B (zh) * 2020-03-12 2023-02-28 合肥市规划设计研究院 一种提升城市气候宜居度的城市通风廊道划定方法

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000259700A (ja) * 1999-03-11 2000-09-22 Ohbayashi Corp 風環境表示システム
CN103136432A (zh) * 2013-03-28 2013-06-05 机械工业第三设计研究院 一种基于微气候分析的建筑场地设计方法及系统
KR20170033711A (ko) * 2015-09-17 2017-03-27 한국외국어대학교 연구산학협력단 도시 개발 대상지역의 미래 기후환경 변화 예측 분석시스템 및 이를 이용한 기후 환경 변화 예측 분석 방법
CN105513133A (zh) * 2016-02-03 2016-04-20 东南大学 一种城市风环境数字地图制作及显示方法
CN105913135A (zh) * 2016-03-22 2016-08-31 东南大学 一种基于风环境效应场模型的街区三维形态格局优化方法
CN106156516A (zh) * 2016-07-21 2016-11-23 哈尔滨工业大学 一种基于风洞试验的城市街区行人风环境评估方法
CN109948214A (zh) * 2019-03-11 2019-06-28 天津城建大学 城市多尺度风环境数值模拟方法
CN110110353A (zh) * 2019-03-20 2019-08-09 广西大学 面向绿色住区设计方案初期的参数化生成优化设计方法
CN110175374A (zh) * 2019-05-13 2019-08-27 浙江大学城市学院 一种基于cfd数值模拟的双子楼建筑风环境的优化方法

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115329691A (zh) * 2022-08-01 2022-11-11 上海师范大学 一种基于cfd与gis的超大城市风环境模拟方法
CN115329691B (zh) * 2022-08-01 2024-03-12 上海师范大学 一种基于cfd与gis的超大城市风环境模拟方法
CN116432285A (zh) * 2023-04-12 2023-07-14 江苏大学 一种局部微气候与舒适度优化的建筑形态评价方法
CN116432285B (zh) * 2023-04-12 2023-10-24 江苏大学 一种局部微气候与舒适度优化的建筑形态评价方法
CN116842877A (zh) * 2023-09-04 2023-10-03 江苏省环境监测中心 一种基于多源数据综合利用的小尺度三维风场重构算法
CN116842877B (zh) * 2023-09-04 2023-11-28 江苏省环境监测中心 一种基于多源数据综合利用的小尺度三维风场重构算法
CN117933491B (zh) * 2024-03-21 2024-05-28 山东农业大学 融合城市风场影响的建筑区产流预测方法、系统、装置

Also Published As

Publication number Publication date
CN112100720B (zh) 2021-03-16
CN112100720A (zh) 2020-12-18
US20220309201A1 (en) 2022-09-29

Similar Documents

Publication Publication Date Title
WO2022047959A1 (zh) 一种提升风环境的人工智能城市设计形态布局方法
WO2022126806A1 (zh) 一种基于人工智能的控规地块城市设计多方案生成方法
US20220318443A1 (en) Ai-based method for generating building block in commercial district
CN103150751B (zh) 在数字地图中实现建筑物内外一体化的三维建模方法
CN115292789B (zh) 城市设计中基于形态类型的建筑体量数字化生成方法
CN111767597B (zh) 一种城市模型验证方法、装置、设备及存储介质
CN115329691B (zh) 一种基于cfd与gis的超大城市风环境模拟方法
CN113705125B (zh) 一种高层建筑局域风场cfd模拟分析方法
CN104732038A (zh) 一种基于gis的城市通风廊道计算方法及系统
CN107944203A (zh) 一种风速流线可视化的建筑设计方法
Luo et al. Analysis of urban ventilation potential using rule-based modeling
CN104765903A (zh) 一种融合多源遥感和气候环境信息的综合性城市气候环境评估方法
CN104750938A (zh) 一种基于gis的城市通风廊道识别方法及系统
Yang et al. The centre of city: wind environment and spatial morphology
Wei et al. The case study of BIM in urban planning and design
CN109658513B (zh) 一种城市建筑能耗模型的简化方法
CN114417467A (zh) 城市密集区通风廊道的建立方法、装置、介质及设备
CN103778286A (zh) 一种风压图可视化的建筑设计方法
Yang et al. Design of urban landscape visual simulation system based on three-dimensional simulation technology
Xu et al. Thermal comfort performance prediction method using sports center layout images in several cold cities based on CNN
Jia Neural Network Model of Urban Landscape Design Based on Multi-Target Detection
Yao et al. Urban renewal based wind environment at pedestrian level in high-density and high-rise urban areas in Sai Ying Pun, Hong Kong
Su et al. Procedural modeling technology in Urban design
CN115828794B (zh) 一种城市尺度下树木花粉浓度预测方法及装置
Ma et al. GIS technology applied in urban plot ratio statistics and land suitability evaluation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20952201

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20952201

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20952201

Country of ref document: EP

Kind code of ref document: A1