Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training method and device for urban wind condition simulation model

A technology of simulation model and training method, which is applied in the training field of urban wind condition simulation model, and can solve the problem of unpredictable wind speed and wind direction in the area of ​​building vents.

Pending Publication Date: 2022-02-11
深圳市赑玄阁科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the present invention will solve the technical problem that the wind speed and wind direction in the tuyere area between the buildings in the city cannot be predicted in the prior art, thereby providing a training method and device for a simulation model of urban wind conditions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Training method and device for urban wind condition simulation model
  • Training method and device for urban wind condition simulation model
  • Training method and device for urban wind condition simulation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] This embodiment provides a training method for an urban wind condition simulation model. The training method can be executed by a server and other equipment, so as to obtain a wind condition simulation model, such as figure 1 shown, including the following steps:

[0027] In step S101, an underlying surface model of a target city is established, and the underlying surface model includes the landform features of the target city.

[0028]Specifically, the target city may refer to any city, and all villages and towns under the jurisdiction of the city, or may be a local area selected independently in the city. The underlying surface model may be a three-dimensional model established by a hyperspectral remote sensing satellite combined with a three-dimensional reconstruction method. The underlying surface model contains all the topographic features of the lower atmosphere in the area where the target city is directly in contact with the earth's surface. The topographic fea...

Embodiment 2

[0069] This embodiment provides a training device for a simulation model of urban wind conditions. The device can be set in a server or other equipment, and the modules cooperate with each other to execute the training method for the simulation model of urban wind conditions in the above-mentioned Embodiment 1. Specifically, such as figure 2 As shown, the training device includes:

[0070] A creation module 301 is used to establish an underlying surface model of a target city, where the underlying surface model includes the landform features of the target city;

[0071] The acquisition module 302 is configured to obtain the wind field data samples of the target city according to the landform features and the discrete wind field data detected at each detection point of the target city, wherein the wind field data samples include Wind field change data of various places in the target city in different time periods;

[0072] The training module 303 is configured to train a neu...

Embodiment 3

[0099] This embodiment provides a computer device, such as image 3 As shown, the computer device includes a processor 401 and a memory 402, wherein the processor 401 and the memory 402 can be connected by a bus or in other ways, image 3 Take the connection through the bus as an example.

[0100] The processor 401 may be a central processing unit (Central Processing Unit, CPU). The processor 401 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), graphics processor (Graphics Processing Unit, GPU), embedded neural network processor (Neural-network Processing Unit, NPU) or other Dedicated deep learning coprocessors, Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned types of chips.

[0101] As a non-transitory computer-rea...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides a training method and device for an urban wind condition simulation model, and the method comprises the steps of building an underlying surface model of a target city, and enabling the underlying surface model to comprise the landform features of the target city; according to the landform features and discrete wind field data detected at each detection point of the target city, obtaining a wind field data sample of the target city, the wind field data sample including wind field change data of each place of the target city in different time periods; training a neural network by using the wind field data sample to obtain a wind regime simulation model, the wind condition simulation model being used for predicting the wind condition between the buildings of the target city. The wind condition simulation model obtained through training can effectively solve the technical problem that in the prior art, the wind speed and the wind direction of the tuyere areas among the buildings in the city cannot be predicted, the influence of the wind condition on the city is predicted in advance, and precautionary measures are taken.

Description

technical field [0001] The invention relates to the technical field of wind field prediction, in particular to a training method and device for an urban wind condition simulation model. Background technique [0002] At present, there are many prediction methods for typhoons, and the path of typhoons can be detected in real time through the use of both early warning radar and marine resource satellites. It is also possible to conduct comprehensive meteorological observations through meteorological satellites, such as the Fengyun-4 satellite, which can provide high-resolution images and provide more reliable and detailed observation data for typhoon positioning and intensity determination. However, the current forecast and forecast of typhoons are based on the analysis of the overall movement trajectory, wind direction and wind speed of the typhoon. After the typhoon enters and makes landfall, it is impossible to know the wind field in a certain part of the city, and it is ev...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/28G06F30/27G06N3/08G06F113/06G06F113/08G06F119/14
CPCG06F30/28G06F30/27G06N3/08G06F2113/08G06F2119/14G06F2113/06
Inventor 汤洋许磊
Owner 深圳市赑玄阁科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com