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

Residential unit plan electrical design method based on machine learning

A machine learning and design method technology, applied in machine learning, design optimization/simulation, instrumentation, etc., can solve problems such as lack of electrical design

Inactive Publication Date: 2018-07-10
NANJING UNIV OF INFORMATION SCI & TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved in the present invention is to address the lack of electrical design in existing residential computer-aided design, and propose a machine learning-based electrical design method for residential floor plans to realize rapid design of residential floor plan electrical configurations and reduce the number of architects. workload

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
  • Residential unit plan electrical design method based on machine learning
  • Residential unit plan electrical design method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Embodiment 1: as Figure 1-2 As shown, the electrical design method of residential floor plan based on machine learning, on the basis of the machine learning system learning the residential floor plan that has completed the electrical design, conducts electrical design for a given floor plan that has not been electrically designed. The specific steps are as follows:

[0019] (1) Using the machine learning system, the location and size information of the living room, master bedroom, second bedroom, entrance, storage room, study, kitchen, toilet, balcony, corridor, as well as the layout information of lamps, power switches and power sockets are used to analyze the completed The feature vector extraction of the residential floor plan of the electrical design;

[0020] (2) Using the deep learning system, based on the extracted feature vectors, conduct deep learning and model training on the residential floor plan that has completed the electrical design, perform model perfo...

Embodiment 2

[0023] Embodiment 2: as Figure 1-2 As shown, the electrical design method of residential floor plan based on machine learning, on the basis of the machine learning system learning the residential floor plan that has completed the electrical design, conducts electrical design on the given floor plan without electrical design, the specific steps and implementation Example 1 is the same.

[0024] The method adopts the existing residential house floor plan computer-aided design system and equipment to coordinate implementation. The feature vector extraction and model training are carried out using the Alexnet deep learning neural network in the machine learning system; the machine learning system can distinguish the living room, master bedroom, second bedroom, porch, storage room, study, kitchen, toilet, balcony, Corridor location and size information, and arrange lamps, switches and power sockets according to the size of each room and functional area. The layout of lamps, powe...

Embodiment 3

[0025] Embodiment 3: as Figure 1-2 As shown, the electrical design method of residential floor plan based on machine learning, on the basis of the machine learning system learning the residential floor plan that has completed the electrical design, conducts electrical design on the given floor plan without electrical design, the specific steps and implementation Example 1 is the same.

[0026] The method adopts the existing residential house floor plan computer-aided design system and equipment to coordinate implementation. The extraction of feature vectors and model training are carried out using the Googlenet deep learning neural network in the machine learning system; the machine learning system can distinguish the living room, master bedroom, second bedroom, porch, storage room, study, kitchen, toilet, balcony, Corridor location and size information, and arrange lamps, switches and power sockets according to the size of each room and functional area; the layout of lamps,...

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 invention relates to a residential unit plan electrical design method based on machine learning and belongs to the technical field of a residential electrical computer aided design. The residential unit plan electrical design method comprises the following steps: adopting a machine learning system and carrying out characteristic vector extraction on a residential unit plan with the finished electrical design according to position and size information of a living room, a master bedroom, a second bedroom, an entryway, a storage room, a study, a kitchen, a toilet, a balcony and a corridor, and arrangement information of lamps, power supply switches and power supply sockets; then taking extracted characteristic vectors as a foundation and carrying out deep learning and model training on the residential unit plan with the finished electrical design to generate a domestication model; processing a dwg file of a unit plan without the electrical design by utilizing the domestication model and distinguishing each room; carrying out lamp, power supply switch and power supply socket arrangement on each room and connecting wires; finally, outputting the unit plan with the finished electrical design. The residential unit plan electrical design method provided by the invention has the advantages of convenience, rapidness, standardization and the like, and keeps original design specifications and styles and the like of Party A or a design institute to a certain extent.

Description

technical field [0001] The invention relates to a machine-learning-based electrical design method for residential floor plans, and belongs to the technical field of residential electrical computer-aided design. Background technique [0002] With the development of information technology, the field of artificial intelligence has attracted more and more people's attention. Among them, machine learning, as the core of artificial intelligence technology, has been continuously applied to various aspects of various industries. On the other hand, with the development of the real estate industry, more and more residential buildings are being built all over the country. In the usual real estate real estate development, the developer usually entrusts the design work of the building to the design institute. Because the developer That is, Party A is considering cost planning and project development progress, etc., and Party A's designers need to make frequent revisions to the design of ...

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): G06F17/50G06N99/00
CPCG06N20/00G06F30/13G06F30/20
Inventor 王丽华高子恒张永宏
Owner NANJING UNIV OF INFORMATION SCI & TECH
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