Electric appliance category and use state identification method based on machine learning and socket equipment

A technology of machine learning and state recognition, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as inability to safely locate and support electricity use, and inability to accurately identify the use status of a single electrical appliance, so as to improve safety, The effect of reducing the amount of calculation and reducing the cost

Pending Publication Date: 2022-05-27
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Non-intrusive load monitoring usually has simpler hardware and more complex software. You only need to install a monitoring device at the power inlet to monitor the total electricity consumption information of all electrical appliances, and you can identify the types of all electrical appliances, but often It is impossible to accurately identify the use status of a single electrical appliance, so it is impossible to accurately locate and support the safety of electricity use

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
  • Electric appliance category and use state identification method based on machine learning and socket equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] like figure 1 As shown in the figure, a method for identifying electrical appliance categories and usage states based on machine learning specifically includes the following steps:

[0043] S1. Collect the current data of a plurality of electrical appliances to be tested in continuous use, and construct an electrical current data set;

[0044] S2, constructing a classification network of electrical appliance usage status, obtaining an electrical appliance usage status classification model, classifying the electrical appliance status during use, and further dividing the electrical appliance current data set according to the classification result to obtain the electrical appliance status current data set;

[0045] S3. Perform feature extraction on the current data in the electrical state current data set, and construct a classification network for electrical categories and usage states according to the extracted current features, and obtain an electrical category and usag...

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 an electric appliance category and use state identification method based on machine learning and socket equipment, and the method specifically comprises the steps: S1, collecting the current data of a plurality of to-be-tested electric appliances in continuous use, and constructing an electric appliance current data set; s2, constructing an electrical appliance use state classification network to obtain an electrical appliance use state classification model, classifying electrical appliance states, and performing division according to a classification result to obtain an electrical appliance state current data set; s3, performing feature extraction on the electric appliance state current data set, constructing an electric appliance category and use state classification network according to features, and obtaining an electric appliance category and use state classification model for training; and S4, according to the trained electric appliance category and use state classification model, identifying the electric appliance category and use state of the inserted to-be-tested electric appliance, and predicting the power consumption of the electric appliance. Compared with the prior art, the intelligent socket has the advantages that the safety of the intelligent electric appliance in the using process is improved, the cost of the intelligent socket is reduced, and the full using state of the electric appliance is classified.

Description

technical field [0001] The present invention relates to the technical field of electrical equipment, and in particular, to a method for identifying electrical appliance categories and usage states based on machine learning, and socket equipment. Background technique [0002] With the rapid development of computer technology, communication technology and Internet of Things technology, smart home has gradually entered people's daily life, providing many conveniences for people's lives. Smart sockets are an important part of smart homes. The most widely used smart sockets on the market today are equipped with load monitoring capabilities. Users can monitor the power consumption and working status of household appliances in real time, which is convenient for users to find problems in time and ensure the safety of electrical appliances. [0003] An effective home energy management system (HEMS) at the consumer level is an important part of the smart home of the future, especial...

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): G06K9/62G06N3/04G06N3/08H01R13/66
CPCG06N3/088H01R13/66G06N3/045G06F18/2414Y04S20/242
Inventor 薛广涛张喆陈奕超潘昊
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products