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

Multi-level feature matching non-intrusive electrical equipment detection method for home environment

A feature matching, non-invasive technology, applied in the direction of measuring electricity, measuring devices, measuring electrical variables, etc.

Active Publication Date: 2021-08-27
杭州拓深科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a multi-level feature matching non-intrusive electrical equipment detection method based on Euclidean distance, and adopts a feature database organization structure based on classification and continuous update, which solves the problem of matching and updating iterations of the feature database

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
  • Multi-level feature matching non-intrusive electrical equipment detection method for home environment
  • Multi-level feature matching non-intrusive electrical equipment detection method for home environment
  • Multi-level feature matching non-intrusive electrical equipment detection method for home environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with accompanying drawing.

[0027] Such as figure 1 As shown, the multi-level feature matching non-intrusive electrical equipment detection method based on Euclidean distance of the present invention includes the following steps:

[0028] 1. Electrical feature extraction

[0029] The current and voltage are sampled at a sampling frequency of 6.4kHz, and the following 5-dimensional features are extracted from the sampled values: steady-state current feature (feature F1), start-up time feature (feature F2), start-up impulse current ratio feature (feature F3), current Jump times feature (feature F4), power factor feature (feature F5).

[0030] Steady-state current feature extraction (feature F1): use the sampling current as a calculation unit for each period of 128 sampling points, and calculate the effective value of the current Take the effective value of 50 continuous calculation units, if the val...

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 discloses a multi-level feature matching non-invasive electrical equipment detection method based on Euclidean distance, adopts a feature database organization structure based on classification and continuous updating, and solves the matching and updating iteration problems of the feature database. It includes the following steps: the initial feature library is empty; when the electrical appliance is connected, the current steady-state situation is switched, and the 5-dimensional feature is extracted; the existing feature vectors of all electrical appliances in the first-level feature database are traversed and the characteristics of the above-mentioned connected electrical appliances are calculated. The Euclidean distance d of the vector; traversing the next-level feature database for matching; the obtained recognition result is prompted to the user, and the user modifies it manually. After modification, the current feature vector is bound to the classification manually modified by the user.

Description

technical field [0001] The invention belongs to the field of electric equipment detection, and in particular relates to a family environment-oriented multi-level feature matching non-invasive electric equipment detection method. Background technique [0002] At present, there are two main methods for judging the mainstream electrical equipment. One is to install an independent detection module on each device; the other is to install a module at the meter, which is called non-intrusive detection. method. The first method is very costly and complicated to install; the second non-invasive detection method has huge advantages in cost and convenience. But most of them need to be based on a large number of data samples. For example, if you want to detect an air conditioner access event of a certain brand, you need to collect a large number of current and voltage waveforms of the air conditioner in different operating modes in advance, and extract features as samples. Since ther...

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 Patents(China)
IPC IPC(8): G01R31/00G06F16/21G06F16/23
CPCG01R31/00
Inventor 张轩铭王利强梁昆陈龙
Owner 杭州拓深科技有限公司
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