Canonical correlation analysis-based non-invasive load identification method

A technology of canonical correlation analysis and load recognition, applied in character and pattern recognition, pattern recognition in signals, measurement devices, etc., can solve the problem of low recognition accuracy of similar loads, achieve good recognition characteristics, good representation ability, and reduce performance. effect of demand

Inactive Publication Date: 2018-03-23
TIANJIN UNIV
View PDF9 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the defect of low recognition accuracy of similar loads in the non-intrusive loa

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
  • Canonical correlation analysis-based non-invasive load identification method
  • Canonical correlation analysis-based non-invasive load identification method
  • Canonical correlation analysis-based non-invasive load identification method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0092] Specific embodiment: The load on-line decomposition experiment selects the transient currents of 6 types of non-R type loads in the generalized ON event of the BLUED (Building-Level Fully-labeled dataset for Electricity Disaggregation) database as experimental samples, and the total number of samples is 517. Three quarters of each type of samples were randomly selected as the training set, and one quarter was used as the test set, and the experiment was repeated 8 times under the same experimental environment. The Refrigerator2 and Light transient currents in the 6 types of samples are similar, and are used to verify the recognition performance of the feature selection method described in the present invention for similar electrical appliances.

[0093] For load transient currents such as figure 2 As shown, the multi-dimensional waveform features and S-transform harmonic features are respectively extracted, and the S-transform harmonic features are as follows image 3...

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 present invention relates to the signal process and mode identification field, in particular to a canonical correlation analysis-based non-invasive load identification method. The canonical correlation analysis-based non-invasive load identification method is characterized by starting from the current data on a bus, processing a transient current during a load switching process, firstly extracting the multi-dimension waveform features of the transient current, secondly extracting the S-transform harmonic features of the transient current, and then using the correlation analysis to fuse themulti-dimension waveform features and the S-transform harmonic features, and finally using a SVM classifier to classify the loads, thereby realizing the load on-line decomposition. By using the canonical correlation analysis to fuse the multi-dimension transient current waveform features and the S-transform harmonic features, a final fused feature set has the better representational capacity, hasthe multi-dimension waveform feature identification advantage to the general loads, and also has the identification advantage to the similar loads in details. By using the canonical correlation analysis to fuse the two types of features, the non-invasive load identification method has the better identification feature to the loads of which the electrical properties are similar.

Description

technical field [0001] The invention relates to the field of signal processing and pattern recognition, in particular to a non-invasive load recognition method based on canonical correlation analysis. Background technique [0002] As an important basic component of the smart grid, the smart meter has the functions of raw power consumption data collection, power consumption information storage, two-way multi-rate metering, user-end control, and two-way communication. important basis. The rapid collection and generation of massive power consumption information during the operation of smart meters constitutes big data in the power industry. Through the analysis and mining of these massive smart meter data, better innovative services can be provided for electricity customers, power supply companies and the social environment. This is where the value of smart meter data analysis lies. Another important use of smart meters is to collect and store household load power information...

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
IPC IPC(8): G06K9/00G06K9/62G01R22/06
CPCG01R22/06G06F2218/10G06F2218/12G06F18/2132G06F18/253
Inventor 吕卫蔡志强褚晶辉
Owner TIANJIN 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap