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

An automatic recognition method for foreign objects in electric energy meters based on acoustic detection

An automatic identification and electric energy meter technology, which is applied in the field of electric energy meters, can solve problems such as the low detection accuracy of the sound signal recognition system, the wrong judgment of the listening recognition method, and the inaccurate detection results of the manual detection method, so as to achieve accurate and specific voice parameters. And effective, increase adaptability, beneficial to the effect of algorithm stability

Active Publication Date: 2022-03-22
STATE GRID CHONGQING ELECTRIC POWER CO ELECTRIC POWER RES INST +2
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] (1) The manual detection method is easy to cause inaccurate detection results due to human factors
[0009] During the artificial shaking process, due to factors such as the lead seal of the electric energy meter and the lack of tightening of the fixing screws of the watch case, noise with a frequency similar to that of the foreign object will be generated during the shaking process, resulting in an error in the judgment of the audio recognition method.
[0010] (2) The detection accuracy rate of the existing sound signal recognition system is not high

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
  • An automatic recognition method for foreign objects in electric energy meters based on acoustic detection
  • An automatic recognition method for foreign objects in electric energy meters based on acoustic detection
  • An automatic recognition method for foreign objects in electric energy meters based on acoustic detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Embodiment 1: as Figure 1 to Figure 6 Shown; A method for automatic identification of foreign matter in an electric energy meter based on acoustic detection, which includes:

[0066] S1: collect the sound signal data in the electric energy meter;

[0067] S2: Perform channel conversion on the collected sound signal data, and extract the sound signal data containing the foreign object channel;

[0068] S3: Denoising the extracted sound signal data through the variable step size LMS adaptive filtering algorithm;

[0069] S4: Preprocessing the denoised sound signal data, extracting short-term energy, MFCC coefficients and LPC coefficients and combining them into a feature matrix, performing dimensionality reduction processing on the feature matrix to obtain the feature vector corresponding to the maximum feature value;

[0070] S5: Input the feature vector into multiple Adaboost-based BP neural network weak classifiers, and use the feature vector as the feature of the f...

Embodiment 2

[0110] Embodiment 2: as Figure 1 to Figure 6 As shown; an automatic recognition method for foreign matter in electric energy meters based on acoustic detection, which includes: first, a channel conversion is performed on the collected sound data, and the sound data containing the foreign matter channel is extracted; secondly, through a variable step size adaptive filter The algorithm denoises the extracted sound signal, and then extracts short-term energy, MFCC coefficients and LPC coefficients through preprocessing, combines them into a feature matrix and performs dimensionality reduction processing on it to reduce the amount of data, and reduces dimensionality through matrix transformation The eigenvector corresponding to the largest eigenvalue is obtained; finally, the eigenvector is input into multiple BP neural network weak classifiers based on Adaboost, and the eigenvector is used as the feature of the foreign object sound signal in the electric energy meter and input in...

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 an automatic identification method for foreign objects in an electric energy meter based on acoustic detection, which comprises: collecting sound signal data in an electric energy meter; performing channel transformation on the collected sound signal data, and extracting the sound signal data containing the foreign object channel; Perform denoising processing on the extracted sound signal data; preprocess the denoised sound signal data, combine them into a feature matrix, and process the feature matrix to obtain the eigenvector corresponding to the largest eigenvalue; input the eigenvector into the neural network based on Adaboost. In the network weak classifier, the feature vector is used as the feature of the foreign object sound signal in the electric energy meter to classify and identify. The invention improves the detection efficiency of the electric energy meter, which is beneficial to improve the automatic process of electric energy meter detection; shortens the detection time of the electric energy meter, improves the production efficiency and the utilization rate of the equipment, and realizes a fast, efficient, safe and reliable electric energy meter Foreign object sound detection work; greatly improve the recognition rate of foreign object energy meter.

Description

technical field [0001] The invention relates to the technical field of electric energy meters, in particular to an automatic recognition method for foreign objects in electric energy meters based on acoustic detection. Background technique [0002] The detection of foreign matter in the existing electric energy meter generally adopts the method of "hand crank + human ear listening". In the verification workshop, the verification personnel shake the electric energy meter to listen to the sound, and can only shake one meter at a time, so the detection efficiency is low; in addition, the consistency of the movement of the manual shaking meter is poor, which will lead to unstable test results. Aiming at the problems of low efficiency and poor consistency of manual shaking meter detection, there is an urgent need for a system that can automatically detect the sound of foreign objects in electric energy meters. [0003] The sound detection technology is becoming more and more mat...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06F2218/04G06F2218/08G06F18/214
Inventor 张进周全欧习洋李享友吴华冯凌欧熙胡晓锐宫林吉畅周游陈术吴健唐皇
Owner STATE GRID CHONGQING ELECTRIC POWER CO ELECTRIC POWER RES INST
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