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

A Harmonic Detection Method Based on the Combination of PLL and Neural Network

A neural network and harmonic detection technology, applied in the electrical field, can solve problems such as low accuracy, achieve the effect of improving accuracy and real-time performance, and avoiding delay

Inactive Publication Date: 2011-12-21
UNIV OF SHANGHAI FOR SCI & TECH
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem of low precision of current harmonic detection methods, and proposes a harmonic detection method based on the combination of phase-locked loop and neural network to further improve the accuracy and real-time performance of harmonic detection

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
  • A Harmonic Detection Method Based on the Combination of PLL and Neural Network
  • A Harmonic Detection Method Based on the Combination of PLL and Neural Network
  • A Harmonic Detection Method Based on the Combination of PLL and Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] First, enough samples of three-phase power grid current data signals are collected, and Fourier transform is performed on them offline to calculate the fundamental current amplitude. The collected three-phase current signal and the peak value of the three-phase current calculated in the last power frequency cycle are used as the input of the neural network, and the amplitude of the three-phase current fundamental wave calculated by Fourier transform is used as the output of the neural network, and the hidden layer takes 35 neurons, the neural network is trained offline, the structure of the neural network is as follows figure 1 shown.

[0014] Put the trained neural network into the active power filter system, and calculate the fundamental current amplitude according to the input in real time. At the same time, after the three-phase current passes through the phase-locked loop, a sinusoidal signal with an amplitude of 1 and the same phase as the fundamental amplitude i...

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 harmonic detection method based on the combination of a phase-locked loop and a neural network. After the three-phase current passes through the phase-locked loop, a sinusoidal signal whose amplitude is 1 and whose phase is the same as the amplitude of the fundamental wave is obtained. The signal is multiplied by the current fundamental amplitude calculated by the neural network to obtain the fundamental current signal, and the collected three-phase grid current is subtracted from the fundamental current signal to obtain no pure harmonic signal. This method does not involve a low-pass filter components, thus avoiding the delay in the system caused by the difference equation of the low-pass filter, and the composition of the neural network is basically composed of multiplication and addition operations, which is very suitable for the realization of DSP. In addition, the output of offline neural network training only needs the fundamental wave The amplitude can be calculated by using the traditional Fourier transform, which is not complicated and improves the accuracy and real-time performance of harmonic detection. Also suitable for engineering applications.

Description

technical field [0001] The invention relates to an electrical technology, in particular to a harmonic detection method based on the combination of a phase-locked loop and a neural network. Background technique [0002] With the development of power electronic technology, the pollution of power grid harmonics is becoming more and more serious. The active power filter is a power device specially used for harmonic suppression. Its principle is to control the main circuit to generate harmonics with the same amplitude and opposite phase as the harmonic current of the grid after detecting the harmonic current of the grid to reduce the harmonics of the grid. Offset, so that the grid current approaches the sine wave and reaches the specified level. The traditional harmonic detection method is the ip-iq method based on the instantaneous reactive power theory. The disadvantage of this harmonic detection method is that the detection accuracy is low, and there is a certain time delay, ...

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): G01R23/165
Inventor 马立新肖川郑益文
Owner UNIV OF SHANGHAI FOR 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

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