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

Multifunctional self-adaptive filter based on wavelet neural network and filtering method

A wavelet neural network and adaptive filter technology, applied in the field of filters, can solve the problems of single function and weak adaptive ability.

Active Publication Date: 2016-10-26
JINING POWER SUPPLY CO OF STATE GRID SHANDONG ELECTRIC POWER CO +1
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Conventional adaptive filters or notch filters have the technical problems of single function and weak self-adaptive ability

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
  • Multifunctional self-adaptive filter based on wavelet neural network and filtering method
  • Multifunctional self-adaptive filter based on wavelet neural network and filtering method
  • Multifunctional self-adaptive filter based on wavelet neural network and filtering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention is described in detail below in conjunction with accompanying drawing:

[0041] The structure of the multifunctional adaptive filter system is as follows: figure 1 As shown, it includes an input layer, and the input layer includes an original input unit for inputting an original signal and a reference input unit for inputting a reference signal,

[0042] Hidden layer, in the hidden layer, the signal output by the reference input unit is divided into two paths, one path is directly transmitted to the synchronous sampling unit, the other path is delayed by the delay unit and then transmitted to the synchronous sampling unit, the output of the original input unit Transmission to the synchronous sampling unit, the synchronous sampling unit samples the input original signal and then transmits it to the subtracter, the synchronous sampling unit samples the input reference signal and then transmits it to the algorithm processing unit, the algorithm proces...

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 multifunctional self-adaptive filter based on a wavelet neural network and a filtering method. The filter comprises an input layer, wherein the input layer comprises an original input unit which is used for inputting an original signal and a reference input unit which is used for inputting a reference signal; a hidden layer, wherein in the hidden layer, a synchronous sampling unit samples the input original signal and then the signal is transmitted to a subtracter, and the synchronous sampling unit samples the input reference signal and then the signal is transmitted to an algorithm processing unit; and an output layer, wherein in the output layer, the output of the subtracter is taken as notch output, and the output of an adder is taken as narrowband output. According to the multifunctional self-adaptive filter based on the wavelet neural network (WNN), the filter can be taken as a notch filter for removing one or certain signals with determined frequency, and the filter also can be taken as a narrowband filter for passthrough of the signal with specific frequency.

Description

technical field [0001] The invention relates to a filter, in particular to a wavelet neural network-based multifunctional self-adaptive filter and a filtering method. Background technique [0002] Adaptive filters and notch filters are commonly used devices in electronic circuits, mainly used for harmonic suppression, wave detection, etc. Adaptive filters: In general, the structure of adaptive filters is not changed. The coefficients of the adaptive filter are time-varying coefficients updated by the adaptive algorithm. That is, its coefficients are automatically and continuously adapted to a given signal to obtain the desired response. The most important feature of an adaptive filter is its ability to work effectively in unknown environments and to track the time-varying characteristics of the input signal. [0003] The notch filter is a resonant circuit, or an automatic switch sensor, which can be used in antenna engineering to automatically extend or shorten the length ...

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): H03H21/00
CPCH03H21/002H03H21/0021
Inventor 冯维华李伟明姚博文李萌邵新国杨保徐保友杨卫国李新玲
Owner JINING POWER SUPPLY CO OF STATE GRID SHANDONG ELECTRIC POWER CO
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