Simplified fuzzy neural network reinforced Wiener model based power amplifier predistortion method

A technology of fuzzy neural network and Wiener model, which is applied in biological neural network models, improving amplifiers to reduce nonlinear distortion, etc., can solve problems such as difficult extraction of model parameters, control implementation and application, and achieve simplified learning time and iteration times Few, easy-to-achieve effects

Inactive Publication Date: 2011-03-30
SOUTHEAST UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the neural network is an effective method for nonlinear dynamic system modeling, most neural network models are multi-layer perceptron struc

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
  • Simplified fuzzy neural network reinforced Wiener model based power amplifier predistortion method
  • Simplified fuzzy neural network reinforced Wiener model based power amplifier predistortion method
  • Simplified fuzzy neural network reinforced Wiener model based power amplifier predistortion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The specific steps of the power amplifier predistortion method based on the enhanced Wiener model of the simplified fuzzy neural network of the present invention are as follows:

[0032] a) Using a broadband modulation signal as the baseband input signal of the power amplifier, using a high-speed analog-to-digital converter to collect the input and output baseband data of the power amplifier,

[0033] b) Using the input and output data of the collected power amplifier to establish a power amplifier model for pre-distortion, that is, an enhanced Wiener model based on a simplified fuzzy neural network,

[0034] c) training the parameters of the power amplifier model to achieve a desired error, to finally determine the parameters of the power amplifier model,

[0035] d) Establish the inverse model of the enhanced Wiener model based on the simplified fuzzy neural network,

[0036] f) Pass the baseband input signal through the inverse model, then pass through the quadratur...

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 simplified fuzzy neural network reinforced Wiener model based power amplifier predistortion method, mainly comprising a fuzzy neural network subsystem and an FIR filter subsystem. The fuzzy neural network subsystem is composed of a simplified fuzzy neural network in second order Sugeno FIS structure and is used for compensating amplitude and phase distortion characteristics of power amplifier, and the FIR filter subsystem is composed of two parallel finite-impulse-response (FIP) filters and is used for compensating memory effect of the power amplifier. An indirect learning structure is combined, parameters of the fuzzy neural network are identified by a learning algorithm combining least squares and counterpropagation, and coefficient of a linear FIR filter is determined by least squares. The predistortion scheme has the advantages that implementation complexity is not improved, the characteristics of flexibility and stability of the simplified fuzzy neural network structure are combined, the characteristics of the reinforced Wiener model are utilized, spectral regrowth of wideband power amplifier caused by undesirable wideband matching is compensated, and accurate modelling of power amplifier with wideband depth memory effect can be realized.

Description

technical field [0001] The present invention relates to a predistortion method for linearization of power amplifiers, in particular to a digital predistortion method based on an enhanced Wiener (Augmented Wiener) model of a simplified fuzzy neural network (MANFIS, modified adaptive neuro-fuzzy inference system) method. Background technique [0002] The rapid development of wireless communication technology has put forward higher requirements for the performance indicators of the communication system. As an important part of the wireless communication transmission system, the power amplifier is also the most difficult and expensive part to realize. Indicators such as data transmission rate, coverage, spectrum utilization, and out-of-band spectrum spurs have a great impact. [0003] With the application of modern wireless communication networks (WCDMA, WLAN, WiMAX, etc.), high-speed wireless data transmission increases the peak-to-average ratio of the signal, which requires t...

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): H03F1/32G06N3/02
Inventor 周健义晋石磊洪伟
Owner SOUTHEAST 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