Power amplifier predistortion method of Hammerstein model based on fuzzy neural network

A fuzzy neural network and predistortion technology, applied in biological neural network models, improving amplifiers to reduce nonlinear distortion, physical implementation, etc. problem, to make up for the memory effect, increase the complexity, and achieve the effect of easy

Inactive Publication Date: 2010-03-17
SOUTHEAST UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Technical solution: The power amplifier predistortion method based on the Hammerstein model of the fuzzy neural network of the present invention combines the advantages of the Voltera series and the neural network, avoids its disadvantages, and solves the large amount of calculation of the existing predistortion scheme. The adaptation algorithm is not easy to converge, and it is more complicated to implement. Under the conditions of high bandwidth and peak-to-average signal ratio, it is difficult to compensate the complex memory effect of the power amplifier and other issues.

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
  • Power amplifier predistortion method of Hammerstein model based on fuzzy neural network
  • Power amplifier predistortion method of Hammerstein model based on fuzzy neural network
  • Power amplifier predistortion method of Hammerstein model based on fuzzy neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The baseband input signal I channel and Q channel of the power amplifier are collected through an analog-to-digital converter (ADC) to obtain power amplifier input data.

[0033] Through the analog-to-digital converter, the signals output by the power amplifier after passing through the attenuator, coupler, down-converter and quadrature demodulator are collected to obtain the output data of the power amplifier.

[0034] The inverse model of the power amplifier used in the predistortion scheme is established by using the output and input data of the power amplifier. The model is mainly composed of two parts, including a nonlinear subsystem without memory and a linear subsystem with memory. The nonlinear subsystem without memory is composed of The fuzzy neural network of the first-order Sugeno type (Sugeno) fuzzy inference system (FIS) structure is used to compensate the static amplitude and phase distortion characteristics of the power amplifier. The linear subsystem with...

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

A power amplifier predistortion method of a hammerstein model based on the fuzzy-neural network mainly comprises a non-linear subsystem without memory and a linear subsystem with memory. The non-linear subsystem without memory is composed of a fuzzy-neural network with a one-order Sugeno FIS structure, for compensating the static margin and the phase distortion characteristic of the power amplifier, while the linear subsystem with memory is composed of a finite impulse response (FIR) filter for compensating the memory effect of the power amplifier. Combined with the indirect learning structure, the parameters of the fuzzy-neural network are recognized by combining the Least square and the Back-propagation, and the linear FIR filter coefficient is determined by the Least square. The predistortion project not only makes up the nonlinear characteristics and the memory effect of the power amplifier, but also gives play to the advantages of agility, stabilization and high efficiency of thefuzzy-neural network on the aspect of predistortion and power amplifier modeling.

Description

technical field [0001] The invention relates to a predistortion method for linearization of a power amplifier, in particular to a digital predistortion method based on a Hammerstein model of a fuzzy neural network (ANFIS, adaptive neuro-fuzzy inference system). Background technique [0002] In modern communication systems (WCDMA, CDMA200, and WIMAX, etc.), spectrum resources are increasingly scarce with the ever-increasing data traffic. In order to improve spectrum utilization, various linear modulation techniques (QPSK, QAM and OFDM, etc.) have been proposed. Although the new modulation method can effectively alleviate the contradiction between spectrum and high-speed data transmission, it is harmful to the radio frequency system in the communication system. New problems were raised. Since these digital modulation methods all belong to non-constant envelope modulation, the modulation method with higher efficiency often has a larger peak-to-average ratio (PAR, Peak-to-avera...

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): H03F1/32G06N3/06
Inventor 周健义翟建锋洪伟
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