Unlock instant, AI-driven research and patent intelligence for your innovation.

Ultra-wideband low-noise amplifier based on artificial neural network

A low-noise amplifier, artificial neural network technology, applied in low-noise amplifiers, amplifiers, power amplifiers and other directions, can solve problems such as inability to provide, and achieve the effect of expanding high-frequency gain bandwidth

Active Publication Date: 2017-06-13
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of existing ultra-wideband low-noise amplifiers that cannot provide the best noise data NF in the operating frequency band due to traditional technology and design limitations, the present invention provides an ultra-wideband low-noise amplifier based on artificial neural networks

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
  • Ultra-wideband low-noise amplifier based on artificial neural network
  • Ultra-wideband low-noise amplifier based on artificial neural network
  • Ultra-wideband low-noise amplifier based on artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0039] The core of the present invention is to use the artificial neural network to generate the required control voltage across the variable resistor formed by the second PMOS transistor M4 and the second NMOS transistor M3. The inherent nonlinear mapping capability of the artificial neural network itself enables the network to approximate the nonlinear function with high precision, thereby generating a control voltage that is a nonlinear function of the frequency, and the voltage controls the second PMOS transistor M4, the second NMOS transistor M3 gate Voltage, so that the resistance of the variable resistor changes so that the circuit can obtain the optimal noise figure NF under the conditions of gain and matching.

[0040] Such as figure 1 Shown is a schematic structural diagram of the ultra-wideband low-noise amplifier based on the arti...

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 ultra-wideband low-noise amplifier based on an artificial neural network and belongs to the field of radio frequency integrated circuits. The ultra-wideband low-noise amplifier comprises a control voltage generation module and an ultra-wideband low-noise amplifier module, the ultra-wideband low-noise amplifier module comprises a variable resistor composed of a second NMOS (n-channel metal oxide semiconductor) transistor M3 and a second PMOS (p-channel metal oxide semiconductor) transistor M4, and the control voltage generation module is composed of a sensor, a data selector, an input data processing unit, the artificial neural network and an output data processing unit. Inherent nonlinear mapping capability of the artificial neural network is utilized to enable the artificial neural network to approach a nonlinear function in a high-accuracy manner so as to generate control voltage having a nonlinear relationship with frequency, and the control voltage is applied to grid electrodes of the second NMOS transistor M3 and the second PMOS transistor M4 to change resistance value of the variable resistor, so that noise data NF of a circuit are improved to maximum extent while bandwidth, gain and excellent matching are guaranteed.

Description

technical field [0001] The invention belongs to the field of radio frequency integrated circuits, and in particular relates to an ultra-wideband low-noise amplifier based on an artificial neural network. Background technique [0002] With the development of short-distance wireless communication, people have higher and higher requirements for the performance of high-speed wireless communication systems. Larger capacity, faster speed and safer communication are the inevitable development trend of short-distance wireless communication. The wireless communication system is inseparable from the receiver. The front-end radio frequency module in the receiver is the low-noise amplifier LNA, which has an important impact on the entire receiver and the entire communication system. In order to meet the requirements of high-speed transmission, the low-noise amplifier LNA is required to work in a wide frequency range, so the research on ultra-wideband low-noise amplifiers has been initia...

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 Applications(China)
IPC IPC(8): H03F1/26H03F1/42H03F3/21H03F3/24
CPCH03F1/26H03F1/42H03F3/21H03F3/245H03F2200/294H03F2200/372H03F2200/451
Inventor 刘洋顾珣莫雁杰高宝玲雷旭于奇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA