A negative feedback automatic gain control circuit and method based on a neural network

An automatic gain control, neural network technology, applied in gain control, neural learning methods, biological neural network models, etc., can solve the problems of inaccurate circuit gain, deviation, etc., to improve error, improve linearity, and high gain control. Effect

Pending Publication Date: 2019-06-04
成都市深思创芯科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is: to solve the problem that the automatic gain control circuit in the prior art is biased due to the gain inaccuracy caused by the temperature, the circuit itself deviation, etc., the present invention provides a negative feedback automatic gain control circuit based on artificial neural network and methods

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 negative feedback automatic gain control circuit and method based on a neural network
  • A negative feedback automatic gain control circuit and method based on a neural network
  • A negative feedback automatic gain control circuit and method based on a neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] This embodiment provides a neural network-based negative feedback automatic gain control circuit, including an AGC module and a neural network module;

[0092] Further, the AGC module includes a variable gain amplifier VGA, a peak detection RSSI and a low-pass filter LPF. The variable gain amplifier is the core module of the entire AGC, its gain accuracy determines the accuracy of the AGC, and its linearity is an important factor for the linearity of the entire AGC. The peak detector RSSI is used to detect the energy of the output and quantify it, producing a voltage V p . The log amp converts RSSI to the V p Performing logarithmic amplification so that the entire feedback loop has a fixed time constant can also improve the linearity of the circuit. low pass filter for G m _C active filter to filter out the control voltage V c interference signal.

[0093] The neural network generates a reference voltage that can approximate the desired reference voltage with arbi...

Embodiment 2

[0104] On the basis of providing a neural network-based negative feedback automatic gain control circuit as described in Embodiment 1, Figure 6 It is a negative feedback automatic gain control topology diagram based on the LSTM (or RNN) neural network model proposed in this embodiment, consisting of a negative feedback automatic gain control circuit, an LSTM (or RNN) neural network module, and an analog-to-digital conversion It is composed of an ADC, which converts the input analog signal into a digital signal that the neural network can recognize. input signal V in , converted into a digital signal by the ADC, the LSTM (or RNN) neural network module identifies the signal and outputs a high-precision reference voltage according to its network weight value.

Embodiment 3

[0106] On the basis of a kind of negative feedback automatic gain control circuit based on neural network described in embodiment two, Figure 7 It is a kind of negative feedback automatic gain control topology structure diagram based on CNN (or FNN) neural network model proposed by the present embodiment, consisting of a negative feedback automatic gain control circuit, a CNN (or FNN) neural network module, an analog-to-digital conversion ADC and a two-to-one multiplexer register. After the input signal is converted by the ADC, the first register is enabled. When the first register is full, the second register is enabled. The two-choice one multiplex register can be selectively input, and the register has a trigger value. The two-choice A multi-way selection register and the register jointly realize the corresponding voltage (in this application, mainly the input voltage V in and the first control voltage V c ) adjustment of network weights. At the same time, the data stor...

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 negative feedback automatic gain control circuit and method based on a neural network, and aims to solve the problem of inaccurate gain deviation caused by temperature, circuit deviation and the like of an automatic gain control circuit in the prior art. An input learning sample of the neural network comprises an input voltage Vin of the whole circuit, a detection voltageVp output by the peak value detector and a first control voltage Vc output by the low pass filter; The circuit deviation of each module in the AGC or the working deviation caused by temperature change are better simulated, so that more accurate reference voltage is generated, the gain is more accurately controlled, and high-precision gain control is realized; The circuit and the method are applicable to the related field of gain control circuits.

Description

technical field [0001] The invention relates to the field of radio frequency automatic gain control circuits, in particular to a neural network-based negative feedback automatic gain control circuit. Background technique [0002] The dynamic range DR of the receiver is the power change from the minimum detectable signal to the input 1-dB compression point of the receiver, which is one of the most important performance indicators of the receiver. Generally, the general receiver has a dynamic range of 60-80dB. Modern receivers have strict requirements on the dynamic range, which are generally above 100dB. The size of the dynamic range of the receiver has a great relationship with the automatic gain control. [0003] In order to finally be able to demodulate the signal received by the antenna, an automatic gain control circuit (AGC) is required to amplify the signals of different powers received by the antenna to the minimum required for quantization and demodulation by the ba...

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): H03G3/30G06N3/08
Inventor 史峥宇程和肖潇王雯唐佇
Owner 成都市深思创芯科技有限公司
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