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

A Crystal Oscillator Based on Artificial Neural Network

A technology of artificial neural network and crystal oscillator, applied in the direction of biological neural network model, neural architecture, neural learning method, etc., can solve problems such as insufficient temperature compensation accuracy, achieve improved frequency stability, high compensation accuracy, and overcome compensation effects bad effect

Active Publication Date: 2018-10-16
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the shortcomings of the existing TCXO and VCTCXO that the temperature compensation accuracy is not enough due to the nonlinear relationship between the compensation voltage and frequency, the present invention provides a crystal oscillator based on artificial neural network

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 Crystal Oscillator Based on Artificial Neural Network
  • A Crystal Oscillator Based on Artificial Neural Network
  • A Crystal Oscillator Based on Artificial Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Combine below Figure 4 and Figure 5 , taking BP neural network as a model and taking VCTCXO mode as an example to give a specific embodiment of a crystal oscillator based on artificial neural network of the present invention. The artificial neural network in the present invention can be other forms of models, and the present invention is not only applicable to VCTCXO, but also applicable to TCXO.

[0042] Figure 4 Taking the VCTCXO mode as an example, an embodiment of an artificial neural network-based crystal oscillator of the present invention is provided, and the embodiment includes a control voltage generating module and a crystal oscillator module.

[0043] The control voltage generating module is composed of a temperature sensor, a frequency meter, a data selector, an input data processing unit, an artificial neural network and an output data processing unit, and its function is to generate a nonlinear function V about temperature T and frequency f;

[0044]...

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 belongs to the field of integrated circuits, in particular to an artificial neural network-based crystal oscillator. The crystal oscillator includes a control voltage generating module and a crystal oscillator module. The control voltage generation module is composed of temperature sensor, frequency meter, data selector, input data processing unit, artificial neural network and output data processing unit. The invention generates the control voltage required at both ends of the varactor diode through the artificial neural network, and utilizes the inherent nonlinear mapping capability of the artificial neural network itself, so that the network can approximate the nonlinear function with high precision, thereby generating a nonlinear function to temperature The control voltage accurately compensates the frequency deviation of TCXO and VCTCXO due to temperature changes by controlling the capacitance of the varactor diode, and significantly improves its frequency stability.

Description

technical field [0001] The invention belongs to the field of integrated circuits, in particular to an artificial neural network-based crystal oscillator. Background technique [0002] As a stable frequency source, crystal oscillators are widely used in portable electronic equipment and wireless communication technology, and the stability of their frequency to temperature changes is one of the important indicators to measure the performance of crystal oscillators. A temperature compensated crystal oscillator (TCXO) uses a temperature compensation network to reduce the offset of the oscillator output frequency due to temperature changes, thereby improving frequency stability. [0003] A temperature compensated crystal oscillator (TCXO) generally consists of a temperature compensation network, a varactor diode, a crystal resonator and an oscillation circuit module, such as figure 1 shown. Its working principle is: the temperature compensation network generates a control volta...

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): H03L1/02G06N3/04G06N3/08
CPCH03L1/022G06N3/084G06N3/045
Inventor 刘洋高宝玲王俊杰郭睿莫雁杰顾珣于奇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA