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

Neural network-based TFET device structure optimization and performance prediction method

A neural network and performance prediction technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of small conduction current and significant bipolar effect, so as to improve work efficiency and reduce the cost of modeling process Effect

Active Publication Date: 2021-10-22
XIDIAN UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, TFET devices also have the disadvantages of small conduction current and significant bipolar effect, so further research on TFET devices is still needed

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
  • Neural network-based TFET device structure optimization and performance prediction method
  • Neural network-based TFET device structure optimization and performance prediction method
  • Neural network-based TFET device structure optimization and performance prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] The invention provides a method for predicting the performance of a TFET device based on a neural network, comprising the following steps:

[0034] Step 1, determine the structural parameters and electrical performance parameters of the TFET device; obtain multiple sets of designed TFET device data as data to be trained, and construct a training sample set;

[0035] Wherein, the structural parameters include the gate oxide layer thickness, channel doping concentration, source-drain doping concentration and gate length of the TFET device, the electrical performance parameters include DC characteristic parameters and AC characteristic parameters, and the DC characteristic parameters include Threshold voltage, average sub-threshold swing, maximum transconductance and current switch ratio, the AC characteristic parameter is the maximum cut-off frequency; the TFET device data includes gate oxide layer thickness, channel doping concentration, source-drain doping Dopant concen...

Embodiment 2

[0078] The invention provides a kind of TFET device structure optimization method (reverse design) based on neural network, comprising the following steps:

[0079] Step 1, determine the structural parameters and electrical performance parameters of the TFET device; obtain multiple sets of designed TFET device data as data to be trained, and construct a training sample set;

[0080] Wherein, the structural parameters include the gate oxide layer thickness, channel doping concentration, source-drain doping concentration and gate length of the TFET device, the electrical performance parameters include DC characteristic parameters and AC characteristic parameters, and the DC characteristic parameters include Threshold voltage, average sub-threshold swing, maximum transconductance and current switch ratio, the AC characteristic parameter is the maximum cut-off frequency; the TFET device data includes gate oxide layer thickness, channel doping concentration, source-drain doping Dop...

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

PropertyMeasurementUnit
Thicknessaaaaaaaaaa
Login to View More

Abstract

The invention belongs to the technical field of microelectronic devices and artificial intelligence, and particularly discloses a TFET device structure optimization and performance prediction method based on a neural network. According to the invention, on the basis of the physical mechanism of the TFET, characteristic variables, such as gate oxide layer thickness, channel doping concentration, source-drain doping concentration and gate length, are selected; then a neural network is constructed, and correlation is established between the neural network and the electrical characteristics of the TFETs to serve as forward design. By taking network input data in the forward design as output data, taking the output data as input data, corresponding reverse design is carried out. According to the invention, the neural network is used for establishing the relationship between the structure and the electrical performance of the tunneling field effect transistor, so that the research on structure optimization and performance prediction of the tunneling field effect transistor can be accelerated.

Description

technical field [0001] The invention relates to the fields of microelectronic device technology and artificial intelligence technology, in particular to a method for structure optimization and performance prediction of a TFET device based on a neural network, which can be used in engineering design. Background technique [0002] The rapid development of information science, energy, national defense and other fields has put forward crucial and diverse requirements for devices and materials. However, traditional methods for discovering new devices and new materials, such as methods based on empirical trial and error and density functional theory, often have long development cycles, high costs, and low efficiency, and it is difficult to keep up with the development of today's materials science. The rapid development of neural networks provides another option for rapid prediction of device and material structures or properties, which can reduce computational costs and shorten de...

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): G06F30/27G06N3/04G06N3/08
CPCG06F30/27G06N3/084G06N3/045
Inventor 王树龙马兰王刚段小玲吴介豫刘钰孙承坤
Owner XIDIAN UNIV