A Neural Network-Based Correction Method for Electron Beam Proximity Effect

A neural network and proximity effect technology, applied in the field of computational lithography, can solve problems such as difficult layout calculations, many iterations of physical methods, and limited accuracy of integrated circuit masks

Active Publication Date: 2021-04-27
HUNAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can obtain high-precision correction, but its calculation process is complicated, and it is difficult to apply to large-scale layout calculations.
[0005] Although there is a method to accurately calculate the proximity effect correction, the application of large-scale integrated circuits cannot be quickly and effectively solved due to the large number of iterations of the physical method or the calculation steps include complex calculation units, which limits the masking capacity of integrated circuit manufacturing. Membrane precision

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 Neural Network-Based Correction Method for Electron Beam Proximity Effect
  • A Neural Network-Based Correction Method for Electron Beam Proximity Effect
  • A Neural Network-Based Correction Method for Electron Beam Proximity Effect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] What the present invention relates to is a kind of electron beam proximity effect correction method based on neural network, such as figure 1 As shown, the method first needs to design a two-dimensional training layout of any shape, binary modeling; use any proximity effect dose correction method; input the characteristic training graph as a training sample, and the correction result of the dose correction method As the training sample output of the neural network, the trained neural network can be used as the correction network model of the corresponding features, which can greatly improve the calculation efficiency while ensuring the accuracy.

[0047] 1. Design a two-dimensional training layout according to the minimum graphic features of the required correction layout;

[0048] like figure 2 As shown, the minimum graphic...

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 computational lithography, and discloses a method for correcting the proximity effect of an electron beam based on a neural network. The present invention first corrects the dose of the designed training layout through any kind of proximity effect dose correction method, then adjusts the neural network parameters, and performs neural network training on the training layout according to the prescribed input method to obtain an adaptive neural network. Network, and finally predict the correction dose of any exposure layout according to the specified input method. The invention realizes the correction of the proximity effect of the electron beam based on the neural network, and solves the correction calculation of the proximity effect of the electron beam exposure. On the basis of ensuring high-precision correction, the calculation efficiency of the correction is greatly improved, and it has high calculation accuracy and high calculation efficiency. Efficiency and other characteristics.

Description

technical field [0001] The invention relates to a correction method for proximity effect in accelerated electron beam lithography. Through a neural network training method, on the basis of ensuring high-precision correction, the calculation efficiency of correction is greatly improved, and belongs to the field of computational lithography. Background technique [0002] Electron beam lithography (EBL) is an important technology for micro-nano processing to prepare high-resolution nanoscale lithography layouts, and has broad application prospects. Proximity effects in e-beam lithography degrade pattern quality in small-scale exposures below 10 nanometers, and direct exposure without proximity correction (PEC) has a large impact on resolution, limiting the range of e-beam exposures. resolution. [0003] As the smallest features in integrated circuits are continuously reduced to the nanometer scale to increase circuit density, proximity effects are no longer negligible. The co...

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): G03F7/20G03F1/36G06N3/04G06N3/08
CPCG03F7/2059G03F7/70441G03F1/36G06N3/084G06N3/045
Inventor 刘杰姚文泽侯程阳段辉高陈艺勤周剑
Owner HUNAN 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