Prediction of biases for optical proximity correction through partial coherent identification

Moongyu Jeong, Jae W. Hahn

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Most approaches to model-based optical proximity correction (OPC) use an iterative algorithm to determine the optimum mask. Each iteration requires at least one simulation, which is the most time-consuming part of model-based OPC. As the layout becomes more complicated and the process conditions are driven to the physical limit, the required number of iterations increases dramatically. To overcome this problem, we propose a method to predict the OPC bias of layout segments with a single-hidden-layer neural network. The segments are characterized by length and based on intensities at the corresponding control points, and these features are used as input to the network, which is trained with an extreme learning machine. We obtain a best-error root mean square of 1.29 nm from training and test experiments for layout clips sampled from a random contact layer of a logic device. In addition, we reduced the iterations by 27.0% by initializing the biases in the trained network before performing the main iterations of the OPC algorithm.

Original languageEnglish
Article number013509
JournalJournal of Micro/ Nanolithography, MEMS, and MOEMS
Volume15
Issue number1
DOIs
Publication statusPublished - 2016 Jan 1

Fingerprint

iteration
proximity
Identification (control systems)
layouts
Logic devices
predictions
Learning systems
Masks
Neural networks
clips
machine learning
root-mean-square errors
logic
education
masks
Experiments
simulation

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Condensed Matter Physics
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Cite this

@article{9afa97c660f342ddbee4734ac64f4c2f,
title = "Prediction of biases for optical proximity correction through partial coherent identification",
abstract = "Most approaches to model-based optical proximity correction (OPC) use an iterative algorithm to determine the optimum mask. Each iteration requires at least one simulation, which is the most time-consuming part of model-based OPC. As the layout becomes more complicated and the process conditions are driven to the physical limit, the required number of iterations increases dramatically. To overcome this problem, we propose a method to predict the OPC bias of layout segments with a single-hidden-layer neural network. The segments are characterized by length and based on intensities at the corresponding control points, and these features are used as input to the network, which is trained with an extreme learning machine. We obtain a best-error root mean square of 1.29 nm from training and test experiments for layout clips sampled from a random contact layer of a logic device. In addition, we reduced the iterations by 27.0{\%} by initializing the biases in the trained network before performing the main iterations of the OPC algorithm.",
author = "Moongyu Jeong and Hahn, {Jae W.}",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/1.JMM.15.1.013509",
language = "English",
volume = "15",
journal = "Journal of Micro/ Nanolithography, MEMS, and MOEMS",
issn = "1932-5150",
publisher = "SPIE",
number = "1",

}

Prediction of biases for optical proximity correction through partial coherent identification. / Jeong, Moongyu; Hahn, Jae W.

In: Journal of Micro/ Nanolithography, MEMS, and MOEMS, Vol. 15, No. 1, 013509, 01.01.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of biases for optical proximity correction through partial coherent identification

AU - Jeong, Moongyu

AU - Hahn, Jae W.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Most approaches to model-based optical proximity correction (OPC) use an iterative algorithm to determine the optimum mask. Each iteration requires at least one simulation, which is the most time-consuming part of model-based OPC. As the layout becomes more complicated and the process conditions are driven to the physical limit, the required number of iterations increases dramatically. To overcome this problem, we propose a method to predict the OPC bias of layout segments with a single-hidden-layer neural network. The segments are characterized by length and based on intensities at the corresponding control points, and these features are used as input to the network, which is trained with an extreme learning machine. We obtain a best-error root mean square of 1.29 nm from training and test experiments for layout clips sampled from a random contact layer of a logic device. In addition, we reduced the iterations by 27.0% by initializing the biases in the trained network before performing the main iterations of the OPC algorithm.

AB - Most approaches to model-based optical proximity correction (OPC) use an iterative algorithm to determine the optimum mask. Each iteration requires at least one simulation, which is the most time-consuming part of model-based OPC. As the layout becomes more complicated and the process conditions are driven to the physical limit, the required number of iterations increases dramatically. To overcome this problem, we propose a method to predict the OPC bias of layout segments with a single-hidden-layer neural network. The segments are characterized by length and based on intensities at the corresponding control points, and these features are used as input to the network, which is trained with an extreme learning machine. We obtain a best-error root mean square of 1.29 nm from training and test experiments for layout clips sampled from a random contact layer of a logic device. In addition, we reduced the iterations by 27.0% by initializing the biases in the trained network before performing the main iterations of the OPC algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84961774659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961774659&partnerID=8YFLogxK

U2 - 10.1117/1.JMM.15.1.013509

DO - 10.1117/1.JMM.15.1.013509

M3 - Article

AN - SCOPUS:84961774659

VL - 15

JO - Journal of Micro/ Nanolithography, MEMS, and MOEMS

JF - Journal of Micro/ Nanolithography, MEMS, and MOEMS

SN - 1932-5150

IS - 1

M1 - 013509

ER -