The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
L'interféromètre laser hétérodyne agit comme un appareil de mesure ultra-précis dans la fabrication de semi-conducteurs. Cependant, la propriété de non-linéarité périodique causée par la diaphonie en fréquence constitue un obstacle à l’amélioration de la précision des mesures à l’échelle nanométrique. Afin de minimiser l'erreur de non-linéarité de l'interféromètre hétérodyne, nous proposons un algorithme de compensation de diaphonie en fréquence utilisant une méthode d'intelligence artificielle. Le réseau neuronal à action directe entraîné par rétro-propagation compense l'erreur de non-linéarité et se régule pour minimiser la différence avec le signal de référence. Avec quelques résultats expérimentaux, la précision améliorée est prouvée par comparaison avec la valeur de position d'un capteur de déplacement capacitif.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Wooram LEE, Gunhaeng HEO, Kwanho YOU, "Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 2, pp. 681-684, February 2009, doi: 10.1587/transfun.E92.A.681.
Abstract: The heterodyne laser interferometer acts as an ultra-precise measurement apparatus in semiconductor manufacture. However the periodical nonlinearity property caused from frequency cross-talk is an obstacle to improve the high measurement accuracy in nanometer scale. In order to minimize the nonlinearity error of the heterodyne interferometer, we propose a frequency cross-talk compensation algorithm using an artificial intelligence method. The feedforward neural network trained by back-propagation compensates the nonlinearity error and regulates to minimize the difference with the reference signal. With some experimental results, the improved accuracy is proved through comparison with the position value from a capacitive displacement sensor.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.681/_p
Copier
@ARTICLE{e92-a_2_681,
author={Wooram LEE, Gunhaeng HEO, Kwanho YOU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry},
year={2009},
volume={E92-A},
number={2},
pages={681-684},
abstract={The heterodyne laser interferometer acts as an ultra-precise measurement apparatus in semiconductor manufacture. However the periodical nonlinearity property caused from frequency cross-talk is an obstacle to improve the high measurement accuracy in nanometer scale. In order to minimize the nonlinearity error of the heterodyne interferometer, we propose a frequency cross-talk compensation algorithm using an artificial intelligence method. The feedforward neural network trained by back-propagation compensates the nonlinearity error and regulates to minimize the difference with the reference signal. With some experimental results, the improved accuracy is proved through comparison with the position value from a capacitive displacement sensor.},
keywords={},
doi={10.1587/transfun.E92.A.681},
ISSN={1745-1337},
month={February},}
Copier
TY - JOUR
TI - Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 681
EP - 684
AU - Wooram LEE
AU - Gunhaeng HEO
AU - Kwanho YOU
PY - 2009
DO - 10.1587/transfun.E92.A.681
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 2
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - February 2009
AB - The heterodyne laser interferometer acts as an ultra-precise measurement apparatus in semiconductor manufacture. However the periodical nonlinearity property caused from frequency cross-talk is an obstacle to improve the high measurement accuracy in nanometer scale. In order to minimize the nonlinearity error of the heterodyne interferometer, we propose a frequency cross-talk compensation algorithm using an artificial intelligence method. The feedforward neural network trained by back-propagation compensates the nonlinearity error and regulates to minimize the difference with the reference signal. With some experimental results, the improved accuracy is proved through comparison with the position value from a capacitive displacement sensor.
ER -