Mask optimization method based on residual network

Zainan Xiao; Shuang Xu; Zhiqiang Chen

doi:10.1117/12.2649554

14 October 2022 Mask optimization method based on residual network

Zainan Xiao, Shuang Xu, Zhiqiang Chen

Proceedings Volume 12343, 2nd International Conference on Laser, Optics and Optoelectronic Technology (LOPET 2022); 1234332 (2022) https://doi.org/10.1117/12.2649554
Event: 2nd International Conference on Laser, Optics and Optoelectronic Technology (LOPET 2022), 2022, Qingdao, China

Abstract

With the development of the integrated circuit manufacturing process, the critical dimension of optical lithography is reduced. Due to the optical diffraction effect, the influence of the distortion of the lithography output pattern on the integrated circuit is gradually increasing. Mask optimization in lithography is a very critical issue. In this paper, a residual network-based mask optimization method is proposed. Using the optimization masks generated by the traditional gradient descent method and its corresponding initial input masks as the training set, the residual network is trained by the inverse lithography optimization process. The parameters of the residual network weight layer are optimized. The optimized results are projected in the forward lithography model to obtain an exposure pattern of the wafer. Compared with the traditional gradient descent method, this method can improve the calculation efficiency and realize the distortion correction of the images generated by lithography.

Citation Download Citation

Zainan Xiao, Shuang Xu, and Zhiqiang Chen "Mask optimization method based on residual network", Proc. SPIE 12343, 2nd International Conference on Laser, Optics and Optoelectronic Technology (LOPET 2022), 1234332 (14 October 2022); https://doi.org/10.1117/12.2649554

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available