Abstract
Optical scatterometry by use of a neural network is now recognized as an efficient method for retrieving dimensions of gratings in semiconductors or glasses. For an on-line control, a small number of measurements and a rapid data treatment are needed. We demonstrate that these requirements can be met by combining data preprocessing and a proper neural learning method. A good accuracy is attainable with the measurement of only a few orders, even in the presence of experimental errors, with a reduction in learning and computing time.
Highlights
The increasing integration density in integrated electronic circuits gives rise to new manufacturing capabilities that can be used in the optical domain for the realization of periodic structures of increased spatial frequency
The neural network performances were evaluated on the basis of 100 new simulated gratings with parameters randomly chosen in the range defined above
Where n is the number of simulated gratings (n ϭ 100), pex is the exact grating parameter value, and pcal is the calculated value given by the neural network
Summary
The increasing integration density in integrated electronic circuits gives rise to new manufacturing capabilities that can be used in the optical domain for the realization of periodic structures of increased spatial frequency. The last operation is known as the inverse-problem resolution These two stages must be optimized for the low response time needed for a realistic industrial measurement method: The number of diffracted intensities to be measured must be sufficiently low and the treatment of the experimental data instantaneous. In the optical diffracted domain, a neural network has been used to develop an inspection method for a grating structure.[7] several methods for solving the inverse problem include a neural network.[8] Some early results obtained by means of a neural analysis were not as accurate as those obtained from classical linear regression, such as the partial least square method[4] in particular. The conclusion emphasizes the advantages and weaknesses of the method and identifies where future work should be directed
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
