Artificial Neural Networks Estimation for Thicknesses of Multilayer Nano-Scale Films

Abstract:

This study presents a real-time method for determining the thickness of each layer in multilayer thin films. Artificial neural networks (ANNs) were introduced to estimate thicknesses from a transmittance spectrum. After training via theoretical spectra which were generated by thin-film optics and modified by noise, ANNs were applied to estimate the thicknesses of four-layer nanoscale films which were TiO₂, Ag, Ti, and TiO₂ thin films assembled sequentially on polyethylene terephthalate (PET) substrates. The results reveal that the mean squared error of the estimation is 2.6 nm², and is accurate enough to monitor film growth in real time.

• Periodical: Materials Science Forum (Volume 962)
• Pages: 41-48
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.962.41
• Online since: July 2019
• Authors: Tzong Daw Wu*, Jiun Shen Chen, Ching Pei Tseng, Cheng Chang Hsieh
• Keywords: Artificial Neural Networks, Multilayer, Noise, Thickness, Thin Film

References

[1] K. Ali, S.A. Khan, and M.Z.M. Jafri: Effect of double layer (SiO2∕TiO2) anti-reflective coating on silicon solar cells. Int. J. Electrochem. Sci. 9 (Oct. 2014), 7865-7874.

[2] A.A. Solovyev, S.V. Rabotkin, and N.F. Kovsharov: Polymer films with multilayer low-E coatings. Mater. Sci. Semicond. Process. 38 (Oct. 2015), 373-380.

DOI: 10.1016/j.mssp.2015.02.051

[3] M. Ylilammi, and T. Ranta-aho: Optical determination of the film thicknesses in multilayer thin film structures. Thin Solid Films 232 (Sep. 1993), 56-62.

DOI: 10.1016/0040-6090(93)90762-e

[4] J.C. Manifacier, J. Gasiot, and J.P. Fillard: A simple method for the determination of the optical constants n, k and the thickness of a weakly absorbing thin film. J. Phys. E: Sci. Instrum. 9, 11 (1976), 1002-1004.

DOI: 10.1088/0022-3735/9/11/032

[5] Y.D. Pyung, M. Chang, and E. Kim, et al: Modeling and optimization of the growth rate for ZnO thin films using neural networks and genetic algorithms. Expert Syst. Appl. 36, 2 (Mar. 2009), 4061-4066.

DOI: 10.1016/j.eswa.2008.03.010

[6] A. Khorasani, A. Kootsookos, and P. Saadatkia: Artificial Neural Network Modelling on TiN Coating Parameters in Sputtering Process. In 3rd International and 12th National Conference on Manufacturing Engineering (Tehran, Iran, December 27 - 29, 2011). 1-6.

[7] H. Wang, S.J. Hsieh, and A. Stockton: Evaluating the performance of artificial neural networks for estimating the nonmetallic coating thicknesses with time-resolved thermography. Opt. Eng. 53, 8 (Aug. 2014), 083102.

DOI: 10.1117/1.oe.53.8.083102

[8] H.A. Macleod, in: Thin-Film Optical Filters, 4th ed. CPC Press, Boca Raton, Florida, 13-71. (2010).

[9] J.A.K. Suykens, J.P.L. Vandewalle, and B.L.R. Moor: Artificial neural networks: architectures and learning rules. In Artificial Neural Networks for Modelling and Control of Non-Linear Systems. Springer Science + Business Media, Dordrecht, 19-35.

DOI: 10.1007/978-1-4757-2493-6_2

[10] T.D. Wu, J.S. Chen, and C.P. Tseng, et al: Applying theoretical spectra to artificial neural networks for real-time estimation of thin film thickness. Opt. Eng. 55, 12 (Dec. 2016).

DOI: 10.1117/1.oe.55.12.125106

[11] P.G. Benardos, and G.C. Vosniakos: Optimizing feedforward artificial neural network architecture. Eng. Appl. Artif. Intel. 20, 3 (Apr. 2007), 365-382.

DOI: 10.1016/j.engappai.2006.06.005