Application of artificial neural network to determine the thickness profile of thin film

As the thickness of the material decreases compared to the other two dimensions, the surface characteristics dominate the bulk properties of the material and then decide its overall physical and chemical behavior [1]. With the advancement of the thin film technology, now it has become possible to create a wide range of variations in the characteristics of the thin-films by controlling the vital parameters of the growth process paving their way of use in the most technologically advanced applications and industries. As in such applications, almost all the properties of a particular thin film depend on its thickness, hence an accurate estimate of the thickness has been one of the most important deciding factor in the application of thin films in industrial sectors. Some examples of such sectors are display industry, semiconductor devices, eye glasses, stents, solar cells, polymer coatings, photoresists, solar panels, LCD, MEMS, thin-film packaging etc. There have been different methods in use for the measurement of the thin film thicknesses. Ion beam analysis, TEM, ellipsometry, surface profilometry etc. are few examples to mention about. In the present work we have proposed to automate the estimation of the thickness of a growing thin-film by applying an artificial neural network (ANN).