Abstract
Using a neural network, the refractive index of a film deposited in a plasma enhanced chemical vapor deposition is characterized. The deposition process was characterized by a 2 6-1 fractional factorial experiment. Experimental variables and ranges include 20–40 W radio frequency (RF) power, 80–160 Pa pressure, 180–260 sccm SiH 4 flow rate, 1–1.4 sccm NH 3 flow rate, 0–1000 sccm N 2 flow rate, and 200–300°C substrate temperature. To examine the effect of the interaction between variables on the refractive index, a predictive neural network model was constructed. Prediction accuracy was optimized as a function of training factors. Model predictions were certified experimentally. Many complex interactions between the variables not reported previously were revealed. The power effect was transparent only in such plasma conditions as high SiH 4 or NH 3 flow rate. The temperature effect was conspicuous under high pressure. Deposition mechanisms were qualitatively estimated in conjunction with the reported linear dependency of refractive index on SiH/NH ratio.
Sign-in/Register to access full text options 
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.
