Identification of Important Parameters for Laser Photoresist Removal Process Through the Use of Adaptive Neuro-Fuzzy Inference System
(ANFIS) Methodology
B. Petković, S. Resic and D. Petković
Laser photoresist removal in gaseous media is based on different parameters or factors like energy of laser pulse, frequency of pulse repetition and flow rate of gas. A statistical soft computing approach was applied in this article in order to determine which parameters have the most influence on the photoresist removal process by laser. As the statistical approach adaptive neuro-fuzzy inference system (ANFIS) was used since the methodology can handle strongly nonlinear data. By selected the most important factors one can adjust the photoresist removal process in order to produce the best final product. For the selecting process three input parameters are used: laser energy, rate of pulse repetition of laser and flow rate of hydrogen gas. These parameters are selected for the analysing since these are independent variables. Pulse of laser repetition is selected as the most important factor for the photoresist removal process. Predictive models were created based on ANFIS network and corresponding results are compared with standard conventional approaches.
Keywords: Excimer laser, photoresist, gas media, operating parameters, removal, prediction, statistical soft computing, adaptive neuro-fuzzy inference system (ANFIS)