Determination of lapping parameters for silicon wafer using an artificial neural network

An artificial neural network (ANN) simulation was utilized to determine the lapping parameters such as rotation speed, lapping duration and lapping pressure under a constant slurry supply for n-type crystalline Silicon (c-Si) wafers. Experiments were done with a Logitech PM5 lapping and polishing machine to obtain input data and target data for training, testing and validation of ANN. Lapping operation had five main parameters affecting surface quality: rotation speed, lapping duration, lapping pressure, flowrate of abrasive slurry and particle size in abrasive slurry. However, in this study slurry flowrate was assumed constant due the researches performed before. 218 lapping operations were performed with different values of the selected parameters and new lapping parameters were derived for different lapping conditions to achieve the best surface quality by using an ANN. In this study, wafers in 400 µm thickness cut under identical conditions from n-type single c-Si ingot in a STX 1202 DWS cutting machine were employed. Surface roughness (R_a) values were measured three times from different points of the wafers after lapping with a contact type surface roughness measurement tool using a microscopic scale stylus profiler (SP). In ANN simulation 70% of R_a values were utilized for training, 15% of R_a values were utilized for validation and 15% of R_a values were utilized for test data. Results obtained from ANN simulation validated with a success above 99%.