A neural-Taguchi-based quasi time-optimization control strategy for chemical-mechanical polishing processes

Abstract

Besides the major factors such as the down force, back pressure and the rotating speed of wafer carrier, effect of polishing time is also an important issue in CMP processes. In this study, a neural-Taguchi method based on a cost-effective quasi time-optimisation technique for chemical-mechanical polishing (CMP) processes is developed. The key concept of this new technique is that an optimal process parameter set is obtained through a neural-network-simulated CMP process model. Under such an optimal parameter set, the desired material removal rate within-wafer-nonuniformity can be reached with the optimal polishing time. It has been proved by experiment that the proposed method can offer a better polishing performance while reducing the polishing time by 1/3

Fuzzy predictive R2R control to CMP process

“…For nonlinear characteristic of CMP process, intelligence and statistics based the controllers have been presented. The neural network controller [4,[11][12][13][14], a grey predictive model and recursive least square based controller [15], a d-EWMA controller based on recursive Least squares and real coded genetic algorithm[ [16], and a CMP process predivtive model based on Bayesian analysis and statistical regression modeling [17] are proposed.…”

Process parameters selection for laser polishing DF2 (AISI O1) by Nd:YAG pulsed laser using orthogonal design

“…As an orthogonal design of the experimental method [24] has successfully been used in investigating the effect of multifactorial engineering problems [3,9,25], it is herewith used to explore the possible optimal or nearoptimal laser setting parameters for smoothening the originally machined surface of ASSAB DF2 cold work (AISI O1) tool steel specimens with a pulsed Nd:YAG laser under continuously scanning modes (Figs. 1 and 2).…”