The prediction of wafer surface non-uniformity using FEM and ANFIS in the chemical mechanical polishing process

In this paper, modeling of a two-dimensional axisymmetric quasic-static finite element model, in conjunction with an adaptive-network-based fuzzy inference system (ANFIS) for chemical mechanical polishing process, or CMP for short, was established. The prediction of non-uniformity on wafer surfaces under various combinations of process parameters can be achieved. The data of non-uniformity on wafer surface can be obtained under different conditions of the carrier load, the pads elastic modulus and thickness by using the developed finite element model for CMP. Three input process parameters have been used in the ANFIS model to predict the non-uniformity on wafer surfaces. In this model, three types of membership function for analysis in ANFIS training were adopted and their differences compare the accuracy rate of prediction of non-uniformity on wafer surfaces.