Optimisation of Predicted Wear and Friction for Electroless Ni-P by RSM, Fuzzy Logic and ANFIS Using TOPSIS

This study examined the frictional and wear properties of electroless Ni-P coatings in a dry environment. The experiment is carried out with Taguchi's L-27 orthogonal array and three testing parameters: load (N), speed (V) and time (T). Four prediction model, namely response surface methodology (RSM), fuzzy logic (Mamdani), fuzzy logic (Sugeno) and adaptive Network-based fuzzy inference system (ANFIS), has been used to predict the wear depth and Friction coefficient. Further, the TOPSIS technique, a multi-criteria decision analysis method, is used to find the best predictive model concerning friction and wear characteristics. In a dry environment, ANFIS and RSM will be able to predict the best tribological performance; for friction and wear, their coefficients of determination (R-2) are 0.989 and 0.994, respectively.