Abstract

This study presents a new method for modeling an adaptive neuro-fuzzy inference system (ANFIS) based on vibration for predicting surface roughness in the CNC turning process. The input parameters of the model are insert nose radius, cutting speed, feed rate, depth of cut and vibration amplitude, which determine the output parameter of the surface roughness. A Gauss type membership function was used to train on ANFIS. The predicted values derived from ANFIS were compared with experimental data. The obtained prediction accuracy of 97.52% demonstrates that the developed system’s improved performance over other models available in the literature. The resulting ANFIS model based on vibration efficiently uses the fuzzy inference system for predicting surface roughness in turning of AISI 1040 steel.

Key words: Adaptive neuro-fuzzy inference system (ANFIS), CNC turning, surface roughness, prediction model.

Abbreviation

FLIS, Fuzzy logic inference system; ANFIS, adaptive neuro-fuzzy inference system; PEEK, polyether ether ketone; PCD, Poly-Crystalline Diamond; ANN,artificial neural network; MANFIS, multi adaptive Network based fuzzy inference system;RSM, response surface methodology; SVR, support vector regression; MF, membership function