Cutting parameters identification using multi adaptive network based Fuzzy inference system: An artificial intelligence approach

Abstract

The influences of the machine parameters on machined parts are not always precisely known and hence, it becomes difficult to recommend the optimum machinability data for machine process. This paper proposes a method for cutting parameters identification using Multi adaptive Network based Fuzzy Inference System (MANFIS). Three Adaptive Network based Fuzzy Inference System (ANFIS) models were used in the first step to identify the initial values for the cutting parameters (cutting speed, feed rate, and depth of cut) using surface roughness as a single input, in the next step these parameters were modified and verified using another set of ANFIS models. Then, workpiece surface temperature is used as input for another set of ANFIS models to amend the final values of the cutting parameters. In this way, multi-input-multi-output ANFIS structure presented, which can identify the cutting parameters accurately once the desired surface roughness and in-process measured surface temperature were entered to the system. The test results showed that the proposed MANFIS model can be used successfully for machinability data selection.