A fuzzy-net-based multilevel in-process surface roughness recognition system in milling operations

摘要: This paper describes a fuzzy-nets approach for multilevel in-process surface roughness recognition (FN-M-ISRR) system, the goal of which is to predict (R ) under multiple cutting conditions determined by tool material, workpiece size, etc. Surface was measured indirectly extrapolation from vibration signal and condition data, were collected in real-time an accelerometer sensor. These data analysed model constructed using neural fuzzy system. Experimental results showed that parameters spindle speed, feedrate, depth cut, variables could eight different combinations characteristics. system shown with 90% prediction accuracy during milling operation.