Artificial-neural-networks-based surface roughness Pokayoke system for end-milling operations

Abstract

Surface roughness is an important indicator of the quality of machined parts. Commonly, the off-line, manual technique of direct measurement is utilized to assess surface roughness and part quality, which is found to be very time-consuming and costly. For that reason, the neural network-based surface roughness Pokayoke (NN-SRPo) system is developed to keep the surface roughness within a desired value in an in-process manner. Both the surface roughness prediction and machining parameters control are performed online during the machining process. A testing experiment demonstrated the efficacy of this NN-SRPo system.