On-Line Prediction Model of Ultrasonic Polishing Surface Roughness
In order to solve the difficulty of on-line measuring the surface roughness of workpiece under ultrasonic polishing, the artificial neural networks and fuzzy logic systems are introduced into the on-line prediction model of surface roughness. The surface roughness identification method based on fuzzy-neural networks is put forward and used to the process of plane polishing. In the end, the on-line prediction model of surface roughness is established. The actual ultrasonic polishing experiments show that the accuracy of this prediction model is up to 96.58%, which further evidence the feasibility of the on-line prediction model.
Bo Zhao, Guanglin Wang, Wei Ma, Zhibo Yang and Yanyan Yan
M. Zhang et al., "On-Line Prediction Model of Ultrasonic Polishing Surface Roughness", Key Engineering Materials, Vol. 455, pp. 539-543, 2011