Surface roughness is influenced by the machining parameters and other uncontrollable factors resulting from the cutting tool in end milling operations. To perform the in-process surface roughness prediction (ISRP) system accurately, the uncontrollable factors must be monitored. In this paper, an empirical approach using a statistical analysis was employed to discover the proper cutting force to represent the uncontrollable factors in end milling operations. Furthermore, an in-process neural network-based surface roughness prediction (INN-SRP) system was developed. A neural network associated with sensing technology was applied as a decision-making system to predict the surface roughness for a wide range of machining parameters. The good accuracy of the results for a wide range of machining parameters indicates that the system is suitable for application in industry.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
ID="A1"Correspondance and offprint requests to: Dr J. C. Chen, Department of Industrial Education and Technology, Iowa State University, 221 I. ED II, Ames, IA 50011–3130, USA. E-mail: cschen@iastate.edu
Rights and permissions
About this article
Cite this article
Chen, J., Huang, B. An In-Process Neural Network-Based Surface Roughness Prediction (INN-SRP) System Using a Dynamometer in End Milling Operations. Int J Adv Manuf Technol 21, 339–347 (2003). https://doi.org/10.1007/s001700300039
Issue Date:
DOI: https://doi.org/10.1007/s001700300039