Surface roughness monitoring application based on artificial neural networks for ball-end milling operations

Authors:
G. Quintana;M. L. Garcia-Romeu;J. Ciurana
Affiliations:
ASCAMM Technology Centre, Barcelona, Spain;Mechanical Engineering and Industrial Construction Department, University of Girona, Girona, Spain;Mechanical Engineering and Industrial Construction Department, University of Girona, Girona, Spain
Venue:
Journal of Intelligent Manufacturing
Year:
2011

Citing 2
Cited 7

A Bayesian network model for surface roughness prediction in the machining process

International Journal of Systems Science
Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process

Expert Systems with Applications: An International Journal

Application of ANN in milling process: a review

Modelling and Simulation in Engineering
Modeling and adaptive force control of milling by using artificial techniques

Journal of Intelligent Manufacturing
The evolutionary development of roughness prediction models

Applied Soft Computing
Multi-objective prediction model for the establishment of sputtered GZO semiconducting transparent thin films

Journal of Intelligent Manufacturing
Application of fuzzy logic and regression analysis for modeling surface roughness in face milliing

Journal of Intelligent Manufacturing
Neural network based modeling and optimization of deep drawing --- extrusion combined process

Journal of Intelligent Manufacturing
Improvement of surface roughness models for face milling operations through dimensionality reduction

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Surface roughness plays an important role in the performance of a finished part. The roughness is usually measured off-line when the part is already machined, although in recent years the trend seems to have been to focus on online monitoring. Measuring and controlling the machining process is now possible thanks to improvements and advances in the fields of computers and sensors. The aim of this work was to develop a reliable surface roughness monitoring application based on an artificial neural network approach for vertical high speed milling operations. Experimentation was carried out to obtain data that was used to train the artificial neural network. Geometrical cutting factors, dynamic factors, part geometries, lubricants, materials and machine tools were all considered. Vibration was captured on line with two piezoelectric accelerometers placed following the X and Y axes of the machine tool.