Flank Wear Prediction based on Vision System in Turning Process

Abstract

Tool wear and life are major factors that influence part quality. To evaluate the useful life of an instrument, most industries rely on historical data. Tool wear may be measured in two ways: directly and indirectly. Tool wear is traditionally assessed using microscope, which is time-consuming method. The tool wear measured using the indirect approach uses parameter that impact tool life. Direct method such as digital image processing is fast and reliable. The goal of this research is to employ digital image processing techniques to automate flank wear assessment, predict flank wear, and improve tool life parameters. The process of measuring and monitoring tool wear is automated using digital image processing techniques. The three most important characteristics were investigated: speed, feed, and depth of cut. CMOS camera sensor has been used for online image based tool wear measurement. Different algorithms related to feed forward back propagation neural network such as Levenberg - marquardt algorithm, Bayesian regularization Scaled conjugate gradient are used to predict the tool life. Comparative study of different algorithm is done to find most accurate algorithm for tool life prediction system.