Volume 15, No 1, 2018
Development Of Tool Wear Model And Wear Estimation During Turning Of Hard Alloy Steel Using Acoustic Emission Technique
Dr. Sandeep M. Salodkar
Abstract
This study presents the development of a tool wear model aimed at estimating the tool wear during the turning process of E0300 alloy steel. The acoustic emission technique is employed for this purpose. Various process parameters, including cutting speed, feed rate, and depth of cut, are utilized as input variables, while the corresponding flank wear under these conditions serves as the output of the neural network model. The efficacy of the trained neural network is evaluated using experimental data. The research demonstrates the effective application of fuzzy logic techniques for monitoring tool wear in turning operations. Specifically, the paper outlines a predictive approach for detecting tool wear, employing a neural network model to predict the flank wear of a CCMT 09 T3 08 WF 1525 insert during the turning of E0300 alloy steel. Actual cutting tool flank wear data are employed in the study, and a backpropagation neural network model is developed to forecast the flank wear during turning operations.
Pages: 274-286
Keywords: tool wear detection, flank wear, artificial neural network model, fuzzy logic technique.