Volume 15, No 2, 2018
Application Of Neural Network Technique To Predict The Tool Wear During Turning Of E0300 Steel
Dr. Sandeep M. Salodkar
Abstract
This research paper presents a predictive approach for detecting tool wear using neural network modeling of cutting tool flank wear to assess the performance of the CCMT 09 T3 08 WF 1525 insert during turning of E0300 alloy steel. Actual cutting tool flank wear data were utilized in this study, and a back propagation neural network model was developed to forecast flank wear during turning operations. The experimental data were employed to train the artificial neural network model, with cutting speed, feed rate, and depth of cut serving as input parameters and corresponding flank wear as the output of the neural network model. The trained neural network's performance was assessed using experimental data. This investigation demonstrates the effective application of fuzzy logic techniques for tool wear monitoring in turning processes.
Pages: 282-293
Keywords: fuzzy logic techniques, neural network, E0300 alloy steel.