An effective approach to predict the minimum tool wear of machining process of Inconel 718

Abstract

Recently, Inconel 718 plays a crucial role in various manufacturing applications for instance aircraft and gas applications. But it is difficult to machining process. To solve this, Rotary Ultrasonic Machining (RUM) methodology is presented. In general, ultrasonic machine technology requires ultrasonic vibration precision to be applied in the machining process. Also, it is difficult to design of machining process with maximum machining performance with low tool wear in experimental. Since it takes more time and cost as well as energy. Hence, to predict the maximum machining performance with low tool wear in the machining of Inconel 718, a prediction model is required. For this, Levenberg-Marquardt (LM) and Artificial Neural Network-based prediction model is proposed. Here LM algorithm is used for the training process of ANN. The results show that the proposed prediction has outperformed than other methods for predicting machining rate and tool wear of machining of Inconel 718. Since the average errors of the proposed prediction model are low, i.e., 0.008746648 for machining rate and 0.037792507 for tool wear.