Optimum Model for Material Removal Rate in Abrasive Water-Jet Machining: A Validation Through Artificial Neural Network

The current research is centered on creating an ideal model for the material removal rate in Abrasive Water-Jet Machining. When assessing Material Removal Rate (MRR) in Abrasive Water-Jet Machining (AWJM), important process variables such abrasive flow rate, standoff distance, jet pressure, and traverse speed are considered. The model is validated utilizing Artificial Neural Network (ANN). The study centers on EN 8 material, a prevalent technological alloy. Comprehensive experimental data on material removal rate (MRR) for EN 8 material is collected, followed by an in-depth analysis to identify the intricate relationships between the input variables and MRR. The ANN's ability to identify complex and unpredictable relationships in the data makes it a valuable validation tool. The dataset is utilized for training the neural network, and various validation metrics are employed to assess its performance. The study aims to enhance understanding of the dynamics of the AWJM process and provide a reliable approach for measuring MRR in machining operations using EN 8 material. The proposed model and validation techniques help optimize AWJM parameters, leading to enhanced precision and efficiency in cutting EN 8 material.