Key points are not available for this paper at this time.
A prediction model using a linear regression model and Artificial Neural Network for the abrasive water jet machining of Aluminum-alloy 7024 was the main objective of this study. The abrasive water jet experiments were carried out based on the Taguchi Design. The influence of three independent variables such as pressure (200, 250, 300, and 350 MPa), feed rate (40, 60, 80, and 100 mm/min), and Gap or standoff distance (1, 2, 3, and 4 mm) as input and use Surface Roughness (Ra) were examined using analysis of variance (ANOVA) as output. The ANOVA response graphs show that pressure has the greatest impact on Ra as a function of feed rate and Gap. The regression model was sophisticated between the studied factors and the response. The confirmation tests show that the regression models are in well approval. The estimated determination of the coefficient value was (0.96). As a result, the maximum error between the obtained Artificial Neural Network (ANN) and experimental data is less than the regression model. The prediction model of ANN was found to be more accurate when compared with the regression model. The ANN results have a good acceptance between the predicted and experimental data, with a mean square error of training indices equal to (0.001).
Ahmed et al. (Thu,) studied this question.