| Autor: |
Deshpande, Yogesh V., Zanwar, Dinesh R., Andhare, A. B., Barve, P. S. |
| Předmět: |
|
| Zdroj: |
Advances in Materials & Processing Technologies; Sep2023, Vol. 9 Issue 3, p728-741, 14p |
| Abstrakt: |
Abrasive water jet machining (AWJM) is the modern machining method used in various industrial applications. In this paper, an attempt has been made to determine optimum AWJM parameters using artificial neural network (ANN). Flow rate of abrasive, stand-off distance and traverse speed are used as input parameters for machining of AISI 1018 steel. Experimental data are used for training and testing of ANN. A feed forward ANN is established using the experimental data obtained during the AWJ machining of steel. Surface roughness (Ra) and kerf taper angle (ϴ) are estimated, on the basis of ANN performance and regression analysis. The regression plots of both responses show more than 97% of agreement among the estimated values and experimental data. Later on, novel approach of model optimisation is executed using univariate analysis on inputs to ANN to get the optimal AWJM process parameters. Optimal response solution is obtained as surface roughness (Ra) = 2.46 μm and taper angle (ϴ) = 1.25° at flow rate (Af) = 450 g/min; stand-off distance (Sd) = 3 mm and traverse speed (Tv) = 85 mm/min. The study shows that the ANN is proficient tool for deciding the optimum AWJ machining parameters. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
