On the Modelling of the Dimensional Characteristics for Holes After Thermal Friction Drilling | ||||
| The Egyptian International Journal of Engineering Sciences and Technology | ||||
| Article 1, Volume 41, Issue 2, March 2023, Page 56-63 PDF (1.21 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/eijest.2022.127014.1143 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
M. Abdelhameed  1; H. A. E. SH. Alajmi2; S. S. Mohammed2; T. S. Mahmoud2
| ||||
| 1Mechanical Design and Production Department, Faculty of Engineering, Zagazig University, Zagazig 44519, Egypt. | ||||
| 2Mechanical Engineering Department, Faculty of Engineering at Shoubra, Benha University, Cairo 13518, Egypt. | ||||
| Abstract | ||||
| Thermal Friction drilling (TFD) process is a non-traditional, hole forming process that produces bushing without the formation of chips. The TFD is generally used to create a bushing on sheet metal, tubing, or/and thin-walled shapes for joining parts in an easy and effective way. In the present works, the AA6082 aluminium alloy sheets were drilled using TFD using different process variables, namely, the tool rotational speed (TRS), tool feed rate (TFR) and the tool conical angle (TCA). The influence of the abovementioned variables on the hole dimensional characteristics i.e., the hole diameter (HD), the bushing height (BH), and the bushing thickness (BT) were examined. The regression analysis and artificial neural network (ANN) approaches were applied to predict the hole dimensional characteristics. The results revealed that the developed ANN models were successfully used to predict the hole dimensional characteristics. While the linear regression models failed to the hole dimensional characteristics with an acceptable accuracy. The linear regression and ANN models for predicting the dimensional characteristics showed maximum mean average percentage error (MAPE) values of 46.30% and 16.46%, respectively. | ||||
| Keywords | ||||
| Thermal friction drilling; AA6082 aluminium alloy; Bushing thickness; Hole diameter; Artificial neural network | ||||
|
Statistics Article View: 155 PDF Download: 167 |
||||
