Impact Resistance of AISI 304L Stainless Steel Welded Joints at Low Temperatures | ||||
| Engineering Research Journal (Shoubra) | ||||
| Volume 51, Issue 1, January 2022, Page 21-26 PDF (705.43 K) | ||||
| Document Type: Research articles | ||||
| DOI: 10.21608/erjsh.2022.224248 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Abdullah Bader Aljeaan; Samah Samir Mohamed | ||||
| Mechanical Engineering Department, Faculty of Engineering at Shoubra, Benha University | ||||
| Abstract | ||||
| In the present investigation, the impact energy of the AISI 304L austenitic stainless steel (ASS) alloy welded joints were evaluated at both ambient and low temperatures up to -80 ᵒC. Moreover, regression analysis (RA) and artificial neural networks (ANN) techniques were used to develop models to predict the impact energy of the AISI 304L base alloy (BA) and the welded joints. A comparison between the two developed RA and ANN models was carried out. The results revealed that the impact energy of the AISI 304L base alloy and welded joints was found to be reduced with reducing the test temperature. However, the AISI 304L base alloy exhibited higher impact energy when compared with the welded joints. Such behavior was observed at both ambient and low temperatures. Both RA and ANN models can be used to predict the impact energy of the AISI 304L base alloy as well as the welded AISI 304L joints as a function of temperature at both ambient and low temperatures. The RA and ANN models exhibited mean absolute percentage error (MAPE) of 1.22% and 1.34% for the AISI 304L base alloy, respectively. While the RA and ANN models exhibited MAPE of 2.13% and 1.41% for the welded AISI 304L joints, respectively. | ||||
| Keywords | ||||
| AISI 304L; Impact Toughness; GTAW; Low Temperatures; Artificial Neural Networks | ||||
|
Statistics Article View: 112 PDF Download: 413 |
||||
