Weldability analysis and ANFIS modelling on laser welding of Inconel 718 thin sheets

The influence of the pulsed Nd:YAG laser welding process on the microstructure and mechanical characteristics of Inconel 718 alloy weldments of 1 mm thin sheets was investigated. By varying the selected input variables such as laser power, weld speed, and pulse duration, an analysis has been done on...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Materials and manufacturing processes 2022-07, Vol.37 (10), p.1190-1202
Hauptverfasser: Thejasree, Pasupuleti, Krishnamachary, P. C.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The influence of the pulsed Nd:YAG laser welding process on the microstructure and mechanical characteristics of Inconel 718 alloy weldments of 1 mm thin sheets was investigated. By varying the selected input variables such as laser power, weld speed, and pulse duration, an analysis has been done on the weld characteristics, namely penetration and top and bottom width by Taguchi's approach. The results were presented by focusing on weld bead geometry, grain structure in the Fusion Zone (FZ), Heat Affected Zone (HAZ), and the tensile properties. The FZ and HAZ microstructure consists of equiaxed, columnar grain structures, respectively, and clear ductile failure was observed with weldment. The combination of laser power at 2.5 kW, weld speed at 2.38 mm/min, and pulse duration at 6.6 ms achieves minimum top and bottom width. Similarly, a combination with 3.3 kW laser power, 2.02 mm/min weld speed, and 8.4 ms pulse duration offers maximum possible penetration that results in quality weldments. The influence of process variables was analyzed by ANOVA. A hybrid Grey-ANFIS model is evolved for determining the multiple performance index. From the validation outcomes attained (MAPE - 0.0413, correlation coefficient - 0.9991), it is proved that the evolved model is proficient for precise prediction.
ISSN:1042-6914
1532-2475
DOI:10.1080/10426914.2022.2039694