Interface optimization of dissimilar wire arc additive manufactured wall through ANN-TOPSIS conjugate algorithm-Reference-Cited by-同舟云学术

Interface optimization of dissimilar wire arc additive manufactured wall through ANN-TOPSIS conjugate algorithm

Published:2023-01-04 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Paul Amrit Raj¹,Bose S.²,Dhar A.R.²,Biswas S.³,Mukherjee Manidipto⁴^ORCID,Manivannan R.¹

Affiliation:

1. CMERI: Central Mechanical Engineering Research Institute CSIR

2. NIT-Durgapur: National Institute of Technology Durgapur

3. NIT Silchar: National Institute of Technology Silchar

4. Central Mechanical Engineering Research Institute CSIR

Abstract

Abstract The development of functionally graded structures (FGS) through the wire arc additive manufacturing (WAAM) technique is frequently associated with a number of interface-related issues that are mostly controlled by the input parameters. However, it is frequently noticed that the input-output correlation of FGS is quite complex, and a general statistic/stochastic optimisation technique is not very helpful in optimising the process objectives. Therefore, ANN-TOPSIS conjugate algorithm is proposed in this study to predict and optimise the Al-Ni and Ni-SS dissimilar interfaces. The proposed model shows more than 95% accurate prediction of interface characteristics along with <15% error between the validated and optimised responses. The metallurgical characterisation revealed the formation of AlNi intermetallic layer at the Al-Ni interface surrounded by Al3Ni at the Al side and AlNi3 at the Ni side closer to the interface. The SS-Ni interface mainly consist of FeNi3. The microhardness of the Al-Ni interface increases as the Al content of the Al-Ni IMC increases. The hardness of the Al-Ni interface is higher than that of the SS-Ni interface.

Publisher

Research Square Platform LLC

Reference31 articles.

1. Colegrove P & Williams S, High deposition rate high quality metal additive manufacture using wire + arc technology, Cranfield University, 2013.

2. Bekker A, Verlinden JC & Galimberti G, Challenges in assessing the sustainability of wire + arc additive manufacturing for large structures, In International Solid Freeform Fabrication Symposium, University of Texas at Austin, 2016.

3. Matlab deep learning. With machine learning;Kim P;neural networks and artificial intelligence,2017

4. Mahamood RM, Akinlabi ET, Shukla M & Pityana SL, Functionally graded material: an overview, (2012).

5. Paul AR, Mukherjee M, Raja M, Kundu S & Chatterjee A, Development of near homogeneous properties in wire arc additive manufacturing process for near-net shaped structural component of low-carbon steel, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 236(7) (2022) 3497 – 511.