Hybrid prediction-optimization approaches for maximizing parts density in SLM of Ti6Al4V titanium alloy

A. Costa, G. Buffa (), D. Palmeri, G. Pollara and L. Fratini
Additional contact information
A. Costa: University of Catania
G. Buffa: University of Palermo
D. Palmeri: University of Palermo
G. Pollara: University of Palermo
L. Fratini: University of Palermo

Journal of Intelligent Manufacturing, 2022, vol. 33, issue 7, No 5, 1967-1989

Abstract: Abstract It is well known that the processing parameters of selective laser melting (SLM) highly influence mechanical and physical properties of the manufactured parts. Also, the energy density is insufficient to detect the process window for producing full dense components. In fact, parts produced with the same energy density but different combinations of parameters may present different properties even under the microstructural viewpoint. In this context, the need to assess the influence of the process parameters and to select the best parameters set able to optimize the final properties of SLM parts has been capturing the attention of both academics and practitioners. In this paper different hybrid prediction-optimization approaches for maximizing the relative density of Ti6Al4V SLM manufactured parts are proposed. An extended design of experiments involving six process parameters has been configured for constructing two surrogate models based on response surface methodology (RSM) and artificial neural network (ANN), respectively. The optimization phase has been performed by means of evolutionary computations. To this end, three nature-inspired metaheuristic algorithms have been integrated with the prediction modelling structures. A series of experimental tests has been carried out to validate the results from the proposed hybrid optimization procedures. Also, a sensitivity analysis based on the results from the analysis of variance was executed to evaluate the influence of the processing parameter and their reciprocal interactions on the part porosity.

Keywords: Artificial neural network; Response surface methodology; Metaheuristic algorithms; Predictive model; Optimization (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10845-022-01938-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:33:y:2022:i:7:d:10.1007_s10845-022-01938-9

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-022-01938-9

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().