Computational intelligence based design of age-hardenable aluminium alloys for different temperature regimes. (15th February 2016)

• Record Type: Journal Article
• Authors: Dey, Swati; Sultana, Nashrin; Kaiser, Md Salim; Dey, Partha; Datta, Shubhabrata
• Is Part Of: Materials & design. Volume 92(2016)
• Page Start: 522
• Page End: 534
• Publication Date: 2016-02-15
• Subjects: Age-hardenable aluminium alloy -- Tensile properties -- Artificial Neural Network -- Multi-objective optimization -- Genetic algorithm -- Alloy design; Materials -- Periodicals; Engineering design -- Periodicals; Matériaux -- Périodiques; Conception technique -- Périodiques; Electronic journals; 620.11
• DOI: 10.1016/j.matdes.2015.12.076
• Languages: English
• ISSNs: 0264-1275

Abstract

Abstract: Computational intelligence based approaches are used in tandem to design novel age-hardenable aluminium alloy, which would utilize the effect of all precipitate forming elements together, crossing the limit of the compositions defined within different series. A pool of data is created from the tensile properties of age-hardenable aluminium alloys in the 2XXX, 6XXX and 7XXX series. Based on the testing temperature the data is segregated, and different models for the tensile properties in the different temperature regimes are developed using Artificial Neural Network (ANN). The inherent relation between the composition and processing variables with the mechanical properties are explored using sensitivity analysis (SA). In order to design alloys with the conflicting objectives of high strength and adequate ductility, Multi-Objective Genetic Algorithm (MOGA) is used to search optimum solutions using the ANN models as the objective functions. The Pareto solutions from MOGA and the SA results are used along with prior knowledge of the alloy systems to design age-hardenable aluminium alloys with improved mechanical properties at different temperature regimes. The designed composition, which is beyond any of the age-hardenable series, has been developed experimentally, with encouraging results and interesting observations. Graphical abstract: Highlights: The Artificial Neural Network models for tensile properties of aluminium alloys are developed. The alloy is designed after analysis of the Pareto solutions generated from genetic optimization using above models. In the designed alloy nearly all the alloying elements contributing towards age hardening are preferred, along with Fe and Ni. The experimental finding of the designed alloy provides promising results that provides cue for further experimentation.