Multi-objective optimisation of DMLS process parameters using evolutionary algorithm
by C.D. Naiju; M. Adithan; P. Radhakrishnan
International Journal of Rapid Manufacturing (IJRAPIDM), Vol. 3, No. 1, 2012

Abstract: A multi-objective optimisation study is carried out for direct metal laser sintering process (DMLS). In order to optimise the individual process parameters and mechanical properties, analysis of variance (ANOVA) methods were used. Experiments were conducted by varying the process parameters using Taguchi's modified L8 orthogonal array method. Mechanical properties such as fatigue cycles to failure, tensile strength, compressive strength, hardness and wear rate of components have been ascertained and a mathematical model has been developed using multi-variable linear regression analysis. Genetic algorithm (GA) was used to carry out final multi-objective optimisation studies. Optimal process parameters for better mechanical properties were observed by initiating multi-objective optimisation using genetic algorithm. By selecting better process parameters, components could be manufactured in the near future with improved mechanical properties. Results obtained will be useful to manufacturing components for functional application so that DMLS technology can be brought to the mainstream manufacturing process.

Online publication date: Sat, 20-Dec-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Rapid Manufacturing (IJRAPIDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com