Machining parameter optimisation by genetic algorithm and artificial neural network

Nafis Ahmad, Tomohisha Tanaka and Yoshio Saito

International Journal of Data Analysis Techniques and Strategies, 2014, vol. 6, issue 3, 261-274

Abstract: Machining operations are used for creating surfaces by cutting away unwanted materials from workpieces. These operations are highly constrained and non-linear in nature. As a result traditional techniques are not suitable for machining parameter optimisation. Turning and milling are the two most commonly used machining operations where machining time or cost is minimised by optimising cutting parameters. The important constraints are maximum cutting force, machine power, available rotational speed, tool deflection, required surface finish cusp height etc. Here, a genetic algorithm (GA) and artificial neural network (ANN)-based hybrid approach is presented. The proposed approach gives more emphasis on searching optimum cutting parameters near boundaries of feasible and infeasible solution spaces. The optimum solution obtained by this method also does not violate constraints for a specific machining operation. An example of ball end milling operation is presented to explain this technique.

Keywords: machining parameters; cutting parameters; ball end milling; genetic algorithms; GAs; artificial neural networks; ANNs; parameter optimisation. (search for similar items in EconPapers)
Date: 2014
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.inderscience.com/link.php?id=63061 (text/html)
Access to full text is restricted to subscribers.

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:ids:injdan:v:6:y:2014:i:3:p:261-274

Access Statistics for this article

More articles in International Journal of Data Analysis Techniques and Strategies from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().