Simulation-based selection of optimum pressure die-casting process parameters using neural nets and genetic algorithms

Krimpenis, A; Benardos, PG; Vosniakos, GC; Koukouvitaki, A

dc.contributor.author	Krimpenis, A	en
dc.contributor.author	Benardos, PG	en
dc.contributor.author	Vosniakos, GC	en
dc.contributor.author	Koukouvitaki, A	en
dc.date.accessioned	2014-03-01T01:25:09Z
dc.date.available	2014-03-01T01:25:09Z
dc.date.issued	2006	en
dc.identifier.issn	0268-3768	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17567
dc.subject	genetic algorithms	en
dc.subject	neural networks	en
dc.subject	pressure die-casting	en
dc.subject	process conditions	en
dc.subject	simulation	en
dc.subject.classification	Automation & Control Systems	en
dc.subject.classification	Engineering, Manufacturing	en
dc.subject.other	OPTIMIZATION	en
dc.subject.other	PREDICTION	en
dc.subject.other	KNOWLEDGE	en
dc.subject.other	RUNNER	en
dc.subject.other	SYSTEM	en
dc.subject.other	DESIGN	en
dc.title	Simulation-based selection of optimum pressure die-casting process parameters using neural nets and genetic algorithms	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s00170-004-2218-0	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s00170-004-2218-0	en
heal.language	English	en
heal.publicationDate	2006	en
heal.abstract	Pressure die-casting condition selection mainly relies on the experience and expertise of individuals working in production industries. Systematic knowledge accumulation regarding the manufacturing process is essential in order to obtain optimal process conditions. It is not safe a priori to presume that rules of thumb, which are widely used on the shop floor, always lead to fast prototype production calibration and to increased productivity. Thus, neural network meta-models are suggested in this work in order to generalise from examples connecting input process variables, such as gate velocity, mould temperature, etc., to output variables, such as filling time, solidification time, defects, etc. These examples, or knowledge, are gathered from experiments conducted on casting simulation software, which are designed systematically using orthogonal arrays (DoE). They could also be based on experiments from industrial practice. Neural models derived in this way can help in avoiding excessive numbers of what-if scenarios examined on the casting simulation software, which can be very time-consuming. Furthermore, they can be employed in the fitness function of a genetic algorithm that can optimise the process, i.e. yield the combination of input parameters which achieves the best output parameter values.	en
heal.publisher	SPRINGER LONDON LTD	en
heal.journalName	INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY	en
dc.identifier.doi	10.1007/s00170-004-2218-0	en
dc.identifier.isi	ISI:000233725700011	en
dc.identifier.volume	27	en
dc.identifier.issue	5-6	en
dc.identifier.spage	509	en
dc.identifier.epage	517	en