Automated process parameters tuning for an injection moulding machine with soft computing

(整期优先)网络出版时间:2011-03-13
/ 1
Ininjectionmouldingproduction,thetuningoftheprocessparametersisachallengingjob,whichreliesheavilyontheexperienceofskilledoperators.Inthispaper,takingintoconsiderationoperatorassessmentduringmouldingtrials,anovelintelligentmodelforautomatedtuningofprocessparametersisproposed.Thisconsistsofcasebasedreasoning(CBR),empiricalmodel(EM),andfuzzylogic(FL)methods.CBRandEMareusedtoimitaterecallandintuitivethoughtsofskilledoperators,respectively,whileFLisadoptedtosimulatetheskilledoperatoroptimizationthoughts.First,CBRisusedtosetuptheinitialprocessparameters.IfCBRfails,EMisemployedtocalculatetheinitialparameters.Next,amouldingtrialisperformedusingtheinitialparameters.ThenFLisadoptedtooptimizetheseparametersandcorrectdefectsrepeatedlyuntilthemouldedpartisfoundtobesatisfactory.Basedontheabovemethodologies,intelligentsoftwarewasdevelopedandembeddedinthecontrollerofaninjectionmouldingmachine.Experimentalresultsshowthattheintelligentsoftwarecanbeeffectivelyusedinpracticalproduction,anditgreatlyreducesthedependenceontheexperienceoftheoperators.