简介：Processmodelsareveryusefultocontrolhighefficientindustrialmetallurgicalprocesses.Howevertheiraccuracydependsstronglyonthechoiceofboundaryconditionsandthermodynamicaswellaskineticdataused.WhereasthecommercialdatabaseFactSageorThermocalcisusedasthesourceofthermodynamicdatathekineticparameterarecharacteristicforeachprocessandprocessdesign.Thereforeitisessentialtoestimatethekineticparameterinwelldesignedexperimentssupportedbyusingofnumericalmethods.Inthispaperthesteelmeltflowparameter,gas-meltinterfacialareaandmasstransfercoefficientobtainedin30tindustrialgasstirredladlesaredescribed.Ontheexampleofnitrogenabsorptionanddesorptionthepredictiveprocessmodelfornitrogencontrolwhileladletreatmentanddecarburisationprocessispresentedfordifferentsteelalloys.Themodellingresultsarecomparedwithresultsfromindustrialprocesses.

简介：Baosteeldevelopedadigitalautomaticanalysistechniqueformaceralspecificationin2002.Thisanalysissystemcombinesdigitalimageprocessing,graphics,databases,expertsystems,artificialintelligenceandotheradvancedtechnologies.After6yearsofapplicationincokeproduction,thesystemproveditselfsuccessfulincoalqualitytestingandcoalblendingguidanceonmaceral.However,duringthislongprocess,someinadequacieswerefoundthatimpactedtheprecisionandaccuracyoftheanalysis.So,in2008Baosteelbegantoworkonimprovingthecoalmaceralanalysissystem.Theimprovementsincludedthefollowing:furtherupgradingandenhancingtheanalysisperformanceofmicroscopicimages;extendingthegraylevelstoincreasethereflectancemeasurementaccuracy64times;changingthefocusmethodandeffectivelyeliminatingtheinterferenceofhalo.Inaddition,animprovedimagerecognitionmethodwasadoptedtomaketheextractionofvitrinitemoreaccurateandanewmodelofcoalconstituentalgorithmwasaddedwhichcanaccuratelydeterminethecompositionofmaceral(exinite,vitrinite,inertinite).Sincetheseimprovementswerecompleted,thesystemhasachievedhigherautomation,speedandaccuracy,collectedmoreinformationandperformedmoreaccuratemaceralanalysisforcokeproduction.Meanwhile,theimprovedsystemhasprovidedareliableanalyticalbasisforthefurtherstudyontherelationshipbetweencokequalityandcoalblending.

简介：Artificialintelligencetechniqueshavebeenusedtopredictbasicoxygenfurnace(BOF)end-points.However,themainchallengeistoeffectivelyreducetheinputnodesastoomanyinputnodesinneuralnetworkincreasecomplexity,decreaseaccuracyandslowdownthetrainingspeedofthenetwork.Simplypicking-upvariablesasinputusuallyinfluencevalidityofmodel.Itisquitenecessarytodevelopaneffectivemethodtoreducethenumberofinputnodeswherebytosimplifythenetworkandimprovemodelperformance.Inthisstudy,avariable-filtratingtechniquecombiningbothmetallurgicalmechanismmodelandpartialleast-squares(PLS)regressionmethodhasbeenproposedbytakingtheadvantagesofbothofthem,i.e.qualitiveandquantativerelationshipsbetweenvariablesrespectively.Accordingly,afuzzy-reasoningneuralnetwork(FNN)predictionmodelforbasicoxygenfurnace(BOF)end-pointcarboncontentbasedonthistechniquehasbeendeveloped.Thepredictionresultsshowedthatthismodelcaneffectivelyimprovethehitrateofend-pointcarboncontentandincreasenetworktrainingspeed.Thesuccessfulhitrateofthemodelcanreachupto94.12%withabout0.02%errorrange.