Neural network modeling for weld shape process of P-GMAW

(整期优先)网络出版时间:2007-01-11
/ 1
Weldshapecontrolisafundamentalissueinautomaticwelding.Inthispaper,adoublesidevisualsystemisestablishedforpulsedgasmetalarcwelding(P-GMAW),andbothtopsideandbacksideweldpoolimagescanbecapturedandstoredcontinuouslyinrealtime.Byanalyzingtheweldshaperegulationwiththemoltenmetalvolume,sometopsideweldpoolcharacterizedparameters(WPCPs)areproposedfordeterminingpenetrationinbuttweldingofthinmildsteel.Moreover,someBPnetworkmodelsareestablishedtopredictbacksideweldpoolwidthwithweldingparametersandWPCPsasinputs.