Prediction of bead geometry with consideration of interlayer temperature effect for CMT-based wire-arc additive manufacturing

Cold metal transfer (CMT)–based wire-arc additive manufacturing (WAAM) is increasingly popular for the production of large and complex metallic components due to its high deposition rate, low heat input, excellent material efficiency. The accurate prediction bead geometry great importance enhance stability process dimensional accuracy. Besides wire feed speed (WFS) travel (TS), interlayer temperature another key factor in determining because accumulation multilayer deposition. In this paper, considering varying temperature, WFS, TS as inputs, an artificial neural network (ANN) developed predict width, height, contact angle; then, by connecting ANN model with a geometric model, combined established improve model. Based on experimental test data, random combinations input parameters, demonstrated be able accurately (mean error < 5.1%). general effect was also investigated experiment.