Wire arc additive manufacturing (WAAM) is a promising technique for fabricating large-scale metallic components with complex geometries. However, achieving optimal deposition rates is crucial for enhancing productivity and ensuring part quality in WAAM processes. In this paper, we propose a machine learning-based approach to predict deposition rates in WAAM components. By leveraging historical process data and various input parameters, including welding current, voltage, wire feed rate, and travel speed, we develop predictive models capable of estimating deposition rates with high accuracy. The trained models are evaluated using validation datasets and compared against traditional empirical models. Our results demonstrate the efficacy of machine learning techniques in predicting deposition rates, offering valuable insights for process optimization and quality control in WAAM.

Wire Arc Additive Manufacturing (WAAM), Machine Learningartificial neural networks (ANNs).