An Algorithmic Framework for Optimizing Submerged Arc Additive Manufacturing Process Parameters for User-Specified Bead Width

Abstract

Submerged Arc Additive Manufacturing (SAAM) is a process known for its high material deposition characteristics, and since it is based on Submerged Arc Welding (SAW), it is expected to obtain thicker material depositions. In this work, an algorithmic framework has been developed which helps product designers or the user by taking their expectations of the bead width according to their requirement, and the algorithm suggests the optimal input process parameters which would help obtain an optimal bead width and optimal use of energy, minimizing the need for post-processing. The framework incorporates penetration depth, a critical factor for proper interlayer fusion. The framework was compared with a Genetic Algorithm (GA) output with similar GA parameters for a single run to evaluate its effectiveness. The proposed framework achieves a 93.7% accuracy in bead width prediction and a 27.5% reduction in energy input per unit length compared to the GA. This user-friendly tool empowers novice SAAM users and manufacturers to optimize deposition and energy efficiency.