Machine-learning framework for predicting process-property relationships in additively manufactured NiTi shape memory alloys

Key Points

• High accuracy in predicting process-property relationships underscores the model's utility.
• The predictive model demonstrated a remarkable accuracy rate of 92% in simulations.
• Machine learning techniques were applied to evaluate the effects of various parameters in additive manufacturing processes.
• These findings support the use of AI-driven methods in optimizing material properties for future applications.