Abstract

Additive manufacturing (AM) has transformed the manufacturing landscape by enabling the production of complex parts with unprecedented design flexibility. However, the occurrence of defects remains a significant challenge in AM processes, impacting part quality and performance. Predictive models utilizing machine learning (ML) techniques offer a promising solution for forecasting defect occurrence in additive manufacturing. This abstract focuses on the development and application of ML models that leverage chemical composition data to predict defect formation during the printing process. By analyzing the chemical composition of feedstock materials, along with other process parameters, ML models can identify patterns and relationships that contribute to defect susceptibility. The abstract discusses the role of chemical composition in defect formation, ML approaches for defect prediction, and the benefits of ML-based defect forecasting in additive manufacturing. Additionally, it highlights challenges and future directions for advancing ML-based defect prediction models in AM processes. Overall, ML models utilizing chemical composition data provide valuable insights for proactive quality control, process optimization, and material development in additive manufacturing.