Machine Learning-Assisted Prediction of Fatigue Behaviour in Fiber-Reinforced Composites Manufactured via Material Extrusion

The recent advancements in material extrusion (MEX) have expanded the potential use of polymeric and composite structures in a wide range of structural and load-bearing applications. However, cyclic loads can induce fatigue, resulting in the development of structural damage and potentially leading to catastrophic failure at lower stress levels compared to normal mechanical loading. Therefore, it is crucial to thoroughly investigate and understand the fatigue behavior of composite parts manufactured using MEX. Predicting the fatigue life of polymeric composite components poses a significant challenge due to the complex nature of the materials involved. In this research, the aim is to utilize Machine Learning (ML) techniques to predict the fatigue life of fiber-reinforced composites produced through the MEX process. ML focuses on developing models that can learn from data, recognize underlying patterns within the data, and use those patterns to make accurate predictions or decisions.