Machine Learning-Based Investigation of Stress in Carbon Fiber Rotating Cylinders

Abstract

This study analyzed elastic stresses in a rotating cylinder consisting of carbon fiber material using analytical methods and machine learning techniques. Elastic stress ranges were determined according to the Von Mises yield criterion, which provided a comprehensive understanding of the material's behavior under rotational loads. The analytical results were validated and improved through machine learning-based predictions, demonstrating the potential of these approaches in stress analysis. The results are presented graphically for clarity and comparison. The study emphasizes that there is an inverse relationship between the rotational speed parameter and the elastic stress that occurs inside the cylinder. These findings contribute to understanding stress behavior in high-performance composite materials but also demonstrate the effectiveness of machine learning in predicting stress distributions for complex engineering.