Prognostics and Machine Learning to Assess Embedded Delamination Tolerance in Composites

Laminated composites are extensively used in the aerospace industry. However, structures made from laminated composites are highly susceptible to delamination failures. It is therefore imperative to consider a structure’s tolerance to delamination during design and operation. Hybrid composites with laminas containing different fibers were used earlier in laminates to achieve certain benefits in strength, stiffness, and buckling. However, the concept of mixing laminas with different fibers was not explored by researchers to enhance delamination tolerance levels. This article examines the above aspect of hybridization by employing machine learning algorithms and proposes a reliable method of analysis to study delamination, which is crucial to ensure the safety of airframe composite panels. In this article, fracture-mechanics-based structural integrity results related to mode I Strain Energy Release Rate (SERR) are obtained using geometrical non-linear three-dimensional finite element analysis. The parametric study helped to subject the data to multiple polynomial regressions for predictive model development. A standalone executable program deploys the machine learning model to predict the delamination tolerance of laminated composite panels. It is confirmed from the current study that appropriate hybridization with glass plies in between a few top and bottom carbon layers enhances the levels of delamination tolerance.