Experimental and Computational Vibration Analysis for Diagnosing the Defects in High Performance Composite Structures Using Machine Learning Approach

Delamination in laminated structures is a concern high-performance structural applications, which challenges the latest non-destructive testing techniques. This study assesses delamination damage glass fiber-reinforced composite using health monitoring Glass rectangular laminate plates with and without were considered to obtain forced vibration response an in-house developed finite element model. The was diagnosed machine learning algorithms through statistical information extracted from response. Using attribute evaluator, features that made greatest contribution identified features. selected further classified algorithms, such as decision tree, random forest, naive Bayes, Bayes net diagnose structure. tree method found be computationally effective model diagnosing of effectiveness validated experimental results, obtained modal analysis fabricated delaminated plates. Our proposed showed 98.5% accuracy Hence, this research work motivates development online prognostic modules for detecting early prevent catastrophic failures structures.