A REVIEW ON ROLE OF AI IN DAMAGE ASSESSMENT INLAMINATED COMPOSITE STRUCTURES

Abstract

Composite structures are susceptible to various forms of non-linear failures, such as delamination,voids, and matrix cracks, during their operational life. Detecting such damages early is crucial to ensuring the structural integrity and reliability of these materials. As a result, researchers are continuously exploring more accurate and efficient methods for structural health monitoring of composite plates. In recent years, Artificial Intelligence (AI) techniques have shown immense potential as versatile tools for assessing damages in these materials.The present work provides a comprehensive review of the feasible methodologies utilized for delamination and crack observations in laminated composites, with a particular emphasis on machine learning techniques. The objective ofthe present article is to demonstrate a comprehensive perspective on the present state-of-the-art of health monitoring of laminated composite structures. Such insights are invaluable, given the escalating usage of laminated composites in various product engineering industries like automotive, aviation and aerospace, where critical quality, presence and location of damages/cracks is critical for improving their structural integrity. Furthermore, this review provides a critical analysis of thestrengths and limitations of wide damage detection techniques and offers insights into potential future research directions.