Effects of Seawater on Mechanical Performance of Composite Sandwich Structures: A Machine Learning Framework

• Published in: Materials Vol. 17; no. 11; p. 2549
• Main Authors: Osa-uwagboe, Norman, Udu, Amadi Gabriel, Silberschmidt, Vadim V., Baxevanakis, Konstantinos P., Demirci, Emrah
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 25.05.2024; MDPI
• Subjects: Acoustic emission; Algorithms; Cluster analysis; Clustering; Composite materials; Composite structures; Corrosion resistance; Damage detection; Data mining; Ensemble learning; Fiber reinforced plastics; Glass fibers; Hardness tests; Indenters; Interfacial bonding; Machine learning; Mechanical properties; Moisture absorption; Moisture resistance; Polyvinyl chloride; Prediction models; Sandwich structures; Sea vessels; Sea-water; Seawater; Strength to weight ratio; Structural health monitoring; Structural integrity; Temperature; United Kingdom; United Kingdom > UK; damage prediction; seawater exposure; acoustic emission; composite sandwich; machine learning
• ISSN: 1996-1944; 1996-1944
• DOI: 10.3390/ma17112549

Sandwich structures made with fibre-reinforced plastics are commonly used in maritime vessels thanks to their high strength-to-weight ratios, corrosion resistance, and buoyancy. Understanding their mechanical performance after moisture uptake and the implications of moisture uptake for their structural integrity and safety within out-of-plane loading regimes is vital for material optimisation. The use of modern methods such as acoustic emission (AE) and machine learning (ML) could provide effective techniques for the assessment of mechanical behaviour and structural health monitoring. In this study, the AE features obtained from quasi-static indentation tests on sandwich structures made from E-glass fibre face sheets with polyvinyl chloride foam cores were employed. Time- and frequency-domain features were then used to capture the relevant information and patterns within the AE data. A k-means++ algorithm was utilized for clustering analysis, providing insights into the principal damage modes of the studied structures. Three ensemble learning algorithms were employed to develop a damage-prediction model for samples exposed and unexposed to seawater and were loaded with indenters of different geometries. The developed models effectively identified all damage modes for the various indenter geometries under different loading conditions with accuracy scores between 86.4 and 95.9%. This illustrates the significant potential of ML for the prediction of damage evolution in composite structures for marine applications.