The intersection of damage evaluation of fiber-reinforced composite materials with machine learning: A review

Abstract

Machine learning (ML) has emerged as a useful predictive tool based on mathematical and statistical relationships for various engineering problems. The pairing of structural health monitoring (SHM) and nondestructive evaluation (NDE) methods with ML algorithms has yielded beneficial results in addressing the damage state of a material or system. Damage state descriptions addressed with ML include detecting a damage mechanism, locating a mechanism, identifying the type of mechanism, assessing the extent of the damage mechanism, and estimating the useful remaining life of a material or system. Damage evaluation research of composite materials has progressed with the increased usage of composite structural elements in the aerospace industry. NDE methods are a viable candidate for pairing with ML algorithms to improve damage state monitoring of composite materials due to the complexity associated with the structure of composites. Fiber-reinforced polymers (FRP), for example, contain at least two constituent materials a fiber and matrix material whose mechanical behavior and interactions contribute to the performance of an FRP. Unlike conventional composite analytical models that require explicit information about the constituents and microstructure of a laminate, an ML algorithm can construct damage evaluation predictions when employing exclusively past operational performance or data from an SHM or NDE method. A researcher determines the type of data selected when applying an ML model for trend analysis, anomaly detection, or prediction making. However, no one specific input feature is required for utilizing an ML model, and examples of possible data features include material properties, physical dimensions, and collected evaluation data. In the present review, applications of ML combined with the damage state evaluation of composite materials, particularly examining FRPs, are discussed to demonstrate the predictive capabilities of ML and its viability for future applications, especially in industrial environments, to minimize costs and improve damage detection rates.

Graphene nanoparticles as data generating digital materials in industry 4.0

“…Finally, the machine/deep learning-based surrogate/predictive models can be used for process simulations [155][156][157] as well as for failure predictions in diagnostic and prognostic maintenance [158][159][160] . Using the data provided by a set of pressure sensors, Zhu et al 161 implemented a neural network model for the prediction of flow-front patterns at any impregnation time.…”

Fatigue performance evaluation of bistable composites at different combinations of loading and environmental conditions

“…The damage mechanisms are affected by parameters such as fiber type, matrix type, type of reinforcement structure (unidirectional, mat, fabric, braiding), laminate stacking sequence, environmental conditions (mainly temperature and moisture absorption), loading conditions (stress ratio R, cycling frequency), and boundary conditions. 21 Researchers predicted damage with fatigue life models, 22 phenomenological models based on residual stiffness [23][24][25][26][27][28][29][30] and residual strength, [31][32][33][34][35] and progressive damage models [36][37][38][39][40] to characterize fatigue life for a wide range of test conditions. There have been different damage identification techniques Figure 1.…”

Non-contact embedded sensing by Magnetostrictive Carbon Fiber Reinforced Polymer (MagCFRP): A smart material for early inter-lamina localized damage detection

“…In other words, the US Army's future aerospace vehicles need to be able to ''feel'' damage at a microscopic scale to warn, adapt, and survive in tactical situations. This paper explores a novel and sustainable methodology for Non-Destructive Evaluation (NDE) of CFRP interphase with implications to act as a data source for Structural Health Monitoring (SHM) machine learning schemes (Farrar and Worden, 2013;Nelon et al, 2022). Potential use cases for this work include but are not limited to NDE for condition-based maintenance, non-contact strain/stress sensing, and real-time composite SHM.…”