Carbon Fiber-Reinforced Polymer (CFRP) composites, widely used across industries, exhibit various damage mechanisms depending on the loading conditions applied. This study employs a structural health monitoring (SHM) approach to investigate the three primary failure modes, fiber breakage, matrix cracking, and delamination, in thermoset quasi-isotropic CFRPs subjected to quasi-static tensile loading until failure. Acoustic emission (AE) signals acquired from an experiment were leveraged to analyze and classify these real-time signals into the failure modes using machine learning (ML) techniques. Due to the extensive number of AE signals recorded during testing, manually classifying these failure mechanisms through waveform inspection was impractical. ML, alongside ensemble learning, algorithms were implemented to streamline the classification, making it more efficient, accurate, and reliable. Conventional AE parameters from the data acquisition system and feature extraction techniques applied to the recorded waveforms were implemented exclusively as classification features to investigate their reliability and accuracy in classifying failure modes in CFRPs. The classification models exhibited up to 99% accuracy, as depicted by evaluation metrics. Further studies, using cross-correlation techniques, ascertained the presence of fiber break events occurring in the bundles as the thermoset CFRP composite approached failure. These findings highlight the significance of integrating machine learning into SHM for the early detection of real-time damage and effective monitoring of residual life in composite materials.
Damage in composite laminates evolves through complex interactions of different failure modes, influenced by load type, environment, and initial damage, such as from transverse impact. This paper investigates damage growth in cross-ply polymeric matrix laminates under tensile load, focusing on three primary failure modes: transverse matrix cracks, delaminations, and fiber breaks in the primary loadbearing 0-degree laminae. Acoustic emission (AE) techniques can monitor and quantify damage in real time, provided the signals from these failure modes can be distinguished. However, directly observing crack growth and related AE signals is challenging, making numerical simulations a useful alternative. AE signals generated by the three failure modes were simulated using modified step impulses of appropriate durations based on incremental crack growth. Linear elastic finite element analysis (FEA) was applied to model the AE signal propagating as Lamb waves. Experimental attenuation data were used to modify the simulated AE waveforms by designing arbitrary magnitude response filters. The propagating waves can be detected as surface displacements or surface strains depending upon the type of sensor employed. This paper presents the signals corresponding to surface strains measured by surface-bonded piezoelectric sensors. Fiber break events showed higher-order Lamb wave modes with frequencies over 2 MHz, while matrix cracks primarily exhibited the fundamental S0 and A0 modes with frequencies ranging up to 650 kHz, with delaminations having a dominant A0 mode and frequency content less than 250 kHz. The amplitude and frequency content of signals from these failure modes are seen to change significantly with source–sensor distance, hence requiring an array of dense sensors to acquire the signals effectively. Furthermore, the reasonable correlation between the simulated waveforms and experimental acoustic emission signals obtained during quasi-static tensile test highlights the effectiveness of FEA in accurately modeling these failure modes in composite materials.
Accurate damage characterization in thermoset Carbon Fiber-Reinforced Polymer (CFRP) composites using Acoustic Emission (AE) requires statistically robust and interpretable models. This study employs multinomial logistic regression with forward selection and Type III analysis to identify the minimal set of AE parameters necessary for classifying damage mechanisms (fiber breaks, delamination, matrix cracks) in quasi-isotropic thermoset CFRP laminates under synchronously recorded load conditions. Starting from 18 conventional time- and frequency-domain descriptors, forward selection yielded seven candidate predictors. However, Type III analysis revealed that only four parameters, Load, Initiation Frequency, Amplitude, and Average Frequency, provide unique, statistically significant contributions (p < 0.05). The remaining predictors became redundant once these four were included. Machine learning and deep learning models trained on this minimal feature set achieved validation accuracies up to 98.7% on external specimens. High-frequency components (>1 MHz), as recorded at the sensor location after propagation and sensor convolution, were associated with fiber break events at elevated loads, while delamination events exhibited higher amplitude and lower-frequency content (<200 kHz) compared to matrix crack events. These observed frequency ranges reflect the combined effects of source mechanisms, guided wave dispersion in the 2.4 mm thick laminate, PWAS sensor response, and HDT-based hit segmentation, and are consistent with established AE damage signatures in literature. The results indicate that this four-parameter set is sufficient to classify the labeled AE waveform classes under monotonic tensile loading of quasi-isotropic [45/90/−45/0]2s laminates, achieving 98.7% agreement with reference labels assigned via waveform morphology and spectral analysis. The proposed approach reduces computational overhead and enhances interpretability for structural health monitoring applications, pending validation across broader material systems and loading scenarios. A limitation of this study is that reference labels were assigned using waveform morphology and spectral analysis, lacking independent physical validation (e.g., microscopy).
Thermoset and thermoplastic composites are extensively used in aerospace because of their exceptional mechanical properties. Compared to thermoset composites, thermoplastic matrix composites offer excellent chemical and physical damage resistance and are more cost-effective to produce. However, barely visible impact damage (BVID) poses a critical risk to thermoplastic Carbon Fiber Reinforced Polymer (CFRP) aerospace structures due to its limited surface manifestation and significant effect on compressive strength. This study presents a thermographic nondestructive evaluation (TNDE) approach based on Thermographic Signal Reconstruction (TSR) fingerprints to enable repeatable depth and area estimation of impact-induced damage. A data-driven threshold is derived from the logarithmic slope histogram sequence, allowing consistent separation of sound and damaged regions without relying on contrast extrema or operator-dependent frame selection. The method is first validated using flat-bottom holes (FBH) of known geometry and then applied to an industrial thermoplastic composite demonstrator subjected to multiple impact energies. Quantitative comparisons with ultrasonic C-scan measurements demonstrate convincing correlation and stable trends, with error magnitudes consistent with known physical limitations of flash thermography for deeper or structurally constrained defects. The results demonstrate that the proposed methodology offers a resilient, contactless alternative for swift BVID screening and comparative damage quantification in aerospace composite inspection.
The evolution of the damage process in PAEK-type thermoplastic carbon fiber-reinforced polymer (CFRP) quasi-isotropic composite tensile specimens was investigated using acoustic emission (AE) monitoring under quasi-static loading to failure. Key objectives were to apply a deep learning (DL)-machine learning (ML) framework to the AE signals from tested specimens, identify the participating signal classes using unsupervised classification, and quantify their relative extent at different stages of the loading cycle. Unlike prior studies that rely on conventional AE features (i.e., amplitude, rise time, etc.), this work automated feature extraction directly from AE signals using a deep learning model. A 1D convolutional neural network (CNN) automatically extracted frequency and temporal features from AE events recorded from nominally identical specimens tested according to ASTM D3039. Principal component analysis reduced the high-dimensional feature space while retaining 85% of the variance, and spectral clustering identified four distinct classes validated by Davies–Bouldin index < 1.2 and Calinski–Harabasz index > 200 across both specimens. Fast Fourier transform analysis revealed that classes are primarily distinguished by frequency content. Low- and mid-frequency signals (1600 kHz) with low amplitude, surging rapidly beyond 80% of ultimate load until failure. Cross-correlation analysis revealed minimal formation of groups of fiber breaks called the ‘multiplets’ characteristic, suggesting the ductile PAEK matrix suppresses clustered fiber damage. The proposed DL-ML framework exhibited promising results, with the prospect of eliminating dependence on subjective, test-setup-sensitive parameters and providing a reproducible methodology for damage classification in thermoplastic composites. Besides, automated feature extraction could improve the likelihood of early detection of real-life damage progression before final failure. As a potential mathematical model, the scope for further improvement includes that the performance of the current framework depends significantly on the preprocessing of the data (i.e., the right size of signal that has substantial information on damage modes of both short and long type with least noise, elimination of the amplitude parameter by choosing manual amplitude bin). Direct validation of frequency-to-damage mode assignments through synchronized in situ imaging remains necessary to confirm the damage modes.