Quantitative Evaluation of Thermomechanical Fatigue Damage in Composite Materials Using X-Ray Computed Tomography and Machine Learning.

The fatigue degradation of polymer-matrix composite materials, especially in the case of thermomechanical fatigue, when the self-heating effect dominates the process of the cyclically bent structure in fully reversed mode, results in complex damage patterns with a heterogeneous nature. It is therefore essential to evaluate the structural condition of tested objects in a non-destructive way to predict their fatigue lifetime. One of the most accurate non-destructive testing techniques used for such examinations is X-ray computed tomography, which enables the evaluation of the resulting fatigue damage in a three-dimensional space. However, the main challenge in the evaluation of such results is the attribution of the observed damage to specific types, the assessment of its severity, and its quantitative analysis. In this study, we have proposed a novel framework based on intensity and morphological features for the classification of damage types and a 3D U-Net-based approach for segmentation. The acquired results demonstrated the high accuracy of the performance evaluation indices, which exceeded 99% for the proposed framework, allowing effective evaluation of the resulting damage and being potentially helpful in the assessment of structural performance and residual fatigue life. Such analysis contributes to the trends of NDE 4.0 and adaptive mechanics, where composite structures are tailored to specific operational conditions to reach the target lifecycle.