Reliable detection of subsurface defects in thick composite materials is critical for ensuring structural integrity in industrial applications such as wind turbine blades, aerospace components, and marine structures. This paper addresses dataset scarcity in AI-aided damage detection for thick composites using infrared thermography through a transfer learning framework leveraging finite element simulation data. Experimental datasets were obtained by conducting step-heating thermography experiments on glass-fiber-reinforced polymer (GFRP) and epoxy resin plates with artificial subsurface defects. Transient thermal analyses were performed on finite element models to mimic the actual step-heating thermography process, resulting in a large simulated dataset containing thermal videos representing the plate's surface thermal behavior during the heating-cooling process. Principal component thermography was used to extract features from both simulated and experimental thermal videos, compressing damage-related information in the raw data and enhancing the most informative features. Noise analysis on the experimental data revealed key differences compared to the simulated dataset. A U-Net architecture for image segmentation was implemented within the transfer learning framework, first pre-trained on simulated data and then fine-tuned with experimental data. The results revealed fundamental features shared across domains and demonstrated improved damage detectability in thick composite plates, especially for defects deeper than 15mm. This approach demonstrates the potential of transfer learning to improve damage detection in industrial applications involving thick composite structures, such as wind turbine blades.

Increasing train speeds and the reduction of maintenance slots places high demands on the railway rails. To meet the challenging demands, producers regularly introduce new steel types. In this experimental investigation is the mechanical behavior of an air-cooled vanadium-alloyed hypereutectoid rail steel presented. The rail is produced applying conventional hot rolling of a reheated bloom and is then cooled on a cooling bed. The mechanical behavior is determined by performing standardized linear elastic fracture mechanics tests. The necessary specimens are extracted from new rails that are made in series production. Monotonic tensile test results have shown that the strain-hardenability of the steel is comparable to standard grade eutectoid rail steel and is higher than that of an accelerated-cooled eutectoid rail grade. The fracture toughness test results showed, statistically, no difference when compared with the fracture toughness values of the accelerated-cooled eutectoid rail grade. The tests were performed at room temperature. The fatigue crack growth rates are, in the linear Paris-regime, slightly higher than in the previously mentioned steels. The results are explained considering the distinct microstructural characteristics of the air-cooled vanadium-alloyed hypereutectoid steel and the fractured surface of the specimens. This experimental investigation contributes to selecting railway steels and predicting the actual in-service behavior.

This study reports an experimental investigation of the fatigue and fracture resistance of R350HT, a heat-treated pearlitic rail steel with refined microstructure used in rails. Monotonic tensile, rotating bending, linear elastic plane strain fracture toughness, and fatigue crack growth rate tests are presented. The results are used to outline the basic properties and are corroborated by fractographic investigation. This enables the identification of the dominant type of fracture. Regarding fatigue and fracture resistance, the investigated material shows similar properties as other pearlitic rail steels, such as R260. At room temperature, the dominating fracture is of brittle cleavage type, showing some ductile regions associated with pro-eutectoid.

R350HT is a standard premium heat-treated rail steel and the reference for new rail steel development. The present study discusses an experimental characterization of fatigue crack growth rate and fracture toughness for this refined pearlitic rail steel in mode-I-loading. The tests are carried out on compact tension specimens extracted from the rail head with the straight notch pointing to the rail foot. As a result, the crack path orientation approximates deep rolling contact fatigue cracks. The fracture surfaces obtained under cyclic and monotonic loading are compared by means of scanning electron microscopy. The results are analyzed and discussed with reference to the morphology of the fracture surfaces for the crack initiation sites, fatigue crack growth region, and the final fracture region, evidencing the role of the microstructure, and inclusions on the fracture behavior. From the analysis of the crack path and fracture surface, it is concluded that the refined microstructure and ferrite ductility play an important role in fracture behavior.