The precise identification of micro-features on 2.25Cr1Mo0.25V steel is of great significance for understanding the mechanism of hydrogen embrittlement (HE) and evaluating the alloy’s properties of HE resistance. Presently, the convolution neural network (CNN) of deep learning is widely applied in the micro-features identification of alloy. However, with the development of the transformer in image recognition, the transformer-based neural network performs better on the learning of global and long-range semantic information than CNN and achieves higher prediction accuracy. In this work, a new transformer-based neural network model Swin–UNet++ was proposed. Specifically, the architecture of the decoder was redesigned to more precisely detect and identify the micro-feature with complex morphology (i.e., dimples) of 2.25Cr1Mo0.25V steel fracture surface. Swin–UNet++ and other segmentation models performed state-of-the-art (SOTA) were compared on the dimple dataset constructed in this work, which consists of 830 dimple scanning electron microscopy (SEM) images on 2.25Cr1Mo0.25V steel fracture surface. The segmentation results show Swin–UNet++ not only realizes the accurate identification of dimples but displays a much higher prediction accuracy and stronger robustness than Swin–Unet and UNet. Moreover, efforts from this work will also provide an important reference value to the identification of other micro-features with complex morphologies.

The 2.25Cr1Mo0.25V steel is a vanadium-modified 2.25Cr1Mo steel and is being widely used in the manufacture of heavy-wall hydrogenation reactors in petrochemical plants. However, the harsh service environment requires a thorough understanding of high-temperature tensile and creep behaviors of 2.25Cr1Mo0.25V steel and its weld for ensuring the safety and reliability of hydrogenation reactors. In this work, the high-temperature tensile and creep behaviors of base metal (BM) and weld metal (WM) in a 2.25Cr1Mo0.25V steel weldment used for a hydrogenation reactor were studied experimentally, paying special attention to its service temperature range of 350–500 °C. The uniaxial tensile tests under different temperatures show that the WM has higher strength and lower ductility than those of BM, due to the finer grain size in the WM. At the same time, the short-term creep tests at 550 °C reveal that the WM has a higher creep resistance than that of BM. Moreover, the creep damage mechanisms were clarified by observing the fracture surface and microstructures of crept specimens with the aid of scanning electron microscopy (SEM). The results showed that the creep damage mechanisms of both BM and WM are the initiation and growth of creep cavities at the second phase particles. Results from this work indicate that the mismatch in the high-temperature tensile strength, ductility, and creep deformation rate in 2.25Cr1Mo0.25V steel weldment needs to be considered for the design and integrity assessment of hydrogenation reactors.

The development of FeCrAl alloys has commenced for use as nuclear fuel cladding material, intended to serve as an enhanced accident-tolerant alternative to Zr-based alloys. In this study, the Fe-13Cr-4Al alloy, specifically designed for advanced accident-tolerant fuel (ATF) cladding, was carefully prepared through vacuum induction melting and hot-working processes. Mechanical properties and serrated flow behavior of this alloy were investigated through tensile tests at temperatures ranging from 200 to 800 °C. Intriguingly, serrations emerged within a specific temperature range, accompanied by unique mechanical behavior characteristics indicative of dynamic strain aging (DSA). Additionally, the alloy’s fracture modes showed a transition from a mix of ductile and cleavage fracture features to fully ductile fracture as the temperature increased. This study offers insights into the mechanical properties and serration behaviors of FeCrAl alloys, highlighting their potential for use in nuclear fuel cladding.