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.

Hydrogen embrittlement (HE) is a critical issue that affects the reliability of hydrogenation reactors. The hydrogen diffusivity/trap characteristics of 2.25Cr-1Mo-0.25V steel are important parameters mainly used to study the HE mechanism of steel alloys. In this work, the hydrogen diffusivity/trap characteristics of heat-treated (annealed) and untreated 2.25Cr-1Mo-0.25V steel were studied using an electrochemical permeation method. The microstructures of both 2.25Cr-1Mo-0.25V steels were investigated by metallurgical microscopy. The effect of cementite on the hydrogen diffusivity/trap mechanisms was studied using thermodynamics-based and Lennard–Jones potential theories. The results revealed that the cementite located at the grain boundaries and at the interfaces of lath ferrite served as a kind of hydrogen trap (i.e., an irreversible hydrogen trap). In addition, hydrogen was transported from ferrite to cementite via up-hill diffusion, thereby supporting the hypothesis of cementite acting as a hydrogen trap.

Hydrogen embrittlement (HE) is a critical issue that hinders the reliability of hydrogenation reactors. Hence, it is of great significance to investigate the effect of hydrogen on fracture toughness of 2.25Cr-1Mo-0.25V steel and weld. In this work, the fracture behavior of 2.25Cr-1Mo-0.25V steel and welds was studied by three-point bending tests under hydrogen-free and hydrogen-charged conditions. The immersion charging method was employed to pre-charge hydrogen inside specimen and the fracture toughness of these joints was evaluated quantitatively. The microstructure and grain size of the specimens were observed by scanning electron microscopy (SEM) and by metallurgical microscopy to investigate the HE mechanisms. It was found that fracture toughness for both the base metal (BM) and the weld zone (WZ) significantly decreased under hydrogen-charged conditions due to the coexistence of the hydrogen-enhanced decohesion (HEDE) and hydrogen-enhanced localized plasticity (HELP) mechanisms. Moreover, the formation and growth of primary voids were observed in the BM, leading to a superior fracture toughness. In addition, the BM compared to the WZ shows superior resistance to HE because the finer grain size in the BM leads to a larger grain boundary area, thus distributing more of the diffusive hydrogen trapped in the grain boundary and reducing the hydrogen content.

Efficient and accurate predictions of creep rupture life are essential for ensuring the integrity of high-temperature components. In this work, a machine learning-based framework is developed for the quick screening of crucial features and accurate prediction of the creep rupture life of modified 9Cr-1Mo steels. A feature screening protocol based on correlation filtering and sequential feature selection techniques is established for identifying critical features that significantly affect the prediction performance from a set of numerous descriptors. Moreover, several machine learning algorithms are employed for model training to examine their ability to map the complex nonlinear interactions between multivariate features and creep life. The results show that the test stress, test temperature, tempering time, and the contents of S and Cr are identified as the crucial features that greatly influence the life prediction performance of modified 9Cr-1Mo steels. Moreover, the Gaussian process regression (GPR) model with these five selected crucial features exhibits the highest prediction accuracy among various machine learning strategies. Finally, an additional dataset out of model training and testing is used to further validate the efficacy of the constructed GPR model. The validated results demonstrate that most creep data are distributed inside the two-factor band lines. Results from this work show that the developed machine learning framework can offer high accuracy and excellent adaptability in predicting the creep life of modified 9Cr-1Mo steels under various environmental conditions.

Fracture failure caused by hydrogen embrittlement (HE) is a major concern for the system reliability and safety of hydrogen storage vessels, which are generally made of 2.25Cr1Mo0.25V steel. Thus, study of the influence of pre-charged hydrogen on fracture toughness of as-received 2.25Cr1Mo0.25V steel and weld is of significant importance. In the current work, the influence of hydrogen on fracture toughness of as-received 2.25Cr1Mo0.25V steel and weld was systematically studied. Base metal (BM) and weld metal (WM) specimens under both hydrogen-free and hydrogen-charged conditions were tested using three-point bending tests. Hydrogen was pre-charged inside specimens by the immersion charging method. The J-integral values were calculated for quantitatively evaluating the fracture toughness. In order to investigate the HE mechanisms, optical microscopy (OM) and scanning electron microscopy (SEM) were used to characterize the microstructure of BM and WM specimens. The results revealed that the presence of pre-charged hydrogen caused a significant decrease of the fracture toughness for both BM and WM specimens. Moreover, the pre-charged hydrogen led to a remarkable transition of fracture mode from ductile to brittle pattern in 2.25Cr1Mo0.25V steel.

In this work, the fatigue crack growth (FCG) behavior and fatigue damage mechanism of the 2.25Cr1Mo0.25V steel welded joint used in hydrogenation reactors were investigated. The multi-pass welding was carried out to manufacture the welded joint using the combined shielded metal arc welding (SMAW) and submerged automatic arc welding (SAAW) processes. The FCG behavior of different zones in the welded joint, including the base metal (BM), the heat-affected zone (HAZ) and the weld metal (WM), were studied by compact tension tests. Moreover, the acoustic emission (AE) technique was used to monitor AE signals generated from FCG process for further understanding FCG behavior and fatigue mechanisms. Additionally, the microstructures and fracture surfaces of different specimens were observed by optical microscopy (OM) and scanning electron microscopy (SEM). The results revealed that the microstructure of BM is fine granular bainite, while the WM shows coarser bainite grains. The HAZ exhibits the most significant inhomogeneity with large dispersion of grain size. FCG results showed that the HAZ exhibits much higher fatigue crack growth rate (FCGR) at low ΔK values, while the BM shows the most superior fatigue resistance. The AE technique is successful in monitoring and identifying damage evolutions during the FCG process. Moreover, an enhanced AE activity is observed in FCG of the WM specimen, which is attributed to the combined influence of the formation of numerous secondary cracks and coarse-grained microstructures.