The effects of prior austenite grain (PAG) refinement on the mechanical properties of bainitic/martensitic steels not only come from itself, but also have more complex effects by affecting the substructure formed by coherent transformation. In this study, the samples of a low-alloy steel were water quenched from different austenitizing temperatures and the bainitic/martensitic microstructures with different PAG sizes were obtained. Electron back-scattered diffraction was used to characterize the microstructure and different types of boundaries were identified and quantitatively analyzed. The tensile tests and series temperature Charpy impact tests of different heat treatment were also carried out and comprehensively analyzed with microstructure characterization works. The results show that the uniform refinement of prior austenite grain can increases the density of packet boundary and block boundary, which leads to microstructure refinement with higher density of high-angle grain boundaries with misorientation >45°. The contribution of this microstructure refinement to toughness is significant, but its contributions to strength and elongation are relatively limited. Compared to uniform refined PAG, if the PAGs are mixed crystal, the density of block boundary will be reduced, which leads to a lower density of the high-angle boundary with misorientation >45° and the positive effects of microstructure refinement on toughness improvement are weakened. The observation of fracture surface of impact specimens indicates that refining the PAG can delay the tendency of brittle fracture with the decrease in test temperature, and even in the case of brittle fracture, the cleavage facet of the fracture surface is relatively smaller. This result also verifies that PAG refinement can effectively improve toughness by inhibiting cleavage fracture.

In the present study, we predict elastic modulus of triply periodic minimal surface (TPMS) structures for biomedical material, titanium, using three different machine learning (ML) methods (Random Forest, XGBoost and Adaboost). A dataset is generated from elastic finite element analysis, which model has large number of lattice-cells (4 × 4 × 4 lattice-cells). In terms of three manufacturing features including unit configuration and two structural parameters (k and C), the elastic moduli of TPMS structures are calculated. It was found that all methods have high R² and low mean square error (MSE). The Adaboost performed best (R² = 0.959, MSE = 0.532) and the RF performed worst (R² = 0.929, MSE = 0.923). This shows that ML methods realise a leap from limited results of finite element analysis to theoretically infinite results with ML model, and computing efficiency has also been greatly improved.

We elucidate here the deformation behaviour and delamination phenomenon in a high-strength low-alloy bainitic steel, in terms of microstructure, texture and stress evolution during deformation via in situ electron back-scattered diffraction and electron microscopy. Furthermore, the selective role of bainitic lath boundary on slip systems was studied in terms of dislocation pile-up and grain boundary energy models. During tensile deformation, the texture evolution was concentrated at {1 1 0} and the laths were turn parallel to loading direction. The determining role of lath on the deformation behaviour is governed by length/thickness (l/t) ratio. When l/t > 28, the strain accommodates along the bainite lath rather than along the normal direction. The delamination crack initiated normal to (0 1 1) plane, and become inclined to (0 1 1) plane with continued strain along (0 1 1) plane and lath plane. This indicated that the delamination is not brittle process but plastic process. The lack of dimples at the delaminated surface is because of lack of strain normal to the direction of lath. The delaminated (0 1 1) planes were associated with cleavage along the (1 0 0) plane.

Coherent transformation is considered to be an effective approach to refine the microstructure and enhance toughness of structural steels. However, there are gaps in the knowledge on the key aspects of microstructure that govern toughness. In this regard, a low alloyed experimental steel with lean chemistry was subjected to a simple heat treatment involving austenitization at different temperatures, followed by quenching and tempering to obtain bainitic microstructures with different boundary composition. The microstructure of the four experimental steels was characterized by electron backscattered diffraction and mechanical properties were determined. The study indicated that the density of high angle grain boundaries does not adequately reflect the change of ductile-to-brittle transition temperatures (DBTT) of the experimental steels. Thus, we propose here a new mechanism on reducing DBTT from the perspective of misorientation of boundary, which takes into consideration these aspects in defining DBTT. One is inhibition effect on cleavage fracture by boundaries with high {100}-plane misorientation angles, and the other is ductility improvement by boundaries with high {110}-plane misorientation angles. Furthermore, the contribution of prior austenite grain boundary, packet boundary, block boundary, and sub-block boundary on toughness is also analyzed.

A novel YOLOv5 network is presented in this paper to quantify the degree of defects in continuously cast billets. The proposed network addresses the challenges posed by noise or dirty spots and different defect sizes in the images of these billets. The CBAM-YOLOv5 network integrates the channel and spatial attention of the Convolutional Block Attention Module (CBAM) with the C3 layer of the YOLOv5 network structure to better fuse channel and spatial information, with focus on the defect target, and improve the network’s detection capability, particularly for different levels of segregation. As a result, the feature pyramid is improved. The feature map obtained after the fourth down-sampling of the backbone network is fed into the feature pyramid through CBAM to improve the perceptual field of the target and reduce information loss during the fusion process. Finally, a self-built dataset of continuously cast billets collected from different sources is used, and several experiments are conducted using this database. The experimental results show that the average accuracy (mAP) of the network is 93.7%, which can achieve intelligent rating.

Central segregation, a typical internal defect in continuous casting slabs, significantly deteriorates the mechanical properties of steel products. However, traditional manual defect evaluation methods rely heavily on experience, are highly subjective and inefficient, making it difficult to meet the quality assessment requirements of today’s high-end steel materials. In this study, an approach which combines an unsupervised image enhancement algorithm and Otsu algorithm analysis was proposed to achieve automatic recognition and quantitative features extracting of central segregation in continuous casting slabs. The challenges posed by insufficient brightness and low contrast in central segregation images were addressed using unsupervised image enhancement algorithms. Following this enhancement, batch objective quantification of the segregation images was conducted through Otsu processing. Comparative experimental results showed that the enhanced images yielded an average Dice Similarity Coefficient of 0.965 for segregation recognition, representing a 38% improvement over unprocessed images, with consistent accuracy gains across complex segregation scenarios. This intelligent detection method eliminates the need for manually labeling a training set, substantially improves the consistency of segregation quantification and reduces the time cost significantly. Consequently, multiple parameters can be employed to quantify segregation characteristics, offering a more comprehensive and precise approach than current simplified rating methods. This advancement holds promise for enhancing quality control in steel processing and advancing Artificial Intelligence-driven technological progress within the metallurgical sector.