The dissolution behavior of carbides in martensitic stainless steel and its effect on microstructure and hardness were investigated by using X-ray diffractometer (XRD) and field emission scanning electron microscopy (FE-SEM) with energy dispersive spectrometer (EDS) and electron backscattering diffraction (EBSD). The results indicated that the microstructure after austenitizing heat treatment and oil quenched consisted of martensite, M₂₃C₆ carbides and retained austenite. The temperature and particle size had great influence on the dissolution of carbides. The EBSD results showed that the twin-related variant pair V1/V2 governed the phase transformation. Meanwhile, the density of high-angle grain boundaries (HAGBs) increased with the increase of austenitizing temperature from 950 to 1150 °C. The hardness test results indicated that the hardness first increased and then decreased with the increase of the austenitizing temperature, and the peak appeared at 1050 °C with a Rockwell hardness value of 59.8 HRC. A model was established to quantitatively explain the contribution of different microstructures to hardness. The contribution to hardness came mainly from martensite. The retained austenite had a negative effect on hardness when the volume fraction was more than 10%. In contrast, carbides contributed less to hardness due to their small content.

The solidification structure and segregation of continuously cast billets produced by different continuous casting processes are investigated to elucidate their effect on segregated bands in hot-rolled section steel. It suggested that segregated spots are mainly observed in the equiaxed crystal zone of a billet. The solidification structure is directly related to superheating and the intensities of secondary cooling. To a certain extent, the ratio of the columnar crystal increases with the increase of superheating and secondary cooling. Moreover, the number of spot segregations decreases with the decrease of the equiaxed crystal ratio. After hot rolling, the segregation spots are deformed to form segregated bands in steels. The severe segregation of Mn in segregated bands corresponds with that in the segregation spots. The elongation ratio and low temperature toughness deteriorate significantly by a high fraction of degenerate pearlite caused by central segregation. With a decrease of central segregation, the total elongation is increased by 10% and the ductile–brittle transition temperature (DBTT) is also reduced from −10 to −40 °C. According to the experimental results, columnar crystal in billets is preferred to effectively reduce the degree of central segregation and further improve low temperature toughness and the elongation ratio.

Low variability in mechanical properties is required for pipeline project designs to meet a strain-based design, which is used in regions of large ground movements. The objective of this study is to elucidate the influence of centerline segregation in continuously cast slab on variability in the mechanical property of pipeline steel, and controlling centerline segregation can meet the requirements of a strain-based design. Mannesmann rating method was used to evaluate the degree of segregation of two slabs and its effect on variability in mechanical properties of corresponding plates. Microstructural characterization indicated that bainite/martensite was formed in a segregated area where the content of C and Mn enriched. The mechanical property results indicated that controlling the degree of centerline segregation can reduce tensile strength variability and improve ductile-brittle transition temperature (DBTT).

The influence of centerline segregation on the low-temperature impact toughness of the heat-affected zone (HAZ) of welded joints was studied by welding experiments on X70 steel plates rolled from continuous casting slabs with segregation grades of class 2 and class 3. The experimental results show that the impact toughness at HAZ from class 2 slab steel plate is more stable and has excellent low-temperature toughness than that of class 3 slab steel plate. The impact toughness of the HAZ of the class 3 slab steel plate is low to 100 J at −40 °C and has a severe fluctuation range (~150 J), and the delamination phenomenon is also observed in the fracture cross-section. The reason for this phenomenon is due to the enrichment of C and Mn elements in the centerline segregation zone. The formation of abnormal microstructure (martensite/bainite) in the segregation zone leads to stress concentration, which easily weakens the low-temperature toughness of the joint.

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.