In this study, microstructural evolution and its effects on mechanical properties across the thickness of a 120 mm Ni-Cr-Mo industrial ultra-heavy steel plate were quantitatively investigated by means of optical microscope (OM), scanning electron microscope (SEM), transmission electron microscope (TEM) and electron back-scatter diffraction (EBSD). The results show that the martensite fraction is 65% at 10 mm and disappears at 40 mm, while granular bainite appears at 35 mm and climbs up to as high as 32% at 60 mm, with M-A constituents significantly coarsened. The strength drops with the gradual coarsening of the laths as well as decreased martensite fraction from the surface to the centre. The toughness is mainly affected by the block size and the morphology and quantity of M-A constituents. This study established a multivariate function between the microstructure and toughness (50% fibre area transition temperature, FATT₅₀) with careful consideration of the influence of effective grain size (EGS) and M-A constituent size distribution.

The isothermal bainitic transformation kinetics, microstructure, and mechanical properties of the quenched low-carbon high-strength steel have been investigated via dilatometric measurements, microstructural characterization, and mechanical tests. The results show that the pre-transformed isothermal bainite promotes martensitic transformation, increasing the martensitic transformation temperature, and enhancing the transformation rate. The microstructure of the 400 °C isothermal steel consists predominantly of lath bainite ferrite with dot/slender M-A constituents, whereas the steel treated at 450 °C contains a combination of martensite/lath bainite and granular bainite. The presence of massive M-A constituents contributes to brittle fracture as these constituents tend to promote crack initiation. Hence, the 450 °C treatment, which leads to the formation of massive M-A constituents, induces brittleness, while the finer M-A constituents formed at 400 °C exert minimal influence on the toughness and result in a more stable microstructure owing to their small size and the surrounding fine lath microstructure. The differences in microstructure and properties between the steels treated at 400 °C and 450 °C illustrate the importance of controlling the quenching cooling rate in the high-temperature bainitic transformation region during thick plate quenching processes.

The constitutive model refers to the mapping relationship between the stress and deformation conditions (such as strain, strain rate, and temperature) after being loaded. In this work, the hot deformation behavior of a Ni-Cr-Mo steel was investigated by conducting isothermal compression tests using a Gleeble-3800 thermal simulator with deformation temperatures ranging from 800 °C to 1200 °C, strain rates ranging from 0.01 s⁻¹ to 10 s⁻¹, and deformations of 55%. To analyze the constitutive relation of the Ni-Cr-Mo steel at high temperatures, five machine learning algorithms were employed to predict the flow stress, namely, back-propagation artificial neural network (BP-ANN), Random Committee, Bagging, k-nearest neighbor (k-NN), and a library for support vector machines (libSVM). A comparative study between the experimental and the predicted results was performed. The results show that correlation coefficient (R), root mean square error (RMSE), mean absolute value error (MAE), mean square error (MSE), and average absolute relative error (AARE) obtained from the Random Committee on the testing set are 0.98897, 8.00808 MPa, 5.54244 MPa, 64.12927 MPa² and 5.67135%, respectively, whereas the metrics obtained via other algorithms are all inferior to the Random Committee. It suggests that the Random Committee can predict the flow stress of the steel more effectively.