Despite of extensive researches for decades, there are many unclear aspects for recrystallization phenomenon in the cold rolled Ni-based alloys. Hence, different thermal cycles were conducted in order to determine microstructural evolutions and its effect on the magnetic and mechanical properties of a 90% cold-rolled thin sheet of a Ni-Fe-Cu-Mo alloy (~80 μm). The obtained results revealed that the recrystallization was started at a temperature of 550°C and was completed after 4 hours. An increase in the number of annealing twins was observed with an increase in annealing temperature, which was due to a bulging and long-range migration of grain boundaries during the discontinuous recrystallization. Ordering transformation occurred in the temperature range of 400-600°C and as a result, hardness, yield strength, and UTS were increased, while with an increase in the annealing temperature these mechanical properties were decreased. Maximum toughness was obtained by annealing at 550°C for 4 hours, while the highest elongation was obtained after annealing at 1050°C, where other mechanical properties including toughness, hardness, yield strength, and UTS were decreased due to the grain growth and secondary recrystallization. Moreover, coercivity and remanence magnetization were decreased from 4.5 Oe and 3.8 emu/g for the cold rolled sample to below 0.5 Oe and 0.15 emu/g for the sample annealed at 950°C, respectively.

Recent advances in artificial intelligence have opened up new avenues for microstructure characterization, notably in metallic materials. Physical and mechanical properties generally depend on the microstructure of the metallic material. On the other hand, microstructural characterization takes time and calls for specific techniques that don’t always lead to conclusive results quickly. To address this issue, this research focuses on the application of artificial intelligence approaches to microstructural categorization. We demonstrate the advantages of the AI approach using an example of Al-Si alloy, a material that is widely employed in a variety of industries. To specify a suitable convolutional neural network (CNN) approach for the microstructural classification of the Al-Si alloy, CNN models were trained and compared using DenseNet201, Inception v3, InceptionResNetV2, ResNet152V2, VGG16, and Xception architectures. Resulting from the comparison, it was determined that the developed supervised transfer learning model can execute the microstructural classification of Al-Si alloy microstructural images. This paper is an attempt to advance methods of microstructure recognition/classification/characterization by using Deep Learning approaches. The significance of the established model is demonstrated and its accordance with the literature data. Also, necessity is shown of developing material models and optimization through systematic microstructural investigation, production conditions, and material attributes.