Investigation on hot forging strategy for 5CrNiMoV via high-throughput experiment and machine learning

Abstract

Hot deformation conditions have important influence on the final properties of 5CrNiMoV steel. Based on the developed high-throughput forging equipment, a combined method of high-throughput simulation and machine learning was put forward to efficiently explore the best deformation conditions for 5CrNiMoV steel. A dataset containing 960 sets of data was established, describing the average grain size, damage, and dynamic recrystallization volume fraction of samples, strain rates and temperatures. The RFR (Random Forest Regression) model was trained and used to predict the optimal hot deformation conditions of 5CrNiMoV steel. Based on the searching space and the screening strategies, the optimal hot deformation conditions of 5CrNiMoV at different strains was successfully achieved. The results show that the designed strategy could be used to improve the research efficiency for better production processes and provide a certain theoretical reference for further experimental verification.

Application of Constitutive Models and Machine Learning Models to Predict the Elevated Temperature Flow Behavior of TiAl Alloy

“…Recently, more and more date-driven models such as artificial neural networks (ANNs) [17][18][19], support vector machines (SVMs) [20], random forests (RFs) [21], and Gaussian process regressors (GPRs) [22] have been developed to predict the hot-deformation behaviors of alloys with the development of machine learning techniques. Ge et al [17] utilized the ANN model and Arrhenius type model to predict the hot-deformation behavior of a high-Nb-containing TiAl alloy with β + γ phases.…”