Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel

Abstract

The invention discloses a method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel, and belongs to the technical field of crossing of steel research and machinelearning. The method comprises the steps: based on a dynamic recrystallization type rheological stress curve of a series of Nb microalloyed steel and experimental data of steel type information, learning parameters in a mathematical model corresponding to each rheological stress curve by adopting a genetic algorithm, establishing a network relationship model between steel grade information and rheological stress curve characteristics by using a Bayesian regularized BP neural network, and then predicting the dynamic recrystallization type rheological stress by combining the mathematical modelcorresponding to the rheological stress curve. The model established by the method can predict the rheological stress curve of the series of steel under various components and process conditions withhigh precision, the workload of a single-pass compression experiment is obviously reduced, and the prediction efficiency and precision of the dynamic recrystallization type rheological stress curve are improved.

Description

technical field [0001] The invention belongs to the cross technical field of iron and steel research and machine learning, and in particular relates to a method for predicting dynamic recrystallization flow stress of Nb microalloy steel. Background technique [0002] Nb micro-alloyed high-strength steel is widely used in pipelines, bridge construction and so on. Nb microalloyed high strength steel requires high strength and good toughness. Fine-grain strengthening can improve the strength and toughness of steel at the same time, and dynamic recrystallization, as one of the important ways to refine the austenite grain size, has a great influence on the final mechanical properties of Nb microalloyed high-strength steel. At present, there are two main methods to study the flow stress of austenite dynamic recrystallization type. One is to use single-pass compression experiments to directly obtain the flow stress curve of the experimental steel; the other is to establish the flo...

AI Technical Summary

Problems solved by technology

[0003] By searching the database of the State Intellectual Property Office and the SOOPAT database, there is currently no relevant patent publication on the dynamic recrystallization flow stress of Nb microalloy steel; the prediction of the dynamic recrystallization flow stress in the relevant literature is only for a single steel type Or under single process conditions, the accuracy is low and the scope of application is limited

For example, Abarghooei et al. established a machine learning model for the steady-state flow stress of X70 steel during thermal deformation, and predicted the steady-state flow stress. Flow Stress Curve of Deformation Process [Abarghooei H, Arabi H, Seyedein S H, et al. Modeling of Steady State Hot Flow Behavior of API-X70 Microalloyed Steel using Genetic Algorithm and Design of Experiments [J]. Applied Soft Computing, 2017, 52: 471 -477.]

Images