Ultrahigh-strength stainless steel design method based on machine learning under guidance of physical metallurgy

Abstract

The invention provides an ultrahigh-strength stainless steel design method based on machine learning under guidance of physical metallurgy, and relates to the technical field of steel and iron material design. The method comprises the following steps: firstly, acquiring data, and dividing the data into a training set and a test set by adopting a multiple-leaving method; establishing an ensemble learning algorithm model based on physical metallurgy guidance according to the training set; taking the ensemble learning algorithm model of which the correlation coefficient is greater than 90% as a target function in the genetic algorithm; wherein the genetic algorithm is used for optimizing design components and process to obtain the ultrahigh-strength stainless steel, and designing the components and heat treatment conditions of the stainless steel; and classifying and screening a large number of obtained design results by adopting an SVC classifier, and outputting components, processes andhardness of typical alloys of the design results. According to the method, the generalization ability of the model can be improved, the design is more efficient, and the design result better conformsto the physical metallurgy principle.

Description

technical field [0001] The invention relates to the technical field of iron and steel material design, in particular to an ultra-high-strength stainless steel design method based on machine learning under the guidance of physical metallurgy. Background technique [0002] Ultra-high-strength stainless steel is widely used in nuclear power, military and other high-end equipment industries because of its excellent characteristics such as high strength and good corrosion resistance. The performance optimization of traditional ultra-high-strength steel is mainly based on systematic experiments. Although many ultra-high-strength stainless steels with excellent properties have been successfully developed, with the complexity of alloy systems and processing techniques, the traditional research and development methods of systematic experiments have exposed the development cycle. Long time, high capital cost and other disadvantages. At the same time, low R&D efficiency can hardly meet...

AI Technical Summary

Problems solved by technology

Although some advanced materials have been successfully designed based on physical models, some shortcomings are constantly exposed in further applications: (1) There are a large number of physical and metallurgical parameters in the PM model, which are crucial to the accuracy of the model

However, the acquisition of these important parameters often requires complex microstructure characterization, which greatly increases the amount of experiments required for modeling and reduces the efficiency of PM model development.

(2) Some complex phase transition mechanisms are still controversial in academia, which limits further optimization of the model

(3) As people have a deeper understanding of the physical mechanism in phase transitions, the physical model has been continuously optimized, which greatly increases the complexity of the PM model and limits the universality of the model

However, the current performance prediction and design of materials based on pure machine learning methods is only a purely mathematical process, and few physical metallurgical parameters are involved in the design process, which greatly wastes the unique advantages of physical metallurgy in material design

Images