A deep learning-based prediction method for high temperature mechanical properties of heat-resistant alloys

Abstract

A method for predicting high-temperature mechanical properties of heat-resistant alloys based on deep learning, comprising the following steps: S1. Forming an original experimental database; S2. Performing data preprocessing on microstructure photos in the original experimental database; S3. For the distribution of mechanical performance experimental values, the original experimental database is divided into continuous N categories, and the divided category values ​​are used as the category labels of the corresponding images; the labeled image data are grouped; S4, and all groups of image data are divided into Perform digital tensorization processing; S5. Build a deep learning model, configure the model structure and model parameters, and optimize the prediction effect of the deep learning model; S6. Use the optimized deep learning model to predict its high-temperature mechanical properties based on the microstructure pictures of heat-resistant alloys. The invention can realize the direct prediction of the heat-resistant alloy from the microstructure to the high-temperature mechanical performance, improve the detection efficiency of the high-temperature performance of the heat-resistant alloy, and save the high-temperature detection cost of the heat-resistant alloy.

Description

technical field [0001] The invention relates to the field of high-temperature performance analysis of heat-resistant alloy materials, in particular to a method for predicting high-temperature mechanical properties of heat-resistant alloys based on deep learning. Background technique [0002] The mechanical properties of a material are directly determined by its microstructure. Heat-resistant alloys are high-end products of metal materials and are widely used in petroleum, chemical, power generation, aerospace and other industries that are related to national security and the lifeline of the national economy. The development of heat-resistant alloys There is also a very strong connection to progress in these fields. With the rapid development of world industrialization, the demand for heat-resistant alloys is on the rise. With the increasing application of heat-resistant alloys in today's society, the scale of demand for high-temperature mechanical performance testing of hea...

AI Technical Summary

Problems solved by technology

With the development of material genome technology for many years, the prediction of the mechanical properties of materials has always been its shortcoming. The reason is that the mechanical properties involve the formation and interaction of dislocations, the interaction between dislocations and microstructure and other defects, and the formation of defects and cracks. It is still a very complex and difficult task to establish a prediction model for the mechanical properties of materials due to different mechanisms from atomic to microscopic to mesoscopic scales, such as growth, material, and interaction between defects and the environment.

Images