Data-driven approach to predict the fatigue properties of ferrous metal materials using the cGAN and machine-learning algorithms

作     者：Si-Geng Li Qiu-Ren Chen Li Huang Min Chen Chen-Di Wei Zhong-Jie Yue Ru-Xue Liu Chao Tong Qing Liu 

作者机构：School of Advanced TechnologyXi’an Jiaotong-Liverpool UniversitySuzhou215123JiangsuPeople’s Republic of China Key Laboratory for Light-weight MaterialsNanjing Tech UniversityNanjing210009People’s Republic of China Materials Bigdata and Application DivisionMaterial Academy JitriSuzhou215131JiangsuPeople’s Republic of China School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai200240People’s Republic of China 

出 版 物：《Advances in Manufacturing》 (先进制造进展（英文版）)

年 卷 期：2024年第12卷第3期

页      面：447-464页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：support provided by the Jiangsu Industrial Technology Research Institute and the Yangtze Delta Region Institute of Advanced Materials supported by the National Natural Science Foundation of China(Grant No.52205377) the National Key Research and Development Program(Grant No.2022YFB4601804) the Key Basic Research Project of Suzhou(Grant Nos.#SJC2022029,#SJC2022031) 

主　　题：Fatigue life curve Machine learning Transfer learning Conditional generative adversarial network(cGAN) 

摘      要：The stress-life curve(S–N)and low-cycle strain-life curve(E–N)are the two primary representations used to characterize the fatigue behavior of a *** material fatigue curves are essential for structural fatigue ***,conducting material fatigue tests is expensive and *** address the challenge of data limitations on ferrous metal materials,we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S–N and E–N curves of ferrous *** addition,a data-augmentation framework is introduced using a conditional generative adversarial network(cGAN)to overcome data *** incorporating the cGAN-generated data,the accuracy(R2)of the Random Forest Algorithm-trained model is improved by 0.3–*** is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.