Evaluating data-driven algorithms for predicting mechanical properties with small datasets:A case study on gear steel hardenability  

作　　者：Bogdan Nenchev Qing Tao Zihui Dong Chinnapat Panwisawas Haiyang Li Biao Tao Hongbiao Dong 

机构地区：[1]NISCO UK Research Centre,School of Engineering,University of Leicester,Leicester LE17RH,UK [2]Nanjing Iron&Steel United Co.,Ltd.,Nanjing 210044,China

出　　处：《International Journal of Minerals,Metallurgy and Materials》2022年第4期836-847,共12页矿物冶金与材料学报（英文版）

摘　　要：Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are identified.Challenges in analysing small datasets are discussed,and solution is proposed to handle small datasets with multiple variables.Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity.The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability.Metallurgical-property relationships between chemistry,sample size,and hardness are predicted via two optimized machine learning algorithms:neural networks(NNs)and extreme gradient boosting(XGboost).A comparison is drawn between all algorithms,evaluating their performance based on small data sets.The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.

关 键 词：machine learning small dataset XGboost HARDENABILITY gear steel 

分 类 号：TG142.1[一般工业技术—材料科学与工程] TP181[金属学及工艺—金属材料]