典型文献
Evaluating data-driven algorithms for predicting mechanical properties with small datasets: A case study on gear steel hardenability
文献摘要：
Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenab-ility. The limitations of current data-driven algorithms and empirical models are identified. Challenges in analysing small datasets are dis-cussed, and solution is proposed to handle small datasets with multiple variables. Gaussian methods in combination with novel predictive al-gorithms 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.
文献关键词：
中图分类号：
作者姓名：
Bogdan Nenchev;Qing Tao;Zihui Dong;Chinnapat Panwisawas;Haiyang Li;Biao Tao;Hongbiao Dong
作者机构：
NISCO UK Research Centre,School of Engineering,University of Leicester,Leicester LE17RH,UK;Nanjing Iron&Steel United Co.,Ltd.,Nanjing 210044,China
文献出处：
引用格式：
[1]Bogdan Nenchev;Qing Tao;Zihui Dong;Chinnapat Panwisawas;Haiyang Li;Biao Tao;Hongbiao Dong-.Evaluating data-driven algorithms for predicting mechanical properties with small datasets: A case study on gear steel hardenability)[J].矿物冶金与材料学报,2022(04):836-847
A类：
hardenab,Metallurgical
B类：
Evaluating,driven,algorithms,predicting,mechanical,properties,small,datasets,case,study,gear,steel,hardenability,Data,are,evaluated,limitations,current,empirical,models,identified,Challenges,analysing,dis,cussed,solution,proposed,handle,multiple,variables,Gaussian,methods,combination,novel,predictive,utilized,overcome,challenges,insight,into,alloying,elements,interaction,structure,gained,fundamental,knowledge,integrated,machine,learning,shown,superior,equations,property,relationships,between,chemistry,sample,size,hardness,predicted,via,optimized,neural,networks,NNs,extreme,gradient,boosting,XGboost,comparison,drawn,evaluating,their,performance,results,reveal,that,has,highest,potential,using,class,imbalance,large,inhomogeneity,issues
AB值：
0.52271
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
