首页|New Findings Reported from University Indonesia Describe Advances in Machine Lea rning (Machine learning-based forward and inverse designs for prediction and opt imization of fracture toughness of aluminum alloy)
New Findings Reported from University Indonesia Describe Advances in Machine Lea rning (Machine learning-based forward and inverse designs for prediction and opt imization of fracture toughness of aluminum alloy)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News ; New study results on artificial intell igence have been published. According to newsreporting from the University Indo nesia by NewsRx journalists, research stated, “Utilization of machinelearning f ramework to design aluminum alloy with high fracture toughness is increasing.”The news editors obtained a quote from the research from University Indonesia: “ Nonetheless, beforesuch model can be applied, the generalizability of the model becomes imperative thus it can give a betterperformance not only in the presen t, but also against the future data. In this work, we deployed shallowand deep machine learning techniques represented by support vector regression (SVR), k-ne arest neighbors(KNN), extreme gradient boosting (XGBoost) and artificial neural network (ANN) was deployed to predictthe fracture toughness of various aluminu m alloys in the scheme of MLDS framework. Our study revealsthat the highest pre diction accuracy can be obtained for XGBoost technique with R2 score, RMSE, andMAPE values were found to be 90.6 %, 2.57, and 7.0 %, respectively with robust k-fold validation valueof 90.1 ± 1.5. The superior per formance of Xgboost due to its capability handling non-linear regressionproblem s with a small amount of data. The forward properties to compositions (P2C) and reversecompositions to properties (C2P) models exhibited good accuracies in pre dicting the fracture toughnessas illustrated by the error values lower than the machine learning design system (MLDS) error criteriaof 5 %. The X GBoost model feasibility to predict fracture toughness for various aluminum allo ys ofAlcoa 7055-T7751, AA 7055-T7751, 2024-T852, 5083-O 8090-T8151 was demonstr ated as well as usedto search aluminum alloy compositions with high fracture to ughness.”
University IndonesiaAluminumCyborgsEmerging TechnologiesLight MetalsMachine Learning
NETL
NSTL
