首页|New Machine Learning Study Findings Have Been Reported by Investigators at Unive rsity of Illinois (Prediction of Stress-strain Behavior of Pet Frp-confined Conc rete Using Machine Learning Models)
New Machine Learning Study Findings Have Been Reported by Investigators at Unive rsity of Illinois (Prediction of Stress-strain Behavior of Pet Frp-confined Conc rete Using Machine Learning Models)
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 Daily News Daily News – Fresh data on Machine Learning are pre sented in a new report. According to news reporting from Urbana, Illinois, by Ne wsRx journalists, research stated, “Polyethylene terephthalate (PET) fiber-reinf orced polymer (FRR) has been recently developed, which possesses a bilinear tens ile stressstrain relationship and a large rupture strain (LRS) capacity. This s tudy presents a novel approach for accurately predicting the stress-strain behav ior of PET FRP-confined concrete using machine learning (ML) techniques.” The news correspondents obtained a quote from the research from the University o f Illinois, “A comprehensive dataset comprising 154 axial compression test speci mens, including both circular and noncircular cases, was utilized for training a nd testing ML models. Three advanced ML models, namely extreme gradient boosting (XGBoost), random forest regression (RFR), and k-nearest neighbors (KNN), were applied to predict mechanical properties for both circular and noncircular speci mens. XGBoost consistently outperformed RFR and KNN, demonstrating superior accu racy in predicting stress-strain curves for both specimen types. Performance eva luation relied on key metrics such as coefficient of determination (R2), mean sq uare error (MSE), root mean square error (RMSE), and mean absolute error (MAE). Furthermore, the predicted stress-strain curves generated by XGBoost were compar ed to experimental data and a mechanism model, highlighting the superiority of X GBoost in capturing critical curve points and emphasizing its accuracy and consi stency.”
UrbanaIllinoisUnited StatesNorth a nd Central AmericaCyborgsEmerging TechnologiesMachine LearningUniversity of Illinois
NETL
NSTL
