首页|Graduate University of Advanced Technology Researchers Publish New Studies and F indings in the Area of Machine Learning (Residual energy evaluation in vortex st ructures: On the application of machine learning models)
Graduate University of Advanced Technology Researchers Publish New Studies and F indings in the Area of Machine Learning (Residual energy evaluation in vortex st ructures: On the application of 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 – Researchers detail new data in artific ial intelligence. According to news originating from Kerman, Iran, by NewsRx cor respondents, research stated, “Vortex structures are widely employed for energy dissipation in urban surface water conveyance systems. When transporting wastewa ter through these networks, a substantial amount of water energy is dissipated.” Our news correspondents obtained a quote from the research from Graduate Univers ity of Advanced Technology: “The effectiveness of these structures is usually ev aluated by their efficiency in dissipating energy. Recent literature reviews on vortex structures have emphasized that, despite numerous experimental studies ai med at assessing their hydraulic performance, a reliable mathematical model to p redict the residual energy head ratio remains elusive. In this study, resilient numerical models employing Artificial Intelligence (AI) methodologies (such as n on-parametric regression, decision trees, and ensemble learning) have been struc tured by reliable experimental tests. By analyzing the experiments, three primar y factors, referred to as flow Froude number (Fr), the ratio of sump height (Hs) to shaft diameter (D), and the ratio of drop total height (L) to shaft diameter (D) were determined to estimate the residual energy head ratio. Through experim ental study, the residual energy head ratio is computed as a ratio of downstream flow energy (E2) to upstream flow energy (E1) at vortex structure. During the t raining and testing phases of AI models, the results of statistical tests, servi ng as quantitative evaluations, have shown that ensemble learning models namely Adaptive Boosting (AdaBoost) and Categorical Boosting (CatBoost) models had high er level of efficiency in the E2/E1 predictions and followed by Model Tree (MT), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Extreme Gradient Boosti ng (XGBoost) and Multivariate Adaptive Regression Spline (MARS). Additionally, t he second-order regression-based equation was obtained from Fully Factorial Meth od (FFM) which had lower level of precision (R = 0.8275, RMSE = 0.1156, and MAE = 0.0846) in the residual energy head ratio predictions when compared with all p redictive AI models.”
Graduate University of Advanced Technolo gyKermanIranAsiaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
