首页|Reports Outline Machine Learning Study Results from University of Technology (In sights Into Water-lubricated Transport of Heavy and Extra-heavy Oils: Applicatio n of Cfd, Rsm, and Metaheuristic Optimized Machine Learning Models)
Reports Outline Machine Learning Study Results from University of Technology (In sights Into Water-lubricated Transport of Heavy and Extra-heavy Oils: Applicatio n of Cfd, Rsm, and Metaheuristic Optimized 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 originating from Selangor, M alaysia, by NewsRx correspondents, research stated, “With diminishing light crud e oil reserves, the focus shifts to heavy and extra-heavy crude oil, posing chal lenges with high viscosity impeding flow. Water-lubricated technology addresses this issue in oil transmission lines.” Financial support for this research came from Taif University, Saudi Arabia. Our news editors obtained a quote from the research from the University of Techn ology, “This study introduces a novel method integrating response surface method ology (RSM), computational fluid dynamics (CFD), and optimized machine learning (ML) models to analyze pipeline pressure gradients (PG) in oil-water two-phase f lows downstream of T-junctions. The present study uses the D-optimal technique f or simulation design to optimize CFD computational demands efficiently. This stu dy breaks new ground by proposing a framework that leverages support vector mach ines (SVMs). The proposed framework incorporates metaheuristic optimization algo rithms (genetic algorithm (GA) and particle swarm optimization (PSO)) to achieve superior PG prediction accuracy. The optimized ML models outperformed RSM model s for predicting PG. Results indicated that oil-to-water viscosity ratio and oil inlet velocity significantly affect PG, followed by water inlet velocity and su rface tension between phases. In contrast, the oil-to-water density ratio, oil e ntry angle at the T-junction, and wall contact angle have minimal impact. Furthe rmore, statistical metrics and visual comparison tools identified the PSO-optimi zed SVM model based on linear kernel function as the most effective (MAPE = 13.2 % and R = 0.9949).”
SelangorMalaysiaAsiaCyborgsEmerg ing TechnologiesMachine LearningUniversity of Technology
NETL
NSTL
