Frictional loss in bend pipes: numerical simulation and data driven modeling

作     者：Vasa, Adarsh Chaudhury, Kaustav 

作者机构：Natl Inst Technol Rourkela Dept Mech Engn Rourkela 769008 India 

出 版 物：《SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES》 (Sadhana)

年 卷 期：2023年第48卷第3期

页      面：1-16页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：The present work was supported by a doctoral scholarship for AV from the Ministry of Education, India and through a seed grant for KC from the National Institute of Technology, Rourkela, India [vide letter number, NITR/RG/2018/M/0430, Dated: August 20,2018 Ministry of Education, India National Institute of Technology, Rourkela, India NITR/RG/2018/M/0430 

主　　题：Data driven modeling ensemble of metamodels bend pipes friction factor 

摘      要：Here, we present a quasi-universal correlation for the friction factor in 90-degree and 180-degree bend pipes using the ensemble of metamodels (EOM). Using computational simulations, we obtain frictional losses at curvature ratios from 0.01 to 0.2 and Reynolds numbers up to 0.1 million. With the help of this data, we develop the EOM based correlation. The extensive window of parameters considered in the present study encompasses a vast design and operating conditions of 90-degree and 180-degree bend pipes. The large parametric space considered here essentially represents a variety of hydrodynamic scenarios. We use a sufficient yet nominal set of parameters representative of the variation and perform numerical simulations over the sampled set. Using the simulation data, we then train and validate the EOM to develop the required correlation. The k-fold cross-validation technique is employed to the EOM to optimize the model s predictive capabilities over the changing flow regimes. We believe that this modeling strategy, along with the database, may act as a base framework towards the further development of data augmentation techniques in pipes of various configurations, in general. Using this EOM based correlation, we further generate a large database for the friction factor in the two smooth bend pipe configurations at various curvature ratio and different Reynolds number. This approach can be viewed as an alternative to the Moody chart, however, for pipe bends.