Physics-guided deep neural network to characterize non-Newtonian fluid flow for optimal use of energy resources

作者：

Highlights：

• A data redundant deep learning HB-NET to characterize non-Newtonian fluid.

• Physics guided data-driven method to efficiently utilize energy in complex system.

• Simulation and experimental results show excellent correlation.

• Uncertainty quantification of fluid behavior is presented by Monte Carlo simulation.

摘要

•A data redundant deep learning HB-NET to characterize non-Newtonian fluid.•Physics guided data-driven method to efficiently utilize energy in complex system.•Simulation and experimental results show excellent correlation.•Uncertainty quantification of fluid behavior is presented by Monte Carlo simulation.

论文关键词：Deep neural network,Energy conservation,Machine learning,Non-Newtonian fluid,Navier-Stokes equation

论文评审过程：Received 15 August 2020, Revised 26 April 2021, Accepted 9 June 2021, Available online 19 June 2021, Version of Record 23 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115409