Results 141 to 150 of about 431 (173)

Learning Rocking Dynamics From Sparse Shake‐Table Data With Interpretable Physics‐Informed Neural Networks

open access: yesEarthquake Engineering &Structural Dynamics, EarlyView.
ABSTRACT We present a hybrid interpretable Physics‐Informed Neural Network Long‐Short Term Memory (Hybrid PINN LSTM) framework for predicting the seismic response of rocking blocks. Existing analytical models rely on uncertain idealizations, while purely data‐driven and machine‐learning approaches lack physical consistency and interpretability.
Shirley Shen   +1 more
wiley   +1 more source

Flow Characteristics and Response Surface Methodology‐Based Pressure‐Loss Prediction Models for the Reverse Circulation Converter in Double‐Wall Drill Pipes

open access: yesEnergy Science &Engineering, EarlyView.
Flow characteristics and pressure loss mechanisms of a reverse circulation converter in dual‐wall drill pipes are systematically investigated using CFD and response surface methodology. The results reveal the dominant role of inertial dissipation and provide a predictive framework for optimizing converter design and operational parameters. ABSTRACT The
Mingming Geng   +8 more
wiley   +1 more source

Edge‐Based Discretizations on Triangulations in Any Dimension, With Special Attention to Four‐Dimensional Space

open access: yesInternational Journal for Numerical Methods in Fluids, EarlyView.
This article provides important geometric formulas for node‐centered, edge‐based schemes in any number of dimensions. These formulas are noteworthy, as they do not require the explicit formation of dual regions. We prove several key geometric results, with a particular focus on the four‐dimensional case, due to potential space‐time applications ...
Nicholas Tufillaro   +2 more
wiley   +1 more source

Employing the Moving Least‐Squares Aided Finite Element Method to Study Heat Transfer Phenomenon in Closed‐Cell Polymeric Foam

open access: yesInternational Journal for Numerical Methods in Fluids, EarlyView.
Employing the moving least‐squares aided finite element method (MLS‐FEM) allows detailed thermal analysis in complex porous structures, such as polymeric foams, where the conductive heat transfer mechanism governs in the solid matrix and the convective mechanism dominates within the gas‐filled voids.
Mehdi Mostafaiyan   +2 more
wiley   +1 more source

Modelling Disease Progression of Multiple Sclerosis in a South Wales Cohort.

open access: yesNeuroepidemiology
Uzochukwu EC   +7 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy