High-performance modeling of conventional and active hydrostatic/hybrid bearings: Applying coupled physics-informed neural networks (PINN) for reducing data volume and time costs

Advanced Engineering Informatics 2026

View at publisher

Authors: Denis Shutin, Ivan Stebakov, Yuri Kazakov, Leonid Savin

DOI: 10.1016/j.aei.2026.104822

Cited by: 1

References: 36

Fields of Study & Subjects

Tribology and Lubrication Engineering Model Reduction and Neural Networks Gear and Bearing Dynamics Analysis

References 36