A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles

The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which is a time-consuming and laborious task. A more efficient way of choosing EMS is to combine deep reinforcement learning (DRL)...

An end-to-end geometric deficiencies elimination algorithm for 3D meshes

The 3D mesh is an important representation of geometric data. It is widely used in computer graphics and has attracted more attention in computer vision community recently. However, in the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices, self-intersection, and inner faces) are...

Analysis and improvement of railway crossing performance using numerical and experimental approach: application to 1:9 double crossovers

The paper presents an integrated approach for analysis and improvement of performance of railway crossings. The approach consists of a detailed finite element (FE) model of a wheel rolling over a crossing (validated against the measured crossing accelerations) and experimental tools installed on the crossings in situ. The studied crossings are...

Hydrologic and cryospheric processes observed from space

Ten Dragon 3 projects deal with hydrologic and cryosphere processes, with a focus on the Himalayas and Qinghai – Tibet Plateau, but not limited to that. At the 1st Dragon 3 Progress Symposium in 2013 a significant potential for a better and deeper integration appeared very clearly and we worked out an overview of the ten projects identifying...

Analytical study on the vibration response of curved track subjected to moving load