E nergy management is a critical technology in plug-in hybrid-electric vehicles (PHEVs) for maximizing efficiency, fuel economy, and range, as well as reducing pollutant emissions. At the same time, deep reinforcement learning (DRL) has become an effective and important methodology to formulate model-free and realtime energy-management strategies for HEVs and PHEVs. In this article, we describe the energy-management issues of HEVs/PHEVs and summarize a variety of potential DRL applications for onboard energy management. We also discuss the prospects for various DRL approaches in the energy-management field.
Heavy summer rainfall induces significant soil erosion and shallow landslide activity on the loess hillslopes of the Xining Basin at the northeast margin of the Qinghai-Tibet Plateau. This study examines the mechanical effects of five native shrubs that can be used to reduce shallow landslide activity. We measured single root tensile resistance and shear resistance, root anatomical structure and direct shear and triaxial shear for soil without roots and five rootsoil composite systems. Results show that Atriplex canescens (Pursh) Nutt. possessed the strongest roots, followed by Caragana korshinskii Kom., Zygophyllum xanthoxylon (Bunge) Maxim., Nitraria tangutorum Bobr. and Lycium chinense Mill. Single root strength and shear resistance relationships with root diameter are characterized by power or exponential relations, consistent with the MohrCoulomb law. Root mechanical strength reflects their anatomical structure, especially the percentage of phloem and xylem cells, and the degree and speed of periderm lignifications. The cohesion force of rootsoil composite systems is notably higher than that of soil without roots, with increasing amplitudes of cohesion force for A. canescens, C. korshinskii, Z. xanthoxylon, N. tangutorum and L. chinense of 75.9%, 75.1%, 36.2%, 24.6% and 17.0 % respectively. When subjected to shear forces, the soil without root samples show much greater lateral deformation than the root-soil composite systems, reflecting the restraining effects of roots. Findings from this paper indicate that efforts to reduce shallow landslides in this region by enhancing root reinforcement will be achieved most effectively using A. canescens and C. korshinskii.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.