This study employs deep reinforcement learning for active flow control in a turbulent flow field of high Reynolds numbers at Re = 274 000. That is, an agent is trained to obtain a control strategy that can reduce the drag of a cylinder while also minimizing the oscillations of the lift. Probes are placed only around the surface of the cylinder, and a proximal policy optimization (PPO) agent controls nine zero-net mass flux jets on the downstream side of the cylinder. The trained PPO agent effectively reduces drag by 29% and decreases lift oscillations by 18% of amplitude, with the control effect demonstrating good repeatability. Control tests of this agent within the Reynolds number range of Re = 260 000 to 288 000 show that the agent's control strategy possesses a certain degree of robustness, with very similar drag reduction effects under different Reynolds numbers. Analysis using power spectral energy reveals that the agent learns specific flow frequencies in the flow field and effectively suppresses low-frequency, large-scale structures. Graphically visualizing the policy, combined with pressure, vorticity, and turbulent kinetic energy contours, reveals the mechanism by which jets achieve drag reduction by influencing reattachment vortices. This study successfully implements robust active flow control in realistically significant high Reynolds number turbulent flows, minimizing time costs (using two-dimensional geometrical models and turbulence models) and maximally considering the feasibility of future experimental implementation.

Wireless Power Transfer (WPT) for electric vehicles is transitioning from laboratory prototypes to deployable charging infrastructure, driven by the demand for safer, automated, and weather-robust charging in residential parking, depots, and public bays, and more recently by pilot electric-road concepts. This review focuses on near-field resonant inductive WPT and explicitly frames the discussion around standardization and deployment readiness, with SAE J2954 and related international frameworks as reference points for interoperability, alignment, conformance testing, and certification planning across static, quasi-dynamic, and dynamic solutions. Recent surveys and representative demonstrators are synthesized to consolidate dominant research and engineering themes, including magnetic coupler and shielding design, compensation-network and control co-design, segment architecture and handover strategies for dynamic tracks, safety functions, electromagnetic exposure verification, electromagnetic compatibility constraints, bidirectional operation, and data-driven methods supporting design and field adaptation. For light-duty static charging, interoperable pad families, alignment procedures, and mature compensation topologies enable repeatable high-efficiency operation and increasingly standardized validation workflows, supporting early commercial availability. Heavy-duty depot charging appears technically attractive where duty cycles favor opportunity charging and packaging constraints are manageable. Dynamic WPT has reached pilot readiness via segmented selective-energization tracks and coordinated localization and handover, but corridor-scale rollout remains limited by maintainability, seasonal reliability, cost per kilometer, and route and site-specific verification of safety, exposure, and EMC margins.

This study employs Deep Reinforcement Learning (DRL) for active flow control in a turbulent flow field of high Reynolds numbers at $Re=274000$. That is, an agent is trained to obtain a control strategy that can reduce the drag of a cylinder while also minimizing the oscillations of the lift. Probes are placed only around the surface of the cylinder, and a Proximal Policy Optimization (PPO) agent controls nine zero-net mass flux jets on the downstream side of the cylinder. The trained PPO agent effectively reduces drag by $29\%$ and decreases lift oscillations by $18\%$ of amplitude, with the control effect demonstrating good repeatability. Control tests of this agent within the Reynolds number range of $Re=260000$ to $288000$ show the agent's control strategy possesses a certain degree of robustness, with very similar drag reduction effects under different Reynolds numbers. Analysis using power spectral energy reveals that the agent learns specific flow frequencies in the flow field and effectively suppresses low-frequency, large-scale structures. Graphically visualizing the policy, combined with pressure, vorticity, and turbulent kinetic energy contours, reveals the mechanism by which jets achieve drag reduction by influencing reattachment vortices. This study successfully implements robust active flow control in realistically significant high Reynolds number turbulent flows, minimizing time costs (using two-dimensional geometrical models and turbulence models) and maximally considering the feasibility of future experimental implementation.