HEИндивидуална стипендия2027–2029

WPT for EV · Wireless Power Train for Electric Vehicles an optimization framework for efficient solar powered

„Хоризонт Европа“ — Действия „Мария Склодовска-Кюри“

Период
2027-05-05 → 2029-05-04
Финансиране от ЕС
267 419 €
Участници
2
Схема
HORIZON-TMA-MSCA-PF-EF

Линиите свързват координатора с партньорите.

Накратко на български

Безжични зарядни станции за електромобили, захранвани от слънчева енергия и електрическата мрежа, се оптимизират чрез специални алгоритми. Това помага за повишаване на ефективността на зареждането и намаляване на вредните емисии от транспорта.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Цел на проекта

Climate neutrality by 2050, as envisioned under the European Green Deal, causes urgent transformations in the transportation sector, which handles nearly 25% of greenhouse gas emissions. The dominance of internal combustion engines must give way to sustainable, fully electric transportation systems. However, adopting electric vehicles (EVs) faces persisting barriers, particularly range anxiety, dependency on conventional energy, reliance on user intervention, and limitations of intermittent renewable power sources.This project WPT for EV proposes a solar-photovoltaic (PV) integrated wireless EV charger with seamless utility grid support. This system eliminates fossil fuel reliance, ensures uninterrupted charging despite PV intermittency, and mitigates range anxiety through automated wireless operation that requires no user involvement.The key objectives are to:Enhance charging efficiency beyond 95%, surpassing existing wireless systems (85–90%).Eliminate user dependency with automatic wireless charging.Integrate renewable PV power with grid interconnection for continuous operation.Support the EU Green Deal, Fit for 55, and AFIF infrastructure goals. The methodology employs a Hybrid Evolutionary-Reinforcement Optimization (HERO) technique. Genetic Algorithms (GA) are used for static design optimisation, such as sizing coils and predicting inverter operating frequencies under varying solar input. Reinforcement Learning (RL) dynamically fine-tunes system parameters, adjusting inductive coil values in real time to maintain resonance and maximise power transfer efficiency. This hybrid optimisation approach ensures robust static performance and adaptive dynamic control to efficiently deliver the required charging power. The proposed WPT for EV chargers offers a highly efficient, user-independent, renewable-powered solution for advancing EV adoption by combining PV integration.

Оригинален текст от CORDIS (на английски).

Участници

Връзки

Данни: CORDIS, © Европейски съюз