Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184112,
        author = {Mr. G. Haribabu and Mr. Badiganchela Shiva Kumar and Mr. Borsaniya Rajdeep Kishorbhai and Mr. Hanuman Kondiba Kadam and Mr. Mitesh Mahendrabhai Dalwadi and Mr. Paramaesha R},
        title = {Hybrid AI Models for Improving Efficiency and Safety in Next-Generation Wireless Charging Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {3800-3803},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184112},
        abstract = {Wireless Power Transfer (WPT) has emerged as a transformative technology for electric vehicles, consumer electronics, and industrial Internet of Things (IoT) devices. However, conventional WPT systems face persistent challenges such as misalignment losses, dynamic load variations, electromagnetic interference, and safety risks associated with overheating or overvoltage conditions. This paper proposes a hybrid Artificial Intelligence (AI) framework that integrates machine learning (ML), deep learning (DL), and reinforcement learning (RL) to enhance both efficiency and safety in next-generation wireless charging systems. The proposed model employs ML algorithms for real-time misalignment detection and adaptive resonance tuning, DL architectures for nonlinear system behavior prediction under varying operating conditions, and RL controllers for optimal power flow allocation across multi-receiver environments. To address safety concerns, anomaly detection models are embedded within the framework to identify overheating, leakage flux, or abnormal current surges, thereby enabling predictive maintenance. Simulation and experimental validation on a prototype resonant inductive coupling WPT setup demonstrate that the hybrid AI system achieves up to 20–25% improvement in transfer efficiency, while reducing voltage fluctuations and minimizing thermal hotspots. Furthermore, the framework ensures robust performance under diverse load and environmental conditions. The results highlight the potential of hybrid AI-driven control to establish safer, smarter, and more energy-efficient wireless charging infrastructures, paving the way for future large-scale deployment in electric mobility, healthcare devices, and sustainable IoT networks.},
        keywords = {Wireless Power Transfer (WPT), Hybrid Artificial Intelligence (AI), Resonant Inductive Coupling, Power Electronics, Efficiency Optimization, Control Feedback, Safety Mechanisms, Deep Learning, Reinforcement Learning, Electric Vehicle (EV) Charging, Internet of Things (IoT), Smart Grid Integration.},
        month = {September},
        }