Scholarlink

<p>The introduction of Artificial Intelligence (AI) and Machine Learning (ML) in the field of EV battery charging has brought about a new revolution in efficiency, durability, and energy management. Over the past decade (2015–2025), advancements in supervised, unsupervised, and reinforcement learning algorithms have enabled instantaneous State-of-Charge (SOC) and State-of-Health (SOH) estimation, predictive maintenance, and intelligent charging infrastructure optimization. The existing survey papers mainly focus on grid stability and isolated battery metrics, this review study comprehensively presents a decade-span state-of-the-art AI-driven analysis, such as deep learning models, reinforcement learning-based charging strategies, and federated learning for secure data-driven battery management. The paper explores AI-powered demand-response mechanisms, task-oriented frameworks to bridge the gap between laboratory research and real-world implementation. Moreover, the effectiveness of AI-based thermal management systems and AI-based battery charge scheduling systems is investigated to understand their influence on reducing the degradation rate of the batteries. The literature survey also discusses the practical applications of AI technology, important datasets, software solutions, and future scope, particularly in the area of explainable artificial intelligence (XAI), neurosymbolic AI, and decentralized learning. In addition to that, as the electric vehicle (EV) industry evolves further, AI combined with renewable energy sources would play an essential role in designing the future.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning techniques for electric vehicles battery charging: a decade of revolutionary progress (2015-2025)

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Shubh Garg,
  • Aditya Sachdeva,
  • Karan Veer Singh,
  • Neeru Jindal,
  • Manoj Kumar,
  • Mukesh Singh

摘要

The introduction of Artificial Intelligence (AI) and Machine Learning (ML) in the field of EV battery charging has brought about a new revolution in efficiency, durability, and energy management. Over the past decade (2015–2025), advancements in supervised, unsupervised, and reinforcement learning algorithms have enabled instantaneous State-of-Charge (SOC) and State-of-Health (SOH) estimation, predictive maintenance, and intelligent charging infrastructure optimization. The existing survey papers mainly focus on grid stability and isolated battery metrics, this review study comprehensively presents a decade-span state-of-the-art AI-driven analysis, such as deep learning models, reinforcement learning-based charging strategies, and federated learning for secure data-driven battery management. The paper explores AI-powered demand-response mechanisms, task-oriented frameworks to bridge the gap between laboratory research and real-world implementation. Moreover, the effectiveness of AI-based thermal management systems and AI-based battery charge scheduling systems is investigated to understand their influence on reducing the degradation rate of the batteries. The literature survey also discusses the practical applications of AI technology, important datasets, software solutions, and future scope, particularly in the area of explainable artificial intelligence (XAI), neurosymbolic AI, and decentralized learning. In addition to that, as the electric vehicle (EV) industry evolves further, AI combined with renewable energy sources would play an essential role in designing the future.