AI-Driven Hybrid Battery–Supercapacitor Systems for Electric Vehicles: Performance Analysis and Opportunities
Stella N. Arinze、Augustine O. Nwajana
4. AI-Driven Hybrid Battery–Supercapacitor Systems for Electric Vehicles: Performance Analysis and Opportunities
- 标题：AI-Driven Hybrid Battery–Supercapacitor Systems for Electric Vehicles: Performance Analysis and Opportunities
- DOI/URL：https://doi.org/10.3390/wevj17070380
- 期刊/会议/预印本平台：World Electric Vehicle Journal
- 发表日期：2026-07-22
- 作者和机构：Stella N. Arinze（Department of Electrical and Electronic Engineering, Enugu State University of Science and Technology, Nigeria）；Augustine O. Nwajana（School of Engineering, University of Greenwich, UK）。
- 通讯作者：Stella N. Arinze（MDPI 页面标注 1,*，Author to whom correspondence should be addressed）
- 脚本评分：58
纳入理由和命中证据：全文为 open access review，覆盖 hybrid battery-supercapacitor systems、AI energy management、battery state estimation、diagnostics、prognostics、battery lifetime、digital twins 等主题。它不是新的寿命预测算法，但可作为 HESS/EV 侧寿命保护和 AI 诊断综述背景。
创新点：整合 181 篇 2020–2026 文献，试图把 HESS 架构、AI energy management、state estimation、diagnostics/prognostics、thermal management、V2G、edge intelligence、federated learning 放在一个系统层框架内比较。
主要内容：先综述 lithium-ion、LFP、solid-state battery 与 supercapacitor 技术，再介绍 passive/semi-active/active HESS 架构，随后讨论传统与 AI 能量管理、状态估计、诊断和预后。
模型架构/方法流程：综述文章，无单一模型；涉及 machine learning、deep learning、reinforcement learning、digital twin、federated learning、edge intelligence 等方向。
输入特征与输出目标：综述性总结，未提出统一输入/输出；相关任务包括 SOC/SOH/RUL、故障诊断、热管理、功率分配和寿命保护。
数据来源/数据结构/电池类型/循环协议：文献收集来自 IEEE Xplore、ScienceDirect、SpringerLink、Web of Science、Scopus、MDPI、Wiley、SAGE、Google Scholar 等；筛选 181 篇 2020–2026 文献。
结果指标：无新增实验指标；讨论 battery lifetime、power density、energy efficiency、thermal performance、regenerative braking recovery、driving-cycle behavior 等性能维度。
Baseline/对比方法：与既有 HESS/AI/energy management 综述做主题覆盖比较。
泄漏风险/局限性/复现性：非 PRISMA 严格系统综述；可能存在文献选择主观性；不提供可直接复现的预测模型。主题偏能量管理/系统层，不应和原始 SOH/RUL 模型论文等权对待。
对哥哥研究/落地的启发和后续动作：可用来梳理 EV HESS 中“通过功率平滑降低电池老化”的系统级约束；若哥哥做寿命预测 + 控制闭环，可从其 AI energy management 和 digital twin 小节提炼约束变量。
查看关键词分类依据
- Federated learning · 摘要包含「federated」
ns, including explainable AI, digital twins, federated learning, edge intelligence, vehicle-to-grid integration, and cybersecurity-awa - Generic neural network / deep learning · 摘要包含「deep learning」
rgy management strategies, machine learning, deep learning, reinforcement learning, battery state estimation, diagnostics, prognostics, th - Generic machine learning · 摘要包含「machine learning」
and AI-driven energy management strategies, machine learning, deep learning, reinforcement learning, battery state estimation, diagnostics, - Hybrid model · 标题包含「hybrid」
AI-Driven Hybrid Battery–Supercapacitor Systems for Electric Vehicles: Performance Analysis and - Li-ion / LIB · 摘要包含「lithium-ion」
safety, and extended service life. Although lithium-ion batteries remain the dominant energy storage technology for EVs, their limited