航空学报 > 2025, Vol. 46 Issue (14): 331440-331440   doi: 10.7527/S1000-6893.2024.31440

电动起降飞机用电池多维健康指标联合估算

杨驹丰1,2, 黄文新3, 孙久康4, 马忠臣5, 范国栋2, 张希2()   

  1. 1.江苏大学 汽车工程研究院,镇江 212013
    2.上海交通大学 机械与动力工程学院,上海 200240
    3.南京航空航天大学 自动化学院,南京 211106
    4.上海飞机客户服务有限公司,上海 200240
    5.江苏大学 计算机科学与通信工程学院,镇江 212013
  • 收稿日期:2024-10-23 修回日期:2024-11-11 接受日期:2024-12-14 出版日期:2025-01-10 发布日期:2025-01-10
  • 通讯作者: 张希 E-mail:braver1980@sjtu.edu.cn
  • 基金资助:
    国家自然科学基金(52307244);上海商用飞机系统工程科创中心联合研究基金(CASEF-2023-XM3);中国博士后科学基金(2023M742255)

Joint estimation of multidimensional battery health indicators for electric vertical take-off and landing aircraft applications

Jufeng YANG1,2, Wenxin HUANG3, Jiukang SUN4, Zhongchen MA5, Guodong FAN2, Xi ZHANG2()   

  1. 1.Automotive Engineering Research Institute,Jiangsu University,Zhenjiang 212013,China
    2.School of Mechanical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China
    3.College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
    4.COMAC Shanghai Aircraft Customer Service Co. ,Ltd,Shanghai 200240,China
    5.School of Computer Science and Communication Engineering,Jiangsu University,Zhenjiang 212013,China
  • Received:2024-10-23 Revised:2024-11-11 Accepted:2024-12-14 Online:2025-01-10 Published:2025-01-10
  • Contact: Xi ZHANG E-mail:braver1980@sjtu.edu.cn
  • Supported by:
    National Natural Science Foundation of China(52307244);Shanghai Center for Systems Engineering of Commercial Aircraft Joint Research Foundation(CASEF-2023-XM3);China Postdoctoral Science Foundation(2023M742255)

摘要:

电动垂直起降飞机(eVTOL)是绿色低空飞行器发展的重要趋势之一。为满足eVTOL安全可靠运行需求,需要电池管理系统结合飞行工况特性准确高效估算机载锂离子电池系统的健康状态。目前,大部分面向eVTOL应用的电池健康状态估计算法仅考虑了电池容量损失,缺乏根据飞行工况数据同时对电池能量衰退及功率衰减进行全面精准感知。针对上述问题,提出使用eVTOL起飞阶段电池电流和电压数据集作为估计算法输入参数,并选取电池容量、欧姆内阻和极化内阻作为健康指标综合表征电池性能衰退。为了提高多指标估算问题中模型的训练效率和估算精度,提出了一种基于多输出最小二乘支持向量回归的电池多健康指标联合估算方法,通过考虑输出变量间的耦合关系实现电池容量和内阻参数的快速准确估算。最后,基于eVTOL电池数据集进行了实验验证。对比分析结果表明:基于该方法估算所得电池容量和内阻的总体平均绝对百分比误差均低于2.5%,且模型训练时间控制在0.05 s以内,成功实现了面向eVTOL应用锂离子电池健康指标的全面、高效和准确估算。

关键词: 电动垂直起降飞机, 锂离子电池, 电池管理系统, 健康指标估算, 最小二乘支持向量回归

Abstract:

Electric Vertical Take-off and Landing (eVTOL) aircraft is one of the significant trends in the development of renewable low-altitude aircraft. To meet the requirements for safe and reliable operation of eVTOL, it is necessary for the battery management system to accurately and efficiently estimate the State-of-Health (SoH) of the on-board lithium-ion battery system based on the characteristics of the flight profile. At present, most SoH estimation algorithms for eVTOL applications only consider the battery capacity loss, and lack the ability to comprehensively and precisely estimate battery degradation in both energy and power based on the data recorded during the specific flight phase. To address the aforementioned issue, the battery current and voltage measured during the take-off phase of the eVTOL aircraft are selected as the inputs for the estimation algorithm, and the battery capacity, the ohmic resistance, and the polarization resistance are utilized as the health indicators to comprehensively characterize the battery degradation. To improve the training efficiency and estimation accuracy of the model for multi-indicator estimation, a multi-output least squares support vector regression-based method for joint estimation of multiple battery health indicators is proposed, which can achieve rapid and accurate estimation of the battery capacity and resistance by considering the coupling relationship among output parameters. Finally, experimental verification is conducted based on the eVTOL Battery Dataset. The results of the comparative study demonstrate that based on the proposed method, the mean absolute percentage error of the estimated battery capacity and internal resistance are overall below 2.5% and the model training time is within 0.05 s, successfully realizing a comprehensive, efficient, and accurate estimation of lithium-ion battery health indicators for eVTOL applications.

Key words: electric Vertical Take-off and Landing (eVTOL) aircraft, lithium-ion battery, battery management system, health indicator estimation, least squares support vector regression

中图分类号: