欢迎来到OAJRC平台！

期刊栏目

投稿

审稿

期刊目次

加入编委

期刊订阅

添加您的邮件地址以接收即将发行期刊数据：

当前位置：电气工程与自动化 > 2026年 5卷 (2)期

Open Access Article

Journal of Electrical Engineering and Automation. 2026; 5: (2) ; 67-77 ; DOI: 10.12208/j.jeea.20260017.

Multi-source transfer GPR-Based SOC estimation method for eVTOL power batteries
面向eVTOL动力电池的多源迁移GPR-SOC估计方法

作者： 李元元¹, 时晓宇² *, 樊宇³

1西南民族大学电气工程学院四川成都

2西华大学电气与电子信息学院四川成都

3内蒙古电子信息职业技术学院电子与自动化系内蒙古呼和浩特

*通讯作者：时晓宇,单位：西华大学电气与电子信息学院四川成都；

国家自然科学基金项目（项目编号：62503406）四川省科技计划资助项目（项目编号：2024NSFSC2039西南民族大学大学维州团队项目（项目编号：SMUWZ202411）内蒙古自治区直属高校基本科研业务费项目（项目编号：JBYWF2026011）

发布时间: 2026-06-28 总浏览量: 41 下载量: 加载中...

PDF 全文下载引用本文

摘要

电动垂直起降飞行器（electric vertical take-off and landing, eVTOL）动力电池在飞行任务中存在负载变化快、功率波动明显和工况持续时间差异较大等特点，对荷电状态（state of charge, SOC）估计的跨工况适应性提出了较高要求。针对公开eVTOL电池数据缺少独立开路电压曲线、脉冲功率测试参数和完整等效电路辨识条件的问题，本文提出一种面向eVTOL动力电池的多源迁移GPR-SOC估计方法。该方法以安时积分结果作为SOC先验，将容量构造标称SOC与先验SOC之间的偏差作为残差学习目标，并利用多个源域迁移高斯过程回归子模型进行残差预测，最后根据预测不确定度对各子模型结果进行加权融合。基于公开eVTOL电池数据的仿真结果表明，所提方法能够在保持安时积分长期变化趋势的基础上，对局部估计偏差进行有效补偿，提高目标域样本有限条件下相对于容量构造标称SOC的拟合精度。由于数据集未提供独立OCV标定或专门实验测量得到的真实SOC，本文报告的误差结果主要反映模型对容量构造标称SOC的残差修正能力，不能直接等同于实际BMS场景中的真实SOC绝对估计误差。该方法可为公开数据条件受限下的eVTOL动力电池SOC估计研究提供一种可复现的残差修正思路。

关键词： eVTOL；动力电池；荷电状态；迁移学习；高斯过程回归

Abstract

Electric vertical take-off and landing (eVTOL) power batteries are characterized by rapid load changes, pronounced power fluctuations, and large differences in operating duration during flight missions, which impose high requirements on the cross-condition adaptability of state-of-charge (SOC) estimation. To address the lack of independent open-circuit voltage curves, pulse power test parameters, and complete equivalent-circuit identification conditions in public eVTOL battery datasets, this paper proposes a multi-source transfer GPR-SOC estimation method for eVTOL power batteries. The proposed method uses coulomb counting as the SOC prior, takes the deviation between the capacity-derived nominal SOC and the prior SOC as the residual learning target, and constructs multiple source-domain transfer Gaussian process regression submodels for residual prediction. The final residual correction is obtained by weighting the outputs of these submodels according to their predictive uncertainty. Simulation results based on public eVTOL battery data show that the proposed method can compensate for local estimation deviations while preserving the long-term trend of coulomb counting, thereby improving the fitting accuracy with respect to capacity-derived nominal SOC under limited target-domain samples. Since the dataset does not provide independently OCV-calibrated or experimentally measured true SOC, the reported errors mainly reflect the residual correction ability of the model for capacity-derived nominal SOC and cannot be directly regarded as the absolute true SOC estimation errors in practical BMS scenarios. This method provides a reproducible residual correction approach for eVTOL battery SOC estimation under limited public data conditions.

Key words： eVTOL; Power battery; State of charge; Transfer learning; Gaussian process regression

参考文献 References

[1] Xiao J Q, Salk N, Haran K. Conceptual design of an eVTOL air shuttle for rapid intercity transport[C]. Urbana-Champaign: 2020 IEEE Power and Energy Conference at Illinois, 2020.

[2] 赵志斌,袁鸿明,刘炳辰,等.eVTOL飞行器电池SOC估计:内嵌等效电路模型的神经网络[J].推进技术, 2026(006): 047.

[3] Zhou Q, Tan F. Avionics of electric vertical take-off and landing in the urban air mobility: a review[J]. IEEE Aerospace and Electronic Systems Magazine, 2024, 39: 1-26.

[4] Phung M T, Nguyen T C H, Akhtar M S, et al. Machine learning approaches for assessing rechargeable battery state-of-charge in unmanned aircraft vehicle-eVTOL[J]. Journal of Computational Science, 2024, 81: 102380.

[5] Hannan M A, Lipu M S H, Hussain A, et al. A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: Challenges and recommendations[J]. Renewable and Sustainable Energy Reviews, 2017, 78: 834-854.

[6] How D N T, Hannan M A, Lipu M S H, et al. State of charge estimation for lithium-ion batteries using model-based and data-driven methods: A review[J]. IEEE Access, 2019, 7: 136116-136136.

[7] Xiong R, Cao J, Yu Q, et al. Critical review on the battery state of charge estimation methods for electric vehicles[J]. IEEE Access, 2018, 6: 1832-1843.

[8] He W, Williard N, Chen C, et al. State of charge estimation for electric vehicle batteries using unscented Kalman filtering[J]. Microelectronics Reliability, 2013, 53(6): 840-847.

[9] Van C N , Quang D T. State of charge estimation for Lithium-Ion battery cell considering the influence of aging parameters and operating temperature[J]. International Journal of Electrochemical Science, 2023, 18(12): 100379.

[10] Yang L, He M, Ren Y, et al. State of charge estimation for lithium-ion batteries via a diffusion-enhanced equivalent circuit model and an improved extended Kalman filter[J]. Energy, 2026, 345: 140181.

[11] Hu X, Li S, Peng H. A comparative study of equivalent circuit models for Li-ion batteries[J]. Journal of Power Sources, 2012, 198: 359-367.

[12] Shen H, Zhou X, Wang Z, et al. State of charge estimation for lithium-ion battery using Transformer with immersion and invariance adaptive observer[J]. Journal of Energy Storage, 2022, 45: 103768.

[13] Liu Y, Shu X, Yu H, et al. State of charge prediction framework for lithium-ion batteries incorporating long short-term memory network and transfer learning[J]. Journal of Energy Storage, 2021, 37: 102494.

[14] Deng Z, Hu X, Lin X, et al. Data-driven state of charge estimation for lithium-ion battery packs based on Gaussian process regression[J]. Energy, 2020, 205: 118000.

[15] Liu Y, Li J, Zhang G, et al. State of charge estimation of lithium-ion batteries based on temporal convolutional network and transfer learning[J]. Ieee Access, 2021, 9: 34177-34187.

[16] Yang Y, Zhao L, Yu Q, et al. State of charge estimation for lithium-ion batteries based on cross-domain transfer learning with feedback mechanism[J]. Journal of Energy Storage, 2023, 70: 108037.

[17] Wang Y X, Chen Z, Zhang W. Lithium-ion battery state-of-charge estimation for small target sample sets using the improved GRU-based transfer learning[J]. Energy, 2022, 244: 123178.

[18] Xiao F, Li C, Fan Y, et al. State of charge estimation for lithium-ion battery based on Gaussian process regression with deep recurrent kernel[J]. International Journal of Electrical Power & Energy Systems, 2021, 124: 106369.

[19] Bills A, Sripad S, Fredericks L, et al. A battery dataset for electric vertical takeoff and landing aircraft[J]. Scientific Data, 2023, 10(1): 344.

引用本文

李元元, 时晓宇, 樊宇, 面向eVTOL动力电池的多源迁移GPR-SOC估计方法[J]. 电气工程与自动化, 2026; 5: (2) : 67-77.

入驻平台

回到顶部

搜索文章: