电源学报

基于多尺度CNN和残差LSTM网络的储能电站SOC估计

PDF下载

黄晓凡 ¹ , 李佳瑞 ¹ , 秦玉文 ² , 汤效平 ¹ , 王彤 ¹ , 王兹尧 ¹

电源学报 | 新能源发电与储能 2026,24(1): 233-241

收起

电源学报 |新能源发电与储能 2026 , 24 (1) : 233 -241

基于多尺度CNN和残差LSTM网络的储能电站SOC估计

全屏

黄晓凡¹, 李佳瑞¹, 秦玉文², 汤效平¹, 王彤¹, 王兹尧¹

作者信息

^1.华电电力科学研究院有限公司北京分院，北京　100000

^2.西安交通大学电气工程学院，西安　710049

通讯作者:

汤效平（1978—　），女，通信作者，博士，正高级工程师。研究方向：储能技术，综合能源。E-mail：xiaoping-tang@chder.com。

作者简介:

黄晓凡（1983—　），男，硕士，高级工程师。研究方向：储能技术，综合能源。E-mail：xiaofan-huang@chder.com。

李佳瑞（1997—　），男，硕士。研究方向：储能，深度学习。E-mail：lijiarui905@163.com。

秦玉文（1999—　），男，硕士。研究方向：人工智能算法设计。E-mail：yuwen_hilbert@stu.xjtu.edu.cn。

王彤（1968—　），男，博士，正高级工程师。研究方向：储能安全运行。E-mail：tong-wang@chder.com。

王兹尧（1978—　），男，硕士，正高级工程师。研究方向：低碳矿山，绿色矿山。E-mail：ziyao-wang@chder.com。

Estimation of State-of-charge in Energy Storage Plant Based Multi-scale CNN and Residual LSTM Network

Xiaofan HUANG¹, Jiarui LI¹, Yuwen QIN², Xiaoping TANG¹, Tong WANG¹, Ziyao WANG¹

Affiliations

^1.Beijing Branch, Huadian Electric Power Research Institute Co., Ltd., Beijing 100000, China

^2.School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, China

出版时间: 2026-01-30 doi: 10.13234/j.issn.2095-2805.2026.1.233

文章导航

摘要

收起

随着储能电站在新型电力系统中的大范围应用，提高锂离子电池荷电状态SOC（state-of-charge）预测精度对提升储能电站乃至电力系统安全稳定具有重大意义。提出1种结合多尺度卷积神经网络CNN（convolutional neural network）和残差长短期记忆LSTM（long short-term memory）网络的电池SOC预测方法，首先利用多尺度CNN自动提取传感器数据中的不同类型特征，然后将特征输入LSTM网络挖掘时间维度的关联性，同时在LSTM网络两端加入残差连接以避免模型过拟合。在储能系统实测数据上的对比实验表明，所提出的模型在各指标下均取得了最好的预测结果，特别是在电池处于复杂工作情况时更能提取关键特征，从而表现出更优秀的预测性能。

关键词

锂离子电池 / 荷电状态 / 多尺度卷积网络 / 长短期记忆网络 / 残差连接 / 深度学习

Abstract

收起

With the widespread applications of energy storage plants in new power systems, improving the prediction accuracy of lithium-ion battery state-of-charge (SOC) is of significance for enhancing the safety and stability of energy storage plants and power systems. A battery SOC prediction method is proposed, which combines a multi-scale convolutional neural network (CNN) and a residual long short-term memory (LSTM) network. First, the multi-scale CNN is employed to automatically extract different types of features from the sensor data. Then, the features are fed into an LSTM network to mine the correlation in the time dimension. Meanwhile, residual connections are added at both ends of the LSTM network to avoid model overfitting. The comparative experiments on the measured data of the energy storage system show that the proposed model achieves the best prediction results in terms of all the indicators. In particular, the key features can be extracted better when the battery is under complex operating conditions, resulting in a better prediction performance.

Key words

Lithium battery / state-of-charge (SOC) / multi-scale convolutional network / long and short-term memory (LSTM) network / residual connectivity / deep learning

引用本文

黄晓凡, 李佳瑞, 秦玉文, 汤效平, 王彤, 王兹尧. 基于多尺度CNN和残差LSTM网络的储能电站SOC估计. 电源学报, 2026 , 24 (1) : 233 -241 . DOI: 10.13234/j.issn.2095-2805.2026.1.233

Xiaofan HUANG, Jiarui LI, Yuwen QIN, Xiaoping TANG, Tong WANG, Ziyao WANG. Estimation of State-of-charge in Energy Storage Plant Based Multi-scale CNN and Residual LSTM Network[J]. Journal of Power Supply, 2026 , 24 (1) : 233 -241 . DOI: 10.13234/j.issn.2095-2805.2026.1.233

基金

收起

中国华电集团有限公司科技资助项目(CHDKJ21-01-103)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

谢小荣, 马宁嘉, 刘威, 等. 新型电力系统中储能应用功能的综述与展望[J]. 中国电机工程学报, 2023, 43(1): 158-169. Xie Xiaorong, Ma Ningjia, Liu Wei, et al. Functions of energy storage in renewable energy dominated power systems: Review and prospect[J]. Proceedings of the CSEE, 2023, 43(1): 158-169. (in Chinese)

[2]

杨涛, 文贤馗, 谈竹奎, 等. 面向新型电力系统储能电站的锂电池荷电状态评估方法研究[J]. 电测与仪表, 2025, 62(3): 30-37. Yang Tao, Wen Xiankui, Tan Zhukui, et al. Research on SOC evaluation method of lithium battery for energy storage station in novel power system[J]. Electrical Measurement & Instrumentation, 2025, 62(3): 30-37. (in Chinese)

[3]

李明维, 张传远, 宿剑飞, 等. 基于电池暂态响应分析的锂电池SOC估计[J]. 电源技术, 2021, 45(11): 1431-1434. Li Mingwei, Zhang Chuanyuan, Su Jianfei, et al. Lithium battery SOC estimation based on battery transient response analysis[J]. Chinese Journal of Power Sources, 2021, 45(11): 1431-1434. (in Chinese)

[4]

Vidal C, Malysz P, Kollmeyer P, et al. Machine learning applied to electrified vehicle battery state of charge and state of health estimation: State-of-the-art[J]. IEEE Access, 2020, 8: 52796-52814.

[5]

Chemali E, Kollmeyer P J, Preindl M, et al. State-of-charge estimation of Li-ion batteries using deep neural networks: A machine learning approach[J]. Journal of Power Sources, 2018, 400: 242-255.

[6]

黎冲, 王成辉, 王高, 等. 锂电池SOC估计的实现方法分析与性能对比[J]. 储能科学与技术, 2022, 11(10): 3328-3344. Li Chong, Wang Chenghui, Wang Gao, et al. Review on implementation method analysis and performance comparison of lithium battery state of charge estimation[J]. Energy Storage Science and Technology, 2022, 11(10): 3328-3344. (in Chinese)

[7]

丁羿茗, 吕瑞强, 蒋超. 基于EKF算法的神经网络估算锂电池SOC[J]. 电源技术, 2021, 45(10): 1260-1263. Ding Yiming, Lü Ruiqiang, Jiang Chao. Estimation of lithium battery SOC based on EKF neural network[J]. Chinese Journal of Power Sources, 2021, 45(10): 1260-1263. (in Chinese)

[8]

许傲然, 戴菁, 谷彩莲, 等. 基于WOA优化扩展卡尔曼算法的锂离子电池SOC估算研究[J]. 电源学报, 2025, 23(2): 232-239. Xu Aoran, Dai Jing, Gu Cailian, et al. Research on SOC estimation of lithium-ion battery based on WOA optimized extended Kalman algorithm[J]. Journal of Power Supply, 2025, 23(2): 232-239. (in Chinese)

[9]

胡劲, 赵靖英, 姚帅亮, 等. 基于阻容参数滤波优化UKF的锂电池SOC估计[J]. 电源学报, 2025, 23(2): 247-255. Hu Jin, Zhao Jingying, Yao Shuailiang, et al. SOC estimation of lithium battery based on resistance-capacitance parameters filtering optimization UKF[J]. Journal of Power Supply, 2025, 23(2): 247-255. (in Chinese)

[10]

贠祥, 张鑫, 王超, 等. 基于联合参数辨识的粒子群优化扩展粒子滤波的锂电池荷电状态估计[J]. 电工技术学报, 2024, 39(2): 595-606. Yun Xiang, Zhang Xin, Wang Chao, et al. State of charge estimation of Li-ion battery using particle swarm optimization extended Kalman particle filter based on joint parameter identification[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 595-606. (in Chinese)

[11]

刘旖琦, 雷万钧, 刘茜, 等. 基于双自适应扩展粒子滤波器的锂离子电池状态联合估计[J]. 电工技术学报, 2024, 39(2): 607-616. Liu Yiqi, Lei Wanjun, Liu Qian, et al. Joint state estimation of lithium-ion battery based on dual adaptive extended particle filter[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 607-616. (in Chinese)

[12]

王辉, 严欢, 张晓滨, 等. 基于分数阶的锂电池SOC和SOH联合在线估计[J]. 电源学报, 2025, 23(2): 256-265. Wang Hui, Yan Huan, Zhang Xiaobin, et al. Joint online estimation of SOC and SOH for lithium batteries based on fractional-order models[J]. Journal of Power Supply, 2025, 23(2): 256-265. (in Chinese)

[13]

Liu Yuefeng, He Yingjie, Bian Haodong, et al. A review of lithium-ion battery state of charge estimation based on deep learning: Directions for improvement and future trends[J]. Journal of Energy Storage, 2022, 52: 104664.

[14]

Charkhgard M, Farrokhi M. State-of-charge estimation for lithium-ion batteries using neural networks and EKF[J]. IEEE Transactions on Industrial Electronics, 2010, 57(12): 4178-4187.

[15]

郑永飞, 文怀兴, 韩昉, 等. 基于LSTM神经网络的动力电池SOC估算研究[J]. 计算机应用与软件, 2020, 37(3): 78-81, 88. Zheng Yongfei, Wen Huaixing, Han Fang, et al. SOC estimation of power battery based on lstm neural network[J]. Computer Applications and Software, 2020, 37(3): 78-81, 88. (in Chinese)

[16]

辛浩东, 赵欣, 周昊, 等. 基于LSTM-UKF的全电船用锂电池SOC容量估计[J]. 船舶工程, 2021, 43(11): 111-117. Xin Haodong, Zhao Xin, Zhou Hao, et al. SOC capacity estimation method of lithium-ion batteries in all-electric ships based on LSTM-UKF[J]. Ship Engineering, 2021, 43(11): 111-117. (in Chinese)

[17]

Yang Fangfang, Li Weihua, Li Chuan, et al. State-of-charge estimation of lithium-ion batteries based on gated recurrent neural network[J]. Energy, 2019, 175: 66-75.

[18]

Tian Jinpeng, Xiong Rui, Shen Weixiang, et al. State-of-charge estimation of LiFePO₄ batteries in electric vehicles: A deep-learning enabled approach[J]. Applied Energy, 2021, 291: 116812.

[19]

陈继斌, 李雯雯, 孙彦玺, 等. 基于卷积-双向长短期记忆网络的电池SOC预测[J]. 电源技术, 2022, 46(5): 532-535. Chen Jibin, Li Wenwen, Sun Yanxi, et al. Battery SOC prediction based on convolution bidirectional long term and short term memory network[J]. Chinese Journal of Power Sources, 2022, 46(5): 532-535. (in Chinese)

[20]

Bhattacharjee A, Verma A, Mishra S, et al. Estimating state of charge for xEV batteries using 1D convolutional neural networks and transfer learning[J]. IEEE Transactions on Vehicular Technology, 2021, 70(4): 3123-3135.

[21]

徐帅, 刘雨辰, 周飞. 基于RNN的锂离子电池SOC估算研究进展[J]. 电源技术, 2021, 45(2): 263-269. Xu Shuai, Liu Yuchen, Zhou Fei. Research progress of SOC estimation of lithium ion batteries based on RNN[J]. Chinese Journal of Power Sources, 2021, 45(2): 263-269. (in Chinese)

2026年第24卷第1期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.1.233

接收时间：2023-03-29
首发时间：2026-10-26
出版时间：2026-01-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-03-29
修回日期：2023-07-26
录用日期：2023-07-28

基金

Science and Technology Project of China Huadian Group Co., Ltd.(CHDKJ21-01-103)

中国华电集团有限公司科技资助项目(CHDKJ21-01-103)

作者信息

^1.华电电力科学研究院有限公司北京分院，北京　100000

^2.西安交通大学电气工程学院，西安　710049

通讯作者:

汤效平（1978—　），女，通信作者，博士，正高级工程师。研究方向：储能技术，综合能源。E-mail：xiaoping-tang@chder.com。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.1.233

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT