电源学报

基于CNN-BiLSTM-Attention的电动装载机电池荷电状态预测

PDF下载

丁伟 ¹ , 邹复民 ¹^,²^,³ , 刘吉顺 ¹^,³ , 张程 ¹

电源学报 | 新能源发电与储能 2026,24(4): 188-195

收起

电源学报 |新能源发电与储能 2026 , 24 (4) : 188 -195

基于CNN-BiLSTM-Attention的电动装载机电池荷电状态预测

全屏

丁伟¹, 邹复民¹^,²^,³, 刘吉顺¹^,³, 张程¹

作者信息

^1.福建理工大学电子电气与物理学院，福州　350118

^2.福建省汽车电子与电驱动技术重点实验室，福州　350118

^3.福建理工大学宁德新能源技术研究院，宁德　352101

通讯作者:

刘吉顺（1976—　），男，通信作者，博士，研究员。研究方向：新能源工程机械。E-mail：jsh.liu@fjut.edu.cn。

作者简介:

丁伟（2000—　），男，硕士研究生。研究方向：新能源。E-mail：2221905082@smail.fjut.edu.cn。

邹复民（1976—　），男，博士，教授。研究方向：交通信息与控制工程，大数据技术与人工智能。E-mail：fmzou@fjut.edu.cn。

张程（1982—　），男，博士，副教授。研究方向：电力系统稳定与控制，新能源。E-mail：zhangcheng@fjut.edu.cn。

State-of-charge Prediction of Electric Loader Batteries Based on CNN-BiLSTM-Attention

Wei DING¹, Fumin ZOU¹^,²^,³, Jishun LIU¹^,³, Cheng ZHANG¹

Affiliations

^1.School of Electronic, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou 350118, China

^2.Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive Technology, Fuzhou 350118, China

^3.Ningde New Energy Technology Research Institute, Fujian University of Technology, Ningde 352101, China

出版时间: 2026-04-30 doi: 10.13234/j.issn.2095-2805.2026.4.188

文章导航

摘要

收起

为准确预测电动装载机电池的荷电状态SOC（state-of-charge），提出1种卷积神经网络CNN（convolutional neural networks）、双向长短期记忆BiLSTM（bi-directional long short-term memory）网络和注意力（attention）机制相结合的预测模型。首先，使用Pearson相关系数分析法对输入特征进行筛选；其次，使用CNN提取空间特征；然后，将提取的特征序列输入到双向LSTM层中进行时序建模，并融合注意力机制分配权重，以增强重要特征；最后，由全连接层输出预测结果。实验结果表明，CNN-BiLSTM-Attention模型的预测精度达到99.97%，预测误差均在1.00%以内。与CNN-LSTM-Attention等模型相比，该模型的预测精度更高、误差更小，能够表现出一定的优越性和可靠性。

关键词

电动装载机 / 电池荷电状态 / 卷积神经网络 / 双向长短期记忆网络 / 注意力机制

Abstract

收起

To accurately predict the state-of-charge (SOC) of electric loader batteries, a prediction model combining convolutional neural networks (CNN), bi-directional long short-term memory (BiLSTM) network and attention mechanism was proposed. First, the Pearson correlation coefficient analysis method was used to filter the input features; second, the spatial features were extracted by CNN; then the extracted feature sequences were input into the bi-directional LSTM layer for time series modeling, in addition, the attention mechanism was fused to allocate weights, so as to enhance the important features; finally, the prediction results were output by the fully-connected layer. Experimental results show that the prediction accuracy of the CNN-BiLSTM-Attention model reached 99.97%, and the prediction error was within 1.00%. Compared with models such as the CNN-LSTM-Attention model, this model had higher prediction accuracy and smaller error, indicating certain superiority and reliability.

Key words

Electric loader / battery state-of-charge (SOC) / convolutional neural networks (CNN) / bi-directional long short-term memory (BiLSTM) networks / attention mechanism

引用本文

丁伟, 邹复民, 刘吉顺, 张程. 基于CNN-BiLSTM-Attention的电动装载机电池荷电状态预测. 电源学报, 2026 , 24 (4) : 188 -195 . DOI: 10.13234/j.issn.2095-2805.2026.4.188

Wei DING, Fumin ZOU, Jishun LIU, Cheng ZHANG. State-of-charge Prediction of Electric Loader Batteries Based on CNN-BiLSTM-Attention[J]. Journal of Power Supply, 2026 , 24 (4) : 188 -195 . DOI: 10.13234/j.issn.2095-2805.2026.4.188

基金

收起

福建省财政厅专项资助项目(GY-Z220230)
福建省自然基金资助项目(2023J01951)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302. Yin Jie, Liu Bo, Sun Guobing, et al. Transfer learning denoising autoencoder-long short term memory for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 289-302. (in Chinese)

[2]

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)

[3]

白俊琦, 贤燕华. 基于BP-多时间尺度UKF优化算法的SOC估计[J]. 电源学报, 2025, 23(3): 363-372. Bai Junqi, Xian Yanhua. State-of-charge estimation based on BP-multi-timescale UKF optimization algorithm[J]. Journal of Power Supply, 2025, 23(3): 363-372. (in Chinese)

[4]

Ng M F, Zhao Jin, Yan Qingyu, et al. Predicting the state of charge and health of batteries using data-driven ma-chine learning[J]. Nature Machine Intelligence, 2020, 2(3): 161-170.

[5]

张梅, 冯涛. 矿用电机车动力锂电池的SOC估算研究[J]. 煤矿机械, 2023, 44(9): 55-58. Zhang Mei, Feng Tao. Research on SOC estimation of power lithium battery for mining electric locomotive[J]. Coal Mine Machinery, 2023, 44(9): 55-58. (in Chinese)

[6]

寇发荣, 罗希, 门浩, 等. 基于特征优选与改进极限学习机的锂电池SOC估计[J]. 储能科学与技术, 2023, 12(4): 1234-1243. Kou Farong, Luo Xi, Men Hao, et al. State of charge estimation of lithium battery based on feature optimazation and improved extreme learning machine[J]. Energy Storage Science and Technology, 2023, 12(4): 1234-1243. (in Chinese)

[7]

于仲安, 邵昊晖, 陈可怡. 基于IGWO-BP神经网络的锂离子电池SOC估计[J]. 电源技术, 2023, 47(9): 1153-1157. Yu Zhongan, Shao Haohui, Chen Keyi. SOC estimation of lithium ion battery based on IGWO-BP neural network[J]. Chinese Journal of Power Sources, 2023, 47(9): 1153-1157. (in Chinese)

[8]

宋磊, 陆春光, 刘琳, 等. 基于修正安时积分法的磷酸铁锂电池荷电状态估计[J]. 郑州大学学报(工学版), 2023, 44(6): 84-90. Song Lei, Lu Chunguang, Liu Lin, et al. State of charge estimation of LiFePO₄ battery based on modified amper-hour integral method[J]. Journal of Zhengzhou University (Engineering Science), 2023, 44(6): 84-90. (in Chinese)

[9]

Zhao Fen, Li Yinguo, Wang Xinheng, et al. Lithium-ion batteries state of charge prediction of electric vehicles using RNNs-CNNs neural networks[J]. IEEE Access, 2020, 8: 98168-98180.

[10]

刘世林, 李德俊, 姚伟, 等. 基于核极限学习机与容积卡尔曼滤波融合的锂电池荷电状态估计[J]. 湖南大学学报(自然科学版), 2023, 50(10): 51-59. Liu Shilin, Li Dejun, Yao Wei, et al. Estimation on state of charge of lithium battery based on fusion of kernel extreme learning machine and cubature Kalman filter[J]. Journal of Hunan University (Natural Sciences), 2023, 50(10): 51-59. (in Chinese)

[11]

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 optimazation extended Kalman particle filter based on joint parameter identification[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 595-606. (in Chinese)

[12]

Li Ran, Xu Shihui, Li Sibo, et al. State of charge predicttion algorithm of lithium-ion battery based on PSO-SVR cross validation[J]. IEEE Access, 2020, 8: 10234- 10242.

[13]

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.

[14]

Tan Mao, Yuan Siping, Li Shuaihu, et al. Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning[J]. IEEE Transactions on Power Systems, 2020, 35(4): 2937-2948.

[15]

董红召, 王桢, 张楠, 等. 电动公交车电池荷电状态的Seq2Seq预测方法[J]. 浙江大学学报(工学版), 2023, 57(10): 2051-2059. Dong Hongzhao, Wang Zhen, Zhang Nan, et al. Seq2Seq prediction method of state of charge of electric bus battery[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(10): 2051-2059. (in Chinese)

[16]

肖占龙, 郑岳久, 李相俊, 等. 变温下磷酸铁锂电池的SOC估计方法研究[J]. 电源学报, 2024, 22(6): 199-206. Xiao Zhanlong, Zheng Yuejiu, Li Xiangjun, et al. Study on SOC estimation method for LiFePO₄ battery at variable temperature[J]. Journal of Power Supply, 2024, 22(6): 199-206. (in Chinese)

2026年第24卷第4期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.4.188

接收时间：2023-12-20
首发时间：2026-10-29
出版时间：2026-04-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-12-20
修回日期：2024-01-19
录用日期：2024-02-19

基金

Special Fund of Fujian Provincial Finance Department(GY-Z220230)

福建省财政厅专项资助项目(GY-Z220230)

Natural Science Foundation of Fujian Province(2023J01951)

福建省自然基金资助项目(2023J01951)

作者信息

^1.福建理工大学电子电气与物理学院，福州　350118

^2.福建省汽车电子与电驱动技术重点实验室，福州　350118

^3.福建理工大学宁德新能源技术研究院，宁德　352101

通讯作者:

刘吉顺（1976—　），男，通信作者，博士，研究员。研究方向：新能源工程机械。E-mail：jsh.liu@fjut.edu.cn。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.4.188

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