不同温度下的基于BPNN-AUKF的新型自动水下航行器SOC估计器

doi:10.19799/j.cnki.2095-4239.2024.0008

储能科学与技术 ›› 2024, Vol. 13 ›› Issue (4): 1205-1215.doi: 10.19799/j.cnki.2095-4239.2024.0008

• 电池智能制造、在线监测与原位分析专刊 • 上一篇下一篇

不同温度下的基于BPNN-AUKF的新型自动水下航行器SOC估计器

李青¹(), 张劭玮², 罗斯伦², 李炬晨², 成海超¹, 卢丞一²()

^1.中国电子科技集团公司第十八研究所，天津 300384
^2.西北工业大学，陕西西安 710072

收稿日期:2024-01-04 修回日期:2024-02-15 出版日期:2024-04-26 发布日期:2024-04-22
通讯作者: 卢丞一 E-mail:xzxk8890@163.com;luchengyi@nwpu.edu.cn
作者简介:李青（1982—），女，博士，高级工程师，研究方向为能源系统及信息处理，E-mail：xzxk8890@163.com；
基金资助:
国家重点研发计划项目(2020YFB1313200)

A novel automatic underwater vehicle SOC estimator based on BPNN-AUKF at different temperatures

Qing LI¹(), Shaowei ZHANG², Silun LUO², Juchen LI², Haichao CHENG¹, Chenyi LU²()

^1.Tianjin Institute of Power Sources, Tianjin 300384, China
^2.Northwestern Polytechnical University, Xi'an 710072, Shaanxi, China

Received:2024-01-04 Revised:2024-02-15 Online:2024-04-26 Published:2024-04-22
Contact: Chenyi LU E-mail:xzxk8890@163.com;luchengyi@nwpu.edu.cn

摘要/Abstract

摘要：

本研究提出了一种基于反向传播神经网络（BPNN）和自适应无迹卡尔曼滤波器（AUKF）的SOC（state of charge）估计方法。首先针对电池SOC与端电压之间在不同温度下的关系，研究设计了一系列温度补偿策略，以提高在低温、低SOC条件下的估计精度。其次，利用反向传播神经网络（BPNN）建立了一个耦合了温度补偿策略的电池模型。这个模型能更好地适应低温和低SOC条件下的电池状态变化，提高了SOC估计的准确性。最后，基于BPNN电池模型建立了BPNN-AUKF的SOC估计框架，通过利用测量值与测量预测值之间的信息和残差序列，对系统过程和测量噪声协方差进行估计修正。通过实验验证，发现该方法在低温环境下具有明显优势，相比传统方法能够更准确地估计电池的SOC，且具备较好的泛化能力。这种基于BPNN-AUKF方法的SOC估计器不仅适用于自主无人潜水器（AUV），而且对于其他在复杂环境中工作的车辆也具有广泛的应用价值。

关键词: SOC估算, 自适应无迹卡尔曼滤波器, 温度补偿策略, 神经元网络模型, 自主水下航行器

Abstract:

This study proposes a state of charge (SOC) estimation method based on backpropagation neural network (BPNN) and adaptive unscented Kalman filter (AUKF). Firstly, a series of temperature compensation strategies were studied and designed to improve the estimation accuracy under low temperature and low SOC conditions, focusing on the relationship between battery SOC and terminal voltage at different temperatures. Secondly, a battery model coupled with temperature compensation strategy was established using backpropagation neural network (BPNN). This model can better adapt to battery state changes under low temperature and low SOC conditions, improving the accuracy of SOC estimation. Finally, a SOC estimation framework for BPNN-AUKF was established based on the BPNN battery model. By utilizing the information and residual sequences between measured and predicted values, the system process and measurement noise covariance were estimated and corrected. Through experimental verification, it was found that this method has significant advantages in low-temperature environments. Compared with traditional methods, it can more accurately estimate the SOC of batteries and has good generalization ability. This SOC estimator based on BPNN-AUKF method is not only suitable for autonomous unmanned underwater vehicles (AUV), but also has broad application value for other vehicles working in complex environments.

Key words: SOC estimation, adaptive unscented Kalman filter, temperature compensation strategy, neural network model, autonomous underwater vehicle

中图分类号:

TM 912

李青, 张劭玮, 罗斯伦, 李炬晨, 成海超, 卢丞一. 不同温度下的基于BPNN-AUKF的新型自动水下航行器SOC估计器[J]. 储能科学与技术, 2024, 13(4): 1205-1215.

Qing LI, Shaowei ZHANG, Silun LUO, Juchen LI, Haichao CHENG, Chenyi LU. A novel automatic underwater vehicle SOC estimator based on BPNN-AUKF at different temperatures[J]. Energy Storage Science and Technology, 2024, 13(4): 1205-1215.

图/表 20

图1

图2

图3

图4

图5

图6

表1

图7

表2

图8

表3

图9

图10

表4

图11

表5

图12

表6

图13

表7

参考文献 14

1	LI B, MAO Z Y, SONG B W, et al. Thermal management performance improvement of phase change material for autonomous underwater vehicles' battery module by optimizing fin design based on quantitative evaluation method[J]. International Journal of Energy Research, 2022, 46(11): 15756-15772.
2	CHEN C, XIONG R, YANG R X, et al. State-of-charge estimation of lithium-ion battery using an improved neural network model and extended Kalman filter[J]. Journal of Cleaner Production, 2019, 234: 1153-1164.
3	YE M, GUO H, XIONG R, et al. A double-scale and adaptive particle filter-based online parameter and state of charge estimation method for lithium-ion batteries[J]. Energy, 2018, 144: 789-799.
4	XIONG R, YU Q Q, WANG L Y, et al. A novel method to obtain the open circuit voltage for the state of charge of lithium ion batteries in electric vehicles by using H infinity filter[J]. Applied Energy, 2017, 207: 346-353.
5	MESBAHI T, KHENFRI F, RIZOUG N, et al. Dynamical modeling of Li-ion batteries for electric vehicle applications based on hybrid Particle Swarm-Nelder-Mead (PSO-NM) optimization algorithm[J]. Electric Power Systems Research, 2016, 131: 195-204.
6	MENG J H, RICCO M, ACHARYA A B, et al. Low-complexity online estimation for LiFePO₄ battery state of charge in electric vehicles[J]. Journal of Power Sources, 2018, 395: 280-288.
7	MENG J H, RICCO M, LUO G Z, et al. An overview and comparison of online implementable SOC estimation methods for lithium-ion battery[J]. IEEE Transactions on Industry Applications, 2018, 54(2): 1583-1591.
8	JULIER S J, UHLMANN J K. New extension of the Kalman filter to nonlinear systems[C] //Proc.aerosense Int.symp.aerospace/defence Sensing Simulation, 1997: 182-193.
9	TONG S J, LACAP J H, PARK J W. Battery state of charge estimation using a load-classifying neural network[J]. Journal of Energy Storage, 2016, 7: 236-243.
10	HUANG C, WANG Z H, ZHAO Z H, et al. Robustness evaluation of extended and unscented Kalman filter for battery state of charge estimation[J]. IEEE Access, 2018, 6: 27617-27628.
11	SUN W, QIU Y, SUN L, et al. Neural network-based learning and estimation of battery state-of-charge: A comparison study between direct and indirect methodology[J]. International Journal of Energy Research, 2020, 44: 10307-10319.
12	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.
13	KOLLMEYER P. Panasonic 18650PF Li-ion battery data, Mendeley Data[DB/OL]. [2023-09-02]. https://data.mendeley.com/datasets/wykht8y7tg/1.
14	CHEN P Y, LU C Y, MAO Z Y, et al. Evaluation of various offline and online ECM parameter identification methods of lithium-ion batteries in underwater vehicles[J]. ACS Omega, 2022, 7(34): 30504-30518.

Temperature/℃	c_T
25	0
10	0.020
0	0.100
-10	0.180
-20	0.310

Methods	MAE	RMSE
BPNN	0.0160	0.0171
ECM_FFRLS	0.0185	0.0208
ECM_EKF	0.0194	0.0351

Methods	MAE	RMSE
BPNN-AUKF	0.0075	0.0270
ECM_FFRLS-UKF	0.0185	0.0443
ECM_EKF-UKF	0.0159	0.0432

Driving cycles	MAE	RMSE
UDDS	0.0064	0.012
LA92	0.0077	0.0179
HWFTE	0.0079	0.0191

Driving cycles	MAE	RMSE
UDDS	0.0160	0.0171
LA92	0.0165	0.0202
HWFTE	0.0056	0.0114

不同温度下的基于BPNN-AUKF的新型自动水下航行器SOC估计器

A novel automatic underwater vehicle SOC estimator based on BPNN-AUKF at different temperatures

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 20

参考文献 14

相关文章 5

编辑推荐

Metrics

本文评价

[1]	杜帮华, 张宇, 吴铁洲, 何衍林, 李子龙. 梯次利用锂离子电池等效模型参数在线辨识方法[J]. 储能科学与技术, 2021, 10(1): 342-348.
[2]	张远进, 吴华伟, 叶从进. 基于AUKF-BP神经网络的锂电池SOC估算[J]. 储能科学与技术, 2021, 10(1): 237-241.
[3]	何瑛, 钟根鹏, 陈翌. 基于特征组合堆叠融合集成学习的锂离子动力电池SOC估算[J]. 储能科学与技术, 2020, 9(5): 1548-1557.
[4]	蒋聪, 王顺利, 李小霞, 熊鑫. 基于改进EKF算法变温度下的动力锂电池SOC估算[J]. 储能科学与技术, 2020, 9(1): 145-151.
[5]	苏振浩, 李晓杰, 秦晋, 杜文杰, 韩宁. 基于BP人工神经网络的动力电池SOC估算方法[J]. 储能科学与技术, 2019, 8(5): 868-873.

Methods	10 ℃		0 ℃		-10 ℃		-20 ℃
Methods	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
BPNN	0.026	0.029	0.020	0.023	0.022	0.028	0.035	0.043
FFRLS	2.615	1106.400	0.023	0.028	2.643×10³³	5.141×10³⁵	0.134	0.201
EKF	0.023	0.040	0.023	0.043	0.028	0.051	0.041	0.072

Methods	10 ℃		0 ℃		-10 ℃		-20 ℃
Methods	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
BPNN	0.0032	0.004	0.0046	0.0521	0.0112	0.0137	0.0148	0.0172
FFRLS	0.006	0.010	0.0319	0.0359	0.0788	0.0914	0.0595	0.0681
EKF	0.0745	0.009	0.0382	0.0515	0.0585	0.0608	0.0434	0.0457