针对径向基神经网络在SOC预测过程中随机产生基函数中心和宽度的不稳定性导致预测精度不佳的问题,提出一种改进RBF的蓄电池SOC估计方法,以麻雀搜索算法优化RBF网络参数以提高网络预测精度。在DST工况仿真验证SSA参数优化的有效性,在US06和FUDS工况下,分别利用改进径向基神经网络、RBF、极限学习机与BP神经网络对SOC进行预测。对比分析结果表明,SSARBF在SOC估计精度方面表现更优,将估计误差降低到2%以内,能够完成高精度的SOC估计,具有一定的理论研究意义与应用价值。
Abstract
To address the issue of poor prediction accuracy caused by the instability of randomly generated center and width of basis functions in Radial Basis Function (RBF) during SOC prediction,an improved RBF-based SOC estimation method is proposed.The method optimizes RBF network parameters using the Sparrow Search Algorithm (SSA) to enhance the prediction accuracy of the network.The effectiveness of SSA parameter optimization is validated through simulation experiments under the DST operating condition.Furthermore,under the US06 and FUDS operating conditions,the SOC prediction is conducted using the improved Radial Basis Function (SSARBF),RBF,Extreme Learning Machine (ELM),and Backpropagation Neural Network (BPNN).Comparative analysis of the results demonstrates that SSARBF outperforms in terms of SOC estimation accuracy,reducing estimation error to within 2% and achieving high-precision SOC estimation.This approach holds significant theoretical research significance and practical value.
关键词
蓄电池 /
SOC估计 /
RBF神经网络 /
SSA算法
Key words
battery /
SOC estimation /
RBF neural network /
SSA algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 赵徐成,王旭昆,朱逸天.模糊神经网络技术的铅酸蓄电池性能检测研究[J].电源技术,2016,40(12):2405-2406.
[2] 李晶,陈轲娜,罗洋.基于Thevenin模型的蓄电池内阻监测装置的现场校验方法研究[J].电测与仪表,2021,58(11):194-200.
[3] 吴海洋,缪巍巍,施健,等.基于改进安时法的蓄电池剩余电量预测模型研究[J].计算机与数字工程,2020,48(5):1247-1251.
[4] 尹乐乐,靳成杰,康健强.基于DP模型的锂离子电池能量状态估算[J].电源技术,2019,43(10):1619-1622.
[5] 郑力得,董建园,马强.基于参数辨识与AEKF的锂电池SOC估计[J].电源技术,2020,44(10):1502-1505.
[6] 韩云飞,谢佳,蔡涛.结合高斯过程回归与特征选择的锂离子电池容量估计方法[J].储能科学与技术,2021,10(4):1432-1438.
[7] 王莉,杨永辉,詹益.基于最小二乘支持向量机阀控式铅酸蓄电池寿命预测[J].大连交通大学学报,2017,38(3):116-119.
[8] 陈凯,彭仲晗,吴启瑞.基于LIBSVM的铅酸蓄电池荷电状态估计[J].电源技术,2020,44(4):578-581.
[9] Kesen Fan,Yiming Wan,Zhuo Wang,et al.Time-efficient identification of lithium-ion battery temperature-dependent OCV-SOC curve using multi-output Gaussian process[J].Energy,2023(268).
[10] He W,Williard N,Chen C,et al.State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation[J].International Journal of Electrical Power & Energy Systems,2014(62):783-791.
[11] 陈峥,李磊磊,舒星,等.基于特征处理与径向基神经网络的锂电池剩余容量估算方法[J].储能科学与技术,2021,10(1):261-270.
[12] XING Y J,HE W,PECHT M,et al.State of charge estimation of lithium-ion batteries using the open-circuit voltage at various ambient temperatures[J].Applied Energy,2014(113):106-115.
基金
*南瑞集团有限公司—智慧型站用交直流电源关键设备研制(SGNR0000KJJS2106316)
PDF(1918 KB)
