基于证据KNN分类器的蓄电池一致性诊断

王楠; 周喜超; 彭勇; 李振; 安坤; 赵鹏翔

doi:10.19912/j.0254-0096.tynxb.2022-0023

PDF(1748 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (4) : 13-19. DOI: 10.19912/j.0254-0096.tynxb.2022-0023

电化学储能安全性与退役动力电池梯次利用关键技术专题

基于证据KNN分类器的蓄电池一致性诊断

王楠, 周喜超, 彭勇, 李振, 安坤, 赵鹏翔

作者信息 +

BATTERY CONSISTENCY DIAGNOSIS BASED ON EVIDENTIAL KNN CLASSIFIER

Wang Nan, Zhou Xichao, Peng Yong, Li Zhen, An Kun, Zhao Pengxiang

Author information +

文章历史 +

摘要

通过串并联方式组成的大容量储能电站在长期运行过程中,会不可避免地出现电池单体不一致性的问题。及时识别出有可能存在异常的电池单体,为储能电站评估电池的健康状态提供数据支撑的同时,还可降低储能电站系统性运行风险。该研究提出一种不依赖于电池模型以及经验数据的,基于证据K近邻（KNN）分类器的储能电池一致性诊断方法。该方法利用储能电站一簇电池中的大量单体电池电压与温度运行数据,使用证据KNN分类器构建能表征电池电压、温度一致性的诊断模型,并通过异常反演算法,准确识别出异常的单体电池。

Abstract

The inconsistency of battery unit inevitably occurs in the long-term operation of the large-capacity energy storage stations composed by series-parallel connection. Therefore, timely identification of battery units with potential abnormalities can not only provide data support for energy storage stations to assess the health status of batteries, but also reduce the systemic operation risks. In this paper, we proposes a consistency diagnosis method for energy storage batteries based on evidential KNN classifier, which is independent of battery model and empirical data. Concretely, this method is based on a large number of single unit voltage and temperature operation data in a cluster of units in an energy storage stations, and uses an evidential KNN classifier to construct a diagnostic model that can characterize the consistency of unit voltage and temperature, and accurately identifies abnormal single units through an anomaly inversion algorithm.

导出引用

王楠, 周喜超, 彭勇, 李振, 安坤, 赵鹏翔. 基于证据KNN分类器的蓄电池一致性诊断[J]. 太阳能学报. 2022, 43(4): 13-19 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0023

Wang Nan, Zhou Xichao, Peng Yong, Li Zhen, An Kun, Zhao Pengxiang. BATTERY CONSISTENCY DIAGNOSIS BASED ON EVIDENTIAL KNN CLASSIFIER[J]. Acta Energiae Solaris Sinica. 2022, 43(4): 13-19 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0023

中图分类号： TK02

参考文献

[1] 李欣然, 黎淑娟, 黄际元, 等. 储能电池参与电网二次调频的高效性评估[J]. 太阳能学报, 2019, 40(9): 2608-2615.
LI X R, LI S J, HUANG J Y, et al. Efficiency analysis of energy storage battery participating in secondary frequency regulation[J]. Acta energiae solaris sinica, 2019, 40(9): 2608-2615.
[2] 戴海峰, 王楠, 魏学哲, 等. 车用动力锂离子电池单体不一致性问题研究综述[J]. 汽车工程, 2014, 36(2): 181-188, 203.
DAI H F, WANG N, WEI X Z, et al. A research review on the cell inconsistency of Liion traction batteries in electric vehicles[J]. Automotive engineering, 2014, 36(2): 181-188, 203.
[3] 靳文涛, 李相俊, 惠东, 等. 规模化储能电站电池一致性的统计特性研究[J]. 发电技术, 2021, 42(3): 298-305.
JIN W T, LI X J, HUI D, et al. Study on statistical characteristics of battery consistency in large-scale energy storage power stations[J]. Power generation technology, 2021, 42(3): 298-305.
[4] 贾学翠, 李相俊, 汪奂伶, 等. 基于运行数据融合的储能电池一致性评估方法研究[J]. 供用电, 2017, 34(4): 29-35.
JIA X C, LI X J, WANG H L, et al. Research on consistency assessment method for energy storage battery based on operating data fusion[J]. Power supply and consumption, 2017, 34(4): 29-35.
[5] 黄彧, 王占国, 张言茹, 等. 基于离群点检测的动力电池一致性快速辨识方法[J/OL]. 电测与仪表: 1-9[2021-07-27]. http://kns.cnki.net/kcms/detail/23.1202.TH.20210326.1545.004.html.
HUANG Y, WANG Z G, ZHANG Y R, et al. Fast identification method of power battery consistency based on outlier detection[J/OL]. Electrical measurement and instrumentation: 1-9[2021-07-27] http://kns.cnki.net/kcms/detail/23.1202.TH.20210326.1545.004.html.
[6] 邓一尊.大规模锂离子电池组不一致性辨识与均衡方法研究[D]. 上海: 上海交通大学, 2018.
DENG Y Z.Research on inconsistency identification and equalization method of large-scale lithium ion battery pack[D]. Shanghai: Shanghai Jiaotong University, 2018.
[7] 宋超, 熊刚, 谢勇波, 等. 基于ARIMA模型的动力电池不一致性预警研究[J]. 控制与信息技术, 2019(5): 82-87.
SONG C, XIONG G, XIE Y B, et al. Research on inconsistency early warning of power battery based on ARIMA model[J]. Control and information technology, 2019(5): 82-87.
[8] PLETT G L.Efficient battery pack state estimation using bar-delta filtering[C]//EVS24 International Battery, Hybrid and Fuel Cell Electric Vehicle Symposium, stavanger, Norway, 2009: 1-8.
[9] ZHENG Y J, OUYANG M G, LU L G, et al. Cell state-of-charge inconsistency estimation for LiFePO₄ battery pack in hybrid electric vehicles using mean-difference model[J]. Applied energy, 2013, 111: 571-580.
[10] SUN F C, XIONG R, HE H W.A systematic state-of-charge estimation framework for multi-cell battery pack in electric vehicles using bias correction technique[J]. Applied energy, 2016, 162: 1399-1409.
[11] 葛云龙, 陈自强.基于STF&LM算法的串联锂离子电池组不一致性辨识与状态估计[J]. 中国电机工程学报, 2018, 38(14): 4271-4280, 4333.
GE Y L, CHEN Z Q.Inconsistency identification and state estimation of series lithium ion battery pack based on STF & LM algorithm[J]. Proceedings of the CSEE, 2018, 38(14): 4271-4280, 4333.
[12] 叶春霖, 邱颖宁, 冯延晖.基于警报信号和D-S证据理论的风电机组故障诊断[J]. 太阳能学报, 2019, 40(12): 3613-3620.
YE C L, QIU Y N, FENG Y H.Fault diagnosis of wind turbine based on alarm signals and D-S evidence theory[J]. Acta energiae solaris sinica, 2019, 40(12): 3613-3620.
[13] 林优, 杨明, 韩学山, 等. 基于条件分类与证据理论的短期风电功率非参数概率预测方法[J]. 电网技术, 2016, 40(4): 1113-1119.
LIN Y, YANG M, HAN X S, et al. Nonparametric approach for short-term probabilistic wind generation forecast based on conditional classification and evidence theory[J]. Power system technology, 2016, 40(4): 1113-1119.
[14] 鲍海波, 韦化, 郭小璇, 等. 考虑风电不确定性的概率区间潮流模型与算法[J]. 中国电机工程学报, 2017, 37(19): 5633-5642, 5840.
BAO H B, WEI H, GUO X X, et al. The model and algorithm of probabilistic interval power flow considering wind power uncertainty[J]. Proceedings of the CSEE, 2017, 37(19): 5633-5642, 5740.
[15] 陈小龙.证据驱动型火电机组状态预警方法及其应用研究[D]. 南京: 东南大学, 2019.
CHEN X L.Research on state early warning method and its application of evidence driven thermal power units[D]. Nanjing: Southeast University, 2019.
[16] 鲍海波, 郭小璇, 韦化.结合证据理论和双层规划的电压稳定不确定分析[J]. 电力系统自动化, 2018, 42(5): 120-126, 146.
BAO H B, GUO X X, WEI H.Uncertainty analysis of voltage stability based on evidence theory and bilevel programming[J]. Automation of electric power systems, 2018, 42(5): 120-126, 146.
[17] YAGER R R.Decision making under Dempster-Shafer uncertainties[J]. International journal of general systems, 1992, 20(3): 233-245.
[18] DENOEUX T.A k-nearest neighbor classification rule based on Dempster-Shafer theory[J]. IEEE transactions on systems, man, and cybernetics, 1995, 25(5): 804-813.
[19] STONE M A.Cross-validatory choice and assessment of statistical predictions[J]. Journal of the Royal Statistical Society, 1974, 36(2): 111-147.