《电池》开通万方论文查重系统.pdf

电池BATTERY BIMONTHLY第 53 卷图 6 车辆 2 诊断结果分析Fig.6 Diagnostic result analysis of vehicle 2从图 6 可知,22 号电池电压由于没有触发目前 BMS 的欠压阈值报警和压差过大报警,未被检出,而所提方法可检测出故障电池并报警。4 结论本文作者首先研究了 VMD 算法,将原始信号进行 VMD分解,然后基于重构信号提取特征,最后利用 LOF 算法对特征进行诊断。经实车数据验证,所提方法能够在车辆热失控前 21 个采样点发出故障预警,且相较于 BMS 提前 17 个采样点。基于 LLE 的锂离子电池故障诊断有如下优势:在特征提取方面,无量纲特征参数在故障诊断领域表现出良好的稳定 性和对故障信息的敏感性。利用 LLE 算法提取特征,既保留了二维空间的关键信息,消除了正常电池的不一致性影响,也降低了计算量,是仅通过传统无量纲参数无法实现的。参考文献:1 朱景哲,张希,高一钊,等.数据驱动的锂离子电池智能故障诊断算法J.电池,2022,52(4):401-405.ZHU J Z,ZHANG X,GAO Y Z,et al.Data driven intelligent fault diagnosis algorithm for Li-ion batteryJ.Battery Bimonthly,2022,52(4):401-405.2JIANG J C,LI T Y,CHANG C,et al.Fault diagnosis method for lithium-ion batteries in electric vehicles based on isolated forest al-gorithmJ.J Energy Storage,2022,50:104177.3 ZHANG H,NIU G X,ZHANG B,et al.Cost-effective lebesgue sam-pling long short-term memory networks for lithium-ion batteries diagnosis and prognosisJ.IEEE T-IE,2022,69(2):1958-1967.4 李洪军,汪大春,杨哲昊,等.基于 DCGAN 的燃料电池故障诊断J.电池,2022,52(5):502-506.LI H J,WANG D C,YANG Z H,et al.Fuel cell fault diagnosis based on DCGANJ.Battery Bimonthly,2022,52(5):502-506.5 XIA B,SHANG Y L,NGUYEN T,et al.A correlation based fault detection method for short circuits in battery packsJ.J Power Sources,2017,337:1-10.6 YAO L,FANG Z P,XIAO Y Q,et al.An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machineJ.Energy,2021,214:118866.7 YAO L,XIAO Y Q,GONG X Y,et al.A novel intelligent method for fault diagnosis of electric vehicle battery system based on wave-let neural networkJ.J Power Sources,2020,453:227870.8 YANG R X,XIONG R,HE H W,et al.A fractional-order model-based battery external short circuit fault diagnosis approach for all-climate electric vehicles applicationJ.J Clean Prod,2018,187:950-959.9 柏云耀,邹时波,李顶根.基于数据分析方法的动力电池系统滥用故障诊断J.新能源进展,2020,8(1):1-5.BAI Y Y,ZOU S B,LI D G.Abuse fault diagnosis method of power battery system based on data analysis methodJ.Advances in New and Renewable Energy,2020,8(1):1-5.收稿日期:2022-10-12电池开通万方论文查重系统根据国家对期刊质量管理的要求,为加强学术不端风险防范,完善学术不端体系建设标准查漏补缺工作,本刊已启用万方查重系统检测,建议各位作者在投稿前,进行论文查重检测。目前,万方公司对个人用户提供了检测服务。作者在外部渠道查重易造成论文与成果泄漏,来稿作者可自愿使用本刊的万方论文查重系统,进行预查重检测。检测链接地址:http:万方检测系统预查重检测属于第三方检测,如有疑问,请作者与检测方接洽(QQ:800856851;电话:18577887362)662