Supervisor of Master's Candidates
Name (Simplified Chinese): 吴慕遥
Name (Pinyin): wumuyao
Date of Birth: 1995-12-08
E-Mail:
Date of Employment: 2022-12-27
School/Department: 车辆工程系
Education Level: With Certificate of Graduation for Doctorate Study
Business Address: 安徽省合肥市屯溪路193号合肥工业大学格物楼515
Gender: Male
Degree: Doctoral Degree in Engineering
Professional Title: Lecturer
Status: Employed
Alma Mater: 中国科学技术大学
Supervisor of Master's Candidates
Discipline: Automobile Engineering
MORE>
基于多阶段分析的内短路诊断及预警
Hits:
Impact Factor:1.6
DOI number:10.19535/j.1001-1579.2026.02.011
Journal:电池
Key Words:锂离子电池; 内短路诊断; 离群点检测; 标准差算法; 遗传算法优化反向传播神经网络(GA-BP); 故障预警
Abstract:针对锂离子电池内短路故障诊断难题,提出一种融合改进的动态离群检测、特征增强和优化预测的三阶段诊断方法。首先,利用基于动态 k 值优化的局部异常因子(LOF)检测模型,通过动态搜索获得最佳邻域参数,以此确定异常单体电池的位置;其次,在传统标准差算法基础上,为了减小测量误差影响,引入滑动窗口机制,放大早期内短路故障的微弱特征,实现故障的精确检测;最后,构建遗传算法优化反向传播神经网络( GA-BP)融合模型,并结合标准差算法对故障进行预警。通过对多辆实际的电动汽车数据的验证,所提出的方法对故障单体检测的准确率超过 95%,并且可以稳定地提前 6 个采样周期实现内短路故障的预警,对于提高电动汽车电池的安全防护能力具有重要意义。
Note:北大核心
Co-author:陈中宇,胡玉叶,杨凌霄
First Author:陈媛
Indexed by:Journal paper
Correspondence Author:吴慕遥
Discipline:Engineering
Document Type:J
Volume:56
Issue:2
Page Number:369-375
ISSN No.:1001-1579
Translation or Not:no
Date of Publication:2026-04-25
Links to published journals:https://kns.cnki.net/kcms2/article/abstract?v=lj-1FT9NYjAIf5XDJWSghy1j0u0CYZzWNLCr2WZyvJJsDLaPv5SY4dfosVow5Mq_7n-65zNZimk_PPDcrCe9lNzjh12PfaZAUPR1gtagR8zNg8oqbSbUvv7Bv7IBEpuDl3NAXxGT47VxsaefzNRc8a-nI5
The Last Update Time : ..
