An early warning method for detecting inconsistency in electric vehicle (EV) power batteries is proposed. This work introduces a novel LOF-based framework that integrates dynamic thresholding and multi-feature extraction, validated using real-world datasets to improve detection accuracy and reduce false alarms. Battery operation data are segmented through a sliding window mechanism, enabling the extraction of both long-term and short-term voltage anomaly characteristics. Four key indicators-Discrete Fréchet Distance (DFD), Clearance Factor (CLF), Shape Factor (SF), and Shannon Entropy (H) are utilized to characterize uncertainty-related inconsistency features. The LOF algorithm analyzes the constructed feature matrix for anomaly identification, while a dynamic threshold adaptively adjusts the warning criteria under varying operating conditions. The proposed method achieves an average early warning lead time of 34 hours, with precision of 0.95, recall of 0.93, and a false alarm rate 42% lower than conventional LOF-based approaches. Validation across ten EV and e-bike datasets under diverse driving and environmental conditions confirms the method’s strong generalization ability. Experimental results verify that the proposed approach significantly improves detection accuracy, reduces false alarms, and provides timely early warning, offering a reliable and practical solution for safe and consistent EV battery operation.
HaldeAEHiroleASKharcheTY. A technological review of charging stations for electric vehicles based on photovoltaic energy. Int J Innov Res Dev2024; 3: 45–67.
2.
AmraniMAHaddadYObeidatF, et al.Driving forward: a decade of electric vehicles progress and challenges in Jordan. JJMIE2024; 18: 280–284.
3.
WangFLiuPZhangZ, et al.Challenges and opportunities in truck electrification revealed by big operational data. Nat Energy2024; 2: 15–39.
4.
HuangBLiaoHWangY, et al.Prediction and evaluation of health state for power battery based on ridge linear regression model. Sci Prog2021; 104: 1–16.
5.
LiXFanDLiuX, et al.State of health estimation for lithium-ion batteries based on improved bat algorithm optimization kernel extreme learning machine. J Energy Storage2024; 101: 113756.
6.
QiuWHaoQAnnamareddySHK, et al. Electric vehicle revolution and implications: ion battery and energy. Engineered Sci. 2022; 20: 100–109.
7.
NęckaKKnagaJ. Environmental impact assessment for electric vehicles. J Phys, Conf Ser2021; 1782: 012023.
8.
KumaresanNRammohanA. Modeling and performance analysis of an electric two-wheeler on various driving cycles and validation using a performance real-time target machine. J Energy Storage2024; 72: 106675.
9.
XuBLiJXieY, et al.Capacity degradation study of NaNi1/3Fe1/3Mn1/3O2 cathode sodium-ion batteries induced by overcharge. J Power Sources2024; 602: 127685.
10.
PengSZhangDDaiG, et al.State of charge estimation for LiFePO4 batteries joint by PID observer and improved EKF in various OCV ranges. Appl Energy2025; 350: 120539.
11.
LiuDWenkaiDZhaoyangL. Estimation of real-vehicle battery state of health using the RUN-GRU-attention model. Energy Storage Science and Technology2024; 13(2): 150–158.
12.
LuoDYangSLiZ, et al.Transient energy, exergy, and economic analysis of an automotive thermoelectric generator with different structures. Appl Energy2025; 344: 120238.
13.
Vega-PerkinsJNewellJKeoleianG. Mapping electric vehicle impacts: greenhouse gas emissions, fuel costs, and energy justice in the United States. Environ Res Lett2023; 18: 014027.
14.
KangYYangXZhouZ, et al.A comparative study of fault diagnostic methods for lithium-ion batteries based on a standardized fault feature comparison method. J Clean Prod2021; 278: 123424.
15.
CongXZhangCJiangJ, et al.A comprehensive signal-based fault diagnosis method for lithium-ion batteries in electric vehicles. Energies2021; 14(5): 1221.
16.
FangWChenHZhouF. Fault diagnosis for cell voltage inconsistency of a battery pack in electric vehicles based on real-world driving data. Comput Electr Eng2022; 102: 108095.
17.
QianKLiuX. Hybrid optimization strategy for lithium-ion battery's state of charge/health using joint of dual Kalman filter and modified Sine-cosine algorithm. J Energy Storage2021; 44: 103319.
18.
QianKLiuXWangY, et al.Modified dual extended Kalman filters for SOC estimation and online parameter identification of lithium-ion battery via modified gray wolf optimizer. Proc Inst Mech Eng - Part D J Automob Eng2022; 236: 1761–1774.
19.
ZhaoJFengXPangQ, et al.Battery safety: machine learning-based prognostics. Prog Energy Combust Sci2024; 102: 101142.
20.
ZhaoJFengXTranMK, et al.Battery safety: fault diagnosis from laboratory to real world. J Power Sources2024; 598: 234111.
21.
ZhangXPanYCaoY, et al.Cloud-based battery failure prediction and early warning using multi-source signals and machine learning. J Energy Storage2024; 93: 112004.
22.
ZhangHNiuGZhangB, et al.Cost-effective Lebesgue sampling long short-term memory networks for lithium-ion batteries diagnosis and prognosis. IEEE Trans Ind Electron2021; 69(2): 1958–1967.
23.
FangWChenHZhouF. Fault diagnosis for cell voltage inconsistency of a battery pack in electric vehicles based on real-world driving data. Comput Electr Eng2022; 99: 107639.
24.
SunWYuQXiongR, et al.Research progress, challenges and prospects of fault diagnosis on battery system of electric vehicles. Appl Energy2020; 279: 115878.
25.
XueQLiGZhangY, et al.Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution. J Power Sources2021; 482: 228964.
26.
ZhangKHuXLiuY, et al.Multi-fault detection and isolation for lithium-ion battery systems. IEEE Trans Power Electron2021; 37: 971–989.
27.
WangGYangJJiaoJ. Voltage correlation-based principal component analysis method for short circuit fault diagnosis of series battery pack. IEEE Trans Ind Electron2023; 70: 9025–9034.
28.
SrividhyaVGowriswariSAntonyNV. Optimizing electric vehicle charging networks using clustering technique. In: 2024 2nd international conference on computer, communication and control (IC4), February 8-10, 2024,Indore, India. IEEE; 2024: 630-635.
29.
ChangJGuXWuJ, et al.Cell consistency evaluation method based on multiple unsupervised learning algorithms. Big Data Mining and Analytics2024; 7(1): 42–54.
30.
YuQLiJChenZ, et al.Multi-fault diagnosis of lithium-ion battery systems based on correlation coefficient and similarity approaches. Front Energy Res2022; 10: 891637.
31.
CaiXYiLWangY, et al. Soft short-circuit fault diagnosis of the lithium-ion battery pack based on an improved EKF algorithm. Recent Pat Mech Eng. 2023; 16(2): 138–149.
32.
SalehpourMJHossainMJ. Leveraging machine learning for efficient EV integration as mobile battery energy storage systems: exploring strategic frameworks and incentives. J Energy Storage2024; 73: 106951.
33.
ZhangXPanYCaoY, et al.Cloud-based battery failure prediction and early warning using multi-source signals and machine learning. J Energy Storage2024; 72: 106901.
34.
LeiYZhanpengFXiaoY, et al.An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machine. Energy2021; 214: 118866.
35.
WangYGuXLiJ, et al.An incipient multi-fault diagnosis method based on deep learning for large-scale lithium-ion battery packs. CCC (Cancer Causes Control)2023: 4916–4921.
36.
GuXShangYLiC, et al.An early multi-fault diagnosis method of lithium-ion battery based on data-driven. In: 2022 41st Chinese Control Conference (CCC).Hefei, China: IEEE, 2022: 5206–5210.
37.
ZhangYJiangMZhouY, et al. Towards high-safety lithium-ion battery diagnosis methods. Batteries. 2023; 9(1): 63.
38.
WangSWangCTakyi-AninakwaP, et al.An improved parameter identification and radial basis correction-differential support vector machine strategies for state-of-charge estimation of urban-transportation-electric-vehicle lithium-ion batteries. J Energy Storage2024; 80: 110222.
39.
WangSWuFTakyi-AninakwaP, et al.Improved singular filtering-Gaussian process regression-long short-term memory model for whole-life-cycle remaining capacity estimation of lithium-ion batteries adaptive to fast aging and multi-current variations. Energy2023; 284: 128677.
40.
DatarMMotwaniR. The sliding-window computation model and results. In: Data Stream Management: Processing High-Speed Data Streams. Springer, 2016, pp. 149–160.
41.
AlghushairyOAlsiniRSouleT, et al.A review of local outlier factor algorithms for outlier detection in big data streams. Big Data and Cognitive Computing2020; 5(1): 1.
42.
XinCGuoYNaJ. Encoder signal-based optimized Savitzky-Golay and adaptive spectrum editing for feature extraction of rolling element bearing under low-speed and variable-speed conditions. ISA Trans. 2024; 154: 288–302.
43.
BuchinMKilgusB. Fréchet distance between two point sets. Comput Geom2022; 103: 101831.
44.
WangZHongJLiuP, et al.Voltage fault diagnosis and prognosis of battery systems based on entropy and Z-score for electric vehicles. Appl Energy2017; 196: 289–302.
