Accurately evaluating battery degradation is not only crucial for ensuring the safe and reliable operation of electric vehicles (EVs) but also fundamental for their intelligent management and maximum utilization. However, the non-linearity, non-measurability, and multi-stress coupled operating conditions have posed significant challenges for battery health prediction. This paper proposes a battery capacity estimation framework based on real-world operating data. Firstly, a comprehensive feature pool is constructed from the direct external features extracted during multi-step fast charging processes and the quantitative representation of operating conditions. Subsequently, a two-step feature engineering is introduced to select the most relevant features and eliminate the interference components. The battery capacity estimation framework is then implemented using machine learning methods. Validation results demonstrate that the proposed framework achieves superior estimation accuracy with lower computational expense compared to the modelling process without feature engineering. The MAPE and RMSE reach 1.18% and 1.98 Ah, respectively, representing reductions in errors of up to 8.53% and 11.21%. Collectively, the proposed framework paves the foundation for online health prognostics of batteries under practical operating conditions.@en

Accurately predicting the battery's aging trajectory is required to ensure the safe and reliable operation of electric vehicles (EVs) and is also the fundamental technique toward residual value assessment. As a critical enabler for mainstreaming EVs, fast charging has presented formidable challenges to health prognosis technology. This study systematically compares the performance of features extracted from the multistep charging process in the state of health (SOH) assessment. First, 12 direct features are extracted from the voltage curve, and the degradation mechanisms strongly correlated to these features are analyzed in detail. Integrating the degradation mechanism and correlation analysis, a data feature construction strategy is designed to categorize extracted features into groups. Then, the performance of different features extracted from the fast charging process in the SOH assessment is compared regarding estimation accuracy. Finally, the generalization and feasibility of the optimal data feature are verified with different fast charging protocols and training data sizes. The verification results indicate that the data feature representing fused degradation modes has excellent generalization and feasibility in SOH estimation, and the mean absolute error (MAE) and root-mean-squared error (RMSE) for various cells under different decline patterns are within 0.90% and 1.10% , respectively.

@en

Battery fault diagnosis is crucial for stable, reliable, and safe operation of electric vehicles, especially the thermal runaway early warning. Developing methods for early failure detection and reducing safety risks from failing high energy lithium-ion batteries has become a major challenge for industry. In this article, a real-time early fault diagnosis scheme for lithium-ion batteries is proposed. By applying both the discrete Fréchet distance and local outlier factor to the voltage and temperature data of the battery cell/module that measured in real time, the battery cell that will have thermal runaway is detected before thermal runaway happens. Compared with the widely used single parameter based diagnosis approach, the proposed one considerably improve the reliability of the fault diagnosis and reduce the false diagnosis rate. The effectiveness of the proposed method is validated with the operational data from electric vehicles with/without thermal runaway in daily use.

@en

It is vital to detect the safety state and identify faults of the battery pack for the safe operation of electric vehicles. The voltage faults such as over-voltage and under-voltage imply more serious battery faults including short-circuit and thermal runaway. The voltage abnormal fluctuation is a warning signal of short-circuit, over-voltage and under-voltage. This paper proposes a scheme of three-layer fault detection method for lithium-ion batteries based on statistical analysis. The first layer fault detection is based on the thresholds of over-charge and over-discharge of a battery pack. In the second layer, confidence interval estimation is applied to identify risky cells. In the third layer, correlation and variability of all cells in one battery pack are analyzed by using an improved K-means method to identify abnormal voltage fluctuation over a certain period. The validity and feasibility of the proposed method are verified by real vehicle data from the National Big Data Alliance of New Energy Vehicles.

@en