| 1. |
- Guo, Wenchao, et al.
(författare)
-
Early diagnosis of battery faults through an unsupervised health scoring method for real-world applications
- 2023
-
Ingår i: IEEE Transactions on Transportation Electrification. - 2332-7782. ; In Press
-
Tidskriftsartikel (refereegranskat)abstract
- Battery fault diagnosis is critical to ensure the safe and reliable operation of electric vehicles or energy storage systems. Early diagnosis of battery faults can enable timely maintenance and reduce potential accidents. However, the lead time for detection is still relatively insufficient, and the identification of target vehicle with unidentified fault type has generally been neglected. To fill the gap, an unsupervised health scoring method for early diagnosis of battery faults is proposed in this paper. First, considering the properties of field data, new features and four types of feature sets related to battery health and fault status are derived for each cell. Then, a novel strategy is proposed to transform a typical classification problem into a quantitative scoring problem by performing multiple clustering. To produce ample clustering results, three cluster algorithms based on different principles are used and the features are randomly divided into feature subsets. By coupling temperature information, early determination of thermal runaway faults can be achieved. Finally, the real-world cloud data of three typical accidents are employed for verification, the results indicate that the proposed approach can innovatively achieve the detection of the abnormal cells at the level of days in advance, demonstrating excellent performance.
|
|
| 2. |
- Guo, Wenchao, et al.
(författare)
-
Rapid online health estimation for lithium-ion batteries based on partial constant-voltage charging segment
- 2023
-
Ingår i: Energy. - 0360-5442. ; 281
-
Tidskriftsartikel (refereegranskat)abstract
- Battery health evaluation is vital for ensuring the security and reliability of lithium-ion batteries. However, the currently proposed methods generally require high-quality input data for feature extraction in online applications. To overcome this obstacle, this paper proposes a rapid online health estimation method only based on partial constant-voltage (CV) charging segment. Firstly, through primary analysis of battery test data, the evolution of CV charging current is confirmed to be correlated with battery capacity. Subsequently, the current evolution constant of CV charging phase is mathematically formulated and quantitatively characterized using a novel health indicator (HI). Besides, charging time and charging capacity are also extracted as HIs to comprehensively capture the CV charging behavior and enhance the robustness of data-driven models. Considering the user's charging habits, an optimized CV segment is determined, enabling a significant reduction in data size and coverage. Finally, three data-driven methods are employed to construct health estimation models by using the extracted HIs, and the best performance is achieved by Gaussian process regression with MAE and RMSE lower than 0.8% and 1%, respectively. Remarkably, the proposed method demonstrates superiority in dealing with sparse sampling, and satisfactory results with 2.9% error under the sparsity of 10 s are obtained.
|
|
