Battery cycle life prediction using early degradation data has many potential applications throughout the battery product life cycle. For that reason, various data-driven methods have been proposed for point prediction of battery cycle life with minimum knowledge of the battery degradation mechanisms. However, managing the rapidly increasing amounts of batteries at end-of-life with lower economic and technical risk requires prediction of cycle life with quantified uncertainty, which is still lacking. The interpretability (i.e., the reason for high prediction accuracy) of these advanced data-driven methods is also worthy of investigation. Here, a physics-informed Quantile Regression Forest (QRF) model, having the advantage of not assuming any specific distribution of cycle life, is introduced to make cycle life range prediction with uncertainty quantified as the width of the prediction interval, in addition to point predictions with high accuracy. The hyperparameters of the QRF model are optimized with a proposed alpha-logistic-weighted criterion so that the coverage probabilities associated with the prediction intervals are calibrated. The interpretability of the final QRF model is explored with two global model-agnostic methods, namely permutation importance and partial dependence plot.
Catalpol is an iridoid glycoside, distributed in the roots of Rehmannia glutinosa Libosch. In vitro results showed that preincubation with catalpol (0.5-0.5 mM) for 0.5 hours before and during 48 hour exposure to 0.2 mM MPP+ appeared to be significant protective effect while catalopl was considerably less effective at the doses of 0.001 to 0.01 mM. The addition of catalpol at the dose of 0.05-0.5 mM significantly increased DA and DOPAC to MPP+ treated group. C57bl/6 mice received administration of catalpol for 12 hours before and during the 7 day treatment with MPTP. Such treatment at doses of 15 mg/kg significantly and dramatically blocked tyrosine hydroxylase-positive cell loss in mice. DA turnover in MPTP mice was reversed in the nigrostriatal pathway. In conclusion, data obtained in the above study suggested that catalpol exerted neuroprotective action in vitro and in vivo PD model.
A synthetic dataset of 12 LG M50 cells was generated using physics-based models. The model parameters for this commercial NMC 811/graphite-SiOx cell were taken from multiple sources in the literature. In particular, five degradation parameters were varied from their default values as parameter sensitivity analysis. The 12 LG M50 cells were identically discharged at a 1C galvanostatic profile to 0 % state-of-charge (SoC) and then charged at a 1C constant-current and constant-voltage (CC-CV) protocol to 100 % SoC. The ambient temperature in the simulation was set to be constant at 25 °C. As a result, 4 degradation pathways were identified with 4 different configurations of interacting degradation mechanisms, i.e., solid electrolyte interphase (SEI) growth, particle cracking, lithium plating, and loss of active material. The dataset allows for the validation of battery degradation diagnosis and prognosis methods with insights into interactions between multiple degradation mechanisms. One exemplary application of validating a knee identification method can be found in Ref. [1].
Abrupt capacity fade can have a significant impact on performance and safety in battery applications. To address concerns arising from possible knee occurrence, this work aims for a better understanding of their cause by introducing a new definition of capacity knees and their onset. A curvature-based identification of a knee and its onset is proposed, which relies on the discovery of a distinctly fluctuating behavior in the transition between an initial and a final stable acceleration of the degradation. The method is validated on experimental degradation data of two different battery chemistries, synthetic degradation data, and is also benchmarked to the state-of-the-art knee identification method in the literature. The results demonstrate that our proposed method could successfully identify capacity knees when the state-of-the-art knee identification method failed. Furthermore, a significantly strong correlation is found between knee and end of life (EoL) and almost equally strong between knee onset and EoL. As the method does not require the full capacity fade curve, this opens up online knee-onset identification as well as knee and EoL prediction.