Search

With the increasing trend of electric vehicles sales, the awareness for safety issues in energy storage systems has seen a rapid growth. In this context, literature predominantly focuses on the assessment of lithium‐ion battery cell State of Health (SoH) under regular operating conditions. An interesting gap is highlighted by scarce contributions with reference to the SoH in case of collision impacts. This paper proposes a method for estimating the battery cell SoH from collision deformation features via finite element (FE) simulation. An experimental series of collision impact tests is performed on battery cells to study deformation features. A 3D scanning procedure is performed on the cells to retrieve the geometrical features. The cells damage evaluation is carried out by considering physical and electrical performances. The SoH classification is modeled as a machine learning–based pattern recognition enabled by Artificial Neural Network (ANN) trained with deformation features and classifying cells into safe, latent danger, and unsafe cells respectively. Utilizing such pattern classifier, a FE approach is used to conduct an impact simulation on a battery module. In this respect, the deformation features obtained via simulation are input into the ANN pattern classifier experimentally trained to predict the cells SoH within the module. [ABSTRACT FROM AUTHOR]

Cloud condensation nuclei (CCN) spectra, that indicate the dependence of CCN number concentrations (N CCN) on supersaturation, are important factors in aerosol–cloud interactions. Owing to the lack of direct measurements of N CCN , calculating the CCN spectra based on conventional observational data of aerosols is important to obtain N CCN ; however, this is challenging owing to the complex relationship between aerosol properties and CCN activity. Machine learning techniques have recently been applied to estimate N CCN and found to be a promising method for CCN prediction. In this study, the random forest (RF) model was applied to predict CCN spectral parameters using the observation data measured in four campaigns in the North China Plain, and the effects of chemical and optical properties of aerosol on the estimation of CCN spectra were investigated. The results show that the RF model trained with the data of one campaign can be used to estimate CCN spectral parameters in another campaign, with the coefficient of determination between the estimated and measured CCN spectral parameters being approximately 0.5. The deviations of the estimation by the RF model may result from the difference in both the aerosol properties and measurement uncertainties among different campaigns, whose influence on the deviations can be further magnified by overfitting the RF model. Further analysis revealed that the major aerosol properties among the input variables of the RF model were the mass concentration of black carbon and aerosol hemispheric backscattering fraction at a wavelength of 450 nm. In addition, the roles of chemical compositions of aerosol in estimating CCN spectra parameters are different among different campaigns because the poor correlation between aerosol chemical compositions and CCN spectra parameter can affect the performance of the RF model. For estimating CCN spectra, using aerosol optical properties, including the hemispheric backscattering fraction and absorption coefficient, as model inputs is more recommended than using aerosol chemical properties. • Random forest model is used to estimate CCN spectra based on observation data in the North China Plain. • Mass concentration of black carbon and hemispheric backscattering fraction are the most important input variables. • Aerosol optical properties data are recommended in estimation of CCN spectra parameters. [ABSTRACT FROM AUTHOR]