Search

Accurately estimating the capacity degradation of lithium-ion batteries (LIBs) is crucial for evaluating the status of battery health. However, existing data-driven battery state estimation methods suffer from fixed input structures, high dependence on data quality, and limitations in scenarios where only early charge–discharge cycle data are available. To address these challenges, we propose a capacity degradation estimation method that utilizes shorter charging segments for multiple battery types. A learning-based model called GateCNN-BiLSTM is developed. To improve the accuracy of the basic model in small-sample scenarios, we integrate a single-source domain feature transfer learning framework based on maximum mean difference (MMD) and a multi-source domain framework using the meta-learning MAML algorithm. We validate the proposed algorithm using various LIB cell and battery pack datasets. Comparing the results with other models, we find that the GateCNN-BiLSTM algorithm achieves the lowest root mean square error (RMSE) and mean absolute error (MAE) for cell charging capacity estimation, and can accurately estimate battery capacity degradation based on actual charging data from electric vehicles. Moreover, the proposed method exhibits low dependence on the size of the dataset, improving the accuracy of capacity degradation estimation for multi-type batteries with limited data. [ABSTRACT FROM AUTHOR]

This article discusses a rare genetic disorder called Hypotrichosis with juvenile macular dystrophy (HJMD). HJMD is characterized by short and sparse hair at birth and progressive visual impairment due to mutations in the CDH3 gene. The article presents two families with HJMD and describes the specific mutations found in each family. Ophthalmic examinations revealed retinal abnormalities in the patients. The article also mentions the importance of the extracellular domains of the P-cadherin protein encoded by CDH3 and the potential for retinal gene therapy as a treatment option. [Extracted from the article]

Research on internal waves in the coastal ocean is one of the most important tasks both in physical oceanography and ocean monitoring network. Currently, how to quickly and accurately detect the ocean internal waves from the huge ocean surface is still a challenging issue. In this paper, we model the ocean internal wave detection as a task of region classification for texture images and then propose a rapid internal waves detection method based on a deep learning framework (PCANet). In the proposed method, two models have been trained: one is the deep feature representation model, which combines principal component analysis (PCA), binary hashing, and block-wise histograms and can extract more distinguishing features than handcraft feature. Moreover, because the filter learning in PCANet does not require regularized parameters and numerical optimization solver, the training process of the representation model is very fast. The other one is a classification model based on a linear support vector machine. The object proposal method has been applied to get the possible candidates when analyzing a captured image, which dramatically decreases the searching time. Experiment results on the data set captured by unmanned aerial vehicles verify the speed ability and effectiveness of the proposed method.

Introduction: Infantile hepatic hemangioma (IHH) is a common liver tumor in infants and shares the same characteristics as cutaneous infantile hemangioma (IH). Propranolol is effective for symptomatic IHH. The clinical features between cutaneous IH and IHH, and treatment efficacy of IHH (smaller than 4 cm) is unclear. To evaluate the correlation of clinical features between cutaneous IH and IHH, as well as efficacy of systemic propranolol in the treatment of cutaneous IH combined with IHH. Materials and Methods: The clinical data of infants with complicated cutaneous IH combined with IHH treated with systemic propranolol (1.5 ~ 2 mg/(kg d)) from January 2011 to October 2020 were retrospectively analyzed. Results: Forty‐five cases with IHH combined with complicated cutaneous IH were reviewed. Single cutaneous IH is more likely to be combined with focal IHH, cutaneous IH greater than 5, more likely to be combined with multiple IHH (Pearson = 0.546, p < 0.01). The mean age of focal and multiple IHH regression was 11.93 ± 14.42 months and 10.20 ± 9.15 months, respectively. Conclusions: The number of cutaneous IH were correlated with the number of IHH. There was no difference in the age of complete remission for focal and multiple IHH. [ABSTRACT FROM AUTHOR]

It is very important to establish a life prediction model that evaluates the combined high and low cycle fatigue (CCF) damage of materials. Based on the toughness exhaustion, this paper develops a CCF life prediction model considering loading interaction effect. The loading interaction factor is proposed to reflect the interaction effect between high cycle fatigue and low cycle fatigue. The proposed model does not require any additional material parameters and is convenient for application. The experimental data of four materials including GH4033 Ni-basis alloy, TC11 titanium alloy, LY12-CZ aluminum alloy, and 45 steel are applied to verify the proposed model. Comparing the prediction results of the proposed model with the Miner's rule and the T-K model, the results show that the predicted results of the proposed model are more satisfactory. [ABSTRACT FROM AUTHOR]