Browse Topic: Lithium-ion batteries
As the main power source for modern portable electronic devices and electric vehicles, lithium-ion batteries (LIBs) are favored for their high energy density and good cycling performance. However, as the usage time increases, battery performance gradually deteriorates, leading to a heightened risk of thermal runaway (TR) increases, which poses a significant threat to safety. Performance degradation is mainly manifested as capacity decline, internal resistance increase and cycle life reduction, which is usually caused by internal factors of LIBs, such as the fatigue of electrode materials, electrolyte decomposition and interfacial chemical reaction. Meanwhile, external factors of LIBs also contribute to performance degradation, such as external mechanical stresses leading to internal structural damage of LIBs, triggering internal short-circuit (ISC) and violent electrochemical reactions. In this paper, the performance degradation of LIBs and TR mechanism is described in detail, as well
Battery cell aging and loss of capacity are some of the many challenges facing the widespread implementation of electrification in mobility. One of the factors contributing to cell aging is the dissimilarities of individual cells connected in a module. This paper reports the results of several aging experiments using a mini-module consisting of seven 5 Ah 21700 lithium-ion battery cells connected in parallel. The aging cycle comprised a constant current-constant voltage charge cycle at a 0.7C C-rate, followed by a 0.2C constant current discharge, spanning the useful voltage range from minimum to maximum according to the cell manufacturer. Charge and discharge events were separated by one-hour rest periods and were repeated for four weeks. Weekly reference performance tests were executed to measure static capacity, pulse power capability and resistance at different states of charge. All diagnostics were normalized with respect to their starting numbers to achieve a percentage change
Letter from the Guest Editors
Predictive maintenance is crucial for Industry 4.0, and deep neural networks are a promising approach for predicting the capacity of electric batteries. However, few applications effectively utilize neural networks for this purpose with lithium-ion batteries. In this work, different deep learning models are developed, starting with simple neural networks, dense neural networks, convolutional networks, and recurrent networks. Using a public domain dataset, training, testing, and validation datasets were generated to predict battery capacity as a function of the number of cycles. Despite the limited number of samples in the dataset, deep learning techniques are employed to ensure robust prediction performance. The work presents the loss functions for each iteration of the algorithms and the average absolute error. The models made good generalizations over the test dataset within a short prediction time window. Finally, the work presents an average absolute error below 0.3, ensuring good
Items per page:
50
1 – 50 of 1348