Analyzing capacity degradation characteristics and accurately predicting the knee point of capacity are crucial for the safety management of lithium-ion batteries (LIBs). A recent breakthrough study presented by researchers from Shandong University introduces a knee point prediction method based on neural network. This advanced method can help us clarify the degradation mechanism and predict the knee point.
The study focuses on battery life, which is the result of multiple coupling aging mechanisms affected by multiple factors. It is significantly necessary to clarify the mechanism for the capacity degradation at each stage and possess the ability to detect the knee point. It can not only achieve effective predictive maintenance, but also prevent the occurrence of failures. More importantly, predicting the occurrence of the knee point and its onset in each cell is valuable to cell and battery manufactures, which can help them to adjust the production standard.
The overall framework consists of several main parts: data acquisition and processing, battery data visualization and analysis, feature extraction and selection, and capacity knee point prediction.
Firstly, the battery cycle aging data is obtained in the public data set. The data of voltage, current and capacity are further preprocessed. Secondly, the mechanism of battery capacity degradation is analyzed based on capacity degradation gradient and IC curve. On the basis of the analysis, the features are further extracted and selected. The feature sets are composed of the capacity degradation gradient and the difference of the maximum correlation IC curve. Based on LSTM, the extracted target features are taken as inputs. The corresponding capacity and cycle are taken as outputs to train the network. Finally, the knee point of capacity degradation is predicted by using the trained prediction network and extracted features.
The capacity degradation is innovatively divided into four stages through external features such as degradation gradient. The degradation mechanism of LIBs is analyzed in two aspects which includes the longitudinal and horizontal contents. The former is concentrated in whole cycle life degradation. The latter is analyzed from the charge–discharge protocol and internal materials. Understanding degradation mechanisms helps improve charging and discharging strategies, maximizing battery lifespan and efficiency.
The advanced prediction method using LSTM performs better than other benchmark methods in predicting knee point's capacity and cycle synthetically. The average mean relative error (MRE) of the capacity and cycle of the proposed LSTM method are 0.68% and 9.64%, respectively.
As the demand for efficient and sustainable energy storage solutions continues to grow, understanding these critical degradation patterns is more important than ever. Capacity knee point represents key moments in a battery's life cycle when its performance and capacity begin to shift significantly. By accurately predicting these points, manufacturers and researchers can develop advanced strategies to optimize battery performance, extend longevity, and enhance safety across various industries.
In future, to accurately predict capacity and knee point, it is essential to use real-world scenario data in research. It guarantees that the analysis reflects real-world usage conditions and battery performance over time, leading to more accurate and trustworthy predictions.
Reference
[1] He H, Sun F, Wang Z, Lin C, Zhang C, Xiong R, et al. China's battery electric vehicles lead the world: achievements in technology system architecture and technological breakthroughs. Green Energy IntelligTransp 2023;1(1):100020.
[2] You H, Zhu J, Wang X, Jiang B. Nonlinear health evaluation for lithium-ion battery within full-lifespan. J Energy Chem 2022;72:333–41.
[3] Tanim T, Paul P, Thampy V. Heterogeneous behavior of lithium plating during extreme fast charging. Cell Rep Phys Sci 2020;1(7):100114.
Author: Teng Wang, Yuhao Zhu, Wenyuan Zhao, Yichang Gong, Zhen Zhang, Wei Gao, Yunlong Shang
Title of original paper: Capacity degradation analysis and knee point prediction for lithium-ion batteries
Article link: https://doi.org/10.1016/j.geits.2024.100171
Journal: Green Energy and Intelligent Transportation
https://www.sciencedirect.com/science/article/pii/S2773153724000239
