Abstract
In recent years, the pervasive use of lithium ion (Li-ion) batteries in applications such as cell phones, laptop computers, electric vehicles, and grid energy storage systems has prompted the development of specialized battery management systems (BMS). The primary goal of a BMS is to maintain a reliable and safe battery power source while maximizing the calendar life and performance of the cells. To maintain safe operation, a BMS should be programmed to minimize degradation and prevent damage to a Li-ion cell, which can lead to thermal runaway. Cell damage can occur over time if a BMS is not properly configured to avoid overcharging and discharging. To prevent cell damage, efficient and accurate cell charging cycle characteristics algorithms must be employed. In this paper, computationally efficient and accurate ensemble learning algorithms capable of detecting Li-ion cell charging irregularities are described. Additionally, it is shown using machine and deep learning that it is possible to accurately and efficiently detect when a cell has experienced thermal and electrical stress due to cell overcharging by measuring charging cycle divergence.
Highlights
A battery management system (BMS) is designed to maintain a reliable and safe battery power source while maximizing its calendar and performance life
We have tested a severe overcharge case with the intent to trigger cell failure to compare the differences seen in the outlier points of the ensemble learning in a mild overcharge case vs. a severe overcharge case
Using the experimental charge cycle dataset, a deep feedforward neural network was composed of 20 hidden layers and trained using the Levenberg-Marquardt backpropagation function [37] resulting in rapid convergence during training, with test, validation and convergence occuring after only 28 epochs with low percentage root mean squared error (RMSE) Ri prediction accuracy (RMSE < 5%)
Summary
A battery management system (BMS) is designed to maintain a reliable and safe battery power source while maximizing its calendar and performance life. Model-based filtering approaches for simultaneous estimation of SoC and SoH in Li-ion batteries, such as the Dual Extended Kalman Filter [13] or Fuzzy Unscented Kalman Filter [14], have shown improved estimation performance when compared to methods that only estimate SoC assuming known and constant battery parameters These methods are especially relevant for batteries approaching their end-of-life, when degraded cells experience accelerated capacity and power fade. Unlike standard parametric statistical approaches such as linear least-squares regression, the methods described in this paper can be used to detect charging cycle divergence when the charging cycle data is non-linear, as during charging current tapering that is often performed to avoid overcharging a cell
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
