Prediction of Lithium-Ion Battery Capacity based on The ARMA Method

2020 ◽  
Author(s):  
Bo Ma ◽  
Wei Guo ◽  
Zhaojun Steven Li
Keyword(s):  
Lithium Ion Battery ◽  
Lithium Ion ◽  
Battery Capacity

A generalized additive model-based data-driven solution for lithium-ion battery capacity prediction and local effects analysis

2021 ◽  
pp. 014233122110579
Author(s):  
Tao Chen ◽  
Ciwei Gao ◽  
Hongxun Hui ◽  
Qiushi Cui ◽  
Huan Long
Keyword(s):  
Energy Storage ◽  
Lithium Ion Battery ◽  
Lithium Ion ◽  
Additive Models ◽  
Data Driven ◽  
Local Effects ◽  
Interaction Terms ◽  
Battery Capacity ◽  
Formulation Parameters ◽  
Capacity Prediction

Lithium-ion battery-based energy storage systems have been widely utilized in many applications such as transportation electrification and smart grids. As a key health status indicator, battery performance would highly rely on its capacity, which is easily influenced by various electrode formulation parameters within a battery. Due to the strongly coupled electrical, chemical, thermal dynamics, predicting battery capacity, and analysing the local effects of interested parameters within battery is significantly important but challenging. This article proposes an effective data-driven method to achieve effective battery capacity prediction, as well as local effects analysis. The solution is derived by using generalized additive models (GAM) with different interaction terms. Comparison study illustrate that the proposed GAM-based solution is capable of not only performing satisfactory battery capacity predictions but also quantifying the local effects of five important battery electrode formulation parameters as well as their interaction terms. Due to data-driven nature and explainability, the proposed method could benefit battery capacity prediction in an efficient manner and facilitate battery control for many other energy storage system applications.

scholarly journals State-of-Health Estimate for the Lithium-Ion Battery Using Chi-Square and ELM-LSTM

2021 ◽  
Vol 12 (4) ◽  
pp. 228
Author(s):  
Jianfeng Jiang ◽  
Shaishai Zhao ◽  
Chaolong Zhang
Keyword(s):  
Neural Network ◽  
Lithium Ion Battery ◽  
Short Term Memory ◽  
Lithium Ion ◽  
Constant Current ◽  
State Of Health ◽  
Chi Square ◽  
Mean Temperature ◽  
Battery Capacity ◽  
Learning Machine

The state-of-health (SOH) estimation is of extreme importance for the performance maximization and upgrading of lithium-ion battery. This paper is concerned with neural-network-enabled battery SOH indication and estimation. The insight that motivates this work is that the chi-square of battery voltages of each constant current-constant voltage phrase and mean temperature could reflect the battery capacity loss effectively. An ensemble algorithm composed of extreme learning machine (ELM) and long short-term memory (LSTM) neural network is utilized to capture the underlying correspondence between the SOH, mean temperature and chi-square of battery voltages. NASA battery data and battery pack data are used to demonstrate the estimation procedures and performance of the proposed approach. The results show that the proposed approach can estimate the battery SOH accurately. Meanwhile, comparative experiments are designed to compare the proposed approach with the separate used method, and the proposed approach shows better estimation performance in the comparisons.

scholarly journals Charge and Discharge Behaviour of Li-Ion Batteries at Various Temperatures Containing LiCoO2 Nanostructured Cathode Produced by CCSO

2015 ◽  
Vol 15 (4) ◽  
pp. 301 ◽  
Author(s):  
Y.Y. Mamyrbayeva ◽  
R.E. Beissenov ◽  
M.A. Hobosyan ◽  
S.E. Kumekov ◽  
K.S. Martirosyan
Keyword(s):  
Lithium Ion Battery ◽  
Active Material ◽  
Lithium Ion ◽  
Synthetic Approach ◽  
Capacity Fade ◽  
Li Ion Batteries ◽  
Material Loss ◽  
Method Performance ◽  
Battery Capacity ◽  
Li Ion

<p>There are technical barriers for penetration market requesting rechargeable lithium-ion battery packs for portable devices that operate in extreme hot and cold environments. Many portable electronics are used in very cold (-40 °C) environments, and many medical devices need batteries that operate at high temperatures. Conventional Li-ion batteries start to suffer as the temperature drops below 0 °C and the internal impedance of the battery  increases. Battery capacity also reduced during the higher/lower temperatures. The present work describes the laboratory made lithium ion battery behaviour features at different operation temperatures. The pouch-type battery was prepared by exploiting LiCoO<sub>2</sub> cathode material synthesized by novel synthetic approach referred as Carbon Combustion Synthesis of Oxides (CCSO). The main goal of this paper focuses on evaluation of the efficiency of positive electrode produced by CCSO method. Performance studies of battery showed that the capacity fade of pouch type battery increases with increase in temperature. The experimental results demonstrate the dramatic effects on cell self-heating upon electrochemical performance. The study involves an extensive analysis of discharge and charge characteristics of battery at each temperature following 30 cycles. After 10 cycles, the battery cycled at RT and 45 °C showed, the capacity fade of 20% and 25% respectively. The discharge capacity for the battery cycled at 25 °C was found to be higher when compared with the battery cycled at 0 °C and 45 °C. The capacity of the battery also decreases when cycling at low temperatures. It was important time to charge the battery was only 2.5 hours to obtain identical nominal capacity under the charging protocol. The decrease capability of battery cycled at high temperature can be explained with secondary active material loss dominating the other losses.</p>

scholarly journals Machine Learning-Based Lithium-Ion Battery Capacity Estimation Exploiting Multi-Channel Charging Profiles

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 75143-75152 ◽  
Author(s):  
Yohwan Choi ◽  
Seunghyoung Ryu ◽  
Kyungnam Park ◽  
Hongseok Kim
Keyword(s):  
Machine Learning ◽  
Lithium Ion Battery ◽  
Lithium Ion ◽  
Capacity Estimation ◽  
Battery Capacity

scholarly journals Lithium-Ion Battery Capacity Estimation: A Method Based on Visual Cognition

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Yujie Cheng ◽  
Laifa Tao ◽  
Chao Yang
Keyword(s):  
Lithium Ion Battery ◽  
Feature Vector ◽  
Geodesic Distance ◽  
Lithium Ion ◽  
Visual Cognition ◽  
Cognitive Computing ◽  
Capacity Estimation ◽  
Capacity Degradation ◽  
Battery Capacity ◽  
Low Dimensional

This study introduces visual cognition into Lithium-ion battery capacity estimation. The proposed method consists of four steps. First, the acquired charging current or discharge voltage data in each cycle are arranged to form a two-dimensional image. Second, the generated image is decomposed into multiple spatial-frequency channels with a set of orientation subbands by using non-subsampled contourlet transform (NSCT). NSCT imitates the multichannel characteristic of the human visual system (HVS) that provides multiresolution, localization, directionality, and shift invariance. Third, several time-domain indicators of the NSCT coefficients are extracted to form an initial high-dimensional feature vector. Similarly, inspired by the HVS manifold sensing characteristic, the Laplacian eigenmap manifold learning method, which is considered to reveal the evolutionary law of battery performance degradation within a low-dimensional intrinsic manifold, is used to further obtain a low-dimensional feature vector. Finally, battery capacity degradation is estimated using the geodesic distance on the manifold between the initial and the most recent features. Verification experiments were conducted using data obtained under different operating and aging conditions. Results suggest that the proposed visual cognition approach provides a highly accurate means of estimating battery capacity and thus offers a promising method derived from the emerging field of cognitive computing.

Sign in / Sign up

Export Citation Format

Share Document