Estimating Battery State-of-Charge using Machine Learning and Physics-Based Models

电池(电) 均方误差 荷电状态 电压 计算机科学 人工神经网络 健康状况 校准 模拟 电气工程 工程类 机器学习 功率(物理) 数学 统计 物理 量子力学
作者
Harsh Darshan Sapra,Michael Wagner,Sage Kokjohn,Lukas Desorcy,Sahana Upadhya,Chol-Bum Kweon,Shivaram Venkataraman,Justin L. Shumaker,Olesia Elfimova
出处
期刊:SAE technical paper series
标识
DOI:10.4271/2023-01-0522
摘要

<div class="section abstract"><div class="htmlview paragraph">Lithium-ion and Lithium polymer batteries are fast becoming ubiquitous in high-discharge rate applications for military and non-military systems. Applications such as small aerial vehicles and energy transfer systems can often function at C-rates greater than 1. To maximize system endurance and battery health, there is a need for models capable of precisely estimating the battery state-of-charge (SoC) under all temperature and loading conditions. However, the ability to perform state estimation consistently and accurately to within 1% error has remained unsolved. Doing so can offer enhanced endurance, safety, reliability, and planning, and additionally, simplify energy management. Therefore, the work presented in this paper aims to study and develop experimentally validated mathematical models capable of high-accuracy battery SoC estimation. In this work, experiments are performed with Lithium Polymer battery cells to measure performance parameters such as current, battery capacity, temperatures, and voltage. Next, physics-based and machine learning modeling approaches are developed to study their ability to predict SoC. Measurements performed at high C-rates (1C – 4C) are used for model training and calibration, validation, and testing. The results show that the Pseudo-2D electrochemical model can predict SoC within about 2 % root-mean-squared-error (RMSE) at different C-rates. However, the Feed Forward Neural Network modeling approach with Butterworth and Hampel filters achieved lower than and close to 1 % RMSE for battery SoC estimations.</div></div>
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
2秒前
Eurus发布了新的文献求助10
2秒前
2秒前
3秒前
orixero应助日富一日采纳,获得10
3秒前
有个公子她姓李完成签到,获得积分10
3秒前
Cfj818268完成签到,获得积分20
4秒前
施宇宙发布了新的文献求助10
4秒前
4秒前
小二郎应助H丶化羽采纳,获得10
5秒前
5秒前
研友_850EYZ发布了新的文献求助10
6秒前
6秒前
赘婿应助mysci采纳,获得10
7秒前
子车茗应助搁浅采纳,获得20
8秒前
8秒前
yanlibiu发布了新的文献求助10
8秒前
万默发布了新的文献求助10
9秒前
都市丽人完成签到,获得积分10
10秒前
少华完成签到,获得积分10
10秒前
喜悦的尔阳完成签到,获得积分10
11秒前
11秒前
我是老大应助科研恶霸采纳,获得10
11秒前
11秒前
多宝鱼发布了新的文献求助10
11秒前
12秒前
13秒前
13秒前
顾矜应助wxr采纳,获得10
13秒前
13秒前
共享精神应助Li采纳,获得10
14秒前
14秒前
14秒前
15秒前
Billy应助YY采纳,获得30
15秒前
15秒前
无花果应助爽爽采纳,获得10
15秒前
16秒前
杨杨发布了新的文献求助10
16秒前
高分求助中
Encyclopedia of Mathematical Physics 2nd edition 888
Technologies supporting mass customization of apparel: A pilot project 600
Introduction to Strong Mixing Conditions Volumes 1-3 500
Pharmacological profile of sulodexide 400
Optical and electric properties of monocrystalline synthetic diamond irradiated by neutrons 320
共融服務學習指南 300
Essentials of Pharmacoeconomics: Health Economics and Outcomes Research 3rd Edition. by Karen Rascati 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3805015
求助须知:如何正确求助?哪些是违规求助? 3350144
关于积分的说明 10347372
捐赠科研通 3065969
什么是DOI,文献DOI怎么找? 1683448
邀请新用户注册赠送积分活动 808961
科研通“疑难数据库(出版商)”最低求助积分说明 765153