返回
Solving Limited Data Challenges in Battery Parameter Estimators by Using Generative Adversarial Networks
DOI:10.1109/POWERAFRICA52236.2021.9543237.png)
摘要
En 中文
There has been an increased demand for Energy Storage Systems (ESS) as they power most of today's remote devices and are needed to sustain the ongoing transportation electrification revolution to curb pollution levels. State-of-Charge (SOC) and State-of-Health (SOH) assessment of batteries is vital to prevent unexpected shutdown of battery powered consumer electronics and to determine the expected range from an Electric Vehicle. SOC & SOH estimators demand high-quality curated battery parameter data such as current, temperature and voltage over several charge/discharge cycles. Experiments needed to collect such data are expensive and tedious. Lack of diversity in open access battery datasets have hindered research in this area. This paper is focused on synthetic generation of battery parameters from sparse datasets. The goal is to produce high-fidelity heterogeneous time-series datasets which help to overcome the problem of lack of data in the ESS domain.
Keyword:
Generative Adversarial Network
Battery
Energy Storage
Synthetic Data
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
0
论文数:
32
被引数:
0
机构
引用论文
Lithium-Ion Battery Pack State of Charge and State of Energy Estimation Algorithms Using a Hardware-in-the-Loop Validation使用硬件在环验证的锂离子电池组充电状态和能量状态估计算法
Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine基于自适应无迹卡尔曼滤波和支持向量机的聚合物锂电池荷电状态估计
Water Molecules in Channels of Natural Emeralds from Dayakou (China) and Colombia: Spectroscopic, Chemical and Crystal Structural Investigations
Crystals
IF0
A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: Challenges and recommendations电动汽车应用中的锂离子电池荷电状态估计和管理系统综述: 挑战和建议
没有更多内容

