LG 18650HG2 Li-ion Battery Data

The included tests were performed at McMaster University in Hamilton, Ontario, Canada by Dr. Phillip Kollmeyer ([e-mail]). If this data is utilized for any purpose, it should be appropriately referenced.
A brand new 3Ah LG HG2 cell was tested in an 8 cu.ft. thermal chamber with a 75amp, 5 volt Digatron Firing Circuits Universal Battery Tester channel with a voltage and current accuracy of 0.1% of full scale.
The tests can be used to test Neural Network and Kalman Filter State of Charge algorithms, or to develop battery models, and are intended to be a reference so researchers can compare their algorithm and model performance for a standard data set.
The test data, or similar data, has been used for some publications, including:

Vidal, C., Naguib, M., Gross, O., Malysz, P., Kollmeyer P. and Emadi, A. (2020). Robust xEV Battery State-of-Charge Estimator Design using Deep Neural Networks. [online] Sae.org. Available at: https://www.sae.org/publications/technical-papers/content/2020-01-1181/ [Accessed 28 Jan. 2020].

C. Vidal, P. Kollmeyer, E. Chemali and A. Emadi, "Li-ion Battery State of Charge Estimation Using Long Short-Term Memory Recurrent Neural Network with Transfer Learning," 2019 IEEE Transportation Electrification Conference and Expo (ITEC), Detroit, MI, USA, 2019, pp. 1-6.

本数据集的测试工作由加拿大安大略省汉密尔顿市的麦克马斯特大学教授菲利普·科莱梅耶（[e-mail]）主持进行。如本数据集被用于任何目的，应适当引用来源。测试采用了一款全新的3Ah LG HG2电池，在容积为8立方英尺的热室中进行，配合75安培、5伏特的Digatron通用电池测试仪通道，其电压和电流精度高达满量程的0.1%。该测试可用于验证神经网络和卡尔曼滤波充电状态算法，亦可用于开发电池模型，旨在为研究者提供一个参考，以便于他们在标准数据集上比较各自算法和模型的性能表现。测试数据或类似数据已被用于某些出版物中，包括：

Vidal, C., Naguib, M., Gross, O., Malysz, P., Kollmeyer P. and Emadi, A. (2020). 基于深度神经网络实现的鲁棒xEV电池充电状态估算器设计。[在线] Sae.org. 可访问：https://www.sae.org/publications/technical-papers/content/2020-01-1181/ [访问日期：2020年1月28日]。

C. Vidal, P. Kollmeyer, E. Chemali and A. Emadi, '使用长短期记忆循环神经网络和迁移学习对锂离子电池充电状态进行估算'，2019 IEEE交通运输电气化会议和展览（ITEC），美国密歇根州底特律，2019年，第1-6页。

搜集汇总

背景与挑战

背景概述

该数据集包含LG 18650HG2锂离子电池在不同温度条件下的测试数据，由麦克马斯特大学研究人员采集，旨在为神经网络、卡尔曼滤波等电池状态估计算法和模型开发提供标准参考。数据集覆盖从-20°C到40°C的温度范围，适用于电池性能研究和算法比较，已用于相关学术出版物。