相关实验视频

Updated: Jul 17, 2025

The Effect of Charging and Discharging Lithium Iron Phosphate-graphite Cells at Different Temperatures on Degradation

The Effect of Charging and Discharging Lithium Iron Phosphate-graphite Cells at Different Temperatures on Degradation

Published on: July 18, 2018

使用机器学习进行日历衰老建模:对离子电池化学的实验研究

Burak Celen¹, Melik Bugra Ozcelik², Furkan Metin Turgut²

¹Bogazici University, Istanbul, Turkey.

Open research Europe

|August 30, 2023

概括

极端渐变增强 (XGBoost) 和人工神经网络 (ANN) 预测了电池日历的老化. XGBoost为预测电动汽车电池电池的降解提供了卓越的准确性,特别是对于高需求的化学品.

科学领域:

材料科学材料科学材料科学
电化学电化学电化学
数据科学数据科学数据科学

背景情况:

日历老化显著影响电池性能和运行寿命.
预测容量退化对于识别和减轻电池老化问题至关重要.
了解衰老机制对于提高各种应用中的电池寿命至关重要.

研究的目的:

评估机器学习算法的有效性,以预测电池日历老化.
为了比较Extreme Gradient Boosting (XGBoost) 和人工神经网络 (ANN) 在不同电池化学的预测性能.
确定最适合电动汽车电池日历衰老预测的算法.

主要方法:

使用的机器学习算法:极端梯度增强 (XGBoost) 和人工神经网络 (ANN).
应用算法来预测六种细胞化学中的日历衰老数据:LCO,LFP,LMO,LTO,NCA和NMC.
使用平均绝对百分比误差 (MAPE) 和平均绝对误差 (MAE) 评估模型性能.

主要成果:

XGBoost的整体MAPE值为0.0126,超过了ANN的整体MAE值为0.0472.
对于,,氧化物 (NCA) 和,,氧化物 (NMC) 化学物质,XGBoost的MAPE分别为0.0035和0.0057,其表现非常出色.
与XGBoost相比,ANN在100%充电状态和60°C时显示NMC的安装性能不佳.

结论:

XGBoost是电动汽车电池日历衰老预测的首选算法,由于其较低的错误率和卓越的安装性能.
在电动汽车电池中广泛使用的NCA和NMC化学物质显示了XGBoost.com的特别强大的预测结果.
这些发现支持采用XGBoost来对电动汽车的电池健康状况进行可靠的监测和管理.

关键词:

在XGBoost上使用.人工神经网络的人工神经网络日历老龄化日历老龄化离子电池是一种离子电池.机器学习是机器学习.

更多相关视频

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway

Published on: March 7, 2022

Three-electrode Coin Cell Preparation and Electrodeposition Analytics for Lithium-ion Batteries

Three-electrode Coin Cell Preparation and Electrodeposition Analytics for Lithium-ion Batteries

Published on: May 22, 2018

相关概念视频

Batteries and Fuel Cells

Batteries and Fuel Cells

A battery is a galvanic cell that is used as a source of electrical power for specific applications. Modern batteries exist in a multitude of forms to accommodate various applications, from tiny button batteries such as those that power wristwatches to the very large batteries used to supply backup energy to municipal power grids. Some batteries are designed for single-use applications and cannot be recharged (primary cells), while others are based on conveniently reversible cell reactions that...