首页|Studies from University of Science and Technology China Yield New Information ab out Machine Learning (Machine Learning Based Battery Pack Health Prediction Usin g Real-world Data)

Studies from University of Science and Technology China Yield New Information ab out Machine Learning (Machine Learning Based Battery Pack Health Prediction Usin g Real-world Data)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-Research findings on Machine Learning are discussed in a new report. According tonews reporting out of Hefei, People' s Republic of China, by NewsRx editors, research stated, "The complexoperationa l conditions in real-world electric vehicles (EVs) contribute to the complexity of managing andmaintaining battery packs. Adding to these challenges is the int ricate task of modeling the inconsistentcoupling among individual cells within these packs."Financial support for this research came from National Natural Science Foundatio n of China (NSFC).Our news journalists obtained a quote from the research from the University of S cience and TechnologyChina, "This study addresses the ongoing challenges in mod eling lithium-ion battery (LIB) cells withinpacks and estimating their state of health (SOH) for practical applications. This research proposed aPCA-CNN-Trans former method to model and predict the SOH model of real-world EV. Three main contributions are presented: a novel approach to defining an attenuation SOH model based on deliveredenergy, a methodology utilizing Principal Component Analysis (PCA) for cell modeling, and an SOHestimation model employing CNN-Transformer architecture. To address both pack and cell-level modeling,a hierarchical featu re extraction approach is proposed. The health features extracted from both leve lsare assessed using grey relational analysis, showing a strong correlation wit h LIB SOH, exceeding 0.70.The proposed cell modeling method significantly reduc es data size by 96%, enhancing computationalefficiency. Furthermor e, the integration of 1D-CNN in the SOH estimation model overcomes the limitations of the attention mechanism, achieving a MAE with 0.0406 and r-square of 0.932 7, improved the originaltransformer network performance by 10.95%. "

HefeiPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningUniversity of Science and Tec hnology China

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Oct.31)