A Vehicle-Cloud Collaborative Strategy for State of Energy Estimation based on CNN-LSTM Networks

  • Peng Mei
  • , Cong Huang
  • , Daoguang Yang
  • , Shichun Yang*
  • , Fei Chen
  • , Qiu Song
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the current market of electric vehicles (EVs) in full swing, the real-time and accuracy of lithium batteries are getting more and more attention. Due to the EV's complexity and changeable external environment, an accurate energy estimation is difficult to achieve in the vehicle system. Although the machine learning algorithm can significantly improve the accuracy of battery estimation, it cannot be performed on the vehicle control unit as it requires a large amount of data and computing power. This paper proposes a state of energy (SOE) prediction algorithm, which combines long short-term memory (LSTM) and convolutional neural networks (CNN) for EVs based on vehicle-cloud fusion. With the validation of the Center for Advanced Life Cycle Engineering battery data set, the error of the proposed method is kept within 3%, and the feasibility of vehicle-cloud collaboration is promising in future battery management.

Original languageEnglish
Title of host publicationProceedings - 2022 2nd International Conference on Computers and Automation, CompAuto 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages128-132
Number of pages5
ISBN (Electronic)9781665481946
DOIs
StatePublished - 2022
Event2nd International Conference on Computers and Automation, CompAuto 2022 - Virtual, Online, France
Duration: 18 Aug 202220 Aug 2022

Publication series

NameProceedings - 2022 2nd International Conference on Computers and Automation, CompAuto 2022

Conference

Conference2nd International Conference on Computers and Automation, CompAuto 2022
Country/TerritoryFrance
CityVirtual, Online
Period18/08/2220/08/22

Keywords

  • CNN
  • EVs
  • LSTM
  • SOE
  • vehicle-cloud collaboration

Fingerprint

Dive into the research topics of 'A Vehicle-Cloud Collaborative Strategy for State of Energy Estimation based on CNN-LSTM Networks'. Together they form a unique fingerprint.

Cite this