Long-term battery voltage, power, and surface temperature prediction using a model-based extreme learning machine

Xiaopeng TANG, Ke YAO, Boyang LIU, Wengui HU, Furong GAO*

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

40 Citations (Scopus)

Abstract

A battery's state-of-power (SOP) refers to the maximum power that can be extracted from the battery within a short period of time (e.g., 10 s or 30 s). However, as its use in applications is growing, such as in automatic cars, the ability to predict a longer usage time is required. To be able to do this, two issues should be considered: (1) the influence of both the ambient temperature and the rise in temperature caused by Joule heat, and (2) the influence of changes in the state of charge (SOC). In response, we propose the use of a model-based extreme learning machine (Model-ELM, MELM) to predict the battery future voltage, power, and surface temperature for any given load current. The standard ELM is a kind of single-layer feedforward network (SLFN). We propose using a set of rough models to replace the active functions (such as logsig()) in the ELM for better generalization performance. The model parameters and initial SOC in these "rough models" are randomly selected within a given range, so little prior knowledge about the battery is required. Moreover, the identification of the complex nonlinear system can be transferred into a standard least squares problem, which is suitable for online applications. The proposed method was tested and compared with RLS (Recursive Least Square)-based methods at different ambient temperatures to verify its superiority. The temperature prediction accuracy is higher than ±1.5 °C, and the RMSE (Root Mean Square Error) of the power prediction is less than 0.25 W. It should be noted that the accuracy of the proposed method does not rely on the accuracy of the state estimation such as SOC, thereby improving its robustness.

Original languageEnglish
Article number86
Number of pages16
JournalEnergies
Volume11
Issue number1
Early online date3 Jan 2018
DOIs
Publication statusPublished - Jan 2018
Externally publishedYes

Bibliographical note

Funding Information:
We would like to thank Kaori Lkegaya for helping to correct the language problems. We would like to thank Yongxiao Xia and Zhenwei He for their assistance with the experiment. We would also like to acknowledge the financial support of the National Natural Science Foundation of China (61433005) and Guangdong scientific and technological project (2017B010120002).

Publisher Copyright:
© 2018 by the authors.

Keywords

  • Battery management system (BMS)
  • Electric vehicle
  • Extreme learning machine
  • State-of-power

Fingerprint

Dive into the research topics of 'Long-term battery voltage, power, and surface temperature prediction using a model-based extreme learning machine'. Together they form a unique fingerprint.

Cite this