Offline and Online Blended Machine Learning for Lithium-Ion Battery Health State Estimation
Artikel i vetenskaplig tidskrift, 2021

This article proposes an adaptive state of health (SOH) estimation method for lithium-ion batteries using machine learning. Practical problems with feature extraction, cell inconsistency, and online implementability are specifically solved using a proposed individualized estimation scheme blending offline model migration with online ensemble learning. First, based on the data of pseudo-open-circuit voltage measured over the battery lifespan, a systematic comparison of different incremental capacity features is conducted to identify a suitable SOH indicator. Next, a pool of candidate models, composed of slope-bias correction (SBC) and radial basis function neural networks (RBFNNs), are trained offline. For online operation, the prediction errors due to cell inconsistency in the target new cell are then mitigated by a proposed modified random forest regression (mRFR) based ensemble learning process with high adaptability. The results show that compared to prevailing methods, the proposed SBC-RBFNN-mRFR-based scheme can achieve considerably improved SOH estimation accuracy (15%) with only a small amount of early-age data and online measurements are needed for practical operation. Furthermore, the applicability of the proposed SBC-RBFNN-mRFR algorithms to real-world operation is validated using measured data from electric vehicles, and it is shown that a 38% improvement in estimation accuracy can be achieved.

Lithium-ion batteries

online machine learning

modified random forest regression

incremental capacity analysis

state of health estimation

Författare

Chengqi She

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Beijing Institute of Technology

Yang Li

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Changfu Zou

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Torsten Wik

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Zhenpo Wang

Beijing Institute of Technology

Fengchun Sun

Beijing Institute of Technology

IEEE Transactions on Transportation Electrification

2332-7782 (eISSN)

Vol. In press

Datadriven prediktion av batteriåldring

Energimyndigheten (50187-1), 2020-08-01 -- 2023-07-31.

Drivkrafter

Hållbar utveckling

Styrkeområden

Transport

Energi

Ämneskategorier

Energiteknik

Reglerteknik

Signalbehandling

Annan elektroteknik och elektronik

DOI

10.1109/TTE.2021.3129479

Mer information

Senast uppdaterat

2021-12-07