A

Detection of abnormal SOH estimates in battery field data using statistical learning

Cell Reports Physical Science, vol. 6, pp. 102788

Abstract

Battery field data collection enables car manufacturers to monitor battery aging throughout the entire life cycle. However, to fully utilize the potential of these data, it is essential to identify anomalous aging estimates. These estimates can either stem from irregular battery aging or alterations in estimation algorithms due to software updates. In this work, we provide an unsupervised framework based on the big data of battery field readouts where we cluster battery data sharing similar aging conditions and further apply statistical learning to identify anomalies within each cluster. Our dataset includes 12 million readouts from 600,000 vehicles. To validate our model, we use real-world data from a corrupted prototype software and successfully flag 98% of the outlier data as anomalies. Thus, our framework offers robust identification of anomalous estimated aging values, facilitating cost-sensitive decisions such as battery replacements or software updates, ultimately optimizing overall battery operation strategies.

Authors 7

  1. BMW (Germany) · RWTH Aachen University

    Affiliation as printed

    BMW AG, Petuelring 130, 80809 München, Germany

    Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Aachen, Germany

    Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

  2. RWTH Aachen University

    Affiliation as printed

    Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Aachen, Germany

    Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

  3. BMW (Germany)

    Affiliation as printed

    BMW AG, Petuelring 130, 80809 München, Germany

  4. RWTH Aachen University

    Affiliation as printed

    Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Aachen, Germany

    Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

  5. BMW (Germany)

    Affiliation as printed

    BMW AG, Petuelring 130, 80809 München, Germany

  6. Forschungszentrum Jülich · Helmholtz-Institute Münster · Jülich Aachen Research Alliance · RWTH Aachen University

    Affiliation as printed

    Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Aachen, Germany

    Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

    Helmholtz Institute Münster (HI MS), IEK 12, Forschungszentrum Jülich, 52425 Jülich, Germany

    Jülich Aachen Research Alliance, JARA-Energy, Templergraben 55, 52056 Aachen, Germany

  7. Jülich Aachen Research Alliance · RWTH Aachen University

    Affiliation as printed

    Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Aachen, Germany

    Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

    Jülich Aachen Research Alliance, JARA-Energy, Templergraben 55, 52056 Aachen, Germany

Cited by 3 stored of 3

3 results

No patents citing this paper on Lens.org (checked 2026-10-06).

References 46