Verfahren zum Trainieren eines Datenmodells zur Erkennung einer Anomalie in einem Traktionsbatteriepack eines Fahrzeugs sowie Verfahren zur Erkennung und Handhabung einer Anomalie in einem Traktionsbatteriepack

Details

Veröffentlichungs-Nr.

EP4789896

Anmeldetag

6. Februar 2025

Veröffentlichung

12. August 2026

Rechtsraum

EP

Abstract

The disclosure relates to a method for training a data model (56) for detecting an anomaly in a traction battery pack (14) of a vehicle (12). The method comprises obtaining first data (D1) indicative of at least one state parameter of the traction battery pack (14) and second data (D2) indicative of a usage history statistic of the traction battery pack (14). The first data (D1) and the second data (D2) relate to a plurality of traction battery packs (14) of vehicles (12) out of a group (64) of vehicles (12). The first data (D2) and the second data (D2) are labelled with labelling data indicative of a presence or absence of an anomaly of the associated traction battery pack (14). The method further comprises training the data model (56) based on the labelled first data (D1) and the labelled second data (D2). The disclosure further relates to a method for detecting an anomaly in a traction battery pack (14) of a vehicle (12). Moreover, the disclosure is directed to a method for handling an anomaly in a traction battery pack (14) of a vehicle (12).

Anmelder

Firma

Volvo Car Corporation

Land

🇸🇪 Schweden