Technologies and techniques for processing a state of health for a battery in a battery management system. A plurality of time series windows are extracted from a multivariate time series battery-related data associated with a plurality of vehicles. One or more data features are extracted from the plurality of time series windows and clustered to group the data features into a plurality of first groups, based on a similarity metric. Each of the clustered plurality of first groups are labeled with correlated values indicating a state, and a plurality of label compositions are generated, each label composition comprising an aggregation of vehicles associated with each label. The plurality of label compositions are clustered to determine vehicle clusters sharing the most similar usage patterns. A state of health indication may then be for the battery information based on the vehicle clusters sharing the most similar usage patterns.
MODELLING OF ELECTRIC VEHICLE CHARGING AND DRIVING USAGE BEHAVIOR WITH VEHICLE-BASED CLUSTERING
2024-07-04
Patent
Elektronische Ressource
Englisch
Europäisches Patentamt | 2024
|Transportation Research Record | 2018
|