Disclosed are systems and methods for updating of a machine learning model on a vehicle. A data processing system having at least one processor coupled with memory can predict a first value for a characteristic of the vehicle based at least on a model and measure a second value for the characteristic of the vehicle based at least on a sensor of the vehicle. The data processing system can determine a difference between the first value predicted based at least on the model and the second value measured is greater than a tolerance. The data processing system can identify a state of the vehicle associated with the difference between the first value and the second value and provide, in response to the difference determined greater than the tolerance, the state of the vehicle to a server remote from the vehicle to update the model.
Battery management systems and methods
2024-05-07
Patent
Elektronische Ressource
Englisch