CPC B60L 58/16 (2019.02) [G01R 31/367 (2019.01); G01R 31/371 (2019.01); G01R 31/392 (2019.01); B60L 2240/72 (2013.01)] | 18 Claims |
1. A method for optimizing a battery management system (BMS), comprising:
obtaining training data, wherein the training data comprises data from a target vehicle and data from auxiliary vehicles, and the auxiliary vehicles are vehicles mounted with a same or similar battery system as the target vehicle; and
optimizing a BMS related algorithm for the target vehicle by performing transfer learning based on the training data, wherein the BMS related algorithm comprises one or a combination of: a battery model, parameters for the battery model, a battery management algorithm, and parameters for the battery management algorithm;
wherein before optimizing the BMS related algorithm for the target vehicle by performing transfer learning based on the training data, the method further comprises:
pretraining an initial BMS related algorithm based on experimental data of fresh battery cells for the target vehicle; or,
establishing a basic BMS related algorithm based on the experimental data of the fresh battery cells for the target vehicle, and optimizing the basic BMS related algorithm based on calibration data based on test vehicles to obtain the initial BMS related algorithm, the initial BMS related algorithm comprising one or a combination of: an initial battery model, parameters for the initial battery model, an initial battery management algorithm, and parameters for the initial battery management algorithm.
|