Back to results
US 2024/0201687 A1Published application
Neural net optimization of continuously variable powertrain
AssigneeStrong Force TP Portfolio 2022, LLC
InventorCharles Howard Cella
Life of this patent
Estimating the term…
Abstract
A method for optimizing a vehicle system involves using a neural network to optimize at least one operating parameter of a transmission portion of a continuously variable powertrain based at least in part on a classified current state of a vehicle, wherein the current state is associated with a predicted future vehicle state.
Claims22
A method for optimizing a vehicle system, the method comprising:
- classifying a current state as a classified current state of a vehicle based on at least one operating parameter of a transmission of a continuously variable powertrain of the vehicle;
- predicting a future vehicle state as a predicted future vehicle state based the classified current state;
- and
- using a neural network to optimize the at least one operating parameter of the transmission of the continuously variable powertrain based at least in part on the classified current state and the predicted future vehicle state.
1 more element
A vehicle, comprising:
- a continuously variable powertrain with a transmission portion having at least one operating parameter;
- and
- a processor programmed to:
- classify a current state as a classified current state of the vehicle based, at least in part, on the at least one operating parameter of the transmission portion;
- predict a future vehicle state as a predicted future vehicle state based the classified current state;
- and
- execute a neural network configured to optimize the at least one operating parameter based, at least in part, on the classified current state of the vehicle and the predicted future vehicle state.
4 more elements
Dependencies are inferred from the claim text.