Vehicle dynamics control using deep learning to update an operational parameter of a vehicle drive train
A system may include sensors, provided on a vehicle, to sense one or more operational states of the vehicle and output the sensed operational states. A system may include a cloud computing platform to receive the sensed operational states, a modeling application, provided at the cloud computing platform, having a processor to execute software to generate and operate a digital twin of the vehicle, the digital twin encompassing twin subsystems of the vehicle and simulating operations thereof; and an artificial intelligence system, associated with the cloud computing platform, to receive and process the sensed operational states and updates an operational parameter of the drive train of the vehicle based on the modeling application.
1. A transportation system to update an operational parameter of a drive train of a vehicle, the transportation system comprising:
at least one sensor, associated with the vehicle, configured to sense one or more operational states of the vehicle and to output the sensed one or more operational states;
a cloud computing platform configured to receive the sensed one or more operational states;
a modeling application, provided at the cloud computing platform, having a processor configured to execute software to generate and operate a digital twin of the vehicle, the digital twin encompassing twin subsystems of the vehicle and simulating operations thereof; and
an artificial intelligence system, associated with the cloud computing platform, configured to:
receive and to process the sensed one or more operational states;
update the operational parameter of the drive train of the vehicle based on the modeling application;
and update the operational parameter in real time responsive to detecting of a detected satisfaction state of a rider user by a first neural network,
wherein the artificial intelligence system includes the first neural network to detect the detected satisfaction state of the rider user occupying the vehicle through analysis of data gathered from user sensors deployed in the vehicle for gathering physiological conditions of the rider user.
2. The transportation system of claim 1 , wherein the at least one sensor includes at least one of an on-board diagnostic system or a telemetry system.
3. The transportation system of claim 1 , wherein the cloud computing platform further comprises an identity management system to manage a set of identities and roles of a user of the vehicle.
4. The transportation system of claim 1 , wherein the artificial intelligence system is configured to optimize the operational parameter based on a correlation between a vehicle operating state and a rider satisfaction state of the rider user.
5. The transportation system of claim 1 , wherein the modeling application is populated via an API from an edge intelligence system of the vehicle to provide 5G connectivity to systems external to the vehicle.
6. The transportation system of claim 1 , wherein the digital twin is automatically configured by the artificial intelligence system based on a training set of usage activity by a set of digital twin users.
7. The transportation system of claim 1 , wherein the modeling application is configured to retrieve data from data sources via a digital twin I/O system.
8. The transportation system of claim 1 , wherein the digital twin of the vehicle is updated based on an effect of collected vibration data on a set of digital twin dynamic models, wherein the digital twin provides a computer-generated representation of a transportation entity.
9. A method of updating an operational parameter of a drive train of a vehicle, the method comprising:
sensing at least one vehicle parameter of the vehicle;
receiving, at an artificial intelligence system, one or more vehicle operating states, wherein the artificial intelligence system includes a first neural network to detect a detected satisfaction state of a rider user occupying the vehicle through analysis of data gathered from sensors deployed in the vehicle for gathering physiological conditions of the rider user;
tracking, at the artificial intelligence system, the one or more vehicle operating states over time;
generating a digital twin of the vehicle to simulate twin subsystems of the vehicle and to simulate operations of the one or more vehicle operating states; and
updating the operational parameter of the drive train of the vehicle based on:
the simulated operations; and
a correlation between the one or more vehicle operating states and the detected satisfaction state of the rider user.
10. The method of claim 9 , wherein the sensing at least one vehicle parameter includes using at least one of: an on-board diagnostic system or a telemetry system.
11. The method of claim 9 , further comprising:
managing a set of identities and roles of a user of the vehicle; and
configuring the digital twin of the vehicle based on the set of identities of the user of the vehicle.
12. The method of claim 9 , wherein generating the digital twin of the vehicle includes populating the digital twin of the vehicle via an API from an edge intelligence system of the vehicle configured to provide 5G connectivity to systems external to the vehicle.
13. The method of claim 9 , further comprising automatically configuring the digital twin of the vehicle with the artificial intelligence system based on a training set of usage activity by a set of digital twin users.
14. The method of claim 9 , further comprising retrieving data from selected data sources via a digital twin I/O system for use in generating the digital twin.
15. The method of claim 9 , wherein updating the operational parameter of the drive train of the vehicle includes optimizing the operational parameter in real time responsive to the tracking of the one or more vehicle operating states over time.
16. The method of claim 9 , wherein generating the digital twin of the vehicle includes updating properties of the digital twin based on an effect of collected vibration data on a set of digital twin dynamic models.