Adaptive prognostics systems and methods for vehicles

Patent metadata

Field	Value
Publication number	US-11904875-B2
Application number	US-201916595738-A
Country	US
Kind code	B2
Filing date	Oct 8, 2019
Priority date	Oct 8, 2019
Publication date	Feb 20, 2024
Grant date	Feb 20, 2024

Abstract

A system includes an assessment module and a training module. The assessment module is configured to receive event data about an event associated with a subsystem of a vehicle. The assessment module is configured to determine deviations between reference data for the subsystem indicating normal operation of the subsystem and portions of the event data that precede and follow the event. The assessment module is configured to determine whether the event data indicates a fault associated with the subsystem by comparing the deviations to a threshold deviation. The training module is configured to update a model trained to identify faults in vehicles to identify the event as a fault associated with the subsystem of the vehicle based on the event data in response to the deviations indicating a fault associated with the subsystem.

First claim

What is claimed is:

1. A system comprising:
an assessment module configured to:
receive event data about an event associated with a subsystem of a vehicle, wherein the event includes an indication of an operating condition of the subsystem;
determine deviations between reference data for the subsystem indicating normal operation of the subsystem and portions of the event data that precede and follow the event; and
determine whether the event data indicates a fault associated with the subsystem by comparing the deviations to a threshold deviation; and

a training module configured to update a model trained to identify faults in vehicles to identify the event as a fault associated with the subsystem of the vehicle based on the event data in response to the deviations indicating a fault associated with the subsystem;
wherein the assessment module is configured to update the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event remaining greater than the threshold deviation for a time period following the event.

2. The system of claim 1 wherein the assessment module is configured to:
add the event data to the reference data in response to the deviations not indicating a fault associated with the subsystem; and
use the reference data including the event data to determine deviations of subsequent events in the vehicle and in other vehicles.

3. The system of claim 1 wherein the assessment module is further configured to identify one or more faulty components of the subsystem based on the deviations in response to the deviations indicating a fault associated with the subsystem.

4. The system of claim 1 wherein the model is trained for use in vehicles manufactured in a different vehicle program or a different model year than that in which the vehicle is manufactured and wherein the training module is configured to update the model for use in the vehicle.

5. The system of claim 1 wherein the model is trained for use in multiple vehicles and wherein the training module is configured to update the model for use in the vehicle.

6. The system of claim 1 wherein the event includes a repair performed on the vehicle and wherein the assessment module is configured to update the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event being less than the threshold deviation.

7. The system of claim 1 wherein the assessment module is further configured to normalize the event data and to select portions of the normalized data to determine the deviations.

8. A method comprising:
receiving event data about an event associated with a subsystem of a vehicle, wherein the event includes an indication of an operating condition of the subsystem;
filtering the event data to remove outliers from the event data;
normalizing the filtered event data using a predetermined range;
selecting data from the normalized data that precede and follow the event;
determining deviations between reference data for the subsystem indicating normal operation of the subsystem and portions of the selected data that precede and follow the event;
determining whether the event data indicates a fault associated with the subsystem by comparing the deviations to a threshold deviation;
identifying one or more faulty components of the subsystem based on the deviations in response to the deviations indicating a fault associated with the subsystem;
updating a model trained to identify faults in vehicles to identify the event as a fault associated with the subsystem based on the event data in response to the deviations indicating a fault associated with the subsystem; and
updating the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event remaining greater than the threshold deviation for a time period following the event.

9. The method of claim 8 further comprising:
adding the event data to the reference data in response to the deviations not indicating a fault associated with the subsystem; and
using the reference data including the event data to determine deviations of subsequent events in the vehicle and in other vehicles.

10. The method of claim 8 further comprising:
training the model for use in vehicles manufactured in a different vehicle program or a different model year than that in which the vehicle is manufactured; and
updating the model for use in the vehicle.

11. The method of claim 8 wherein the event includes a repair performed on the vehicle, the method further comprising updating the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event being less than the threshold deviation.

12. A system comprising:
a processor; and
a memory storing instructions which when executed by the processor configure the processor to:
receive event data about an event associated with a subsystem of a vehicle, wherein the event includes an indication of an operating condition of the subsystem;
determine deviations between reference data indicating normal operation of the subsystem and portions of the event data that precede and follow the event;
determine whether the event data indicates a fault associated with the subsystem by comparing the deviations to a threshold deviation; and
update a model trained to identify faults in vehicles to identify the event as a fault associated with the subsystem based on the event data in response to the deviations indicating a fault associated with the subsystem,
wherein the model is trained for use in the vehicles manufactured in a different vehicle program or a different model year than that in which the vehicle is manufactured; and

wherein the instructions configure the processor to update the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event remaining greater than the threshold deviation for a time period following the event.

13. The system of claim 12 wherein the instructions configure the processor to:
add the event data to the reference data in response to the deviations not indicating a fault associated with the subsystem; and
use the reference data including the event data to determine deviations of subsequent events in the vehicle and in other vehicles.

14. The system of claim 12 wherein the instructions configure the processor to identify one or more faulty components of the subsystem based on the deviations in response to the deviations indicating a fault associated with the subsystem.

15. The system of claim 12 wherein the event includes a repair performed on the vehicle, and wherein the instructions configure the processor to update the model in response to the deviations of the portions of the event data preceding the event being greater than the threshold deviation and in response to the deviations of the portions of the event data following the event being less than the threshold deviation.

16. The system of claim 12 wherein the instructions confi

Assignees

• Gm Global Tech Operations Llc

Inventors

• Du Xinyu
• Nagose Atul
• Sanchez Joshua J
• Krajewski Paul E

Classifications

• B60W50/04 Primary

  Monitoring the functioning of the control system · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06N20/00

  Machine learning · CPC title

• G07C5/085

  using electronic data carriers · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title