Vehicle fault diagnostics and prognostics using automatic data segmentation and trending

Patent metadata

Field	Value
Publication number	US-11645880-B2
Application number	US-202117148643-A
Country	US
Kind code	B2
Filing date	Jan 14, 2021
Priority date	Jan 14, 2021
Publication date	May 9, 2023
Grant date	May 9, 2023

Abstract

A controller processes data from one or more sensors of a subsystem of a vehicle. The processing includes smoothing the data and calculating a mean of the data. The controller identifies a transition point in the processed data where a moving average of the data is less than the mean by a predetermined amount indicating a trend. The controller selects a segment of the processed data subsequent to the transition point, detects the trend in the segment using regression, and extrapolates the detected trend to reach a predetermined fault threshold. The controller predicts a failure of the subsystem based on a slope of the extrapolated trend and provides an indication of the prediction based on the slope to schedule a service for the subsystem.

First claim

What is claimed is:

1. A system comprising:
a plurality of sensors associated with a plurality of subsystems of a vehicle; and
a controller configured to communicate with the plurality of subsystems of the vehicle and further configured to:
process data received from one or more sensors of one of the subsystems of the vehicle, wherein the processing includes smoothing the data and calculating a mean of the data;
identify a transition point in the processed data where a moving average of the data is less than the mean by a predetermined amount indicating an upward trend or where the moving average is greater than the mean by the predetermined amount indicating a downward trend;
select a segment of the processed data subsequent to the transition point;
detect a trend in the segment of the processed data subsequent to the transition point using regression, wherein the trend includes the upward trend or the downward trend;
extrapolate the detected trend to reach a predetermined fault threshold;
predict a failure of the one of the subsystems based on a slope of the extrapolated trend; and
provide an indication of the prediction based on the slope of the extrapolated trend to schedule a service for the one of the subsystems.

2. The system of claim 1 wherein the controller is further configured to accurately diagnose a fault in the one of the subsystems, modify a control parameter of the vehicle to improve vehicle safety, and/or prolong life of a component of the one of the subsystems before the component fails using the detected trend.

3. The system of claim 1 wherein the controller is further configured to:
detect a second trend in second data collected from the one or more sensors of one of the subsystems after the service; and
evaluate the service based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

4. The system of claim 1 wherein the received data includes first and second data for first and second parameters of the one of the subsystems, respectively, and wherein the controller is further configured to:
determine whether to generate an alert about a condition of the one of the subsystems based on whether the first data for the first parameter has crossed a first threshold; and
detect the trend using the second data for the second parameter,
wherein the second parameter is different than the first parameter.

5. The system of claim 1 wherein the controller is configured to provide the indication of the prediction in response to the slope of the extrapolated trend being greater than a first predetermined threshold.

6. The system of claim 1 wherein the controller is configured to:
estimate an operational life of the one of the subsystems based on the slope of the extrapolated trend; and
provide the indication of the prediction based on the estimation.

7. The system of claim 1 wherein the controller is configured to select a type of the regression depending on a type of a parameter of the one of the subsystems for which the data is received.

8. The system of claim 1 wherein the controller is configured to detect the trend by excluding data before the transition point.

9. The system of claim 1 wherein the controller is located in a computing device remote from the vehicle and wherein the computing device includes a mobile device, a service tool, or a server in a cloud.

10. A system comprising:
a processor; and
a memory storing instructions that when executed by the processor configure the processor to:
process data received from one or more sensors of a subsystem of a vehicle, wherein the processing includes smoothing the data and calculating a mean of the data;
identify a transition point in the processed data where a moving average of the data is less than the mean by a predetermined amount indicating an upward trend or where the moving average is greater than the mean by the predetermined amount indicating a downward trend;
select a segment of the processed data subsequent to the transition point;
detect a trend in the segment using regression, wherein the trend includes the upward trend or the downward trend;
extrapolate the detected trend to reach a predetermined fault threshold;
predict a failure of the subsystem based on a slope of the extrapolated trend; and
provide an indication of the prediction based on the slope of the extrapolated trend to schedule a service for the subsystem.

11. The system of claim 10 wherein the instructions further configure the processor to accurately diagnose a fault in the subsystem, modify a control parameter of the vehicle to improve vehicle safety, and/or prolong life of a component of the subsystem before the component fails using the detected trend.

12. The system of claim 10 wherein the instructions further configure the processor to:
detect a second trend in second data collected from the one or more sensors of the subsystem after the service; and
evaluate the service based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

13. The system of claim 10 wherein the received data includes first and second data for first and second parameters of the subsystem, respectively, and wherein the instructions further configure the processor to:
determine whether to generate an alert about a condition of the subsystem based on whether the first data for the first parameter has crossed a first threshold; and
detect the trend using the second data for the second parameter,
wherein the second parameter is different than the first parameter.

14. The system of claim 10 wherein the instructions further configure the processor to provide the indication of the prediction in response to the slope of the extrapolated trend being greater than a first predetermined threshold.

15. The system of claim 10 wherein the instructions further configure the processor to:
estimate an operational life of the subsystem based on the slope of the extrapolated trend; and
provide the indication of the prediction based on the estimation.

16. The system of claim 10 wherein the instructions further configure the processor to select a type of the regression depending on a type of a parameter of the subsystem for which the data is received.

17. The system of claim 10 wherein the instructions further configure the processor to detect the trend by excluding data before the transition point.

18. A computing device comprising the system of claim 10 wherein the computing device is remote from the vehicle and includes a mobile device, a service tool, or a server in a cloud.

19. A method comprising:
processing data received from one or more sensors of a subsystem of a vehicle, wherein the processing includes smoothing the data and calculating a mean of the data;
identifying a transition point in the processed data where a moving average of the data is less than the mean by a predetermined amount indicating an upward trend or where the moving average is greater than the mean by the predetermined amount indicating a downward trend;
selecting a segment of the processed data subsequent to the transition point;
detecting a trend in the segment using regression, wherein the trend includes the upward trend or the downward trend;
extrapolating the detected trend to reach a predetermined fault threshold;
predicting a failure of the subsystem based on a slope of the extrapolate

Assignees

• Gm Global Tech Operations Llc

Inventors

• Du Xinyu
• Yang Zhongyu
• Sanchez Joshua J
• Corr Kevin M
• Zhang Yilu
• Nowak Mateusz M

Classifications

• G07C5/0816

  Indicating performance data, e.g. occurrence of a malfunction · CPC title

• G07C5/0808 Primary

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

• B60W50/0205 Primary

  Diagnosing or detecting failures; Failure detection models · CPC title

• G05B23/0232

  based on qualitative trend analysis, e.g. system evolution · CPC title

• G05B23/0283 Primary

  Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06) · CPC title