Systems and methods for monitoring drive unit bearings

Patent metadata

Field	Value
Publication number	US-12416545-B2
Application number	US-202318331447-A
Country	US
Kind code	B2
Filing date	Jun 8, 2023
Priority date	Jun 8, 2023
Publication date	Sep 16, 2025
Grant date	Sep 16, 2025

Abstract

Vehicles and systems and methods for health monitoring drive unit bearings in vehicles are provided. A system for health monitoring a drive unit bearing in a vehicle includes a sensor mounted to a drive unit of the vehicle and configured to provide a vibration signal; and a processor configured to: pre-process the vibration signal from the sensor to enhance a fault signature and form a frequency domain signal; and process the frequency domain signal to estimate a health stage of the drive unit bearing.

First claim

What is claimed is:

1. A system for health monitoring a drive unit bearing in a vehicle, the system comprising:
a sensor mounted to a drive unit of the vehicle and configured to provide a vibration signal;
a motor speed sensor for sensing motor speed and/or a torque sensor for sensing torque; and
a processor configured to:
determine whether the motor speed is in a speed range and/or to determine whether the torque is in a torque range suitable for monitoring the drive unit bearing;
pre-process the vibration signal from the sensor to enhance a fault signature and form a frequency domain signal; and
process the frequency domain signal to estimate a health stage of the drive unit bearing.

2. The system of claim 1 , wherein the processor is configured to process the frequency domain signal to extract and fuse health indicators, and estimate a fault level and a fault location from the health indicators.

3. The system of claim 1 , wherein the processor is configured to process the frequency domain signal to detect whether a bearing is healthy or faulty.

4. The system of claim 1 , wherein the processor is configured to process the frequency domain signal to isolate a fault in a particular bearing and to determine a location of the fault on the particular bearing.

5. The system of claim 1 , wherein the processor is configured to pre-process the vibration signal from the sensor by performing a phase domain transformation, a discrete frequency removal, an impulsiveness enhancement, an envelope filter, and a short time Fourier transformation (STFT).

6. The system of claim 1 , wherein the processor is configured to process the frequency domain signal by:
calculating health indicators;
applying a regression model to the health indicators to find health stages; and
comparing the health stages with predefined thresholds to detect a state of health of the drive unit bearing.

7. The system of claim 1 , wherein the processor is configured to perform a calibration process comprising:
fitting a regression model to health indicators to find health stages;
calculating a modeling error;
ranking the health stages;
selecting specific health stages to fuse; and
determining pre-defined weights for the health stages, and wherein outputs from the calibration process are stored in the system.

8. The system of claim 7 , wherein the processor is configured to:
calculate health indicators;
apply the pre-defined weights to generate weighted health stages;
sum the weighted health stages to provide a fused health stage; and
compare the fused health stage with a predefined threshold to detect a state of health of the drive unit bearing.

9. The system of claim 1 , wherein the processor is further configured to communicate an output indicating the health stage of the drive unit bearing.

10. A method for monitoring health of a drive unit bearing in a vehicle, the method comprising:
performing a calibration process comprising:
fitting a regression model to health indicators to find health stages;
calculating a modeling error;
ranking the health stages;
selecting specific health stages to fuse;
determining pre-defined weights for the health stages; and
storing outputs from the calibration process;

sensing vibrations with a sensor at a known location relative to a drive unit and providing sensor data;
performing a short time Fourier transform (STFT) to form spectrum signals over a plurality of segments;
calculating health indicators of the drive unit bearing based on the spectrum signals and on critical frequencies of the drive unit bearing; and
determining a health stage of the drive unit bearing based on each health indicator.

11. The method of claim 10 , wherein determining the health stage of the drive unit bearing based on each health indicator comprises applying a regression model to each of the health indicators.

12. The method of claim 10 , further comprising detecting a state of health of the drive unit bearing based on the health stage.

13. The method of claim 10 , further comprising
sensing motor speed with a motor sensor and/or sensing torque with a torque sensor; and
determining whether the motor speed is in a speed range and/or determining whether the torque is in a torque range suitable for monitoring the drive unit bearing.

14. The method of claim 10 , further comprising applying the pre-defined weights to the calculated health indicators to generate weighted health stages.

15. The method of claim 14 , further comprising calculating a fused health stage from the weighted health stages.

16. The method of claim 15 , further comprising comparing the fused health stage with a predefined threshold to detect a state of health of the drive unit bearing.

17. The method of claim 10 , further comprising communicating an output indicating the health stage of the drive unit bearing.

18. The method of claim 10 , wherein the drive unit bearing is a first drive unit bearing, and wherein the method further comprises monitoring health of a second drive unit bearing.

19. A vehicle comprising:
a drive unit bearing;
a vibration sensor configured to provide sensor data; and
a processor or processors individually or collectively configured to:
perform a calibration process comprising:
fitting a regression model to health indicators to find health stages;
calculating a modeling error;
ranking the health stages;
selecting specific health stages to fuse; and
determining pre-defined weights for the health stages, and wherein outputs from the calibration process are stored in the system;

pre-process the sensor data to generate a spectrum; and
process the spectrum to estimate health stages of the drive unit bearing.

20. The vehicle of claim 19 , further comprising a motor speed sensor for sensing motor speed and/or a torque sensor for sensing torque, wherein the processor is configured to determine whether the motor speed is in a speed range and/or to determine whether the torque is in a torque range suitable for monitoring the drive unit bearing.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Jafarzadeh Ehsan
• Sadjadi Hossein
• Sant Anna Paola Scarassatti
• Li Dezhi
• Rahimifard Sara Sadat
• Cao Yu

Classifications

• F16C19/527 Primary

  related to vibration and noise · CPC title

• F16C2233/00

  Monitoring condition, e.g. temperature, load, vibration · CPC title

• F16C2361/65

  Gear shifting, change speed gear, gear box · CPC title

• G01M13/045 Primary

  Acoustic or vibration analysis · CPC title

• G06F2218/20

  by applying autoregressive analysis · CPC title