System and method for filtering temperature profiles of a wheel

• US 8,280,675 B2
• Filed: 08/04/2009
• Issued: 10/02/2012
• Est. Priority Date: 08/04/2009
• Status: Active Grant

• Current Assignee: Progress Rail Services Corporation (Caterpillar Incorporated)
• Original Assignee: Progress Rail Services Corporation (Caterpillar Incorporated)
• Inventors: Church, Benjamin Paul, Arndt, Donald
• Primary Examiner(s): Charioui, Mohamed
• Assistant Examiner(s): Suarez, Felix
• Application Number:
  US12/535,057
• Publication Number:
  US 20110035181A1
• Time in Patent Office: 1,155 Days
• Field of Search: 702/99, 702/130, 702/134, 702/135, 702/138, 702/184, 702/185, 246/169.D, 310/52, 340/463
• US Class Current: 702/130
• CPC Class Codes: B61K 9/04 Detectors for indicating the overheating of axle bearings and the like, e.g. associated with the brake system for applying the brakes in case of a fault
• CPC Class Codes: G01J 5/0022 for sensing the radiation of moving bodies
• CPC Class Codes: G01J 5/02 Constructional details
• CPC Class Codes: G01J 5/026 Control of working procedures of a pyrometer, other than calibration; Bandwidth calculation; Gain control
• CPC Class Codes: G01J 5/48 Thermography; Techniques using wholly visual means

Abstract

A method for inspecting a rail vehicle includes receiving signals representative of temperatures of a wheel of the rail vehicle and generating a sensed wheel temperature profile of the wheel based on the signals. At least a portion of the sensed wheel temperature profile is representative of the temperatures of the wheel. The method also includes identifying waveform attributes in the sensed wheel temperature profile and designating the sensed wheel temperature profile as at least one of a typical wheel profile and an atypical wheel profile based on the waveform attributes in the sensed wheel temperature profile.

Claims

1. A computer-implemented method for inspecting a rail vehicle, the method comprising:

receiving, at a processor, signals representative of temperatures of a wheel of the rail vehicle;

generating, by the processor based on the received signals, a sensed wheel temperature profile of the wheel based on the signals, at least a portion of the sensed wheel temperature profile being representative of the temperatures of the wheel;

filtering the signals representative of temperatures based on the sensed wheel temperature profile not exceeding a detection threshold;

identifying waveform attributes in the portion of the sensed wheel temperature profile representative of the temperatures of the wheel; and

designating the sensed wheel temperature profile as at least one of a typical wheel profile and an atypical wheel profile based on the waveform attributes in the sensed wheel temperature profile.

2. The computer-implemented method of claim 1, further comprising analyzing the sensed wheel temperature profile to determine whether the wheel exhibits an elevated temperature when the sensed wheel temperature profile is designated as the typical wheel profile.

3. The computer-implemented method of claim 1, further comprising filtering the sensed wheel temperature profile to inhibit activation of an alarm associated with an elevated wheel temperature when the sensed wheel temperature profile is designated as the atypical wheel profile.

4. The computer-implemented method of claim 1, wherein the designating operation comprises classifying the sensed wheel temperature profile as the atypical wheel profile when a number of the waveform attributes exceeds a predetermined threshold.

5. The computer-implemented method of claim 1, wherein the identifying operation comprises identifying waveform peaks within the sensed wheel temperature profile, where the waveform peaks are identified when the signals in the sensed wheel temperature profile increase above a rising edge peak threshold then decrease below a falling edge peak threshold.

6. The computer-implemented method of claim 1, wherein the identifying operation comprises identifying waveform peaks in the sensed wheel temperature profile and a midpoint temperature between the waveform peaks, the midpoint temperature compared to a predetermined temperature threshold to determine if the sensed wheel temperature profile is the atypical wheel profile.

7. The computer-implemented method of claim 1, wherein the designating operation comprises designating the sensed wheel temperature profile as the atypical wheel profile when signals representative of temperatures of the wheel obtained outside of the wheel exceed the detection threshold.

8. The computer-implemented method of claim 1, further comprising identifying a distance, between waveform peaks in the sensed wheel temperature profile to approximate a wheel chord width, wherein the designating operation comprises classifying the sensed wheel temperature profile as the atypical wheel profile when the wheel chord width is less than a predetermined minimum threshold or greater than a maximum threshold.

9. The computer-implemented method of claim 1, wherein the designating operation comprises designating the sensed wheel temperature profile as a typical wheel profile when the sensed wheel temperature profile comprises two waveform peaks that rise above a rising edge peak threshold and subsequently fall below a falling edge peak threshold.

10. A rail vehicle inspection system comprising:

a temperature sensor for sensing temperatures of a wheel of a rail vehicle, the temperature sensor generating signals representative of the temperatures; and

a processor to receive the signals from the temperature sensor, the processor programmed to;

generate a sensed wheel temperature profile, at least a portion of the sensed wheel temperature profile being based on a portion of the signals that are representative of the temperatures of the wheel,

filter the signals representative of temperatures based on the sensed wheel temperature profile not exceeding a detection threshold,

identify waveform attributes in the portion of the sensed wheel temperature profile representative of the temperatures of the wheel, and

designate the sensed wheel temperature profile as at least one of an atypical wheel profile and a typical wheel profile based on the waveform attributes.

11. The system of claim 10, wherein the processor is programmed to, if the sensed temperature profile is designated as the typical wheel profile, analyze the sensed wheel temperature profile to determine whether the wheel exhibits an elevated temperature and, if the sensed temperature profile is designated as the atypical wheel profile, filter the sensed wheel temperature profile to inhibit activation of an alarm associated with the elevated temperature.

12. The system of claim 10, wherein the processor is programmed to classify the sensed wheel temperature profile as the atypical wheel profile when a number of the waveform attributes exceeds a predetermined threshold.

13. The system of claim 10, wherein the processor is programmed to identify waveform peaks within the sensed wheel temperature profile, the waveform peaks identified when the signals in the sensed wheel temperature profile increase above a rising edge peak threshold then decrease below a falling edge peak threshold.

14. The system of claim 10, wherein the processor is programmed to identify waveform peaks in the sensed wheel temperature profile and a midpoint temperature between the waveform peaks, the processor further programmed to compare the midpoint temperature to a predetermined temperature threshold to determine if the sensed wheel temperature profile is the atypical wheel profile.

15. A non-transitory computer readable storage medium for a rail inspection system having a processor and a temperature sensor configured to sense temperatures of a wheel of a rail vehicle and to generate signals representative of the temperatures, the computer readable storage medium comprising instructions stored therein for causing the processor to:

receive the signals from the temperature sensor;

generate a sensed wheel temperature profile based on the signals, at least a portion of the sensed wheel temperature profile representative of the temperatures of the wheel;

filter the signals representative of temperatures based on the sensed wheel temperature profile not exceeding a detection threshold;

identify waveform attributes in the portion of the sensed wheel temperature profile representative of the temperatures of the wheel; and

designate the sensed wheel temperature profile as at least one of a typical wheel profile and an atypical wheel profile based on the waveform attributes.

16. The non-transitory computer readable storage medium of claim 15, wherein the instructions direct the processor to:

if the sensed wheel temperature profile is designated as the typical wheel profile, analyze the sensed wheel temperature profile to determine whether the wheel exhibits an elevated temperature; and

if the sensed wheel temperature profile is designated as the atypical wheel profile, filter the sensed wheel temperature profile to inhibit activation of an alarm associated with the elevated wheel temperature.

17. The non-transitory computer readable storage medium of claim 15, wherein the instructions direct the processor to:

identify waveform peaks in the sensed wheel temperature profile and a midpoint temperature between the waveform peaks; and

compare the midpoint temperature to a predetermined temperature threshold to determine if the sensed wheel temperature profile is the atypical wheel profile.

18. The non-transitory computer readable storage medium of claim 15, wherein the instructions direct the processor to designate the sensed wheel temperature profile as the atypical wheel profile when signals representative of temperatures of the wheel obtained outside of the wheel exceed the detection threshold.

19. The non-transitory computer readable storage medium of claim 15, wherein the instructions direct the processor to:

identify a distance between waveform peaks in the sensed wheel temperature profile; and

classify the sensed wheel temperature profile as the atypical wheel profile when the distance is less than a predetermined minimum threshold or greater than a maximum threshold.

20. The non-transitory computer readable storage medium of claim 15, wherein the instructions direct the processor to designate the sensed wheel temperature profile as a typical wheel profile when the sensed wheel temperature profile comprises two waveform peaks extending above a peak threshold.

21. A computer-implemented method for inspecting a rail vehicle, the method comprising:

generating, by a processor, a sensed wheel temperature profile of a wheel of the rail vehicle, wherein the sensed wheel temperature profile comprises a plurality of respective temperatures of the wheel sensed at different locations of the wheel as the wheel passes a sensor during movement of the rail vehicle;

filtering, by a processor, the signals representative of temperatures based on the sensed wheel temperature profile not exceeding a detection threshold;

identifying, by a processor, waveform peaks within at least a portion of the sensed wheel temperature profile comprising the plurality of respective temperatures of the wheel, wherein the waveform peaks are identified when the temperatures in the sensed wheel temperature profile increase above a rising edge peak threshold then decrease below a falling edge peak threshold; and

designating the sensed wheel temperature profile as a typical wheel profile if the waveform peaks meet at least one designated criterion and as an atypical wheel profile if the waveform peaks fail to meet the at least one designated criterion.

22. The computer-implemented method of claim 21, further comprising identifying a midpoint temperature between the waveform peaks, wherein the at least one criterion comprises a designated relationship between the midpoint temperature and a predetermined temperature threshold.

23. The computer-implemented method of claim 21, wherein the at least one criterion comprises the sensed wheel temperature profile having two waveform peaks that rise above the rising edge peak threshold and subsequently fall below the falling edge peak threshold.