Abnormal vehicle dynamics detection

• US 10,040,465 B2
• Filed: 07/24/2017
• Issued: 08/07/2018
• Est. Priority Date: 01/16/2015
• Status: Active Grant

• Current Assignee: International Electronic Machines Corp.
• Original Assignee: International Electronic Machines Corp.
• Inventors: Mian, Zahid F., Gamache, Ronald W., Hayes, Peter
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US15/657,867
• Publication Number:
  US 20170320508A1
• Time in Patent Office: 379 Days
• Field of Search: 701 19, 735705-672, 73659
• CPC Class Codes: B61L 15/0072 On-board train data handling
• CPC Class Codes: B61L 15/0081 On-board diagnosis or maintenance
• CPC Class Codes: B61L 27/40 Handling position reports or trackside vehicle data
• CPC Class Codes: B61L 27/57 for vehicles or trains, e.g. trackside supervision of train conditions
• CPC Class Codes: G01H 1/00 Measuring characteristics of vibrations in solids by using direct conduction to the detector G01H9/00, G01H11/00 take precedence

Abstract

A solution for evaluating a vehicle, such as a railroad vehicle, is provided. Vibration data relating to the railroad vehicle can be acquired by vibration sensing devices located adjacent to a rail. Enhanced signal data can be generated from the vibration data acquired by the vibration sensing devices. The enhanced signal data can be evaluated for any anomalous features, such as vibration peaks. When multiple anomalous features are present, these features can be further evaluated to determine whether they indicate a presence of a defect on the railroad vehicle that is producing a periodic signal.

Claims

1. A method of evaluating a railroad vehicle, the method comprising:

a computer system acquiring vibration data from a plurality of vibration sensing devices located at a plurality of locations along a path the railroad vehicle is traveling;

the computer system processing the vibration data to identify any anomalous vibration features, wherein the identifying includes determining that a vibration feature was detected by at least two of the plurality of vibration sensing devices at highly temporally coherent times;

in response to identifying a plurality of anomalous vibration features in the vibration data, the computer system evaluating the plurality of anomalous vibration features for an indication of a presence of at least one defect on the railroad vehicle, wherein the at least one defect produces signals as the railroad vehicle travels along the path; and

the computer system identifying the railroad vehicle as including a defect in response to identifying the indication of the defect on the railroad vehicle.

2. The method of claim 1, wherein the computer system processing includes the computer system generating enhanced signal data from the vibration data, wherein the generating enhanced signal data includes:

the computer system generating signal data for the vibration data acquired from each of the plurality of vibration sensing devices; and

the computer system adding the signal data for each of the plurality of vibration sensing devices to generate the enhanced signal data.

3. The method of claim 2, wherein the computer system processing further includes the computer system identifying anomalous vibration peaks within the enhanced signal data.

4. The method of claim 2, wherein the computer system processing further includes the computer system identifying any enhanced signal data exceeding a maximum noise peak level.

5. The method of claim 1, wherein the at least one defect includes at least one of:

a wheel flat, an out of round wheel, wheel shelling, a broken wheel, a cracked wheel, a broken spring, or a weak suspension damper.

6. The method of claim 1, wherein the evaluating the plurality of anomalous vibration features includes the computer system evaluating a time spacing between the plurality of anomalous vibration features, wherein a plurality of anomalous vibration features having a substantially uniform time spacing indicates the defect.

7. The method of claim 6, wherein the evaluating the plurality of anomalous vibration features further includes the computer system comparing the substantially uniform time spacing with a time for a wheel revolution of a railroad wheel on the railroad vehicle, wherein a substantially uniform time spacing approximately the same as the time for the wheel revolution indicates the defect.

8. The method of claim 1, further comprising the computer system transmitting a result of the evaluation for processing by a user system.

9. A railroad vehicle management system comprising:

a plurality of vibration sensing devices located along a path railroad wheels travel, wherein the plurality of vibration sensing devices have a known spacing at a plurality of locations along the path; and

a computer system including means for evaluating the railroad vehicle, wherein the means for evaluating is configured to;

acquire vibration data from the plurality of vibration sensing devices;

process the vibration data to identify any anomalous vibration features, wherein the identifying includes determining that a vibration feature was detected by at least two of the plurality of vibration sensing devices at highly temporally coherent times;

in response to identifying a plurality of anomalous vibration features in the vibration data, evaluate the plurality of anomalous vibration features for an indication of a defect on the railroad vehicle; and

identify the railroad vehicle as including a defect in response to identifying the indication of a defect on the railroad vehicle.

10. The system of claim 9, further comprising a set of wheel sensors located adjacent to the path, wherein the computer system activates the plurality of vibration sensing devices in response to receiving an indication of a railroad wheel from a wheel sensor in the set of wheel sensors.

11. The system of claim 9, wherein the defect is one of:

a wheel flat, an out of round wheel, wheel shelling, a broken wheel, a cracked wheel, a broken spring, or a weak suspension damper.

12. The system of claim 9, wherein the plurality of vibration sensing devices includes no more than twelve vibration sensing devices for each side of the path.

13. The system of claim 9, further comprising a user system, wherein the computer system provides the user system with information relating to the evaluation of the railroad vehicle.

14. The system of claim 13, wherein the user system comprises a railroad vehicle management system, and wherein the information includes information relating to a presence of the defect.

15. The system of claim 13, wherein the user system comprises at least one vibration-sensitive device, and wherein the information includes information relating to the vibration generated by the railroad vehicle.

16. A method of evaluating a railroad wheel for a defect, the method comprising:

a computer system acquiring vibration data from a plurality of vibration sensing devices located at a plurality of locations along a path the railroad wheel is traveling;

the computer system processing the vibration data to identify any anomalous vibration features, wherein the identifying includes determining that a vibration feature was detected by at least two of the plurality of vibration sensing devices at highly temporally coherent times; and

in response to identifying a plurality of anomalous vibration features in the vibration data, the computer system evaluating the plurality of anomalous vibration features for an indication of the defect on the railroad wheel based on a time spacing between the plurality of anomalous vibration features, wherein the defect produces signals on the path as the railroad vehicle travels along the path.

17. The method of claim 16, wherein the anomalous vibration features include anomalous vibration peaks, and wherein the evaluating the enhanced signal data includes the computer system identifying any enhanced signal data exceeding a maximum level.

18. The method of claim 16, further comprising in response to the railroad wheel including the indication of a defect, the computer system estimating a severity of the defect using a cepstrum analysis of the vibration data.

19. The method of claim 16, wherein the railroad wheel is one of a plurality of railroad wheels on a railroad vehicle, the method further comprising in response to the railroad wheel including the indication of a defect, the computer system identifying the railroad wheel on the railroad vehicle with the defect.

20. The method of claim 16, wherein the defect is one of:

a wheel flat, an out of round wheel, wheel shelling, a broken wheel, or a cracked wheel.