In-track wheel inspection system

• US 7,555,954 B2
• Filed: 04/26/2006
• Issued: 07/07/2009
• Est. Priority Date: 04/26/2005
• Status: Active Grant

• Current Assignee: Nordco, Inc. (Westinghouse Air Brake Technologies Corporation)
• Original Assignee: Dapco Industries, Inc. (Westinghouse Air Brake Technologies Corporation)
• Inventors: Giragosian, David W., Pagano, Dominick A.
• Primary Examiner(s): CHAPMAN JR, JOHN E
• Application Number:
  US11/412,318
• Publication Number:
  US 20060266122A1
• Time in Patent Office: 1,168 Days
• Field of Search: 735/98, 736/20, 736/34, 736/36
• US Class Current: 73/620
• CPC Class Codes: G01N 2291/0422 Shear waves, transverse waves, horizontally polarised waves
• CPC Class Codes: G01N 2291/2696 Wheels, Gears, Bearings
• CPC Class Codes: G01N 29/043 in the interior, e.g. by shear waves
• CPC Class Codes: G01N 29/275 by moving both the sensor and the material
• CPC Class Codes: G01N 29/348 with frequency characteristics, e.g. single frequency signals, chirp signals measuring frequency of mechanical vibrations or acoustic waves in general G01H1/06, G01H3/04; measuring frequency or analysing frequency spectra G01R23/00

Abstract

An ultrasonic real-time inspection method which is user-friendly in an interactive environment to provide ease of operation, as well as a combination of consistency, thoroughness, and speed of operation in flaw detection not achievable by other methods. The system and method are useable on a traveling wheel so as not to unduly interfere with normal train operation. The system and method includes a test device that moves along train wheels injecting pulses into the wheel to detect acoustic responses caused at a discontinuity in the wheel. A processor can also be included to determine a pattern of a feature of the wheel associated with the discontinuity.

Claims

1. A method of performing real-time defect recognition on a train wheel, comprising:

detecting the train wheel entering a test station;

accelerating a test head to match the speed of the train wheel;

injecting, from the test head, pulses of a plurality of ultrasonic beams into the train wheel;

detecting acoustic responses caused at a discontinuity of an elongated material;

determining at least one characteristic of the detected acoustic responses; and

determining a pattern of a feature of the wheel associated with said discontinuity based on the at least one characteristic and at least one pattern recognition rule.

2. The method of claim 1, wherein said at least one characteristic comprises a beam pulse speed.

3. The method of claim 1, wherein said step of determining the pattern comprises:

classifying features associated with the responses;

clustering the classified features;

performing basic recognition analysis using the clustered classified features to determine a basic recognition; and

performing context recognition analysis on the basic recognition to determine the pattern.

4. A system for performing real-time defect detection on a train wheel, comprising:

a flange bearing track for the train wheel to ride on;

a defect detection unit, said defect detection unit having at least one test head adapted to emit an ultrasonic beam and at least one ultrasonic detector;

a test track adapted to carry the defect detection unit;

a motor coupled to the defect detection unit transducer to move the defect detection unit on the test track; and

a speed matching unit to match the speed of the defect detection unit with the train wheel under test.

5. The system of claim 4, wherein the motor is adapted to move the defect detection unit at about 3 to 10 miles per hour.

6. The system of claim 4, further comprising:

a pattern recognition device coupled to the defect detection unit to optically detect surface defects.

7. A system for performing real-time defect detection on a railroad wheel, said system comprising:

a test device being adapted to move along side a train wheel, said test device injecting pulses of a plurality of ultrasonic beams into the wheel and detecting acoustic responses caused at a discontinuity in the wheel; and

a processor, said processor being programmed to determine a pattern of a feature of the wheel associated with said discontinuity at defect condition.

8. A system being capable of performing real-time defect detection and recognition on all train wheels in a train formation comprising:

a plurality of test stations, each test station having a test head, adapted to detect and sequentially test all said train wheels;

accelerating means to accelerate each individual test head to match the speed of a designated train wheel;

injecting means and detecting means at each test head adapted to inject and detect acoustic responses caused at a discontinuity of an elongated material;

and determining at least one characteristic of the detected acoustic responses; and

a processor, said processor coupled to each test head, said processor being programmed to determine a pattern of a feature of the wheel associated with a defect condition.

9. A remote, non-contact system for detecting a defect in a railroad wheel, said system comprising:

a test unit, located at a first location parallel to the direction of travel of the railroad wheel and adapted to travel in synchronicity with the railroad wheel, for generating in a non-contact manner in said wheel an ultrasonic wave having a specified wavefront; and

a detector, located at a second location parallel to the direction of travel of the railroad wheel adapted to travel in synchronicity with the railroad wheel, for sensing from said wheel the acoustic signal emanating from said wheel that results from said ultrasonic wave traveling through said wheel;

signal processor, responsive to said sensed acoustic signal, capable of distinguishing whether said sensed signal has a component that indicates the existence of a defect in said railroad wheel.