Machine vision system

• US 4,998,005 A
• Filed: 05/15/1989
• Issued: 03/05/1991
• Est. Priority Date: 05/15/1989
• Status: Expired due to Term

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Gantner, Randall C., Rathi, Rajendra P., Bottoms, John J., Tashjian, David G., Wolff, Steven M., Burkel, Richard H.
• Primary Examiner(s): Albritton, C. L.
• Application Number:
  US07/290,476
• Time in Patent Office: 659 Days
• Field of Search: 219/121.6, 219/121.85, 219/121.63, 219/121.64, 219/121.8, 219/121.83, 219/124.34, 364/474.08
• US Class Current: 219/121.83
• CPC Class Codes: B23K 26/032 using optical means
• CPC Class Codes: B23K 26/342 Build-up welding
• CPC Class Codes: B23P 6/007 using only additive methods, e.g. build-up welding
• CPC Class Codes: G05B 19/4207 in which a model is traced or scanned and corresponding data recorded
• CPC Class Codes: G05B 2219/36495 Recording position and other parameters, current, tool diameter, voltage
• CPC Class Codes: G05B 2219/37572 Camera, tv, vision
• CPC Class Codes: G05B 2219/45165 Laser machining
• CPC Class Codes: G05B 2219/50214 Refurbish, refinish, reprofile, recondition, restore, rebuild profile

Abstract

A vision system for automating a machine process. The system includes a conventional CCD camera and a vision processor which automatically determines process parameters from a workpiece surface by generating an image of the workpiece surface, transducing the workpiece image into electrical signals, and electronically determining the process parameters from the electrical signals. Applied to a laser welding process, the vision system locates workpiece edges, determines part centerline and thickness, and calculates process parameters such as weld location, the rate of delivery of weld powder, laser intensity, and the speed at which the weld is applied.

Claims

1. In an automated machining system, a method for determining process parameters from a workpiece surface, comprising the steps of:

generating an image of said workpiece surface;

transducing said image into electrical signals, said transducing step comprising the step of dissecting said image into a plurality of picture elements;

electronically determining a workpiece geometry from said electrical signals, said workpiece geometry determining step comprising the steps of;

(a) identifying a set of coordinates for a group of said plurality of picture elements associated with a specific feature of said workpiece geometry; and

(b) generating a mathematical equation from said set of picture element coordinates; and

electronically determining said process parameters from said workpiece geometry.

2. The method according to claim 1, wherein:

said step of generating an image includes the step of focusing electromagnetic energy received from said surface onto a sensor; and

said step of transducing said image into electrical signals further comprises the step of scanning said picture elements to generate a series of electrical pulses, the amplitude of each of said pulses being proportional to the intensity of electromagnetic energy associated with a corresponding picture element.

3. The method of claim 2, wherein:

said electromagnetic energy comprises light reflected from said workpiece surface;

said sensor comprises a photosensitive array within a television camera; and

said step of transducing said image into electrical signals is performed by said camera.

4. The method according to claim 2, wherein said feature is a workpiece edge.

5. The method according to claim 1, wherein said surface comprises the blade tip of a turbine blade.

6. In an automated welding system, a method for determining welding parameters from a workpiece surface, comprising the step of:

generating an image of said workpiece surface;

transducing said image into electrical signals, said transducing step comprising the step of dissecting said image into a plurality of picture elements;

electronically determining a workpiece geometry from said electrical signals, said workpiece geometry determining step comprising the steps of;

(a) identifying a set of coordinates for a group of said plurality of picture elements associated with a specific feature of said workpiece geometry; and

(b) generating a mathematical equation from said set of picture element coordinates; and

electronically determining said welding parameters from said workpiece geometry.

8. The method according to claim 6, wherein the step of electronically determining said welding parameters includes the step of electronically determining the amount of heat to be applied during said welding process.

9. The method according to claim 6, wherein the step of electronically determining said welding parameters includes the step of electronically determining the locations on said workpiece surface where heat will be applied during the welding process.

10. The method according to claim 6, wherein:

said step of generating an image includes the step of focusing electromagnetic energy received from said surface onto a sensor; and

said step of transducing said image into electrical signals further comprises the step of scanning said picture elements to generate a series of electrical pulses, the amplitude of each of said pulses being proportional to the intensity of electromagnetic energy associated with a corresponding picture element.

11. The method of claim 10, wherein:

said electromagnetic energy comprises light reflected from said workpiece surface;

said sensor comprises a photosensitive array within a television camera; and

said step of transducing said image into electrical signals is performed by said camera.

12. The method according to claim 6, wherein said feature is a workpiece edge.

7. In an automated welding system, a method for determining welding parameters from a workpiece surface, the steps comprising:

generating an image of said surface;

transducing said image into electrical signals;

electronically determining workpiece geometry from said electrical signals; and

electronically determining said welding parameters from said workpiece geometry, said welding parameter determining step comprising the step of electronically determining the amount of welding material to be applied to said workpiece surface.

13. In an automated welding system, a method for determining welding parameters from a blade tip of a turbine blade, comprising the steps of:

generating an image of said surface;

transducing said image into electrical signals;

electronically determining workpiece geometry from said electrical signals; and

electronically determining said welding parameters from said workpiece geometry.

14. A method for determining process parameters in automated system for performing build-up welding on the squealer tip walls of a turbine blade, said squealer tip walls having inner and outer edges, the steps comprising:

generating an image of the blade tip surface of said turbine blade;

transducing said image into electrical signals;

electronically determining the geometry of said blade tip from said electrical signals; and

electronically determining said process parameters from said blade tip geometry.

15. The method according to claim 14, wherein:

said step of determining blade tip geometry includes measuring the width of said squealer tip walls; and

said step of determining said process parameters includes the step of electronically determining the amount of welding material to be applied to the top surface of said squealer tip walls.

16. The method according to claim 15, wherein said step of determining process parameters further includes electronically determining the amount of heat to be applied during the welding process.

17. The method according to claim 14, wherein said step of determining process parameters includes the step of electronically determining the path along which heat will be applied during the welding process.

18. The method according to claim 17, wherein said path comprises the centerline of said squealer wall.

19. The method according to claim 14, wherein:

said step of generating an image includes the step of focusing electromagnetic energy received from said surface onto a sensor; and

said step of transducing said image into electrical signals includes dissecting said image into a plurality of picture elements and scanning said picture elements to generate a series of electrical pulses, the amplitude of each of said pulses being proportional to the intensity of electromagnetic energy associated with a corresponding picture element.

20. The method of claim 19, wherein:

said electromagnetic energy comprises light reflected from said workpiece surface;

said sensor comprises a photosensitive array within a television camera; and

said step of transducing said image into electrical signals is performed by said camera.

21. The method according to claim 19, wherein said step of determining blade tip geometry includes the steps of:

identifying the coordinates of a set of picture elements associated with the outer edge of said squealer wall;

generating a first mathematical equation from said coordinates, said equation defining the curve formed by said outer edge;

electronically determining the slope of said curve at selected coordinates;

generating a set of mathematical equations, each of said last-recited equations defining a line normal to said curve formed by said outer edge and intersecting said curve at one of said selected coordinates; and

measuring the width of said squealer tip walls by measuring the length of each of said lines between said outer edge and said inner edge.

22. The method according to claim 21, wherein said step of determining said process parameters includes the steps of:

electronically determining the amount of welding material to be applied to the top surface of said squealer tip walls;

electronically determining the amount to heat to be applied during the welding process;

electronically determining the midpoint of each of said normal lines; and

electronically determining the path along which heat will be applied during the welding process, said path intersecting the midpoints of each of said normal lines.