NON-DESTRUCTIVE ALUMINUM WELD QUALITY ESTIMATOR

• US 20150069112A1
• Filed: 09/12/2013
• Published: 03/12/2015
• Est. Priority Date: 09/12/2013
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: FILEV, Dimitar Petrov, ABOU-NASR, Mahmoud A., HETRICK, Elizabeth Therese, MOISION, William C.
• Granted Patent: US 9,314,878 B2
• Time in Patent Office: Days
• US Class Current: 228/102
• CPC Class Codes: B23K 11/10 Spot welding; Stitch welding
• CPC Class Codes: B23K 11/115 by means of two electrodes placed opposite one another on both sides of the welded parts
• CPC Class Codes: B23K 11/185 of aluminium or aluminium alloys
• CPC Class Codes: B23K 11/253 the measured parameter being a displacement or a position
• CPC Class Codes: B23K 11/255 the measured parameter being a force B23K11/253 takes precedence
• CPC Class Codes: B23K 11/257 the measured parameter being an electrical current
• CPC Class Codes: B23K 11/258 the measured parameter being a voltage
• CPC Class Codes: B23K 31/125 Weld quality monitoring

Abstract

An aluminum welding system includes a welding machine configured to weld a workpiece with an aluminum nugget and a measurement device configured to measure an attribute of at least one of the aluminum nugget and a welding process. The system further includes a processing device configured to output a weld quality signal representing a quality of an aluminum weld based at least in part on the attribute measured. A method includes measuring an attribute of at least one of an aluminum nugget forming a joint of a workpiece and a welding process, determining a quality of an aluminum weld based at least in part on the attribute measured, and outputting a weld quality signal representing the determined quality.

Claims

1. An aluminum welding system comprising:

a welding machine configured to weld a workpiece with an aluminum nugget;

a measurement device configured to measure an attribute of at least one of the aluminum nugget and a welding process; and

a processing device configured to output a weld quality signal representing a quality of an aluminum weld based at least in part on the attribute measured.

2. The system of claim 1, wherein the processing device includes a dynamic neural network configured to generate the weld quality signal.

3. The system of claim 1, wherein the weld quality signal represents a likelihood that the quality of the aluminum weld meets at least one predetermined criterion.

4. The system of claim 1, wherein the processing device is configured to iteratively determine the quality of the aluminum weld over a predetermined period of time.

5. The system of claim 1, wherein the processing device is configured to:

determine the quality of the weld; and

generate the weld quality signal based at least in part on the determined quality of the weld.

6. The system of claim 1, wherein the processing device is configured to control operation of the welding machine.

7. The system of claim 6, wherein the processing device is configured to adjust a setting of the welding machine to improve the quality of the aluminum weld if the weld quality signal represents a poor weld.

8. The system of claim 6, wherein the processing device is configured to reject the weld if the quality of the aluminum weld is below a predetermined threshold.

9. The system of claim 8, wherein the processing device is configured to determine whether the quality of the aluminum weld can be improved.

10. The system of claim 9, wherein the processing device is configured to reject the aluminum nugget if the quality of the aluminum weld cannot be improved.

11. A method comprising:

measuring an attribute of at least one of an aluminum nugget forming a joint of a workpiece and a welding process;

determining a quality of an aluminum weld based at least in part on the attribute measured; and

outputting a weld quality signal representing the determined quality.

12. The method of claim 11, further comprising generating the weld quality signal with a dynamic neural network.

13. The method of claim 11, wherein the weld quality signal represents a likelihood that the quality of the aluminum weld meets at least one predetermined criterion.

14. The method of claim 11, wherein the quality of the aluminum weld is iteratively determined over a predetermined period of time.

15. The method of claim 11, further comprising generating the weld quality signal based at least in part on the determined quality of the weld.

16. The method of claim 11, further comprising controlling operation of a welding machine based at least in part on the determined quality of the aluminum weld.

17. The method of claim 16, wherein controlling operation of the welding machine includes adjusting a setting of the welding machine to improve the quality of the aluminum weld if the weld quality signal represents a poor weld.

18. The method of claim 16, further comprising rejecting the weld if the quality of the aluminum weld is below a predetermined threshold.

19. The method of claim 18, further comprising:

determining whether the quality of the aluminum weld can be improved; and

rejecting the aluminum nugget if the quality of the aluminum weld cannot be improved.

20. An aluminum welding system comprising:

a welding machine configured to weld a workpiece with an aluminum nugget;

a measurement device configured to measure an attribute of at least one of the aluminum nugget and a welding process; and

a processing device configured to generate and output a weld quality signal representing a quality of an aluminum weld based at least in part on the attribute measured and control operation of the welding machine based at least in part on the weld quality signal,

wherein the processing device includes a dynamic neural network configured to generate the weld quality signal and wherein the weld quality signal represents a likelihood that the quality of the aluminum weld meets at least one predetermined criterion.