Inspection system and method for bond detection and validation of surface mount devices

• US 5,963,662 A
• Filed: 11/20/1996
• Issued: 10/05/1999
• Est. Priority Date: 08/07/1996
• Status: Expired due to Fees

• Current Assignee: Georgia Tech Research Corporation (University System of Georgia)
• Original Assignee: Georgia Tech Research Corporation (University System of Georgia)
• Inventors: Dar, Iqbal M., Sahinci, Erin, Newman, Kimberly E., Vachtsevanos, George J.
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Werner, Brian P.
• Application Number:
  US08/753,181
• Time in Patent Office: 1,049 Days
• Field of Search: 382/145, 382/147, 382/148, 382/149, 382/150, 348/164, 348/87, 348/126, 348/131, 348/166, 348/165, 356/51, 356/372, 356/237, 364/468.17, 364/557, 324/451, 324/501, 438/15, 438/16, 374/5, 374/10, 228/103, 228/105, 209/577, 250/330, 250/316.1, 250/332, 250/339.02, 250/339.14, 250/341.1, 250/341.6, 250/342, 29/407.04
• US Class Current: 382/150
• CPC Class Codes: G01N 2021/8867 using sequentially two or more inspection runs, e.g. coarse and fine, or detecting then analysing
• CPC Class Codes: G01N 21/88 Investigating the presence of flaws or contamination
• CPC Class Codes: G01N 21/95684 Patterns showing highly reflecting parts, e.g. metallic elements
• CPC Class Codes: G01N 25/72 Investigating presence of flaws
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/20036 Morphological image processing
• CPC Class Codes: G06T 2207/30152 Solder
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/0006 using a design-rule based approach

Abstract

A hybrid surface mount component inspection system which includes both vision and infrared inspection techniques to determine the presence of surface mount components on a printed wiring board, and the quality of solder joints of surface mount components on printed wiring boards by using data level sensor fusion to combine data from two infrared sensors to obtain emissivity independent thermal signatures of solder joints, and using feature level sensor fusion with active perception to assemble and process inspection information from any number of sensors to determine characteristic feature sets of different defect classes to classify solder defects.

Claims

1. A system for detecting solder joint defects on surface mount components on a printed wiring board, comprising:

a machine vision sensor that collects visual inspection information pertaining to a surface mount component, said visual inspection information used to develop programmed rectangular windows from which sub-images of said surface mount component are developed, said sub-images used to develop a one-dimensional vector corresponding to placement of said surface mount component on the printed wiring board, said one-dimensional vector having peaks and valleys, wherein said peaks represent solder joints and said valleys represent a substrate upon which said surface mount component is moumted;

at least one infrared sensor that collects thermal signature inspection information pertaining to a surface mount component; and

a processing means for processing said visual inspection information and said thermal signature inspection information in order to detect and classify said solder joint defects on said surface mount components on said printed wiring board, said processing means including a means for processing said one-dimensional vector corresponding to the placement of said surface mount component on the printed wiring board using a morphological filter, said processing means also including means for fusing the data from a plurality of said infrared sensors using data level sensor fusion to obtain emissivity independent thermal signatures of solder joints.

2. The system according to claim 1, wherein said processing means comprises a combinational logic circuit configured to perform said processing.

3. The system according to claim 1, wherein said processing means comprises a neural network configured to perform said processing.

4. The system according to claim 1, further comprising:

an additional infrared sensor; and

means for combining said thermal signature inspection information from said infrared sensor and said additional infrared sensor.

5. The system according to claim 4, wherein said infrared sensor and said additional infrared sensor provide an emissivity independent thermal signature.

6. A computer readable medium having a program for detecting solder joint defects on surface mount components on a printed wiring board, the program comprising:

means for receiving visual inspection information from a machine vision sensor, said visual inspection information used to develop programmed rectangular windows from which sub-images of said surface mount component are developed, said sub-images used to develop a one-dimensional vector corresponding to placement of said surface mount component on the printed wiring board, said one-dimensional vector having peaks and valleys, wherein said peaks represent solder joints amid said valleys represent a substrate upon which said surface mount component is mounted;

means for receiving thermal signature inspection information from at least one infrared sensor; and

means for processing said visual inspection information and said thermal signature inspection information resulting in the inspection of surface mount component solder joints on said surface mount components on said printed wiring board, said processing means including a means for processing said one-dimensional vector corresponding to the placement of said surface mount component on the printed wiring board using a morphological filter, said processing means also including means for fusing the data from a plurality of said infrared sensors using data level sensor fusion to obtain emissivity independent thermal signatures of solder joints.

7. The program according to claim 6, wherein said processing means comprises a combinational logic circuit configured to perform said processing.

8. The program according to claim 6, wherein said processing means comprises a neural network configured to perform said processing.

9. The program according to claim 6, further comprising:

means for receiving an additional thermal signature information from an additional infrared sensor; and

means for combining said thermal signature inspection information from said infrared sensor and said additional infrared sensor.

10. A system for combining and processing the complimentary nature of visual inspection information and thermal signature inspection information to increase the degree of probability of detecting a solder defect in an object, comprising:

a computer system which processes said inspection information, said inspection information including visual inspection information and thermal signature inspection information, said visual inspection information used to develop programmed rectangular windows from which sub-images of said surface mount component are developed, said sub-images used to develop a one-dimensional vector corresponding to placement of a surface mount component on a printed wiring board, said one-dimensional vector having peaks and valleys, wherein said peaks represent solder joints and said valleys represent a substrate upon which said surface mount component is mounted and said thermal signature inspection information obtained by fusing data from a plurality of said infrared sensors using data level sensor fusion to obtain enissivity independent thermal signatures of solder joints; and

a statistical sampling means for detecting said solder defect in said object, said statistical sampling means including a morphological filter for processing said one-dimensional vector.

11. The system of claim 10, further comprising a means for classifying said visual inspection information for comparison against a known good specimen.

12. The system of claim 10, further comprising a means for classifying said thermal signature inspection information for comparison against a known good specimen.

13. A method for detecting solder joint defects on surface mount components on a printed wiring board, comprising the steps of:

collecting visual inspection information and thermal signature inspection information, said visual inspection information used to develop programmed rectangular windows from which sub-images of said surface mount component are developed, said sub-images used to develop a one-dimensional vector corresponding to placement of said surface mount component on the printed wiring board, said one-dimensional vector having peaks and valleys, wherein said peaks represent solder points and said valleys represent a substrate upon which said surface mount component is mounted, said thermal signature inspection information obtained by fusing data from a plurality of infrared sensors using data level sensor fusion to obtain emissivity independent thermal signatures of solder joints; and

processing said visual inspection information and said thermal signature inspection information resulting in the inspection of surface mount component solder joints on said surface mount components on said printed wiring board, said processing step including the step of processing said one-dimensional vector corresponding to the placement of said surface mount component on the printed wiring board using a morphological filter, said processing step also including the step of fusing the data from a plurality of said infrared sensors using data level sensor fusion to obtain emissivity independent thermal signatures of solder points.

14. A system for detecting solder joint defects on surface mount components on a printed wiring board, comprising:

a machine vision sensor that collects visual inspection information pertaining to a surface mount component, said visual inspection information used to develop programmed rectangular windows from which sub-images of said surface mount component are developed, said sub-images used to develop a one-dimensional vector corresponding to placement of said surface mount component on the printed wiring board, said one-dimensional vector having peaks and valleys, wherein said peaks represent solder joints and said valleys represent a substrate upon which said surface mount component is mounted;

at least one infrared sensor that collects thermal signature inspection information pertaining to a surface mount component; and

logic configured to process said visual inspection information and said thermal signature inspection information in order to detect and classify said solder joint defects on said surface mount components on said printed wiring board, said processing means including means for processing said one-dimensional vector corresponding to the placement of said surface mount component on the printed wiring board using a morphological filter, said logic also configured to fuse the data from a plurality of said infrared sensors using data level sensor fusion to obtain emissivity independent thermal signatures of solder joints.

15. The system according to claim 14, wherein said logic comprises a combinational logic circuit configured to perform said processing.

16. The system according to claim 14, wherein said logic comprises a neural network configured to perform said processing.

17. The system according to claim 14, further comprising:

an additional infrared sensor; and

logic configured to combine said thermal signature inspection information from said infrared sensor and said additional infrared sensor.

18. The system according to claim 17, wherein said infrared sensor and said additional infrared sensor provide an emissivity independent thermal signature.