Analysis of weld image to determine weld quality

• US 6,414,261 B1
• Filed: 11/16/2000
• Issued: 07/02/2002
• Est. Priority Date: 11/16/2000
• Status: Expired due to Fees

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Maetschke, Stefan R.
• Primary Examiner(s): Shaw, Clifford C.
• Application Number:
  US09/714,091
• Time in Patent Office: 593 Days
• Field of Search: 219/109, 219/110, 250/358.1, 374/124, 700/212
• US Class Current: 219/109
• CPC Class Codes: B23K 11/252 using digital means

Abstract

A system and method of determining the quality of a spot weld based on a set of image data includes separating the weld data from the background data and estimating a diameter of a weld (e.g., the nugget diameter of a spot weld) based on the weld data. The image data (e.g., a digital image) represents an image of the weld and includes weld data and background data. The estimation indicates the quality of the weld. In one embodiment, the surface brightness of the image data attributable to the spot weld is used to estimate the inner diameter of the spot weld.

Claims

1. A method of determining a measure of the quality of a spot weld based on a set of image data representing an image of the spot weld, wherein the image data includes weld data and background data, comprising:

identifying the image data into a first data set and a second data set, the first data set taken to be weld data and the second data set taken to be background data;

estimating an inner diameter of the spot weld based on the weld data, whereby the estimation provides a measure of the quality of the spot weld;

wherein, the image data include gray-scale values;

wherein, the step of estimating includes calculating the surface brightness and size of the spot weld based on the weld data; and

wherein the step of calculating includes summing the gray-scale values associated with the weld data.

2. The method of claim 1, further comprising acquiring the image data using a digital video camera.

3. The method of claim 1, further comprising providing the image data across an internet protocol network.

4. A method of determining a measure of the quality of a spot weld based on a set of image data representing an image of the spot weld, wherein the image data includes weld data and background data, comprising:

identifying the image data into a first data set and a second data set, the first data set taken to be weld data and the second data set taken to be background data;

estimating an inner diameter of the spot weld based on the weld data, whereby the estimation provides a measure of the quality of the spot weld;

wherein, the image data include gray-scale values;

wherein, the step of identifying includes;

determining the mean gray-scale value of the image data;

comparing the gray-scale of each image data to the mean gray-scale value;

identifying each image data into the first data set or the second data set based on the comparison;

generating binary image data based on the image data, wherein the binary image data indicates a first binary logical value if the gray-scale of the image data is above the mean gray-scale value and the binary image data indicates a second binary logical value if the gray-scale of the image data is below the mean gray-scale value; and

eroding the binary image in at least two passes.

5. The method of claim 4, wherein the step of eroding generates mask image data, further comprising summing the gray-scale values of the mask image data to estimate the inner diameter of the spot weld.

6. A system for determining the quality of a weld, comprising:

a video camera configured to acquire a set of image data representing an image of the weld;

a computer program embodied on a computer-readable medium, wherein the computer program is configured to receive the image data, identify weld data in the image data, and estimate a diameter of the weld based on the weld data, whereby the diameter of the weld indicates the quality of the weld;

wherein the image data include gray-scale values; and

wherein the computer program is configured to estimate the diameter of the weld by summing the gray-scale values associated with the weld data.

7. The system of claim 6, wherein the diameter is an inner diameter of a spot weld.

8. The system of claim 6, wherein the video camera is a digital video camera configured to acquire a set of digital image data.

9. The system of claim 6, wherein the computer program is configured to determine the mean gray-scale value of the image data, compare the gray-scale of each image data to the mean gray-scale value, and identify each image data as weld data or background based on the comparison.

10. The system of claim 6, wherein the computer program is configured to generate display data representative of the quality of the weld.

11. The system of claim 6, wherein the computer program is operable on a computer in communication with the video camera across an internet protocol network.

12. A system for determining the quality of a weld, comprising:

a video camera configured to acquire a set of image data representing an image of the weld;

a computer program embodied on a computer-readable medium, wherein the computer program is configured to receive the image data, identify weld data in the image data, and estimate a diameter of the weld based on the weld data, whereby the diameter of the weld indicates the quality of the weld;

wherein, the image data include gray-scale values;

wherein, the computer program is configured to determine the mean gray-scale value of the image data, compare the gray-scale of each image data to the mean gray-scale value, and identify each image data as weld data or background based on the comparison; and

wherein the computer program is configured to generate a binary image of the image data based on the comparison, wherein the binary image indicates a logical 1 if the gray-scale of the image data is above the mean gray-scale value and a logical 0 if the gray-scale of the image data is below the mean gray-scale value, wherein the computer program is configured to generate eroded image data based on the binary image, wherein the eroded image data includes remaining data points, and wherein the computer program is configured to sum the gray-scales of the remaining data points, whereby the sum is representative of the diameter of the weld.

13. The computer program embodied on a computer-readable medium for analyzing a set of image data representing an image of a weld, wherein the image data includes weld data and background data, comprising:

means for separating the weld data from the background data; and

means for calculating the surface brightness of the spot weld based on the weld data, whereby the surface brightness indicates the quality of the weld;

Wherein, the means for calculating includes means for estimating an inner diameter of the spot weld based on the weld data; and

wherein the means for calculating includes means for summing gray-scale values associated with the weld data.

14. The computer program of claim 13, wherein the means for separating includes:

means for determining the mean gray-scale value of the image data;

means for comparing the gray-scale of each image data to the mean gray-scale value; and

means for identifying each image data as weld data or background data based on the comparison.

15. A computer program embodied on a computer-readable medium for analyzing a set of image data representing an image of a weld, wherein the image data includes weld data and background data, comprising:

means for separating the weld data from the background data;

means for calculating the surface brightness of the spot weld based on the weld data, whereby the surface brightness indicates the quality of the weld;

wherein, the means for separating includes;

means for determining the mean gray-scale value of the image data;

means for comparing the gray-scale of each image data to the mean gray-scale value;

means for identifying each image data as weld data or background data based on the comparison;

wherein the means for identifying includes;

means for generating binary image data based on the image data, wherein the binary image data indicates a logical 1 if the gray-scale of the image data is above the mean gray-scale value and a logical 0 if the gray-scale of the image data is below the mean gray-scale value; and

means for eroding the binary image in two passes.

16. The computer program of claim 15, wherein the means for eroding generates a mask image, further comprising means for summing the gray-scale values of the masked image to estimate the inner diameter of the spot weld.

17. The computer program of claim 15, further comprising means for receiving the image data from an internet protocol network.