# US 2025/0144749 A1 · Method for quality control of a welding joint between a pair of ends of conducting elements of an inductive winding of a stator

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0144749 A1
- Document ID: US20250144749A1
- Status: Published application
- Kind: A1
- Application number: 18/835,488
- Filed: 2023-02-07
- Published: 2025-05-08
- Earliest claimed: 2022-02-07
- Assignees: ATOP S.p.A.
- Applicants: Atop S.P.A.
- Inventors: Massimiliano GIACHI; Emanuele ANGELINI
- Web page: https://patentgrep.com/patent/US20250144749A1

## CPC

- B23K 31/125: {Weld quality monitoring}
- G01N 21/95: characterised by the material or shape of the object to be examined (G01N21/89 - G01N21/91, G01N21/94 take precedence)
- G01N 21/9515: {Objects of complex shape, e.g. examined with use of a surface follower device (measuring contours and curvatures G01B11/24)}
- G01N 21/956: Inspecting patterns on the surface of objects {(contactless testing of electronic circuits G01R31/308; testing currency G07D; manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20)}
- G01N 21/95684: {Patterns showing highly reflecting parts, e.g. metallic elements}
- G01N 33/207: Welded or soldered joints; Solderability
- G06T 7/0004: {Industrial image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/50: Depth or shape recovery
- G06T 7/60: Analysis of geometric attributes
- G06T 7/66: of image moments or centre of gravity
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 7/73: using feature-based methods
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- B23K 2101/38: Conductors
- G01N 2021/8887: {based on image processing techniques}
- G01N 2203/0296: Welds
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/20068: Projection on vertical or horizontal image axis
- G06T 2207/20212: Image combination
- G06T 2207/20224: Image subtraction
- G06T 2207/30108: Industrial image inspection
- G06T 2207/30136: Metal
- G06T 2207/30152: Solder
- G06T 2207/30164: Workpiece; Machine component
- G06T 2219/008: Cut plane or projection plane definition
- B23K: SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for quality control of a welding joint between a pair of ends of conducting elements of an inductive winding of a stator, the method being performed by a computer and comprising the steps that consist in: acquiring a 3D reconstruction of the welding joint; extracting a white 2D grayscale blob area from the 3D reconstruction of the welding join; calculating a center of mass of the 2D grayscale blob area; extracting a plurality of profiles from the 3D reconstruction of the welding joint); searching for and identifying bare zones of the welding joint by analyzing one by one the profiles of the 3D reconstruction; and calculating a bare area of the welding joint by summing the bare zones identified by the analysis of the profiles of the 3D reconstruction.

## Claims

### Claim at position 1

1-16. (canceled)

### Claim 17

A method for quality control of a welding joint between a pair of ends of conducting elements of an inductive winding of a stator, said method being performed by a computer, comprising the steps of:
acquiring a 3D reconstruction of said welding joint;
extracting a white 2D grayscale blob area from said 3D reconstruction of said welding joint, by transversely sectioning said 3D reconstruction with a cutting plane that is arranged at a cutting distance from a peak of said 3D reconstruction, said cutting distance being chosen so that said cutting plane is further downward than a base of said welding joint, and assigning a white color to the area of said 3D reconstruction above said cutting plane in order to determine said 2D grayscale blob area;
calculating a center of mass of said 2D grayscale blob area in order to determine a rotation axis orthogonal to said cutting plane and passing through said center of mass;
extracting a plurality of profiles from said 3D reconstruction of said welding joint, by longitudinally sectioning said 3D reconstruction with a plurality of planes that are orthogonal to said cutting plane, proceeding in rotation about said rotation axis, each orthogonal plane comprising a respective profile of said 3D reconstruction;
searching for and identifying bare zones of said welding joint by analyzing one by one profile portions of said plurality of profiles of said 3D reconstruction, calculating for each profile portion a respective straight interpolation line on points that constitute said profile portion, said profile portion being identified as a bare zone if said respective straight interpolation line has an angular coefficient with an absolute value smaller than or equal to 10°; and
calculating a bare area of said welding joint by summing said bare zones identified by the analysis of said plurality of profiles of said 3D reconstruction, a contribution of each bare zone to said bare area being equal to an arc of an annulus comprised between said respective profile portion in which said bare zone has been identified and a following profile portion from the analysis of said plurality of profile portions.

### Claim 18 (depends on 17)

The method according to claim 17, further comprising the step of calculating a welded area of said welding joint by subtracting said bare area of said welding joint from said 2D grayscale blob area.

### Claim 19 (depends on 17)

The method according to claim 17, further comprising the step of classifying said welding joint according to a respective welding quality level.

### Claim 20 (depends on 17)

The method according to claim 17, wherein said step of extracting said white 2D grayscale blob area further comprises the step of orthogonally projecting an upper portion of said 3D reconstruction of said welding joint on said cutting plane.

### Claim 21 (depends on 17)

The method according to claim 17, wherein, in said step of extracting said plurality of profile portions, said plurality of orthogonal planes longitudinally sectioning said 3D reconstruction of said welding joint are uniformly distributed in breadth, by rotating with respect to each other through a breadth until a total breadth of no more than 179° is reached.

### Claim 22 (depends on 17)

The method according to claim 17, wherein, in said step of searching for and identifying bare zones of said welding joint, a sequence of inspection windows, arranged side by side one after the other, each one of preset width less than the width of said profile portion, slides along each profile portion of said 3D reconstruction, said profile portions being contained in respective inspection windows.

### Claim 23 (depends on 17)

The method according to claim 17, wherein said step of searching for and identifying bare zones of said welding joint further comprises the steps of arranging an exclusion plane which transversely sections said 3D reconstruction at an exclusion distance from said peak of said 3D reconstruction, and calculating, for each profile portion, a respective average height of said points that constitute said profile portion, excluding said profile portion if said respective average height is greater than the height of said exclusion plane.

### Claim 24 (depends on 17)

The method according to claim 17, wherein said step of searching for and identifying bare zones of said welding joint further comprises the step of counting said bare zones of said welding joint, all of said welding joint being identified as a bare area if the number of said bare zones is greater than a percentage of the number of analyzed profile portions.

### Claim 25 (depends on 17)

The method according to claim 17, wherein, in said step of calculating a bare area of said welding joint by summing said bare zones, a contribution of a bare zone arranged at the beginning or at an end of said profile portion to said bare area is weighted on a filling percentage of a respective inspection window.

### Claim 26 (depends on 17)

The method according to claim 17, wherein said step of acquiring said 3D reconstruction of said welding joint is performed with said pair of ends of conducting elements oriented vertically and with the base of said ends pointing upward.

### Claim 27 (depends on 17)

The method according to claim 17, wherein said welding joint between said pair of ends of conducting elements and said 3D reconstruction of said welding joint) have a same orientation with respect to a common geometric reference system.

### Claim 28 (depends on 17)

The method according to claim 17, wherein said step of acquiring said 3D reconstruction of said welding joint is performed with a Fringe Pattern Projection technique.

### Claim 29 (depends on 17)

The method according to claim 17, wherein said step of acquiring said 3D reconstruction of said welding joint is performed using a 3D camera or a 3D laser scanning device.

### Claim 30 (depends on 17)

A computer comprising means configured to perform the steps of the method according to claim 17.

### Claim 31 (depends on 17)

A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method according to claim 17.

### Claim 32 (depends on 17)

A computer-readable storage medium comprising instructions which, when the instructions are executed by a computer, cause the computer to carry out the steps of the method according to claim 17.
