# US 2026/0002894 A1 · Radiographic inspection of mechanical fasteners

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

- Number: US 2026/0002894 A1
- Document ID: US20260002894A1
- Status: Published application
- Kind: A1
- Application number: 18/758,391
- Filed: 2024-06-28
- Published: 2026-01-01
- Earliest claimed: 2024-06-28
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Sk Sahariyaz Zaman; Madhurima Bandyopadhyay; Chandrashekhar Chandrashekhar; Md Shaheed Ali; Ali Azad; Umar Momen
- Web page: https://patentgrep.com/patent/US20260002894A1

## CPC

- G01N 23/18: Investigating the presence of flaws defects or foreign matter
- G01N 23/04: and forming images of the material
- G01N 2223/401: image processing
- G01N 2223/408: display on monitor
- G01N 2223/422: windows within the image
- G01N 2223/646: flaws, defects
- 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)

## Abstract

A system for automated inspection of an installed fastener includes a radiographic generator, a radiographic sensor, and a computer device. The radiographic generator is operable for directing scanning beams of electromagnetic radiation, e.g., x-rays, toward a workpiece having the installed fastener, for instance a rivet. The radiographic sensor collects a radiographic image of a workpiece inclusive of the installed fastener. The computer device processes the image via one or more trained characterization models to localize the installed fastener within the image, and identifies a presence or absence of a defect in the installed fastener. The computer device also characterizes a quality of the installed fastener based on the presence or absence of the defect, and thereafter generates an inspection report indicative of the quality of the fastener. This may include generating an annotated or color-coded image of the installed fastener.

## Claims

### Claim 1

A system for automated inspection of an installed fastener, the system comprising:
a radiographic generator operable for directing beams of electromagnetic radiation toward a workpiece having the installed fastener;
a radiographic image sensor configured to collect a radiographic image of the workpiece and the installed fastener; and
a computer device in communication with the radiographic image sensor, wherein the computer device is configured to process the radiographic image via one or more trained characterization models to thereby localize the installed fastener within the radiographic image, identify a presence or absence of a defect in the installed fastener, characterize a quality of the installed fastener based on the presence or absence of the defect, and generate an inspection report indicative of the quality of the fastener, the inspection report including an annotated image of the installed fastener.

### Claim 2 (depends on 1)

The system of claim 1, wherein the installed fastener is part of a population of installed fasteners on the workpiece, and wherein the computer device is configured to generate a composite image of the workpiece, the composite image visually identifying the installed fasteners that are defected fasteners.

### Claim 3 (depends on 2)

The system of claim 2, wherein computer device is configured to output a bounding box around at least the defected fasteners, the bounding box forming a color-coded graphic of the defected fasteners as part of the annotated image.

### Claim 4 (depends on 3)

The system of claim 3, wherein the bounding box is a red bounding box that individually surrounds each respective one of the defected fasteners.

### Claim 5 (depends on 3)

The system of claim 3, wherein a representation of a defect is displayed within the bounding box of the defected fasteners.

### Claim 6 (depends on 1)

The system of claim 1, wherein the one or more trained characterization models form a population of representative defected fasteners and a population of representative non-defected fasteners.

### Claim 7 (depends on 1)

The system of claim 1, wherein the radiographic generator includes an x-ray generator.

### Claim 8 (depends on 7)

The system of claim 7, wherein the installed fastener is a solid shank rivet, and wherein the system is configured to inspect the solid shank rivet via the x-ray generator.

### Claim 9

A method for inspecting an installed fastener in a workpiece, the method comprising:
generating scanning beams of electromagnetic radiation via a radiographic generator;
directing the scanning beams of electromagnetic radiation toward the workpiece having the installed fastener;
collecting a radiographic image of the workpiece including the installed fastener via a radiographic image sensor; and
processing the radiographic image via one or more trained characterization models, including:
localizing the installed fastener within the radiographic image;
identifying a presence or absence of a defect in the installed fastener;
characterizing a quality of the installed fastener based on the presence or absence of the defect; and
generating an inspection report, via a computer device, that is indicative of the quality of the fastener, the inspection report including an annotated image of the installed fastener.

### Claim 10 (depends on 9)

The method of claim 9, wherein the installed fastener is part of a population of installed fasteners on a workpiece, further comprising:
generating a composite image of the workpiece via the computer device, the composite image visually identifying the installed fasteners that are defected fasteners.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
outputting a bounding box around at least the defected fasteners, via the computer device, the bounding box forming a color-coded graphic of the defected fasteners as part of the annotated image.

### Claim 12 (depends on 11)

The method of claim 11, wherein outputting the bounding box around at least the defected fasteners includes outputting a red bounding box that individually surrounds each respective one of the defected fasteners.

### Claim 13 (depends on 12)

The method of claim 12, wherein outputting the bounding box around at least the defected fasteners includes displaying a representation of a defect within the red bounding box.

### Claim 14 (depends on 11)

The method of claim 11, wherein processing the radiographic image via the one or more trained characterization models includes using the one or more trained characterization models as a population of representative defected fasteners and a population of representative non-defected fasteners.

### Claim 15 (depends on 11)

The method of claim 11, wherein generating scanning beams of electromagnetic radiation via the radiographic generator includes generating x-ray scanning beams via an x-ray generator.

### Claim 16 (depends on 11)

The method of claim 11, wherein the installed fastener is a solid shank rivet, and wherein characterizing the quality of the installed fastener based on the presence or absence of the defect includes characterizing a crack, porosity, or cavitation in the solid shank rivet.

### Claim 17 (depends on 16)

The method of claim 16, wherein the workpiece includes a sheet metal panel, the method further comprising: installing the solid shank rivet into the sheet metal panel.

### Claim 18

A computer device for automated inspection of a population of installed rivets, comprising:
a processor; and
a non-transitory computer-readable storage medium on which is written instructions, wherein the instructions are executable by the processor to cause the computer device to:
receive x-ray images of the installed rivets from an x-ray sensor;
process the x-ray images via one or more trained characterization models to thereby localize the installed rivets within the x-ray images;
identify a presence or absence of a defect in each of the installed rivets;
characterize a quality of each of the installed rivets based on the presence or absence of the defect; and
generate an inspection report indicative of the quality of each of the installed rivets, the inspection report including a respective color-coded bounding boxes around each of the installed rivets, the color-coded bounding box forming a color-coded graphic of defected rivets and non-defected rivets.

### Claim 19 (depends on 18)

The computer device of claim 18, wherein the instructions are executable by the processor to cause the computer device to display a representation of a defect within the bounding box of the defected rivets.

### Claim 20 (depends on 19)

The computer device of claim 19, wherein the instructions are executable by the processor to cause the computer device to display the representation of the defect as a crack, porosity, or cavitation in the defected rivets.
