# US 2024/0177877 A1 · Process For Aiding The Detection Of Migrating Bodies Within A Fuel Assembly

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

- Number: US 2024/0177877 A1
- Document ID: US20240177877A1
- Status: Published application
- Kind: A1
- Application number: 18/523,162
- Filed: 2023-11-29
- Published: 2024-05-30
- Earliest claimed: 2022-11-29
- Assignees: Electricle de France
- Applicants: Electricle de France
- Inventors: Fabien Dory
- Web page: https://patentgrep.com/patent/US20240177877A1

## CPC

- G21C 3/334: Assembling {, maintenance or repair of} the bundles {(assembling, maintenance or repair of other reactor components G21C19/207)}
- G21C 17/06: Devices or arrangements for monitoring or testing fuel or fuel elements outside the reactor core, e.g. for burn-up, for contamination (G21C17/08, G21C17/10 take precedence; detecting leaking fuel elements during reactor operation G21C17/04)
- G06T 7/0008: {checking presence/absence}
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06V 20/05: Underwater scenes
- G21C 3/3206: {Means associated with the fuel bundle for filtering the coolant, e.g. nozzles, grids}
- Y02E 30/30: Nuclear fission reactors
- G21C: NUCLEAR REACTORS (fusion reactors, hybrid fission-fusion reactors G21B; nuclear explosives G21J)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

## Abstract

The invention relates to a process for aiding the detection of migrating bodies within a fuel assembly of a nuclear power plant and more particularly on the anti-debris grid of the lower end piece of said assembly, during which at least one camera is controlled in the direction of said assembly and the stream of images recorded by said at least one camera is directed towards a man-machine interface which comprises at least one screen allowing a first operator to view said stream of video images, characterized in that it comprises a first step of detecting, using an image recognition algorithm, said migrating bodies, as well as at least a second step of alerting said operator if said algorithm has detected the potential presence of at least one migrating body.

## Claims

### Claim 1

A process for aiding the detection of migrating bodies within a fuel assembly of a nuclear power plant and more particularly on the anti-debris grid of the lower end piece of the fuel assembly, during which at least one camera is controlled in the direction of the fuel assembly and the stream of video images recorded by the at least one camera is directed towards a man-machine interface which comprises at least one screen allowing a first operator to view said stream of video images, wherein the process comprises a first step of detecting, using an image recognition algorithm, the migrating bodies, and at least a second step of alerting the first operator if the image recognition algorithm has detected the potential presence of at least one migrating body.

### Claim 2 (depends on 1)

The process according to claim 1, wherein the second step comprises the triggering of an audible alert and/or a visual alert on the screen, of the location where the migrating body is potentially placed, and/or the automatic generation of an inspection report.

### Claim 3 (depends on 2)

The process according to claim 2, wherein, when the image recognition algorithm has detected the potential presence of at least one migrating body, the corresponding video file and the file(s) of detection(s) carried out by the image recognition algorithm are stored and it is (they are) addressed to a second operator with a temporal indication, in the video file, of the instant(s) at which one or more migrating body (bodies) was (were) potentially detected, the second operator validating the presence or lack of presence of at least one migrating body).

### Claim 4 (depends on 3)

The process according to claim 3, wherein the file(s) of detection are transmitted to a third operator who definitively validates the presence or lack of presence of at least one migrating body.

### Claim 5 (depends on 3)

The process according to claim 3, wherein said process comprises an automatic learning step for detecting migrating bodies when the second operator has validated the lack of presence of a migrating body.

### Claim 6 (depends on 3)

The process according to claim 3, wherein use is made of a “convolutional neural network” image recognition software, which is trained on a learning base made up of archives of videos of migrating bodies, the learning base being enriched each time the “convolutional neural network” image recognition software commits a detection error, this detection error having been validated by the second and/or the third operator.

### Claim 7 (depends on 3)

The process according to claim 3, wherein the temporal indication has the shape of at least one bar displayed on the timeline of the video.

### Claim 8 (depends on 4)

The process according to claim 4, wherein it comprises an automatic learning step for detecting migrating bodies when the third operator has validated the lack of presence of a migrating body.
