Communication Dans Un Congrès Année : 2025

A MobileViT-based Detection of Anomaly in Temperature of Nuclear Power Plant Core

Résumé

This paper presents a simple model based on MobileViT-v2 for temperature monitoring within a nuclear power plant. Specifically, we propose utilizing MobileNet-v2 to detect a critical accident: a total and instantaneous blockage. We model the temperature effects of such an event and train a MobileViT-v2 model for detection. The trained classifier's results are then used in a sequential procedure to detect blockage as quickly and reliably as possible. We compare the performance of two sequential detection methods, namely sliding-window and CUSUM, in terms of mean detection delay and probability of detection before a prescribed maximum detection delay. Experimental results, using actual temperature measurements from the Superphénix power station, demonstrate the effectiveness of the proposed detection method.

Fichier principal
Vignette du fichier
BTI_MobileVit_AD.pdf (1) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04884554 , version 1 (22-01-2025)

Licence

Identifiants

  • HAL Id : hal-04884554 , version 1

Citer

Rémi Cogranne. A MobileViT-based Detection of Anomaly in Temperature of Nuclear Power Plant Core. SPIE 10th International Conference on Multimedia and Image Processing (ICMIP 2025), Apr 2025, Okinawa, Japan, Japan. ⟨hal-04884554⟩
5 Consultations
5 Téléchargements

Partager

More