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.
Origine | Fichiers produits par l'(les) auteur(s) |
---|---|
licence |