Optimization of Sensor Configurations for Fault Identification in Smart Buildings - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Optimization of Sensor Configurations for Fault Identification in Smart Buildings

Résumé

In predictive maintenance an important problem is to optimize the quantity of information to be transmitted at the control center to guarantee reliable fault detection while limiting sensor power consumption. This problem relies directly on the sensor configurations (e.g., sampling rate, coding, quantization) and the fault detection algorithm. To address this question, we introduce a codesign framework and an algorithm for joint optimization of the sensor configurations and the accuracy of the fault detection classifier. In a use case based on a dataset consisting of multiple sensor measurements and heating power levels known as the Twin House Experiment, we show that our algorithm can find efficient tradeoffs between sensor power consumption and classifier accuracy.
Fichier principal
Vignette du fichier
Ahmad_ICASSP_2023.pdf (331.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04361063 , version 1 (22-12-2023)

Licence

Paternité

Identifiants

Citer

Naveed Ahmad, Malcolm Egan, Jean-Marie Gorce, Jilles Dibangoye, Frédéric Le Mouël. Optimization of Sensor Configurations for Fault Identification in Smart Buildings. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, United States. pp.1-5, ⟨10.1109/ICASSP49357.2023.10097223⟩. ⟨hal-04361063⟩
20 Consultations
8 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More