We propose a novel data-driven virtual sensor architecture to reconstruct an unmeasurable scheduling signal of a parameter-varying system from input/output measurements. The key idea is to train and feed an Artificial Neural Network (ANN) with input/output measurements and with data generated by processing such measurements through a bank of linear observers. Special attention is paid to the design of both the ANN and the feature extraction mechanism to keep the architecture as lightweight as possible, so that the resulting virtual sensor can be easily implemented in embedded hardware platforms. As a special case, the proposed virtual sensor can be used for hidden mode reconstruction of switched linear systems. Applications of the proposed approach are geared towards fault detection and isolation, predictive maintenance, and gain-scheduling control.

Learning virtual sensors for estimating the scheduling signal of parameter-varying systems

Masti, Daniele;A. Bemporad
2019-01-01

Abstract

We propose a novel data-driven virtual sensor architecture to reconstruct an unmeasurable scheduling signal of a parameter-varying system from input/output measurements. The key idea is to train and feed an Artificial Neural Network (ANN) with input/output measurements and with data generated by processing such measurements through a bank of linear observers. Special attention is paid to the design of both the ANN and the feature extraction mechanism to keep the architecture as lightweight as possible, so that the resulting virtual sensor can be easily implemented in embedded hardware platforms. As a special case, the proposed virtual sensor can be used for hidden mode reconstruction of switched linear systems. Applications of the proposed approach are geared towards fault detection and isolation, predictive maintenance, and gain-scheduling control.
2019
978-1-7281-2803-0
File in questo prodotto:
File Dimensione Formato  
08798519.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 425.37 kB
Formato Adobe PDF
425.37 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
med19_virtual_sensors.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Creative commons
Dimensione 403.89 kB
Formato Adobe PDF
403.89 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11771/13291
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
social impact