Model-based and data-driven prognosis of automotive and electronic systems

  • Authors:

  • Chaitanya Sankavaram;Bharath Pattipati;Anuradha Kodali;Krishna Pattipati;Mohammad Azam;Sachin Kumar;Michael Pecht

  • Affiliations:

  • Electrical and Computer Engineering, University of Connecticut, Storrs, CT;Electrical and Computer Engineering, University of Connecticut, Storrs, CT;Electrical and Computer Engineering, University of Connecticut, Storrs, CT;Electrical and Computer Engineering, University of Connecticut, Storrs, CT;Qualtech Systems Inc., Wethersfield, CT;Center for Advanced Life Cycle Engineering, University of Maryland, College Park, MD;Center for Advanced Life Cycle Engineering, University of Maryland, College Park, MD

  • Venue:
  • CASE'09 Proceedings of the fifth annual IEEE international conference on Automation science and engineering
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent advances in sensor technology, remote communication and computational capabilities, and standardized hardware/software interfaces are creating a dramatic shift in the way the health of vehicles is monitored and managed. Concomitantly, there is an increased trend towards the forecasting of system degradation through a prognostic process to fulfill the needs of customers demanding high vehicle availability. Prognosis is viewed as an add-on capability to diagnosis that assesses the current health of a system and predicts its remaining life based on sensed features that capture the gradual degradation in the operation of the vehicle. This paper discusses a hybrid model-based, data-driven and knowledge-based integrated diagnosis and prognosis framework, and applies it to automotive (suspension and battery systems) and on-board electronic systems.