A Hybrid Model-Data Vehicle Sensor and Actuator Fault Detection and Diagnosis System

This paper proposes a hybrid model/data fault detection and diagnosis system applicable to any vehicle sensor and actuator. This system works based on comparing the measurements of a target sensor or the desired control actions of a target actuator with their estimations. These estimations are obtained by a hybrid estimator developed based on the integration of model-based and data-driven estimators leveraging the strength of each estimator. Considering the weakness of pure data-driven estimators in confronting unknown conditions, a self-updating dataset is proposed to learn new cases. After fault detection, the estimations of the hybrid estimator are used to reconstruct sensor data or find the level of actuator failure. To evaluate the performance of the proposed hybrid fault detection and diagnosis system, it is applied to a vehicle’s lateral acceleration sensor and traction motor. The results of experimental tests conducted on an all-wheel-drive vehicle show the effectiveness of the algorithm in detecting and quantifying faults in the target component.

• Record URL:
  • https://doi.org/10.1109/TITS.2024.3370869
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2024, IEEE.
• Authors:
  • Zabihi, Mehdi
  • 0000-0001-7777-4061
  • Mehrizi, Reza Vallollahi
  • 0000-0002-6601-411X
  • Kasaiezadeh, Alireza
  • Pirani, Mohammad
  • 0000-0003-2677-2140
  • Khajepour, Amir
  • 0000-0002-1998-6100
• Publication Date: 2024-7

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 8121-8133
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 25
  • Issue Number: 7
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Actuators; Diagnosis; Fault location; Sensors; Vehicle components
• Subject Areas: Highways; Maintenance and Preservation; Vehicles and Equipment;

Filing Info

• Accession Number: 01935632
• Record Type: Publication
• Files: TRIS
• Created Date: Oct 31 2024 9:20AM