Integrated model-based and data-driven fault detection and diagnosis approach for an automotive electric power steering system

Author

Ghimire, Rajeev ; Sankavaram, Chaitanya ; Ghahari, Alireza ; Pattipati, Krishna ; Ghoneim, Youssef ; Howell, Mark ; Salman, Mutasim

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Connecticut, Storrs, CT, USA

fYear

2011

fDate

12-15 Sept. 2011

Firstpage

70

Lastpage

77

Abstract

Integrity of electric power steering system is vital to vehicle handling and driving performance. Advances in electric power steering (EPS) system have increased complexity in detecting and isolating faults. In this paper, we propose a hybrid model-based and data-driven approach to fault detection and diagnosis (FDD) in an EPS system. We develop a physics-based model of an EPS system, conduct fault injection experiments to derive fault-sensor measurement dependencies, and investigate various FDD schemes to detect and isolate the faults. Finally, we use an SVM regression technique to estimate the severity of faults.

Keywords

automotive components; electric sensing devices; electrical engineering computing; fault diagnosis; regression analysis; steering systems; support vector machines; EPS system; FDD schemes; SVM regression technique; automotive electric power steering system; data-driven fault detection; fault diagnosis approach; fault injection; fault-sensor measurement dependency; integrated model-based detection; physics-based model; DC motors; Mathematical model; Power systems; Support vector machines; Torque; Vehicles; Wheels; Electric power steering (EPS); SVM regression; double lane change maneuver; multiway partial least squares (MPLS); support vector machines(SVM); torque sensor;

fLanguage

English

Publisher

ieee

Conference_Titel

AUTOTESTCON, 2011 IEEE

Conference_Location

Baltimore, MD

ISSN

1088-7725

Print_ISBN

978-1-4244-9362-3

Type

conf

DOI

10.1109/AUTEST.2011.6058760

Filename

6058760