Title :
Identification of a nonlinear MIMO IC engine model during I/M240 driving cycle for on-board diagnosis
Author :
Luh, Guan-Chun ; Rizzoni, Giorgio
Author_Institution :
Center for Automotive Res., Ohio State Univ., Columbus, OH, USA
fDate :
29 June-1 July 1994
Abstract :
This paper presents application of advanced modelling techniques to construct engine models for the detection and isolation of incipient faults. The models are valid over the range in which the engine operates during execution of the Environmental Agency Inspection and Maintenance 240 cycle. A nonlinear "black-box" engine model is derived using the NARMAX (nonlinear autoregressive moving average model with exogenous inputs) models proposed by Leontaritis and Billings (1985). A forward-regression estimator is applied to identify the model parameters. Experimental validation is performed using data from a production engine.
Keywords :
autoregressive moving average processes; failure analysis; fault diagnosis; internal combustion engines; multivariable control systems; nonlinear control systems; parameter estimation; statistical analysis; I/M240 driving cycle; IC engine; NARMAX models; forward-regression estimator; incipient faults detection; incipient faults isolation; model parameter identification; nonlinear MIMO IC engine model identification; on-board diagnosis; Application specific integrated circuits; Autoregressive processes; Fault diagnosis; Inspection; Integrated circuit modeling; Internal combustion engines; MIMO; Nonlinear systems; Parameter estimation; Vehicle dynamics;
Conference_Titel :
American Control Conference, 1994
Print_ISBN :
0-7803-1783-1
DOI :
10.1109/ACC.1994.752336
