Identification of a nonlinear MIMO IC engine model during I/M240 driving cycle for on-board diagnosis

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.

[1]  H. Melgaard,et al.  Continuous Identification of a Four-Stroke SI Engine , 1990, 1990 American Control Conference.

[2]  Sheng Chen,et al.  Identification of MIMO non-linear systems using a forward-regression orthogonal estimator , 1989 .

[3]  J.A. Cook,et al.  Modeling of an internal combustion engine for control analysis , 1988, IEEE Control Systems Magazine.

[4]  Yuen-Kwok Chin,et al.  Engine Dynamics: Time-Based Versus Crank-Angle Based , 1986 .

[5]  Elbert Hendricks,et al.  Mean Value SI Engine Model for Control Studies , 1990, 1990 American Control Conference.

[6]  M. Ohba,et al.  Application of Reduced Order Model to Automotive Engine Control System , 1987 .

[7]  Giorgio Rizzoni,et al.  Fault detection in IC engines using nonlinear parity equations , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[8]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[9]  John J. Moskwa,et al.  Automotive engine modeling for real time control , 1988 .

[10]  M. B. Priestley,et al.  Non-linear and non-stationary time series analysis , 1990 .

[11]  Ch. Schmidt,et al.  Nonlinear timevariant modelling technique to be used in driveline and engine control and observation , 1992, 1992 American Control Conference.

[12]  S. A. Billings,et al.  Experimental design and identifiability for non-linear systems , 1987 .

[13]  Qiang Luo,et al.  Model-based on-board fault detection and diagnosis for automotive engines , 1991 .

[14]  Sheng Chen,et al.  Extended model set, global data and threshold model identification of severely non-linear systems , 1989 .

[15]  Sheng Chen,et al.  Modelling and analysis of non-linear time series , 1989 .

[16]  Giorgio Rizzoni,et al.  Detection of sensor failures in automotive engines , 1991 .