Neuro-Hybrid Models for Automotive System Identification

In automotive systems almost all steps concerning the calibration of several control systems, e.g., low idle governor or boost pressure governor, are made with the vehicle because the timeto- production and cost requirements on the projects do not allow for the vehicle analysis necessary to build reliable models. Here is presented a procedure using parametric and NN (neural network) models that enables the generation of vehicle system models based on normal ECU engine control unit) vehicle measurements. These models are locally valid and permit pre and follow-up calibrations so that, only the final calibrations have to be done with the vehicle.

Authors:

• Ventura Assuncao

Keywords:

• Automotive systems
• neuro-hybrid models
• demodulator
• nonlinear systems
• identification
• and neural networks.

References:

[1] Kraftfahrtechnisches Taschenbuch, 25th ed., Robert Bosch GmbH,
Plochingen, Germany, 2003.
[2] L. Guzzella, and A. Amstutz, "Control of diesel engines," IEEE Control
Systems Magazine, vol. 18, no. 5, pp. 53-71, October 1998.
[3] Y.-W. Kim, G. Rizzoni, and V. Utkin, "Automotive engine diagnosis
and control via nonlinear estimation," IEEE Control Systems Magazine,
vol. 18, no. 5, pp. 84-99, October 1998.
[4] L. Ljung, System Identification: Theory for the User, 2nd Ed. Prentice
Hall, New Jersey USA, 1999.
[5] K. J. Astrom, and B. Wittenmark, Adaptive Control, 2nd Ed. Addison
Wesley, CA USA, 1995.
[6] S. Sastry, Nonlinear Systems: Analysis, Stability and Control. Springer,
New York USA, 1999.
[7] N. K. Bose, and Ping Liang, Neural Network Fundamentals with
Graphs, Algorithms, and Applications. McGraw-Hill International
Editions, Singapure, 1996.
[8] J. A. Borrie, Modern Control Systems: A Manual of Design Methods.
Prentice Hall, Hertfordshire UK, 1986.
[9] G. F. Franklin, J. D. Powell, and M. Workman, Digital Control of
Dynamic Systems, 3rd Ed. Paddison Wesley, CA USA, 1998.