Nonlinear Identification and Adaptive Control of Combustion Engines

Abstract Advanced engine control systems require accurate models of the thermodynamic-mechanical process, which are substantially nonlinear and often time-variant. After briefly introducing the identification of nonlinear processes with grid-based look-up tables and a special local linear Radial Basis Function network (LOLIMOT), a comparison is made with regard to computation effort, storage requirements and convergence speed. A new training algorithm for online adaptation of look-up tables is introduced which reduces the convergence time considerably. Application examples and experimental results are shown for a multidimensional nonlinear model of NOx emissions of a Diesel engine, and for the adaptive feedforward control of the ignition angle of a SI engine.

[1]  Ulrich Dr. Göbel,et al.  Die Abgasreinigung der FSI-Motoren von Volkswagen , 2000 .

[2]  Martin Brown,et al.  Neurofuzzy adaptive modelling and control , 1994 .

[3]  Rolf Isermann,et al.  Adaptive predictive control of a heat exchanger based on a fuzzy model , 1998 .

[4]  Charles M. Anastasia,et al.  A Cylinder Pressure Sensor for Closed Loop Engine Control , 1987 .

[5]  Michael Heiss.  Error-minimizing dead zone for basis function networks , 1996, IEEE Trans. Neural Networks.

[6]  Werner Herden,et al.  A New Combustion Pressure Sensor for Advanced Engine Management , 1994 .

[7]  O. Nelles.  Nonlinear System Identification , 2001 .

[8]  H. Hanselmann.  Automotive control: from concept to experiment to product , 1996, Proceedings of Joint Conference on Control Applications Intelligent Control and Computer Aided Control System Design.

[9]  Rolf Isermann,et al.  Model-based optimization of IC engines by means of fast neural networks. Part 2: Static and dynamic optimization of fuel consumption versus emissions , 2000 .

[10]  Rolf Isermann,et al.  Adaptive control systems , 1991 .

[11]  Hiroshi Okano,et al.  Toyota Lean Combustion System - The Third Generation System , 1993 .

[12]  Oliver Nelles,et al.  Tool zur Optimierung von Rasterkennfeldern , 2000 .

[13]  Rolf Isermann,et al.  Supervision of nonlinear adaptive controllers based on fuzzy models , 1999 .

[14]  Susanne Ernst,et al.  Identification with Dynamic Neural Networks - Architectures, Comparisons, Applications , 1997 .

[15]  Oliver Nelles,et al.  Nonlinear system identification with local linear neuro-fuzzy models , 1999 .

[16]  Rolf Isermann,et al.  Identifikation dynamischer Systeme , 1988 .