Neural control of fast nonlinear systems - Application to a turbocharged SI engine with VCT

Guillaume Colin (1) , Yann Chamaillard (1) , Gérard Bloch (2) , Gilles Corde (3)

1 LME - Laboratoire de Mécanique et Énergétique
2 CRAN - Centre de Recherche en Automatique de Nancy
3 IFPEN - IFP Energies nouvelles

Nowadays, (engine) downsizing using turbocharging appears as a major way in reducing fuel consumption and pollutant emissions of Spark Ignition (SI) engines. In this context, an efficient control of the air actuators (throttle, Turbo Wastegate and Variable Camshaft Timing (VCT)) is needed for engine torque control. This work proposes a nonlinear model-based control scheme which combines separate, but coordinated, control modules. Theses modules are based on different control strategies: Internal Model Control (IMC), Model Predictive Control (MPC), and optimal control. It is shown how neural models can be used at different levels and included in the control modules to replace physical models, which are too complex to be on-line embedded, or to estimate non measured variables. The results obtained from two different test benches show the real time applicability and good control performance of the proposed methods.

Mots clés: Neural Networks; Nonlinear Control; Engine Control; Internal Model Control; Model Predictive Control

Domaines: Automatique; Automatique / Robotique

Guillaume Colin, Yann Chamaillard, Gérard Bloch, Gilles Corde. Neural control of fast nonlinear systems - Application to a turbocharged SI engine with VCT. IEEE Transactions on Neural Networks, 2007, 18 (4), pp.1101-1114. ⟨10.1109/TNN.2007.899221⟩. ⟨hal-00141374⟩