A novel neural network (NN) controller is developed to control spark ignition (SI) engines at extreme lean conditions. The purpose of neurocontroller is to reduce the cyclic dispersion at lean operation even when the engine dynamics are unknown. The stability analysis of the closed-loop control system is given and the boundedness of all signals is ensured. Results demonstrate that the cyclic dispersion is reduced significantly using the proposed controller. The neuro controller can also be extended to minimize engine emissions with high EGR levels, where similar complex cyclic dynamics are observed. Further, the proposed approach can be applied to control nonlinear systems that have similar structure as that of the engine dynamics.
P. He and J. Sarangapani, "Neuro Emission Controller for Minimizing Cyclic Dispersion in Spark Ignition Engines," Proceedings of the International Joint Conference on Neural Networks, 2003, Institute of Electrical and Electronics Engineers (IEEE), Jan 2003.
The definitive version is available at http://dx.doi.org/10.1109/IJCNN.2003.1223926
International Joint Conference on Neural Networks, 2003
Electrical and Computer Engineering
National Science Foundation (U.S.)
Keywords and Phrases
Closed Loop Systems; Control System Synthesis; Neurocontrollers; Air pollution; Combustion; Internal combustion engines; Nonlinear control theory; Spark ignition engines -- Ignition; Stability
Article - Conference proceedings
© 2003 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.