Modelling the Exhaust Gas Aftertreatment System of a SI Engine Using Artificial Neural Networks

In this paper recurrent neural networks are used for modelling of the exhaust gas aftertreatment system of a spark-ignition engine including a three-way catalytic converter and oxygen sensors. Different network architectures are compared based on their achieved mean squared error. We find that physically inspired architectures surpass naive architectures built without knowledge of the physical system. The best resulting model is evaluated by giving the quantiles of the absolute error.