Artificial Intelligence Methodologies for Oxygen Virtual Sensing at Diesel Engine Intake

In the last decades, worldwide automotive regulations induced the industry to dramatically increase the application of electronics in the control of the engine and of the pollutant emissions reduction systems. Besides the need of engine control, suitable fault diagnosis tools had also to be developed, in order to fulfil OBD-II and E-OBD requirements. At present, one of the problems in the development of Diesel engines is represented by the achievement of an ever more sharp control on the systems used for the pollutant emission reduction. In particular, as far as NOx gas is concerned, EGR systems are mature and widely used, but an ever higher efficiency in terms of emissions abatement, requires to determine as better as possible the actual oxygen content in the charge at the engine intake manifold, also in dynamic conditions, i.e. in transient engine operation. The problem can be resolved by adopting a specific hardware sensor, but a smart efficient and less expensive solution could be also represented by the development of a virtual sensor, able to supply the required information with sufficient precision, as a function of the values of operational parameters already available on board. To this end, in the present work different Artificial Intelligence methodologies are compared, in order to verify the related performance as virtual sensor for the oxygen value at the intake. Several models are set-up and verified, of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and compared with Artificial Neural Networks Models (ANN). The analysis is carried out by using experimental data acquired on a compression ignition engine, either in steady-state tests, or in transient engine operational conditions, and the obtained results discussed.