Least Square Adaptation of a Fast Diesel Engine NOxEmissions Model

The paper focuses on the development of an adaptive NOxemissions model, whose intended deployment is to provide accurate estimation, throughout engine lifetime, in correspondence of the engine exhaust port of a Diesel propulsion system. Particularly, black-box modelling approach is proposed, which specifically in this paper takes advantage of an intake manifold oxygen estimator previously developed. The resulting multi-linear regression model was preliminary validated in steady-state conditions. Upon successful verification of model accuracy, the above NOxpredictor was integrated within a least-square adaptation algorithm, which relies on the experimental NOxmeasurement performed downstream the selective catalytic reduction catalyst. Therefore, it was possible to perform further validation analyses, both to assess prediction reliability in transient conditions, as well as to verify the adaptation capability of the proposed least-square-based algorithm.