Estimation of Engine Maps: A Regularized Basis-Function Networks Approach

Abstract

In this brief, a new methodology for the identification of engine maps from static data is presented. In order to enhance the flexibility of the model and exploit prior knowledge on the boundary conditions of the maps, a basis function neural network with a large number of neurons is used. To ensure smoothness of the estimated map as well as guarantee reliable extrapolation properties, the weights are estimated via a regularization strategy. Dynamic data are used to validate the new methodology. For this purpose, the estimated maps are included in a mean value model whose simulated manifold pressure and crankshaft speed are compared with the experimental ones. The results show a clear improvement with respect to the performances obtained resorting to standard radial basis function networks.