Gaussian networks for fuel injection control

This paper proposes a radial basis function (RBF) based approach for the fu el injection control problem. In the past, neural controllers for this prob lem have centred on using a cerebellar model articulation controller (CMAC) type network with some success. The current production engine control unit s also use look-up tables in their fuel injection controllers, and if adapt ation is permitted to these look-up tables the overall effect closely mimic s the CMAC network. Here it is shown that an RBF network with significantly fewer nodes than a CMAC network is capable of delivering superior control performance on a mean value engine model simulation. The proposed approach requires no a priori knowledge of the engine systems, and on-line learning is achieved using gradient descent updates. The RBF network is then impleme nted on a four-cylinder engine and, after a minor modification, outperforms a production engine control unit.