A neural network based intelligent model reference adaptive controller

This paper presents a novel neural network based intelligent model reference adaptive controller. In this scheme the intelligent supervisory loop (ISL) is incorporated into the traditional model reference adaptive controller (MRAC) framework by utilizing an online growing dynamic radial basis function neural network (RBFNN) structure in parallel with it. The idea is to control the plant by a direct MRAC with a suitable single reference model, and at the same time respond to plant multimodal dynamics by on line tuning of an RBFNN controller. This parallel RBFNN controller is designed in order to precisely track the system output to the desired command signal trajectory, regardless of system multimodality and/or unmodeled dynamics. The updating details of the RBFNN width, centers and weights are derived to ensure error reduction and for improved tracking accuracy. The importance of the proposed scheme is in its ability to perform effectively even when the plant mode swings without using multiple model concept or a multiple reference model adaptive controller if a suitable reference model structure can be established. Further, the parallel controller will be able to precisely track the reference trajectory even with system showing unmodeled dynamics. The performance ability of the scheme is confirmed by applying to control the angular position of the robotic manipulator under tip load variations.