A novel approach to adaptive nulling with neural networks

A neural network approach to the problem of finding the weights of one and two-dimensional adaptive arrays is presented. In modern cellular, satellite mobile communications systems, and in GPS systems, both the desired and interfering signals change their directions continuously. Therefore, a fast tracking system is needed to constantly track the users, and then adapt the radiation pattern of the antenna to direct multiple narrow beams to the desired users and nulls to the sources of interference. In the approach suggested in this paper, the computation of the optimum weights is viewed as a mapping problem which can be modeled using a suitable artificial neural network trained with input output pairs. Three-layer radial basis function neural networks (RBFNN) are used in the design of one and two-dimensional array antennas. The results obtained from this network are in excellent agreement with the Wiener solution. The networks implementing these functions are successful in tracking mobile users as they move across the antenna's field of view.