A Fuzzy-Neural Adaptive Iterative Learning Control for Freeway Traffic Flow Systems

In this paper, a fuzzy-neural adaptive iterative learning control (AILC) is proposed for traffic flow systems of a single lane freeway with random bounded off-ramp traffic volumes. It is assumed that the system dynamic functions and input gains are unknown for controller design. An adaptive fuzzy neural network (FNN) controller and an adaptive robust controller are applied to compensate for the unknown system nonlinearity and input gain respectively. On the other hand, to deal with the disturbance from random bounded off-ramp traffic volumes, a dead zone like auxiliary error with the time-varying boundary layer is introduced as a bounding parameter. This proposed auxiliary error is also utilized for the construction of adaptive laws without using the bound of the input gain for all the adaptation parameters. The traffic density tracking error is shown to converge along the axis of learning iteration to a residual set whose level of magnitude depends on the width of boundary layer.