A 2-D conveyor belt driven by a RD-CNN

In this paper a two-dimensional conveyor belt is controlled by neural processing approach; a particular CNN, named reaction-diffusion CNN, is used to generate waves propagation phenomena. They can propagate on the conveyor belt plane (an elastic membrane), moving an object between two points by a new kind of actuators: the Nitinol wires. A neural identification process of the membrane is illustrated to allow a suitable choice of the Nitinol dimensions. Moreover it is shown like both thermal and timing Nitinol behaviors are very similar to the slow-fast dynamics exhibited by a RD-CNN.