Non-linear system control using learning Petri network

According to the recent knowledge of brain science, it is suggested that there exists function distribution in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have previously (1995, 1996) developed a learning network with function distribution which is called learning Petri network (LPN) and have also shown that this network could learn nonlinear and discontinuous mappings which neural network (NN) can not learn. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using LPN controller, it has been proved that the control performance of LPN controller is superior to that of NN controller