Learning Petri network and its application to nonlinear systemcontrol

摘要

According to recent knowledge of brain science it is suggestednthat there exists functions distribution, which means that specificnparts exist in the brain for realizing specific functions. This papernintroduces a new brain-like model called Learning Petri Network (LPN)nthat has the capability of functions distribution and learning. The ideanis to use Petri net to realize the functions distribution and tonincorporate the learning and representing ability of neural network intonthe Petri net. The obtained LPN can be used in the same way as a neuralnnetwork to model and control dynamic systems, while it is distinctive tona neural network in that it has the capability of functionsndistribution. An application of the LPN to nonlinear crane controlnsystems is discussed. It is shown via numerical simulations that thenproposed LPN controller has superior performance to the commonly-usednneural network one