The Automatic Synthesis of Petri Nets Based on the Functioning of Artificial Neural Network

Abstract

Context. The important task was solved during the scientific research related to the development of the methods for automatic synthesis of Petri nets while tuning up of the coordinating automatic control systems. The importance of development of these methods is due to the evolution of intelligent systems. These systems provide the automation of labor intensive processes in the particular case this is the tuning of the certain type of complex control systems. Objective. The purpose of the scientific work is to minimize the time and automation of process in tuning of the multilevel coordinating automatic control systems. Method. The principle of automatic synthesis of Petri nets and the implementation of certain algorithms for tuning complex control systems based on the functioning of an artificial neural network are proposed. The mathematical description of the method for changing the coefficients in neural connections of network in the synthesis of Petri nets is presented. Results. The experiments were conducted in the Matlab\Simulink 2012a environment. These experiments were bound to the joint functioning of an artificial neural network and Petri nets. The functioning of Petri nets was presented in the Matlab \ Simulink environment using Statflow diagrams. As a result of the experiments we have obtained the temporal characteristics of the functioning of artificial neural network providing the composition of Petri nets. The fundamental suitability of using artificial neural network to provide the automatic composition of Petri nets was determined on the basis of analysis of temporal characteristics. Conclusion. The problem linked to the development of system for the joint functioning of neural network and Petri nets for the formation of algorithms and sequential calculations was solved in this work. Thus the method of automatic synthesis of Petri nets and the method of developing of the certain algorithms based on the functioning of a neural network were further developed.