Model of an artificial neural network for solving the problem of controlling a genetic algorithm using the mathematical apparatus of the theory of Petri nets

In this paper, the aim of the study is to increase the speed and the number of solutions in intelligent systems based on genetic algorithms aimed at solving the problem of structural and parametric synthesis of large discrete systems with a given behavior. algorithm directly in the process of solving the problem of structural-parametric synthesis. Management can be carried out on the basis of data on the state of individuals in the population. In the work, as a methodology, it is proposed using the mathematical apparatus of artificial neural networks and genetic algorithms, adapted to the problem being solved using the theory of Petri nets. The proposed approach, united by one mathematical apparatus of Petri nets, allows one to model: the process of recognizing the state of a population, the procedure of structural-parametric synthesis of large discrete systems with a given behavior, as well as control of the genetic algorithm in order to correct the trajectory of the population movement, prevent attenuation and premature convergence. The article proposes the results of computational experiments that have shown the effectiveness of the developed models and methods in solving the problem of structural-parametric synthesis of large discrete systems with a given behavior based on static intercomponent connections.

1. Orlov A.N., Kurejchik V.V., Glushchenko A.E. Kombinirovannyj geneticheskij algoritm resheniya zadachi raskroya. Izvestiya YUFU. Tekhnicheskie nauki. 2016;6(179):5-13.

2. Petrosov D.A. Matematicheskaya model' formirovaniya konfiguracii vychislitel'noj tekhniki na osnove triggerov. Vestnik Izhevskogo gosudarstvennogo tekhnicheskogo universiteta. 2009;3:139-143.

3. Manzhula V.G., Fedyashov D.S. Nejronnye seti Kohonena i nechetkie nejronnye seti v intellektual'nom analize dannyh. Fundamental'nye issledovaniya. 2011;4:108-114.

4. Hajkin S. Nejronnye seti polnyj kurs, 2-e izdanie: Per. s angl. M.: Izdatel'skij dom "Vil'yams". 2006:1104..

5. Petrosov D.A., Ignatenko V.A. Primenenie informacionnyh setej Petri dlya modelirovaniya nejronnoj seti v zadache upravleniya adaptirovannym geneticheskim algoritmom pri reshenii zadach strukturno-parametricheskogo sinteza diskretnyh system. Uspekhi sovremennoj nauki i obrazovaniya. 2016;5(12):138-141.

6. Petrosov D.A. Adaptaciya geneticheskogo algoritma pri modelirovanii vychislitel'noj tekhniki s izmenyayushchejsya strukturoj i naborom komponentov na osnove setej Petri. Voprosy sovremennoj nauki i praktiki. Universitet im. V.I. Vernadskogo. 2009;6(20):151- 160.