In contemporary intelligent decision support systems, there is still a problem associated with increasing the performance speed of the structural-parametric synthesis of large discrete systems with a given behavior based on genetic algorithms. Currently, there are two main research areas that are designed for mathematical or hardware performance speed improvement. One way to improve hardware performance speed is the use of parallel computing, which includes general-purpose computing on graphics processing units (GPGPU). This article deals with the possibility of improving the performance speed of intelligent systems using the mathematical tool of artificial neural networks by introducing a control module of the genetic algorithm directly when performing the synthesis of solutions. Control of the structural-parametric synthesis process is achieved by predicting and evaluating the state of the genetic algorithm (convergence, attenuation, finding the population in local extremes) using artificial neural networks. This allows changing the operating parameters directly in the course of decision synthesis, changing their destructive ability relative to the binary string, which leads to a change in the trajectory of the population in the decision space, and as a result, should help to improve the performance speed of intelligent decision support systems.
Biogas energy, being one of the important components of ecological agricultural production, on the one hand, allows you to conduct successful disposal of crop and livestock waste, receiving organic fertilizers, and on the other hand makes it possible to provide heating and electricity to greenhouses, farms and other industrial buildings and buildings. At the same time, bioenergy technologies require improvement and development, taking into account the specifics of the agro-industrial complex in which they are used. The problems of organizing scientific research at a biogas station are considered. Based on the analysis of the functioning of the biogas plant, a mathematical formulation of the problem of constructing a schedule for conducting experiments taking into account the costs of equipment retooling is formulated. To determine the coefficients of the objective function of the constructed optimization problem, it is proposed to use expert technologies and a fuzzy inference procedure based on a fuzzy production model of knowledge about the subject area. To construct a solution to the optimization problem, along with the classical methods of discrete linear optimization, it is proposed to use evolutionary genetic algorithms that are effective in solving problems of large dimension.
The aim of the study was to increase the speed, quantity and quality of solutions in intelligent systems aimed at solving the problem of structural–parametric synthesis of models of large discrete systems with a given behavior. As a hypothesis, it was assumed that the adapted model of an artificial neural network is able to control changes in the parameters of the functioning of the operators of the genetic algorithm directly in the process of solving the problem of intelligent structural–parametric synthesis of models of large discrete systems. To solve the problem of managing the process of intelligent search for solutions based on a genetic algorithm, an artificial neural network, which is used as an add-in, must dynamically change the “destructive” ability of operators based on data about the current and/or historical state of the population. In the article, the theory of Petri nets is used as a single mathematical device capable of modeling the work of evolutionary procedures. This mathematical tool is able to simulate the operation of a genetic algorithm adapted to solving the problem of structural–parametric synthesis of models of large discrete systems with a given behavior; simulate the operation and training of an artificial neural network; combine the genetic algorithm with a control add-in based on an artificial neural network to prevent attenuation and premature convergence; simulate the process of recognizing the state of the population; and simulate the operation of the models obtained as a result of the synthesis. As an example of the functioning of the proposed approach, the article presents the results of a computational experiment, which considers the problem of structural–parametric synthesis of computer technology based on the developed models of the element base-RS, D and T triggers that are capable of processing a given input vector into the required (reference) output. In the software implementation of the proposed approach, calculations on the CPU and CPU+GPGPU technologies were used.
В данной статье рассматриваются вопросы использования искусственных нейронных сетей для управле-ния процессом структурно-параметрического синтеза больших дискретных систем с заданным поведением, базирующемся на адаптированном генетическом алгоритме. Процесс структурно-параметрического синте-за дискретных систем с заданным поведением базируется на генетическом алгоритме, который адаптирован к данной предметной области с помощью вложенных сетей Петри. Для моделирования работы искусственной нейронной сети предлагается использовать информационные сети Петри. При управлении процессом струк-турно-параметрического синтеза на основе генетического алгоритма модель искусственной нейронной сети решает «классическую» задачу распознавания образов, для оценки протекающих в генетическом алгоритме процессов. Для этого предложено использование двух графиков, которые отображают состояние популяции в целом и каждой хромосомы в отдельности. На основании данных изображений, которые могут быть объеди-нены в одно, искусственная нейронная сеть принимает решение об изменении параметров функционирования операторов генетического алгоритма, что позволит сократить время поиска решений в задачах структурно-па-раметрического синтеза больших дискретных систем с заданным поведением.Ключевые слова: структурно-параметрический синтез, большие дискретные системы, эволюционные алгоритмы, сети Петри ADAPTIVE STRUCTURAL-PARAMETRIC SYNTHESIS OF LARGE DISCRETE SYSTEMS WITH ASSIGNED BEHAVIOR ON THE BASIS OF EVOLUTION METHODS Petrosov D.A.Belgorod State Agricultural University named after V. Gorin, Belgorod, e-mail: scorpionss2002@mail.ru This article discusses the use of artificial neural networks for controlling the process of structural-parametric synthesis of large discrete systems with a specified behavior based on an adapted genetic algorithm. The process of structurally-parametric synthesis of discrete systems with a given behavior is based on a genetic algorithm that is adapted to the given domain with the help of embedded Petri nets. To simulate the operation of an artificial neural network, it is proposed to use Petri information networks. When managing the process of structural-parametric synthesis based on a genetic algorithm, the model of an artificial neural network solves the «classical» pattern recognition problem for evaluating the processes occurring in the genetic algorithm. For this, two graphs are proposed, which reflect the state of the population as a whole and of each chromosome separately. Based on image data that can be combined into one, the artificial neural network makes a decision to change the parameters of the functioning of the operators of the genetic algorithm, which will reduce the search time for solutions in the problems of structural-parametric synthesis of large discrete systems with a specified behavior. Keywords: structural-parametric synthesis, large discrete systems, evolutionary algorithms, Petri netsСовременные системы в различных предметных областях состоят из большого количества элементов и связей между н...
The article discusses the problems of structural synthesis of large discrete systems with predefined behavior, which assumes transition of a given input signal into required reference output signal. A combined method for building the procedure of synthesis based on evolutionary methods and mathematical analysis of Petri nets has been proposed. An evolutionary procedure of structural synthesis of large discrete systems with static inter-component links has been developed. Computational experiments performed with the use of the built model give evidence to the efficiency of the proposed synthesis procedure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.