Application the Evolutional Modeling to the Problem of Searching the Optimal Sensors Location of Fire-Fighting System

The aim of the study is to develop an evolutionary algorithm for the optimal sensors’ location in multi-sensory systems for early detection of fires in rooms. The legislative acts regulating the sphere of fire safety in Russia are given. It is indicated that there is no justification for choosing the location of fire detectors. An evolutionary algorithm for the optimal placement of sensors controlling such fire factors as temperature, concentration of carbon dioxide and visibility, depending on the density of the smoke. The article describes the process of developing an evolutionary algorithm and its application to the problem of finding the optimal location. Methods of evolutionary modeling, such as genetic methods, genetic programming, methods of particle swarm optimization and methods of “colony of ants”, and their basic applications are described. The main operators of the genetic algorithm, such as reproduction, crossing and mutation, and their modifications are considered. We propose our own modification method for applying it for the current task. In the supercomputer center of the Peter the Great Polytechnic University, we model fires of several types of materials: rags, gasoline, oil, diesel fuel, electric cables. The simulation results were used as data to verify the algorithm. The results of testing the algorithm on model data are presented. It shows the gain in response time of the fire extinguishing system to the occurrence of fire when the sensors are located, calculated by the genetic algorithm, in comparison with the usual uniform arrangement.