Efficiency and quality of operation of local automatic control systems as part of an autonomous object is mainly determined by the regulator in their composition and the used control law, for the synthesis of which is necessary to use modern computer-aided design systems. The article presents the results of the application of genetic algorithm as a method of parametric synthesis of the PID-controller implemented in the SimInTech visual dynamic modeling environment, which currently is used by enterprises in the rocket and space sectors of Russian Federation. Object of research is the dynamic negative feedback system on the example of the automatic angular position of artificial satellite control system. The functional scheme and the simplified mathematical model of the system in the form of the transfer functions of its links are presented. The computer model of the system as well as a process of synthesis of the controller are implemented as a package of projects, based on standard blocks and submodels SimInTech. Projects interact using a common signal base, which provides information exchange between projects, making the system model flexible and versatile. An interactive computing environment for programming language Python, Jupyter Notebook, is used as a third-party software. The organization of interaction between SimInTech and Jupyter Notebook is described, scripts of programs for its implementation are presented.
This paper presents the results of textural segmentation of satellite images with spatial resolution <1 m using U-Net convolutional neural networks. To conduct numerical experiments, a panchromatic image of the WorldView-2 test site on the territory of the Bronnitsky Forestry (Moscow region) used. The possibilities of automating the selection of neural network parameters based on genetic algorithms investigated. The proposed method makes it possible to effectively segment the main types of natural and man-made objects, as well as to distinguish structural classes of woodlands.
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.