Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций
Конференция: Springer Science and Business Media Deutschland GmbH; 14 October 2020 through 17 October 2020; 14 October 2020 through 17 October 2020
Год издания: 2020
Идентификатор DOI: 10.1007/978-3-030-63319-6_44
Ключевые слова: artificial neural networks, automation, induction soldering, neural network structure
Аннотация: This article presents algorithmic and software for determining the optimal structure of an artificial neural network, designed to solve the problem of controlling the technological process of induction soldering of spacecraft’s thin-walled aluminum waveguide paths. The algorithm is designed for experimental determination of the optПоказать полностьюimal structure of an artificial neural network designed to solve the task of controlling the induction soldering process. The result of the algorithm is a trained neural network model with the best structure. The software product itself is an application for Windows operating system. To implement a software system the Python programming language was chosen. The Pandas, Matplotlib, Keras libraries, and PyQt framework were also used as tools for building a graphical user interface. The software application represents an automated control system module for induction soldering automated system. Experimental verification of the module showed that it allows training the neural network models with the best structure to ensure high quality control of the induction soldering process. With this, the process of finding the best neural network structure is greatly facilitated. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.
Журнал: Advances in Intelligent Systems and Computing
Выпуск журнала: Vol. 1295
Номера страниц: 480-490
ISSN журнала: 00253159