{"id":2553,"date":"2025-03-19T18:17:23","date_gmt":"2025-03-19T15:17:23","guid":{"rendered":"https:\/\/t-s.today\/en\/?p=2553"},"modified":"2025-03-19T18:23:16","modified_gmt":"2025-03-19T15:23:16","slug":"09sats424","status":"publish","type":"post","link":"https:\/\/t-s.today\/en\/09sats424.html","title":{"rendered":"Synthesis of technological processes for railway construction using recurrent neural networks"},"content":{"rendered":"<p style=\"text-align: center;\"><strong>Aleksey V. Polyanskiy<\/strong><\/p>\n<p style=\"text-align: center;\">Russian University of Transport, Moscow, Russia<\/p>\n<p style=\"text-align: right;\"><strong>Corresponding author: <\/strong>Aleksey V. Polyanskiy, e-mail: polal_82@mail.ru<\/p>\n<p style=\"text-align: justify;\"><strong>\u00a0<\/strong><strong>Abstract.<\/strong> This article examines the theoretical foundations and practical approaches to synthesizing technological processes for constructing railway infrastructure. The synthesis procedure involves applying methods and tools of artificial intelligence: expert systems and recurrent neural networks. The use of artificial intelligence for developing and multi-criteria optimizing technological processes achieves high efficiency in organizational and technological design for railway construction. Within the framework of forming a methodology for engineer-intelligent support of technological processes in railway construction, the procedure for technological justification of design decisions for railway infrastructure was considered using an expert system based on a production model of knowledge representation. To find the optimal structure of the technological process, considering the dimensionality of the problem and the need to account for a number of constraints, the use of recurrent neural networks is proposed. The article describes a methodology for neural network multi-criteria optimization of technological processes for constructing railway infrastructure, taking into account the resource capacity of the construction organization and production conditions. For this purpose, topological structures of recurrent neural networks were developed, an algorithm for training was implemented, and tuning and testing were conducted using the Matlab\/Neural Network Toolbox system. Based on the results of theoretical research, the article presents practical aspects of determining the nomenclature of construction works using a production expert system, as well as synthesizing technological processes with the help of recurrent neural networks, illustrated by the example of constructing an embankment for a railway earthwork on a weak foundation.<\/p>\n<p>Results presented in the article were obtained during the author&#8217;s dissertation research.<\/p>\n<p style=\"text-align: justify;\"><strong>Keywords:<\/strong> technological process; railway construction; complex technological process; simple technological process; nomenclature of works; railway infrastructure object; earthwork; methods of artificial intelligence; expert system; recurrent neural network<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Aleksey V. Polyanskiy Russian University of Transport, Moscow, Russia Corresponding author: Aleksey V. Polyanskiy, e-mail: polal_82@mail.ru \u00a0Abstract. This article examines the theoretical foundations and practical approaches to synthesizing technological processes for constructing railway infrastructure. The synthesis procedure involves applying methods &hellip;<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55,5],"tags":[],"class_list":["post-2553","post","type-post","status-publish","format-standard","hentry","category-issue-4-2024","category-article"],"_links":{"self":[{"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/posts\/2553","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/comments?post=2553"}],"version-history":[{"count":3,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/posts\/2553\/revisions"}],"predecessor-version":[{"id":2557,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/posts\/2553\/revisions\/2557"}],"wp:attachment":[{"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/media?parent=2553"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/categories?post=2553"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/t-s.today\/en\/wp-json\/wp\/v2\/tags?post=2553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}