METHODS OF CREATING DIGITAL TWINS BASED ON NEURAL NETWORK MODELING

Abstract

It is assumed that by 2021, about half of the companies will use digital counterparts of different levels. The simplest digital twin models may not use machine learning, but the models using machine learning algorithms will have the greatest advantage. In this article, we offer our approach to the construction of digital twins for real objects. We rely on our unified process of constructing approximate solutions of boundary value problems for equations of mathematical physics and accumulated experience in solving numerous specific problems of this type. In this paper, we present five approaches to the construction of digital twin models based on the evolutionary algorithms developed and tested by us. The peculiarity of our approach to evolutionary algorithms is the use of genetic procedures for constructing the structure of the model and nonlinear optimization algorithms for adjusting its parameters. Also, we propose our approach to the construction of multilayer models upon differential equations, which allows doing without the time-consuming procedure of neural networks training. We are confident that the proposed approaches can significantly simplify and unify the creation and adaptation (keeping up to date) of digital twins for real objects of various kinds – technical, biological, socio-economic, etc.

Authors and Affiliations

Alexander Vasilyev, Dmitriy Tarkhov, Galina Malykhina

Keywords

Related Articles

COMPARATIVE ANALYSIS OF OBJECTIVES OF INFORMATICS' LEARNING IN GENERAL EDUCATION

Two triads of the goals of the general educational study of informatics dominate in different countries are compared: “ICT competence - Computer literacy - Information culture” (Russia) and “Computational Thinking - Digi...

MODELING OF THE PROCESS OF PREPARING FUTURE TEACHERS OF INFORMATICS TO RESOURCE-SAVING ACTIVITIES BASED ON EUROPEAN EXPERIENCE

The article describes the model for the preparation of future teachers of informatics for resource-saving activities, the stages of modeling are considered. The developed model, which is a structural interconnection of t...

BUILDING OF THE PROGNOSTIC MODEL OF DEVELOPMENT OF THE THEORY OF TEACHING FOR IT-EDUCATION

The article demonstrates the main directions of development of the theory of teaching in the era of computerization, informatization and technological development. The results of the 25-year research and experimental act...

ARCHITECTURE AND RELIABILITY OF OPERATING SYSTEMS

Progress in the production technology of microprocessors significantly increased reliability and performance of the computer systems hardware. It cannot be told about the corresponding characteristics of the software and...

ELECTRONIC EDUCATIONAL RESOURCE ON QUALITATIVE-NUMERIC RESEARCH OF NON-AUTONOMOUS DYNAMIC SYSTEMS

The main goal and the result of the learning process based on competence-oriented approach in education are development of competences necessary for learners to carry out professional activities. Independent work of lear...

Download PDF file
  • EP ID EP515167
  • DOI 10.25559/SITITO.14.201803.521-532
  • Views 104
  • Downloads 0

How To Cite

Alexander Vasilyev, Dmitriy Tarkhov, Galina Malykhina (2018). METHODS OF CREATING DIGITAL TWINS BASED ON NEURAL NETWORK MODELING. Современные информационные технологии и ИТ-образование, 14(3), 521-532. https://europub.co.uk/articles/-A-515167