SYNTHESIS OF A NEURAL NETWORK MODEL OF INDUSTRIAL CONSTRUCTION PROCESSES USING AN INDICATOR SYSTEM

Authors

  • S. D. Leoshchenko National University “Zaporizhzhia Polytechnic”, Ukraine
  • A. O. Oliinyk National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine., Ukraine
  • S. A. Subbotin National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine., Ukraine
  • V. V. Netrebko National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine., Ukraine
  • Ye. O. Gofman National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine., Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2021-4-7

Keywords:

modeling, industrial processes, indicator system, neuromodel, sampling, training, error.

Abstract

Context. The problem of a neural network model synthesis for industrial processes with the definition of an optimal topology characterized by a high level of logical transparency and acceptable accuracy is considered. The object of research is the process of neural network modeling of industrial processes using an indicator system to simplify and select the topology of neuromodels..

Objective of the work is consists in synthesis a neural network model of industrial processes with a high level of logical transparency and acceptable accuracy based on the use of the system.

Method. A method is proposed to use artificial neural networks of feedforward propagation for modeling industrial processes. After evaluating the overall level of complexity of the modeling problem based on the indicator system, it was decided to build a neuromodel based on historical data. Using the characteristics of the input data of the problem, the most optimal structure of the neural network was calculated for further modeling of the system. A high level of logical transparency of neuromodels significantly expands their practical use and reduces the resource intensity of industrial processes.

Results. Neuromodels of industrial processes are obtained based on historical data. The use of an indicator system made it possible to significantly increase the level of logical transparency of models, while maintaining a high level of accuracy. Constructed neuromodels reduce the resource intensity of industrial processes by increasing the level of preliminary modeling.

Conclusions. The conducted experiments confirmed the operability of the proposed mathematical software and allow us to recommend it for use in practice in modeling industrial processes. Prospects for further research may lie in the neuroevolutionary synthesis of more complex topologies of artificial neural networks for performing multi-criteria optimization.

Author Biographies

S. D. Leoshchenko, National University “Zaporizhzhia Polytechnic”

Post-graduate student of the Department of Software Tools.

A. O. Oliinyk, National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine.

Dr. Sc., Associate Professor, Professor of the Department of Software Tools.

S. A. Subbotin, National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine.

Dr. Sc., Professor, Head of the Department of Software Tools.

V. V. Netrebko, National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine.

Dr. Sc., Associate Professor, Professor of the Department of Equipment and Technology of Welding Production.

Ye. O. Gofman, National University “Zaporizhzhia Polytechnic”, Zaporizhzhia, Ukraine.

PhD, Senior Researcher of the Research Unit.

References

Ameisen E. Building Machine Learning Powered Applications, Going from Idea to Product. California, O’Reilly Media, 2020, 260 p.

Bonaccorso G. Mastering Machine Learning Algorithms, Expert techniques to implement popular machine learning algorithms and fine-tune your models. Birmingham, Packt Publishing, 2018, 576 p.

Patan K. Artificial Neural Networks for the Modelling and Fault Diagnosis of Technical Process. Berlin, Springer, 2008, 112 p. DOI: 10.1007/978-3-540-79872-9

Leoshchenko S., Oliinyk A., Subbotin S., Zaiko T. Using Modern Architectures of Recurrent Neural Networks for Technical Diagnosis of Complex Systems, 2018 International Scientific-Practical Conference Problems of Info-communications. Science and Technology (PIC S&T), Kharkiv, 9–12 October 2018, proceedings. Kharkiv, IEEE, 2018, pp. 411–416. DOI: 10.1109/INFOCOMMST.2018.8632015

Leoshchenko S., Subbotin S., Oliinyk A., Narivs’kiy O. Implementation of the indicator system in modeling complex technical systems, Radio Electronics, Computer Science, Control, 2021, Vol. 1, pp. 117–126. DOI: 10.15588/1607-3274-2021-112

Ahmadian A., Salahshour S. Soft Computing Approach for Mathematical Modeling of Engineering. London, Chapman and Hall (CRC Press), 2021, 222 p.

Sayyaadi H. Modeling, Assessment, and Optimization of Energy Systems. Cambridge, Academic Press, 2020, 558 p.

Koulamas C., Lazarescu M. T. Real-Time Sensor Networks and Systems for the Industrial IoT. Basel, Mdpi AG, 2020, 242 p. DOI: 10.3390/books978-3-03943-431-2

Senge P. M. The Fifth Discipline, The Art & Practice of The Learning Organization. New York, Doubleday, 2006, 445 p.

Bruce P., Bruce A. Practical Statistics for Data Scientists, 50 Essential Concepts. California, O’Reilly Media, 2017, 318 p.

Finch W. H. Exploratory Factor Analysis. California, SAGE Publications, 2019, 144 p.

Rencher A. C., Christensen W.F. Methods of Multivariate Analysis. New Jersey, John Wiley & Sons, 2012, 800 p.

Dean A., Voss D., Draguljić D. Design and Analysis of Experiments (Springer Texts in Statistics), 2nd Edition. Berlin, Springer, 2017, 865 p. DOI: 10.1007/978-3-319-52250-0

Sewak M. Deep Reinforcement Learning, Frontiers of Artificial Intelligence. Berlin, Springer, 2020, 220 p. DOI: 10.1007/978981-13-8285-7

Leoshchenko S. D., Oliinyk A. O., Subbotin S. A., Gofman Ye. O., Ilyashenko M. B. Synthesis and usage of neural network models with probabilistic structure coding, Radio Electronics, Computer Science, Control, 2021, Vol. 2, P. 93–104. DOI, 10.15588/1607-3274-2021-2-10.

Belikov S., Volchok I., Netrebko V. Manganese influence on chromium distribution in high-chromium cast iron, Archives of Metallurgy and Materials, Vol. 58 (3), 2013, pp. 895–897. DOI: 10.2478/amm-2013-0095

Netrebko V.V. Influence of physical and heat processes on the structure and properties of high-chromium cast iron during machining, Science and Transport Progress, Vol. 6(54), 2014, pp. 97–103. DOI: 10.15802/stp2014/33395 [In Russian]

Netrebko V. V. Influence of the cast iron's chemical composition on the content of cr in the base after normalization from 1050°C, Casting and Metallurgy, Vol. 1, 2018, pp. 34–40. [In Russian]

Downloads

Published

2022-01-10

How to Cite

Leoshchenko, S. D., Oliinyk, A. O., Subbotin, S. A., Netrebko, V. V., & Gofman, Y. O. (2022). SYNTHESIS OF A NEURAL NETWORK MODEL OF INDUSTRIAL CONSTRUCTION PROCESSES USING AN INDICATOR SYSTEM . Radio Electronics, Computer Science, Control, (4), 69–77. https://doi.org/10.15588/1607-3274-2021-4-7

Issue

Section

Neuroinformatics and intelligent systems

Most read articles by the same author(s)

> >>