|
This article is cited in 23 scientific papers (total in 23 papers)
Evolutionary computation and soft computing
Neural network data processing for analysis of the industrial networks parameters
R. F. Gibadullina, D. V. Lekomtseva, M. Yu. Perukhinb a Kazan National Research Technical University named after A. N. Tupolev, Kazan, Russia
b Kazan National Research Technological University, Kazan, Russia
Abstract:
We used artificial neural networks and diagnostic network information to assess the condition of PROFINET (Process Field Network). An artificial neural network determines whether the network works fine or not. An important part of this work is data preprocessing. An essential part of the work is data preprocessing. It is done using quantization, data aligning, reducing the number of inputs and other preprocessing techniques to create a new version of the dataset to improve the accuracy. The obtained data makes possible to do a number of experiments and to find out what approach of data preprocessing shows the best results. The results were evaluated on two datasets. The first dataset contains diagnostic data of a well-functioning network, and the second one consists of data in which network problems were detected. The highest accuracy obtained in this work is 98.91% of recognizing problems in the network and the accuracy of 87.70% when the network is working fine. The work also opens up opportunities to improve accuracy in the future.
Keywords:
PROFINET, industrial Ethernet, network diagnostics, artificial neural networks, machine learning, data preprocessing.
Citation:
R. F. Gibadullin, D. V. Lekomtsev, M. Yu. Perukhin, “Neural network data processing for analysis of the industrial networks parameters”, Artificial Intelligence and Decision Making, 2020, no. 1, 80–87; Scientific and Technical Information Processing, 48:6 (2021), 446–451
Linking options:
https://www.mathnet.ru/eng/iipr130 https://www.mathnet.ru/eng/iipr/y2020/i1/p80
|
Statistics & downloads: |
Abstract page: | 28 | Full-text PDF : | 7 | References: | 1 |
|