2024
Mathematical Models and Computer Simulations, Scopus
Статьи в журналах
Vol. 16, No. 2, pp. 235–245.
Shtakin D. V., Shevlyagina S. A., Torgashov A. Y. Neural Network Model for Estimating the Quality Indicators of Industrial Fractionator Products // Mathematical Models and Computer Simulations. – 2024. – Vol. 16. – No. 2. – P. 235-245.
For industrial processes, an operational assessment and forecast of the main difficult to measure quality indicators of output streams are required. Soft sensors have become widely used for their assessment and prediction in real time. The use of neural networks (NNs) for their development allows us to take into account the nonlinear features of a technological object and allows us to obtain a more accurate forecast. However, the structure of NNs is extensive and the choice of the optimal structure, as well as the question of the convergence of learning with the given structure, are still beyond the reach of theoretical methods. In relation to this, a new NN learning algorithm and a new approach to determine the structure of a NN are presented. The latter allows us to establish the structure of a NN with the optimal convergence of the resulting structure. The proposed algorithms are presented in detail on the example of a fractionator and demonstrate their effectiveness.
https://doi.org/10.1134/S2070048224020169