Результаты поиска по 'perceptron complex':
Найдено статей: 3
  1. Editor’s note
    Computer Research and Modeling, 2024, v. 16, no. 7, pp. 1533-1538
  2. Dudarov S.P., Diev A.N., Fedosova N.A., Koltsova E.M.
    Simulation of properties of composite materials reinforced by carbon nanotubes using perceptron complexes
    Computer Research and Modeling, 2015, v. 7, no. 2, pp. 253-262

    Use of algorithms based on neural networks can be inefficient for small amounts of experimental data. Authors consider a solution of this problem in the context of modelling of properties of ceramic composite materials reinforced with carbon nanotubes using perceptron complex. This approach allowed us to obtain a mathematical description of the object of study with a minimal amount of input data (the amount of necessary experimental samples decreased 2–3.3 times). Authors considered different versions of perceptron complex structures. They found that the most appropriate structure has perceptron complex with breakthrough of two input variables. The relative error was only 6%. The selected perceptron complex was shown to be effective for predicting the properties of ceramic composites. The relative errors for output components were 0.3%, 4.2%, 0.4%, 2.9%, and 11.8%.

    Keywords: neural network, perceptron complex, mathematical model, simulation, ceramic composite, carbon nanotubes, flexural strength.
    Views (last year): 2. Citations: 1 (RSCI).
  3. Nikityuk Y.V., Marchanko L.N., Serdyukov A.N., Bruttan I.V.
    Simulation of laser polishing for fused quartz
    Computer Research and Modeling, 2026, v. 18, no. 2, pp. 399-421

    Laser polishing is a promising technology for the finishing of fused quartz (fused silica or quartz glass) products, enabling the removal of subsurface defects induced by mechanical processing. However, the complexity and nonlinearity of the physical processes occurring during laser irradiation complicate the selection of optimal technological parameters. The present paper aims to develop, comparatively analyze, and apply high-precision predictive models for forecasting and optimizing the key performance indicators of the laser polishing process for quartz glass. A verified finite element model implemented in the ANSYS software environment produced a dataset of temperature and stress fields for various combinations of process parameters. This dataset was used to develop and validate four types of predictive models: Polynomial Regression, a Fuzzy Logic System, an Adaptive Neuro-Fuzzy Inference System (ANFIS), and a Multilayer Perceptron (MLP) neural network. The models’ quality was evaluated on a test set using the statistical metrics MAE, RMSE, MAPE, $R^2$, and  $R^2_{Adj}$. A comparative analysis of the models revealed the significant superiority of the MLP neural network, which demonstrated the highest prediction accuracy for all output parameters, achieving Adjusted $R^2$ ($R^2_{Adj}$.) values above 0.97 and a Mean Absolute Percentage Error (MAPE) in the range of 0.7–2.8%. This model was effectively utilized as a surrogate function in combination with a genetic algorithm to successfully identify the optimal process parameters. The constructed MLP neural network model functions as a reliable and high-precision tool, facilitating both prediction and the optimization of fused quartz polishing outcomes using a CO2 laser. This approach effectively approximates the complex nonlinear dependencies inherent in the process and can serve as a foundation for developing intelligent control and optimization systems for this technology.

    Keywords: laser polishing, ANSYS, modeling, regression, fuzzy logic system, ANFIS, neural network model, optimization.

Indexed in Scopus

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the RSCI

International Interdisciplinary Conference "Mathematics. Computing. Education"

Website Copyright © 2009–2026 Institute of Computer Science