Construction of an analytical method for limiting the complexity of neural-fuzzy models with guaranteed accuracy

Abstract

<p>We have proposed an analytical method for limiting the complexity of neural-fuzzy models that provide for the guaranteed accuracy of their implementation when approximating functions with two or more derivatives. The method makes it possible to determine the required minimal number of parameters for systems that employ fuzzy logic, as well as neural models.</p><p>We have estimated the required number of neurons (terms) in a model, which ensure the accuracy required for the area of a model curve to approach the system one along the sections of function approximation. The estimate for an approximation error was obtained based on the residual members of decomposition, in the Lagrangian form, of areas of the approximated system function into a Maclaurin series. The results received make it possible to determine the required number of approximation sections and the number of neurons (terms) in order to ensure the assigned relative and absolute error of approximation.</p><p>We have estimated the required number of neurons (terms) that provide for the necessary accuracy of model implementation based on the maximum deviation between the system and model curves along the section of approximation. This makes it possible to select, depending on the assigned required accuracy, the number of terms of fuzzy variables, input and output variables, linguistic rules, coordinates of modal values along the axes of input and output variables.</p><p>To verify validity of the proposed solutions, we modeled the system curves in the Matlab/Simulink environment, which confirmed the guaranteed accuracy of their implementation in accordance with the analytical calculations reported earlier.</p>The results obtained could be applied in modern intelligent technical systems of management, control, diagnosis, and decision-making. Using the proposed methods for selecting and applying the minimal number of terms (neurons) would help reduce the required computing power in nonlinear systems

Authors and Affiliations

Borys Sytnik, Volodymyr Bryksin, Sergiy Yatsko, Yaroslav Vashchenko

Keywords

Related Articles

Tools for forecasting and optimizing the tuning parameter of the low­speed engine for designing a ship with the kite

<p>The developed simulation (stochastic) mathematical model for calculating fuel consumption of the main low-speed engine of a transport ship with a kite is proposed. The peculiarity of the model is the use of a number o...

Determining the physical-chemical characteristics of the carbon-thermal reduction of scale of tungsten high-speed steels

<p>We determined that scale of the high-speed steel R18 is composed of the phases of Fe<sub>3</sub>O<sub>4</sub>, Fe<sub>2</sub>O<sub>3</sub>, FeO, with the presence of alloying elements as the replacement atoms. The mic...

Development of the technology for the spectral noise control of the vibration conditions of offshore platforms

<p>Because of the shortcomings in both control and diagnostic systems, the accident rate for offshore oil and gas extracting facilities remains unreasonably high. Accidents are often caused by the errors resulting from t...

Experimental investigation of the fire­extinguishing system with a gas­detonation charge for fluid acceleration

<p>To improve the parameters of pulsed fire-extinguishing plants for long-range and mass and dimensional indicators, it was proposed to replace the pneumatic propellant charge with the gas-detonation charge. The charge i...

Development of the method for modeling operational processes for tasks related to decision making

<p class="a">A solution to any problem is valuable only if the results of the solution are reliable. This axiomatic statement is trivial. However, despite the fact that this statement is undeniable, it is violated regula...

Download PDF file
  • EP ID EP666295
  • DOI 10.15587/1729-4061.2019.160719
  • Views 66
  • Downloads 0

How To Cite

Borys Sytnik, Volodymyr Bryksin, Sergiy Yatsko, Yaroslav Vashchenko (2019). Construction of an analytical method for limiting the complexity of neural-fuzzy models with guaranteed accuracy. Восточно-Европейский журнал передовых технологий, 2(4), 6-13. https://europub.co.uk/articles/-A-666295