SURFACE DEFECT DETECTION WITH NEURAL NETWORKS

  • Nataliya Matveeva
  • Alexander Gurtovoy
Keywords: composite materials, neural networks, multilayer perceptron with back-propagation training, defect, function of activity

Abstract

The research results of signal recognition using neural networks are presented. A multilayer perceptron with back-propagation error is implemented on Java. The optimal number of neurons in the hidden layer is selected for building an effective architecture of the neural network. Training network on different sets of signals with noise allowed teaching her to work with distorted information, which is typical for non-destructive testing in real conditions. Experiments were performed to analyze MSE values and accuracy.

References

Fábio M. Soares, Alan M.F. Souza, Neural Network Programming with Java, - Birmingham, 2016. -244 p.

Haykin S. Neural Networks. A Comprehensive Foundation. Second edition. – New Jersey: Prentice Hall, 2008. -1103 p.

Herbert Schildt Java.The Complete Reference Ninth edition, 2014, 1372 p.

Bishop C. M. Neural Networks for Pattern Recognition. Oxford University Press,1995

Matveeva N.A. Using Neural Networks programming on Java for solving the problem of signal recognition. - Dnipro: «System technologies», 2019. -Вип. 1(110). –S. 124-131.

Published
2020-03-27