Open AccessSURFACE DEFECT DETECTION WITH NEURAL NETWORKS
Author(s) -
Н. А. Матвеева,
Andrey A. Gurtovoy
Publication year - 2020
Publication title -
sistemnì tehnologìï
Language(s) - English
Resource type - Journals
eISSN - 2707-7977
pISSN - 1562-9945
DOI - 10.34185/1562-9945-1-126-2020-10
Subject(s) - artificial neural network , computer science , java , pattern recognition (psychology) , perceptron , noise (video) , backpropagation , multilayer perceptron , artificial intelligence , signal (programming language) , time delay neural network , surface (topology) , layer (electronics) , machine learning , mathematics , materials science , geometry , image (mathematics) , programming language , composite material
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.