Analysis and estimation of fading time from thermoluminescence glow curve by using artificial neural network

Isik E., IŞIK İ., TOKTAMİŞ H.

RADIATION EFFECTS AND DEFECTS IN SOLIDS, vol.176, no.9-10, pp.765-776, 2021 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 176 Issue: 9-10
  • Publication Date: 2021
  • Doi Number: 10.1080/10420150.2021.1954000
  • Journal Name: RADIATION EFFECTS AND DEFECTS IN SOLIDS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Chemical Abstracts Core, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.765-776
  • Keywords: Thermoluminescence, fading, Artificial neural network, glow curve
  • Inonu University Affiliated: Yes

Abstract

The artificial neural network (ANN) is an information processing technology inspired by the information processing technique of the human brain. The way the simple biological nervous system works is imitated with ANN. In this study, an ANN model is proposed to analyze and simulate TL intensity of experimental data of quartz crystals with respect to the fading. In this model, network type and transfer function are chosen as the feed-forward backpropagation algorithm and Tansig respectively for the training of the proposed ANN model. The optimization process is also chosen as Levenberg-Marquardt in this study. The performance criteria of the proposed method were evaluated according to the coefficient of determination (R-2) and mean-squared error (MSE) techniques. After simulation results are obtained, the TL glow curve of the prediction results of quartz crystal is obtained as a function of fading time irradiated with beta-source at 70 Gy for stored in 64 h at room temperature.