We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Radiolytic degradation of reactive textile dyes by ionizing high energy (γ - Co<sup>60</sup>) radiation: artificial neural network modelling.
- Authors
Padmanaban, V. C.; Selvaraju, N.; Vasudevan, V. N.; Achary, Anant
- Abstract
In this study, three artificial neural network (ANN) models were developed for the prediction and simulation of the degradation of textile dyes (Reactive Orange 16 - Monoazo; Reactive Red 120 - Diazo; Direct Red 80 - Poly azo) by high energy gamma radiation. Concentration of H2O2 (0–2.0 mM), dose of gamma ray (1–6 kGy), pH (3.0–11.0), concentration of dye (100–500 mg/L) were given as inputs and the output was percentage of degradation. A three-layer feed-forward network was trained using 750 sets of input–output response per dye using Levenberg–Marquardt back propagation algorithm with ten neurons in the hidden layer. The efficiency of the trained network was validated by using sets of input operated at pH 6.0 & 12.0. The results predicted were very close to the experimental results with R2: 0.9967 for Reactive Orange 16; 0.9960 for Reactive Red 120; 0.9977 for Direct Red 80. The sensitivity analysis showed that Concentration of H2O2 & Dose of gamma ray have strong effect whereas pH and concentration of dye have little effect on the degradation process. The results showed that the statistical modelling by ANN could effectively predict the behavior of radiolytic degradation of reactive dyes.
- Subjects
ARTIFICIAL neural networks; DYES &; dyeing
- Publication
Desalination & Water Treatment, 2018, Vol 131, p343
- ISSN
1944-3994
- Publication type
Article
- DOI
10.5004/dwt.2018.23039