Evolving multilayer perceptron, and factorial design for modelling and optimization of dye decomposition by bio-synthetized nano CdS-diatomite composite

Shadi Tajmiri, Ebrahim Azimi, Mohammad Raouf Hosseini, Yousef Azimi

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

Design of experiment and hybrid genetic algorithm optimized multilayer perceptron (GA-MLP) artificial neural network have been employed to model and predict dye decomposition capacity of the biologically synthesized nano CdS diatomite composite. Impact of independent variables such as, light (UV: on-off), solution pH (5–8), composite weight (CW: 0.5–1 mg), initial dye concentration (DC: 10–20 mg/l) and contact time (0–120 min), mainly in two levels, were examined to evaluate dye removal efficiency of the composite. According to the developed response surface based on the factorial design, all independent variables shown positive interactive effect on dye removal (UV > CW > pH > DC), as well as the pH-CW mutual interaction, while both UV-DC and CW-DC had antagonistic effect. The pH-CW interaction was more influential than pH and DC. Incorporation of the intermediate measurements of dye removal between the start and final contact times in GA-MLP approach, had found to improve the accuracy and predictability of the GA-MLP model. Based on the closeness of the R2 (0.98), root mean square error (1.03), variance accounted for (98.23%), mean absolute error (0.61) and model predictive error (9.46%) to their desirable levels, proposed GA-MLP model outperformed the factorial design model. Finally, optimal parameter choice for maximum dye removal using factorial design and GA-MLP were found as: UV (on), pH (9), CW (1 g) and DC (10 mg/l) and UV (on), pH (8.85), CW (0.92 g), DC (12.3 mg/l) and T (117 0.6 min), respectively.

Original languageEnglish
Article number108997
Number of pages13
JournalEnvironmental Research
Volume182
Early online date3 Dec 2019
DOIs
Publication statusPublished - Mar 2020
Externally publishedYes

Keywords

  • Bio-synthesize
  • CdS nanoparticles
  • Factorial design
  • Genetic algorithm
  • Multilayer perceptron artificial neural network
  • Photocatalyst

ASJC Scopus subject areas

  • Biochemistry
  • Environmental Science(all)

Fingerprint

Dive into the research topics of 'Evolving multilayer perceptron, and factorial design for modelling and optimization of dye decomposition by bio-synthetized nano CdS-diatomite composite'. Together they form a unique fingerprint.

Cite this