Cu-doped ZnO nanoparticle for removal of reactive black 5: application of artificial neural networks and multiple linear regression for modeling and optimization

Abstract

The purpose of this study was to use copper oxide-doped zinc oxide (Cu:ZnO) nanoparticles as a catalyst for the degradation of reactive black 5 (RB5) dye in the presence of sunlight. Cu:ZnO nanoparticles were synthesized through mild hydrothermal technique and their characteristics were determined using powder X-ray diffraction, ultraviolet–visible (UV–vis) spectroscopy, Fourier transform infrared spectroscopy, and scanning electron microscopy. Taguchi method was used to design RB5 removal experiments. Artificial neural networks (ANNs) and multiple linear regression (MLR) were used to model the process. The coefficient of determination (R²) and root mean square error (RMSE) of ANNs were compared with MLR model. The results showed that the ANNs model with a higher R² (0.925, 0.9) and lower RMSE (0.03, 0.04) had a better predictability. The sensitivity analysis was performed to determine more important significant parameters influencing the photocatalysis process. The results showed that the concentration of RB5, intensity of UV radiation, and pH values were more important parameters rather than other parameters.

Keywords:

• Cu:ZnO nanoparticles
• Reactive black 5
• Photocatalytic
• Artificial neural networks
• Multiple linear regression

Acknowledgment

This manuscript is extracted from the MSc dissertation of the first author approved by the Environmental Health Research Center and funded by the Kurdistan University of Medical Sciences. The authors offer their thanks to the sponsors of the project.