Optimization of coagulation-flocculation process with dehulled and unhulled Moringa oleifera cake powder by 2⁵ full factorial design and artificial neural networks: effect on dam water quality

ABSTRACT

This study explores parametric optimization of coagulation-flocculation process using statistically designed experimentation via two-level, five factors full factorial design (FFD) and artificial neural network (ANN). The experimental design was produced using Coagulant dosage $(X_1$), Fast mixing $(X_2$), Slow mixing $(X_3$), Settling time $\left(X_4\right)$ and Seeds kind $\left(X_5\right)$. Turbidity removal, pH and conductivity variations have been adopted as responses/outputs. The efficiency of Moringa oleifera Lam (MO) seeds cake powder was tested using dehulled (DSCP) and unhulled (USCP) seeds on dam water treated for drinking purposes. Both methods modelled Turbidity removal with high accuracy with a coefficient of determination (${\mathrm{R}}^2$) of 0.90 and 0.96 for FFD and ANN, respectively. Validation tests also proved to have good efficiency, with a removal rate of 90.42%, which is very close to that obtained by FFD (90.71%) and ANN (92.33%) models. Thus, MO seeds cake powder could serve as a replacement for the chemicals widely used.

KEYWORDS:

• optimization
• Dehulled/Unhulled moringa oleifera
• coagulation-flocculation
• FFD
• ANN

Acknowledgements

The authors gratefully acknowledge the Algerian Ministry of Higher Education and Scientific Research (MESRS), General Direction of Scientific Research and Technological Development (DGRSDT) and Algerian for waters (ADE). We also acknowledge the observations of both the editor and the two anonymous reviewers of this journal. Their comments led to significant improvements to this paper. The remaining errors are solely ours.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.