Predictive capability evaluation of RSM and ANN models in adsorptive treatment of crystal violet dye simulated wastewater using activated carbon prepared from Raphia hookeri seeds
- 2 October 2018
- journal article
- research article
- Published by Taylor & Francis Ltd in Journal of the Chinese Advanced Materials Society
- Vol. 6 (4), 478-496
- https://doi.org/10.1080/22243682.2018.1497534
Abstract
A comparative evaluation of the predictive capability of response surface methodology (RSM) and artificial neural network (ANN) in adsorptive treatment of dye simulated wastewater using acid activated Raphia hookeri seeds (AARHS) as adsorbent was investigated. FTIR spectrum and SEM displayed the functional groups and surface morphology of AARHS, respectively. A 24 central composite experimental design (CCD) and a three-layered (4:n:1) feed-forward architecture of artificial neural network trained by the Levenberg–Marquard back-propagation algorithm were developed to model and predict the process parameters. The best performance for the ANN architecture was obtained at n = 10 neurons. The response (% crystal violet dye adsorbed) was a function of four controllable input variables: adsorbent dosage, time, solution temperature and pH. Sensitivity analyses of the input variables on the response evaluated by Pareto analysis (P) and Relative Contribution (RC) for RSM and ANN, respectively, reveal that pH has the highest effect on the response. The predictive ability of the ANN and RSM models were evaluated in terms of RMSE (0.912; 1.186), χ2 (0.267; 0.472), MPE (0.549; 1.085) and R2 (0.9950; 0.9867), respectively. The result showed the superiority of ANN in capturing the nonlinear behaviour of the adsorptive system. An optimal response of 98.05% was recorded at 3.812 g adsorbent dosage, 65.58 min, 47.83 °C and pH of 7.928.Keywords
This publication has 27 references indexed in Scilit:
- Artificial neural network and response surface methodology modeling in mass transfer parameters predictions during osmotic dehydration of Carica papaya L.Alexandria Engineering Journal, 2013
- Optimization of total phenolic content extracted from Garcinia mangostana Linn. hull using response surface methodology versus artificial neural networkIndustrial Crops and Products, 2012
- Evaluation of neural network variable influence measures for process controlEngineering Applications of Artificial Intelligence, 2011
- Optimization of photocatalytic treatment of dye solution on supported TiO2 nanoparticles by central composite design: Intermediates identificationJournal of Hazardous Materials, 2010
- Adsorption kinetics and thermodynamic parameters of cationic dyes from aqueous solutions by using a new strong cation-exchange resinChemical Engineering Journal, 2009
- Comparison of Artificial Neural Network (ANN) and Response Surface Methodology (RSM) in the Prediction of Quality Parameters of Spray-Dried Pomegranate JuiceDrying Technology, 2009
- Adsorptive removal of methylene blue by tea wasteJournal of Hazardous Materials, 2009
- Adsorption studies on the treatment of textile dyeing effluent by activated carbon prepared from olive stone by ZnCl 2 activationColoration Technology, 2007
- Statistical optimization of medium for the production of recombinant hirudin from Saccharomyces cerevisiae using response surface methodologyProcess Biochemistry, 2000
- Response surface analysis and simulation as a tool for bioprocess design and optimizationProcess Biochemistry, 2000