@article{article_878772, title={Forecasting The Biosorption of Crystal Violet Cationic Dye onto Biomass-driven Graphene-Like Porous Carbon Through Artificial Neural Network Approach}, journal={Avrupa Bilim ve Teknoloji Dergisi}, pages={456–464}, year={2021}, DOI={10.31590/ejosat.878772}, author={Karaman, Ceren}, keywords={Tarımsal Atık, Yapay Sinir Ağı (YSA), Biyosorpsiyon, Crystal Violet, Modelleme, Portakal Kabuğu}, abstract={Textile industries are considered to be the main actors in water pollution. Estimation of the textile dye sorption capacities of the biosorbents/adsorbents are crucial as design considerations. Herein, the feasibility of utilizing orange-peel-derived graphene-like porous carbons (GCs) as a low-cost biosorbent for removal of Crystal Violet (CV) cationic dye from aqueous solution have been evaluated both by batch biosorption experimental-setup and by using an artificial neural network (ANN) approach. The physicochemical characterization results have indicated that as-synthesized GCs has a specific surface area of 985 m2.g-1, a pore volume of 1.04 cm3.g-1, and a point of zero charge (pHPZC) of 6.50. The biosorption capacity of the biosorbent has been investigated as a function of initial pH, bisorbent dosage, initial dye concentration, and temperature. The optimal biosorption performance values have been achieved at pH of 7.5, the biosorbent dosage of 3.0 g.L-1 , the temperature of 25 ℃, in which 91.6% of initial CV (initial dye concentration of 100 ppm) has been successfully removed. The experimental results have indicated that the biosorption process significantly depends on the temperature whereas ca.15 min of contact time is sufficient for reaching equilibrium. The ANN approach has been utilized to forecast the biosorption performance of GPC. The proposed ANN model has been trained by the Levengberg-Marquardt backpropagation algorithm, by using the activation function of purelin and tansig functions at hidden and output layers, respectively. Different hidden topologies have been evaluated to optimize the ANN model. An optimal ANN model structured with two hidden layers with 5 and 10 neurons in each layer has been developed to forecast the biosorption of CV with high-performance parameters (linear correlation coefficient, R= 0.9995; mean squared error, MSE=0.0004). This work has shown that the experimental data are in harmony with ANN-based data, so it can be speculated that the proposed ANN approach can be utilized for predicting the cationic dye biosorption.}, number={23}, publisher={Osman SAĞDIÇ}