Research Info

Title
A comparative study between Response surface methodology and Neural network for removal of crystal violet from aqueous solutions by magnetic active carbon composite
Type Article
Keywords
Adsorption · Crystal violet · Magnetic activated carbon · Central composite design · Artificial neural network
Abstract
The easily separable and regenerable magnetic activated carbon was s ynthesized for adsorption of t oxic cationic dye, crystal violet, from aqueous solution. The s yn-thesized magnetic activated carbon was characterized by SEM–EDX. The magnetic property of sorbent was evalu-ated by VSM method. The obtained saturation magnetization of 41.56 emu g −1 showed facile separation of s orbent after adsorption process. The eff ect of five parameters of pH, tem-perature, time, initial dye concentration and sorbent amount on adsorption ( %) were investigated. The percentage of adsorption was mathematically described as a f unction of experimental parameters and was estimated by central com-posite design ( CCD). The maximum adsorption percent of 99.5 ± 0.2 was obtained experimentally which was close t o the percent of CCD prediction of 99.90 %. The s ame design was used f or a t hree-layer artificial neural network model (ANN). The predicted data of CCD versus ANN showed the linear agreement with regression value ( R 2 ) of 0.9994 which confirmed t he ideality of CCD and ANN. The r esults of two models were compared in terms of coefficient of determi-nation ( R 2 ) and mean absolute percentage error ( MAPE)
Researchers Iman Salehi (First researcher)
Mahboube Shirani (Second researcher)
abolfazl semnani (Third researcher)
Mohsen Hassani (Fourth researcher)
Saeed Habibollh (Fifth researcher)