Synthesis of SBA-15/PAni mesoporous composite for adsorption of reactive dye from aqueous media: RBF and MLP networks predicting models

• Published in: Fibers and polymers 2017-03, Vol.18 (3), p.465-475
• Main Authors: Aghajani, Khadijeh, Tayebi, Habib-Allah
• Format: Article
• Language: English
• Subjects: Adsorbents; Adsorption; Chemistry; Chemistry and Materials Science; Dyes; Fourier transforms; Mathematical models; Networks; Polymer Sciences; Predictions; Scanning electron microscopy
• ISSN: 1229-9197; 1875-0052
• DOI: 10.1007/s12221-017-6610-4

In this research, SBA-15/polyaniline mesoporous composite was synthesized, characterized, and applied for the adsorption of Reactive Orange 16 (RO 16) as a reactive dye from aqueous media. Fourier transform infra-red spectroscopy (FTIR), field emission scanning electron microscope (FESEM), transmission electron microscope (TEM), X-ray diffraction (XRD), thermo gravimetric analysis (TGA), and BET were used to examine the structural characteristics of the obtained adsorbent. The input parameters including pH, dosage, temperature, and contact time were investigated and optimized. The obtained optimized conditions are as follows: pH=2, time=60 min, and adsorbent dose=0.4 g/ l . Moreover, predictive models based on MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) networks were presented to predict the adsorption amount according to the input parameters including pH, dosage, temperature, time, and dye concentration. Two criteria, namely, correlation coefficient (CC) and root mean square error (RMSE) are used between the observed and predicted amounts to validate the models. Comparison of the obtained results using these two models showed that the prediction based on the MLP network model is better than the RBF network.