Örücü E, Tugcu G, Saçan M T
a Institute of Environmental Sciences , Bogazici University , Bebek , Istanbul , Turkey.
SAR QSAR Environ Res. 2014;25(12):983-98. doi: 10.1080/1062936X.2014.976266.
This study was performed to investigate the adsorption of a diverse set of textile dyes onto granulated activated carbon (GAC). The adsorption experiments were carried out in a batch system. The Langmuir and Freundlich isotherm models were applied to experimental data and the isotherm constants were calculated for 33 anthraquinone and azo dyes. The adsorption equilibrium data fitted more adequately to the Langmuir isotherm model than the Freundlich isotherm model. Added to a qualitative analysis of experimental results, multiple linear regression (MLR), support vector regression (SVR) and back propagation neural network (BPNN) methods were used to develop quantitative structure-property relationship (QSPR) models with the novel adsorption data. The data were divided randomly into training and test sets. The predictive ability of all models was evaluated using the test set. Descriptors were selected with a genetic algorithm (GA) using QSARINS software. Results related to QSPR models on the adsorption capacity of GAC showed that molecular structure of dyes was represented by ionization potential based on two-dimensional topological distances, chromophoric features and a property filter index. Comparison of the performance of the models demonstrated the superiority of the BPNN over GA-MLR and SVR models.
本研究旨在考察颗粒活性炭（GAC）对多种纺织染料的吸附性能。吸附实验在间歇系统中进行。将Langmuir和Freundlich等温线模型应用于实验数据，并计算了33种蒽醌和偶氮染料的等温线常数。吸附平衡数据对Langmuir等温线模型的拟合程度优于Freundlich等温线模型。除了对实验结果进行定性分析外，还使用多元线性回归（MLR）、支持向量回归（SVR）和反向传播神经网络（BPNN）方法，利用新的吸附数据建立定量结构-性质关系（QSPR）模型。数据被随机分为训练集和测试集。使用测试集评估所有模型的预测能力。使用QSARINS软件通过遗传算法（GA）选择描述符。与GAC吸附容量的QSPR模型相关的结果表明，染料的分子结构由基于二维拓扑距离、发色特征和性质过滤指数的电离势表示。模型性能比较表明，BPNN优于GA-MLR和SVR模型。
