Optimization of Adsorption Process of Cu(Ⅱ) Ion by Oil Shale Base on GMDH-type neural network

GMDH-type neural network was used to optimize the experiment of Cu(Ⅱ) ion absorption by oil shale. In order to build a mathematical adsorption model on the absorption process, mass proportion for absorbate and absorbent, pH value and contact time were considered as independent variables, while the absorption rate as dependent variable. According to the analysis by using the GMDH-type neural network model, the effect of pH values on the absorption rate is higher than the others. Additionally, GMDH-type neural network explains the absorption mechanism based on the three variables. What’s more, a comparative study was made to confirm the good correlation between GMDH and Langmuir models on sorption isotherms, while the coefficient of correlation was 0.907.