Comparison of two models for the biosorption of Pb(II) using untreated and chemically treated olive stone: Experimental design methodology and adaptive neural fuzzy inference system (ANFIS)

Abstract

The main objective of this work is to fit results from lead biosorption by untreated and chemically treated olive stone (OS) using two models: means of full factorial design methodology and fuzzy neural network. Concretely, OS was modified by three chemical agents: HNO3, H2SO4 and NaOH, in order to improve its biosorption capacity. The examined operational variables were: concentration of chemical agent (0.1–2 M), pH (3–5) and initial lead concentration (50–250 mg/L), and the studied response was biosorption capacity (mg/g).Results obtained from full factorial design methodology showed that all these factors considerably affected the studied response. Experimental results were fitted by a second-order equation showing the influence of each factor and their interactions. While the application of a fuzzy neural network model allowed to predict the results for the dependent variables as a function of the operating conditions used with errors less than 5% in all cases. Observed results were different when the biosorbent was treated with acid treatment or with basic one, although for all treatments the highest biosorption capacity was obtained with a concentration 2 M. Finally, models were compared and it is showed that ANFIS model predicted better experimental data with higher R2 values.