Modeling the Biosorption Process of Heavy Metal Ions on Soybean-Based Low-Cost Biosorbents Using Artificial Neural Networks

Pollution of the environment with heavy metals requires finding solutions to eliminate them from aqueous flows. The current trends aim at exploiting advantages adsorption operation, by using some low-cost sorbents agricultural waste biomass, and good retention capacity metal ions. In this context, it is important provide tools that allow modeling optimization process, in order transpose process a higher operating scale biosorption process. This paper capitalizes on results previous research ions, namely Pb(II), Cd(II), Zn(II) soybean biomass resulting biofuels extraction data were processed applying methodology based Artificial Neural Networks (ANNs) evolutionary algorithms (EAs) capable evolving ANN parameters. EAs are represented Differential Evolution (DE) algorithm, simultaneous training determination topology performed. hybrid hSADE-NN was applied obtain optimal models for expected response system addresses biosorbent (q, mg/g), efficiency (E, %), as functions input parameters: pH, dose (DS, initial concentration solution (c0, mg/L), contact time (tc, h), temperature (T, °C). Models developed two output variables, each ion, high degree accuracy. Furthermore, combinations parameters found which can lead an terms efficiency.