ABSTRACT
In this study, a Plackett-Burman design was applied to investigate critical factors for surface tension. After adding a new factor called "production scale", a central composite design (CCD) was constructed to examine nonlinear relations among factors and surface tension. An artificial neural network (ANN) was trained using data from CCD experiments. The ANN with the best structure of 5-6-1 was then tested with different unseen data sets. The predictions from ANN were within the 95% confidence interval (CI), even for a larger production scale, determined by using the replicates. A genetic algorithm (GA) was developed to check how the values of the factors vary if the production scale was set to a user-defined value. Based on the validation experiments, it was observed that the 95% confidence interval of surface tension was 36.83 ± 1.00 mN m-1 while pH 8, temperature 35 °C, incubation time 12 h, and amount of inoculum 2.30%, respectively, for the production scale of 600 mL. The proposed methodological approach with the integration of ANN and GA is considered to make a serious economic contribution as it allows predicting a proper setup for larger production scales without conducting additional experiments.
Subject(s)
Neural Networks, ComputerABSTRACT
Acid mine drainage (AMD), generated in the active and abandoned mine sites, is characterized by low pH and high metal concentrations. One AMD treatment possibility is biologically oxidizing Fe2+ followed by precipitation through pH control. As compared to autotrophic iron oxidizing microbial community, a microbial community enriched in the presence of organic nutrients was hypothesized to yield higher biomass during commissioning the bioreactor. In this study, the treatment of Fe, Cu, Co, Mn, Zn, Ni, and As containing simulated AMD was studied using an iron-oxidizing ceramic membrane bioreactor (CMBR) at varying hydraulic retention times (HRTs) (6-24 h) and two different feed Fe2+ concentrations (250 and 750 mg/L). The impact of tryptone soya broth (TSB) on the CMBR performance was also investigated. Almost complete Fe2+ oxidation and sustainable flux at around 5.0 L/(m2.h) were obtained in the CMBR with the Alicyclobacillus tolerans and Acidiphilium cryptum dominated enrichment culture. The Fe2+ oxidation rate, as assessed in batch operation cycles of CMBR, increased significantly with increasing Fe2+ loading to the bioreactor. The iron oxidation rate decreased by the elimination of organic matter from the feed. The increase of the CMBR permeate pH to 3.5-4.0 resulted in selective co-precipitation of As and Fe (over 99%) with the generation of biogenic schwertmannite.