Biologically Fe2+ oxidizing fluidized bed reactor performance and controlling of Fe3+ recycle during heap bioleaching: an artificial neural network-based model

Application of artificial intelligence tools in wastewater and waste gas treatment systems: Recent advances and prospects

The non-linear complex relationships among the process variables in wastewater and waste gas treatment systems possess a significant challenge for real-time systems modelling. Data driven artificial intelligence (AI) tools are increasingly being adopted to predict the process performance, cost-effective process monitoring, and the control of different waste treatment systems, including those involving resource recovery. This review presents an in-depth analysis of the applications of emerging AI tools in physico-chemical and biological processes for the treatment of air pollutants, water and wastewater, and resource recovery processes. Additionally, the successful implementation of AI-controlled wastewater and waste gas treatment systems, along with real-time monitoring at the industrial scale are discussed.

Experimental studies and neural network modeling of the removal of trichloroethylene vapor in a biofilter

In this study, bamboo carrier based lab scale compost biofilter was evaluated to treat synthetic waste air containing trichloroethylene (TCE) under continuous operation mode. The effect of inlet TCE concentration and gas flow rate and its removal was investigated. Maximum TCE removal efficiency was found to be 89% under optimum conditions of inlet 0.986 g/m³ TCE concentration corresponding to a loading rate of 43 g/m³ h and 0.042 m³/h gas flow rate at empty bed residence time (EBRT) of 2 min. For the first time, Artificial Neural Network (ANN) was applied to predict the performance of the compost biofilter in terms of TCE removal. The ANN model used a three layer feed forward based Levenberg-Marquardt algorithm, and its topology consisted of 3-25-1 as the optimum number for the three layers (input, hidden and output). An excellent match between the experimental and ANN predicted the value of TCE removal was obtained with a coefficient of determination (R²) value greater than 0.99 during the model training, validation, testing and overall. Furthermore, statistical analysis of the ANN model performance mediated its prediction accuracy of the bioreactor to treat TCE contaminated systems.

A novel carbon monoxide fed moving bed biofilm reactor for sulfate rich wastewater treatment

In this study, a moving bed biofilm reactor was used for biodesulfuruization using CO as the sole carbon substrate. The effect of hydraulic retention time (HRT), sulfate loading rate and CO loading rate on sulfate and CO removal was examined. At 72, 48 and 24 h HRT, the sulfate removal was 93.5%, 91.9% and 80.1%, respectively. An increase in the sulfate loading reduced the sulfate reduction efficiency, which, however, was improved by increasing the CO flow rate into the MBBR. Best results in terms of sulfate reduction (>80%) were obtained for low inlet sulfate and high CO loading conditions. The CO utilization was very high at 85% throughout the study, except during the last phase of the continuous bioreactor operation it was around 70%. An artificial neural network based model was successfully developed and optimized to accurately predict the bioreactor performance in terms of both sulfate reduction and CO utilization. Overall, this study showed an excellent potential of the moving bed biofilm bioreactor for efficient sulfate reduction even under high loading conditions.

Biotreatment of zinc-containing wastewater in a sulfidogenic CSTR: Performance and artificial neural network (ANN) modelling studies

Sulfidogenic treatment of sulfate (2-10g/L) and zinc (65-677mg/L) containing simulated wastewater was studied in a mesophilic (35 degrees C) CSTR. Ethanol was supplemented (COD/sulfate=0.67) as carbon and energy source for sulfate-reducing bacteria (SRB). The robustness of the system was studied by increasing Zn, COD and sulfate loadings. Sulfate removal efficiency, which was 70% at 2g/L feed sulfate concentration, steadily decreased with increasing feed sulfate concentration and reached 40% at 10g/L. Over 99% Zn removal was attained due to the formation of zinc-sulfide precipitate. COD removal efficiency at 2g/L feed sulfate concentration was over 94%, whereas, it steadily decreased due to the accumulation of acetate at higher loadings. Alkalinity produced from acetate oxidation increased wastewater pH remarkably when feed sulfate concentration was 5g/L or lower. Electron flow from carbon oxidation to sulfate reduction averaged 83+/-13%. The rest of the electrons were most likely coupled with fermentative reactions as the amount of methane production was insignificant. The developed ANN model was very successful as an excellent to reasonable match was obtained between the measured and the predicted concentrations of sulfate (R=0.998), COD (R=0.993), acetate (R=0.976) and zinc (R=0.827) in the CSTR effluent.