Prediction of water quality indices by regression analysis and artificial neural networks

The quality of wastewater generated in any process industry is generally indicated by performance indices namely BOD, COD and TOC, expressed in mg/L. The use of TOC as an analytica parameter has become more common in recent years especially for the treatment of industrial wastewater. In this study, several empirical relationships were established between BOD and COD with TOC using regression analysis, so that TOC can be used to estimate the accompanying BOD or COD. A new, the use of Artificial Neural Networks has been explored in this study to predict the concentrations of BOD and COD, well in advance using some easily measurable water quality indices. The total data points obtained from a refinery wastewater [143] were divided into a training set consisting of 103 data points, while the remaining 40 were used as the test data. A total of 12 different models [A1-A12] were tested using different combinations of network architecture. These models were evaluated using the% Average Relative Error values of the test set. It was observed that three models gave accurate and reliable results, indicating the versatility of the developed models

intelligent neural network model for evaluating performance of immobilized cell biofilter treating hydrogen sulphide vapors

Biofiltration has shown to be a promising technique for handling malodours arising from process industries. The present investigation pertains to the removal of hydrogen sulphide in a lab scale biofilter packed with biomedia, encapsulated by sodium alginate and poly vinyl alcohol. The experimental data obtained under both steady state and shock loaded conditions were modelled using the basic principles of artificial neural networks. Artificial neural networks are powerful data driven modelling tools which has the potential to approximate and interpret complex input/ output relationships based on the given sets of data matrix. A predictive computerised approach has been proposed to predict the performance parameters namely, removal efficiency and elimination capacity using inlet concentration, loading rate, flow rate and pressure drop as the input parameters to the artificial neural network model. Earlier, experiments from continuous operation in the biofilter showed removal efficiencies from 50 to 100% at inlet loading rates varying up to 13 g H2S/m[3]h. The internal network parameter of the artificial neural network model during simulation was selected using the 2[k] factorial design and the best network topology for the model was thus estimated. The results showed that a multilayer network [4-4-2] with a back propagation algorithm was able to predict biotilter performance effectively with R[2] values of 0.9157 and 0.9965 for removal efficiency and elimination capacity in the test data. The proposed artificial neural network model for biofilter operation could be used as a potential alternative for knowledge based models through proper training and testing of the state variables

Statistical analysis of main and interaction effects during the removal of BTEX mixtures in batch conditions using wastewater treatment plant sludge microbes

Biodegradation has proved to be a versatile technique to remediate benzene, toluene, ethyl benzene and xylene [BTEX] mixtures in contaminated soil and groundwater. In this study, a mixed microbial culture obtained from a wastewater treatment plant was used to degrade liquid phase BTEX, at initial concentrations varying between 15 to 75 mg/l. Experiments were conducted according to the 2k-1 fractional factorial design to identify the main and interaction effects of parameters and their influence on biodegradation of individual BTEX compounds in mixtures. The removal efficiencies of these compounds varied between 2 to 90% depending on the concentration of other compounds and also on their interaction effects. A statistical interpretation of the results was done based on the Fishers variance ratio [F] and probability [P] values. Though all the main effects were found significant [P < 0.05] at the 5% confidence level, the interactions between benzene and toluene and benzene and xylene concentrations were also found to be statistically significant and play a major role in affecting the total BTEX removal

Performance of upflow anoxic bioreactor for wastewater treatment

Laboratory scale studies were conducted in an up-flow anoxic bioreactor [UFAB] using synthetic fertilizer wastewater for ascertaining the denitrification efficiency. The performance of the reactor was compared using ethanol and topioca starch as the carbon source. The initial NO3-N concentrations [50-250 mg/L] and hydraulic retention time [HRT, 12-24 h] were varied to evaluate the COD and NO3-N removal. The results from this study shows that ethanol gave very good denitrification efficiency [78-98%] compared to topioca starch [68-96%]