Experimental studies were carried out with a laboratory-scale biotrickling filter to treat a gaseous stream contaminated with benzene, toluene and xylene (BTX) operated in a continuous mode. The biotrickling filter initially acclimatised with toluene was used to treat BTX compound individually at loading rates ranging from 7.2 g/m3hr to 62.2 g/m3hr, operated in a sequential mode. The results showed removal efficiencies as high as 100% when operated with toluene as the sole carbon source. An application of the back-propagation neural network to this experimental data is presented in this paper. The performance parameters namely, elimination capacity and removal efficiency were predicted from the experimental observation by selecting the appropriate network topology. The sensitive internal parameters of the network were selected using the 2(k-1) fractional factorial design. The neural-network-based model was found to be an efficient data-driven tool to predict the performance of a biotrickling filter. Copyright © 2006 Inderscience Enterprises Ltd.

Ligy Philip

Department Of Civil Engineering

Thiyagarajan R. Swaminathan

Benzene

BIOFILTERS

carbon

toluene

BIOTRICKLING FILTERS

performance prediction

WASTE GAS TREATMENT

Backpropagation

xylene

Artificial neural network

atmospheric pollution

Back propagation

experimental study

filter

pollutant removal

Topology

Waste treatment

acclimatization

article

Biofilm

BIOFILTER

Bioreactor

carbon source

contamination

flow rate

pollutant

Trickling filter

IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Back-propagation neural network for performance prediction in trickling bed air biofilter

International Journal of Environment and Pollution

The performance of a compost biofilter inoculated with mixed microbial consortium was optimized for treating a gas-phase mixture of benzene and toluene. The biofilter was acclimated to these VOCs for a period of ~18d. The effects of concentration and flow rate on the removal efficiency (RE) and elimination capacity (EC) were investigated by varying the inlet concentration of benzene (0.12-0.95 g/m3), toluene (0.14-1.48 g/m3) and gas-flow rate (0.024-0.072 m3/h). At comparable loading rates, benzene removal in the mixture was reduced in the range of 6.6-41% in comparison with the individual benzene degradation. Toluene removal in mixture was even more affected as observed from the reductions in REs, ranging from 18.4% to 76%. The results were statistically interpreted by performing an analysis of variance (ANOVA) to elucidate the main and interaction effects. © 2015 Elsevier Ltd.

Bioresource Technology

Start-up, performance and optimization of a compost biofilter treating gas-phase mixture of benzene and toluene

Neural networks, which are known for mapping non-linear and complex systems, have been used in the present study to model the grain-refinement behavior of Al-7Si alloy. The development of a feed forward neural network (FFNN) model with back-propagation (BP) learning algorithm has been presented for the prediction of the grain size, as a function of Ti and B addition level and holding time during grain refinement of Al-7Si alloy. Comparison of the predicted and experimental results shows that the FFNN model can predict the grain size of Al-7Si alloy with good learning precision and generalization. © 2004 Elsevier B.V. All rights reserved.

Materials Science and Engineering A

Prediction of grain size of Al-7Si Alloy by neural networks

A microbial consortium acclimatized with benzene, toluene or xylene (BTX) was employed to study the degradation pattern of these compounds individually under aerobic conditions. Batch and continuous experiments were conducted to evaluate the adaptability of the enriched cultures under substrate versatility conditions. The bio-kinetic parameters obtained under substrate versatility conditions were compared with those of a single substrate condition. Similar degradation patterns were observed for all the substrates with inhibition occurring at higher concentration (∼150 mg/L for benzene and xylene, and ∼200 mg/L for toluene). Toluene degradation was highest, followed by benzene and xylene in the aqueous phase. Adaptation to a more toxic compound like benzene and xylene improved the utilization of toluene. On the other hand, microbes grown on a less toxic compound (toluene) grew at a lower rate in the presence of more toxic compounds. Suitable kinetic parameters such as μmax (maximum specific growth rate per hour), Ks (half saturation constant, mg/L), and KI (threshold substrate inhibition constant, mg/L) were determined using Haldane and Levenspiel substrate inhibition models. The Haldane equation seems to be an adequate expression for the system. The degradation behavior of pollutants in the gas phase was also evaluated using a toluene acclimatized biotrickling filter operated in continuous mode. The biotrickling filter acclimatized with toluene could degrade benzene and xylene with a lower elimination capacity. But, the system could recover its original efficiency quite fast even after a prolonged shock loading. The degradation was better for toluene, followed by benzene and xylene. © 2004 Elsevier B.V. All rights reserved.

Journal of Hazardous Materials

Performance of BTX degraders under substrate versatility conditions

Advances in Neural Networks – ISNN 2005 Lecture Notes in Computer Science

A Split-Step PSO Algorithm in Prediction of Water Quality Pollution

Long-Term Prediction of Discharges in Manwan Reservoir Using Artificial Neural Network Models

Applied Energy

Solar potential in Turkey

Journal	International Journal of Environment and Pollution
ISSN	09574352
Open Access	No