Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide

Ηλίας, Α.; Ibarra-Berastegi, Gabriel; Arias, R.; Barona, Astrid

doi:10.1007/s00449-006-0062-3

Cited by 44 publications

(33 citation statements)

References 27 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the five pollutants analyzed, predictions are made using all the types of NNs [4][5][6][7][8][9][10]. However, it was necessary to analyze the effect that the spatial variability of pollutants' emissions have on the different models used at each location.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of air pollution levels using neural networks: influence of spatial variability

Ibarra-Berastegi¹,

Ηλίας²,

Barona³

et al. 2008

WIT Transactions on Ecology and the Environment

Self Cite

View full text Add to dashboard Cite

This work focuses on the prediction of hourly levels up to 8 hours ahead for five pollutants (SO 2 , CO, NO 2 , NO and O 3 ) and six locations in the area of Bilbao (Spain). To that end, 216 models based on neural networks (NN) have been built. Spatial variability for the five pollutants has been assessed using Principal Components Analysis and different behaviour has been detected for the nonreactive pollutant (SO 2 ) and the rest (CO, NO 2 , NO and O 3 ). This can be explained by the very local effects involved in the photochemical reactions. The inputs used to feed the NN models intended to predict forthcoming levels of these five pollutants, include a baseline based on autocorrelation plus a linear or nonlinear combination of different meteorological and traffic variables. The nature of these combinations is different depending on the sensor thus showing the importance of the spatial variability to build the models. The number of hourly cases, due to gaps in data predictions, can have a possible range from 11% to 38% depending on the sensor. Depending on the pollutant, location and number of hours ahead the prediction is made, different types of models have been selected. The use of these models based on NNs can provide Bilbao's air pollution network originally designed for diagnosis purposes, with short-term, real time forecasting capabilities. The performance of these models at the different sensors in the area range from a maximum value of R 2 =0.88 for the prediction of NO 2 1 hour ahead, to a minimum value of R 2 =0.15 for the prediction of ozone 8 hours ahead. These boundaries and the limitation in which the number of cases that predictions are possible represent the maximum forecasting capability that Bilbao's network can provide in real-life operating conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…For this study, historical hourly records of the above mentioned variables corresponding to years 2000 and 2001 were available [4][5][6][7]. Data of year 2000 were used to build the different groups of candidate prognostic models while data belonging to year 2001 were reserved to test and select the best model.…”

Section: Databasementioning

confidence: 99%

Prediction of air pollution levels using neural networks: influence of spatial variability

Ibarra-Berastegi¹,

Ηλίας²,

Barona³

et al. 2008

WIT Transactions on Ecology and the Environment

Self Cite

View full text Add to dashboard Cite

show abstract

“…The preliminary experiments were performed by adding 1 L of toluene or acetone to the bottles with a syringe. Each bottle septum was perforated 8,10,12,14,18, and 20 times with the syringe and possible leakage was determined by weighing every 12 hr. During these experiments, the Mininert valve was in the open position and the bottles were placed on an orbital shaker (Selecta).…”

Section: Selection Among the Supernatant The Settledmentioning

confidence: 99%

“…Thus, different mathematical and statistical models have been proposed in the literature. [17][18][19][20][21] Nevertheless, microbial growth with degrading activity is a wholly undetermined key parameter that governs biofilter "success." The support material itself can supply the biomass responsible for degradation.…”

Section: Introductionmentioning

confidence: 99%

Preliminary Acclimation Strategies for Successful Startup in Conventional Biofilters

Ηλίας

Gallastegi

Barona

et al. 2010

Journal of the Air & Waste Management Association

View full text Add to dashboard Cite

The question of how to obtain the best inocula for conventional biofilters arises when an acclimation/adaptation procedure is to be applied. Bearing in mind that no standardized procedure for acclimating inocula exists, certain preliminary strategies for obtaining an active inoculum from wastewater treatment sludge are proposed in this work. Toluene was the contaminant to be degraded. Concerning the prior separation of sludge phases, no obvious advantage was found in separating the supernatant phase of the sludge before acclimation. As far as a continuous or discontinuous acclimation mode is concerned, the latter is recommended for rapidly obtaining acclimated sludge samples by operating the system for no longer than 1 month. The continuous mode rendered similar degradation rates, although it required longer operating time. Nevertheless, the great advantage of the continuous system lay in the absence of daily maintenance and the ready availability of the activated sample.

show abstract

“…Simulations were also done at the center point of the network parameters, which was used for calculating the errors. Furthermore, for the testing data set, the total mean squared error (RMSE) was computed according to the formulae given by Elias et al (2006). The effects of the main variable and their mutual interactions were analyzed using the F (Fisher's F value), P (Probability value) and T (Student 't' test) values.…”

Section: Selecting the Best Model Architecture Using Factorial Designmentioning

confidence: 99%

Experimental Results and Neural Prediction of Sequencing Batch Reactor Performance under Different Operational Conditions

Rene

Joo²,

Park

2008

J ENV INFORM

View full text Add to dashboard Cite

ABSTRACT. Three lab scale sequencing batch reactors (SBR) were simultaneously operated at different process conditions to understand the dynamics of organic and nitrogen removal from a synthetic wastewater source. The SBRs were operated continuously for 255 days at different C/N ratio (3 -6), aeration time (4 -10 hr) and salt concentrations (0.5 -2%). The COD removal efficiencies under steady state operation were consistently greater than 80%, while nitrogen removal efficiencies (10 -98%) were inhibited by high salt concentrations. Back propagation neural network was applied to model this experimental data using influent COD, influent nitrogen, salt concentration, aeration time, MLSS concentration and C/N ratio as the input parameters to predict the performance parameters, viz., COD removal efficiency (COD-RE), total nitrogen removal efficiency (T-RE), NH 4 + -N, NO 3 --N and NO 2 --N formed. The data points were randomized and divided into training (190 × 3) and testing set (65 × 3). The internal network parameters were selected using the 2 k full factorial design of experiments. The appropriate network topology for this system (6-12-5) was selected by estimating the best correlation coefficient (R) value (0.8482) achieved during prediction of the testing set. The result from this study showed that a neural network based model can be used as an efficient data driven model to predict the performance of a SBR unit.

show abstract

Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide

Cited by 44 publications

References 27 publications

Prediction of air pollution levels using neural networks: influence of spatial variability

Prediction of air pollution levels using neural networks: influence of spatial variability

Preliminary Acclimation Strategies for Successful Startup in Conventional Biofilters

Experimental Results and Neural Prediction of Sequencing Batch Reactor Performance under Different Operational Conditions

Contact Info

Product

Resources

About