Modeling leaching behavior of solidified wastes using back-propagation neural networks

Bayar, Senem; Demir, İbrahim; Engin, Güleda Önkal

doi:10.1016/j.ecoenv.2007.10.019

Cited by 36 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Internal ANN features such as number of hidden layers, number of neurons in each layer, momentum factor, learning rate, transfer functions, and initial weight distribution have great impact on ANN model building. Default values were selected for some of these factors (momentum factor and learning rate), since they only affect the training time [19]. In our study, the maximum number of epochs, target error goal MSE (mean square error), and minimum performance gradient are set to 1500, 0, and 10 -10 , respectively.…”

Section: Artificial Neural Network Architecturementioning

confidence: 99%

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Jokić¹,

Nikolić²,

Lukić³

et al. 2019

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have been used to dynamically model cross-flow microfiltration of Streptomyces hygroscopicus fermentation broths. The aim is to predict permeate flux as a function of temperature, feed flow, transmembrane pressure and processing time. Dynamic modeling of microfiltration performance of complex systems (such as broths) is very important for design of new processes and better understanding of the present. The results of ANN model analysis suggest that the coefficients of the determination have high values. The application of the Bayesian regularization gave better results to the performance of the neural network compared to the Levenberg-Marquet algorithm. The optimal number of neurons in the hidden layer is eight. Analysis of the absolute relative error showed excellent permeate flux estimates for 100 % of the data points, with an error less than 5 % for the data obtained during microfiltration in the presence of a turbulence promoter. Whilst in the case of microfiltration without turbulence promoter 90 % of predictions have an error less than 10 %. The results of applying the concept of neural networks in the dynamic modeling of microfiltration of Streptomyces hygroscopicus fermentative broths with and without a turbulence promoter clearly show the validity of proposed method for simulation and prediction of microfiltration experimental results.

show abstract

Section: Artificial Neural Network Architecturementioning

confidence: 99%

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Jokić¹,

Nikolić²,

Lukić³

et al. 2019

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…The limit value for mercury concentration in the leachate of DIN38414-S4 fractions is 0.02 mg/l (Bayar et al, 2009). The mercury concentrations in all fractions of both samples strongly exceeded this permissible limit (Fig.…”

Section: Resultsmentioning

confidence: 97%

Leaching behaviour of mercury from hazardous solid waste generated by chlor-alkali industry

Busto

Cabrera

2013

E3S Web of Conferences

View full text Add to dashboard Cite

Abstract. Through the conventional chlor-alkali production process, highly mercury (Hg) contaminated waste sludge is produced. Improper handling and disposal of this sludge may cause an environmental hazard. The leaching behaviour of Hg of land disposed mercurial sludge, originating from a chlor-alkali plant that still is in operation, was investigated using the German DIN 38414-S4 test. The total mercury content of the samples was above 1500 mg/kg, allowing the material to be classified as hazardous and high mercury waste. Concentrations of Hg in the leachates were higher than 0.02 mg/l stipulated by the 1991 EEC Landfill Directive Draft as a maximum limit for a waste that is to be landfilled. Total Hg contents and leachability differed markedly between the samples, pointing to a heterogeneity in the production of the sludge. The more limited release of Hg from one of the samples might reflect an ageing effect, or might reflect a better quality of the stabilization process at the time of production. Results indicate that the approach used to stabilize the sludge has not been sufficiently effective, and warrant caution about existing disposal sites and future management of these mercury containing waste materials.

show abstract

“…The back-propagation neural network (BPNN), owing to its excellent ability of non-linear mapping, generalization, self-organization and self-learning, it has been proved to be of widespread utility in pattern recognition [16][17][18][19][20]. BPNN is a three-layered feed forward architecture.…”

Section: Back-propagation Neural Networkmentioning

confidence: 99%

“…In this paper, we applied FT to transforming the processed NIR data from the wavelength domain into the frequency domain, and we used the first 5,10,15,20,25,30,35,40,45, 50 points of Fourier coefficients in the Fourier spectra respectively as the input of the BP neural network classifier.…”

Section: Fourier Feature Extraction Of Chestnuts Nir Spectrummentioning

confidence: 99%

Discriminate of Moldy Chestnut Based on Near Infrared Spectroscopy and Feature Extraction by Fourier Transform

Zhou

et al. 2011

Computer and Computing Technologies in Agriculture IV

View full text Add to dashboard Cite

As near infrared spectra has the characters of multi-variables and strong correlations, to solve the problem, Fourier transform (FT) was used to extract feature variables of shelled chestnuts spectra. FT coefficients and the status of 178 chestnuts were selected as inputs and outputs of the back-propagation neural network (BPNN) classifier to build a recognition model. For comparison, principal component analysis (PCA) was utilized to compress the variables, which then was introduced as input of the neural network model. The results demonstrate that FT is a powerful feature extraction method and is better than PCA as a feature extraction method when employed together with BPNN. When the preprocessing method of standard normal variate transformation(SNV) was carried out and the first 15-point FT coefficients were used as the input, an optimal network structure of 15-6-1 was obtained, where discriminating rates of qualified chestnut, surface moldy chestnut and internal moldy chestnut in prediction set are 100%, 100% and 92.31%, respectively.

show abstract

Modeling leaching behavior of solidified wastes using back-propagation neural networks

Cited by 36 publications

References 18 publications

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Leaching behaviour of mercury from hazardous solid waste generated by chlor-alkali industry

Discriminate of Moldy Chestnut Based on Near Infrared Spectroscopy and Feature Extraction by Fourier Transform

Contact Info

Product

Resources

About