Application of ANN to the Sorption Equilibrium Modelling of Heavy Metal Ions on Clinoptilolite
The latest achievements in the field of mathematical modelling include the application of artificial neural networks (ANN). A growing interest in the ANN is confirmed by the number of publications devoted to the applicability of ANN in chemical, process and environmental engineering. A recent dynamic development of ANN provided an efficient and universal tool that is used to solve many tasks, including modelling, approximation and identification of objects. The initial step of applying the network to a given process consists in the determination of weights of the proposed neural network structure. This is performed on the basis of training data. A network that is properly trained allows correct information to be obtained on the basis of other data which have not been used in the network training. In most cases the network training is performed on the basis of a known mathematical model. However, the training of a network can be also performed using experimental data. In this paper, the sorption isotherms were predicted by means of a multilayer perceptron (MLP). Calculations were made using a training program written in Matlab, which took advantage of the Lavenberg-Marquardt procedure. In the last decade a growing interest is observed in inexpensive and very cheap adsorbents to remove heavy metal ions. Clinoptilolite is the mineral sorbent extracted in Poland used to remove heavy metal ions from diluted solutions. Equilibrium experiments were carried out to estimate sorptivity of a clinoptilolite and its selectivity towards Cu(II), Zn(II) and Ni(II) ions for multicomponent solution. Calculations with the use of MLP enabled description of sorption isotherms for one, two and three ions which were present at the same time in the solution. The network also enabled an analysis of sorption of the single ion, taking into account the effect of its concentration.
The paper explains a method for discerning the parts of a water supply system in need of renovation. The results are based on technical data collected over the last twenty one years, concerning more than two hundred sections of both renovated and nonrenovated pipelines. In the study, an appropriately prepared data set was used for training an artificial neural network (ANN) in the form of a multilayer perceptron (MLP). Further comparison between the responses of the trained MLP and the decisions made by human experts showed satisfactory consistency, although 15% of the database records produced certain discrepancies. The presented method can help create an expert system capable of supporting failure-free operation of a water distribution system.
Recovery of alcohols from diluted aqueous solutions is highly energy-intensive. In order to reduce the costs of concentration of alcohols, membrane processes (including membrane extraction) are used. This paper reports the results of ethanol concentration from diluted aqueous solutions using a hollow fiber membrane contactor with ionic liquid. The studies were performed using a contactor with microporous hollow fiber membranes. The membrane creates a barrier between the feed and extracting solvent, also providing a large mass transfer area. In the process, selected ionic liquid presenting different selectivity towards ethanol was used as extractant. The experiments were performed with feed concentrations of ethanol ranging from 1 to 5 wt.% and various feed flow rates ranging from 1 to 8 dm3/h.
It was examined if buckwheat hull has a potential to be used to adsorb heavy metal ions Zn(II), Cd(II), Co(II), Cu(II), Ni(II) from water. The research involved experiments aimed at the determination of sorption kinetics taking into consideration changes of concentration in a solution and sorbent over time. According to the literature data, kinetics is described with the use of pseudo first-order equations. Application of fractional derivatives for the description of sorption kinetics enables the development of the generalised sorption kinetics equation. Result analysis with this concept requires making a computational procedure using gamma functions and infinite series. Kinetics description using fractional derivatives will be equations with two parameters ie fraction of derivative α and the kinetics constant K dependent on the analysed sorbent-adsorbate system.