Prediction of biosorption efficiency for the removal of copper(II) using artificial neural networks

Various low-cost adsorbents have been used for removing Cu(II) ions from aqueous solutions for the treatment of copper containing wastewaters to remove organic compounds and color. Sawdust is an impressive adsorbent in terms of adsorption efficiency, cost and availability; hence the use of sawdust as biosorbent has been widely studied. Many earlier investigations tried to correlate the experimental data with available models or some modified empirical equations, but these results were unable to predict the values of parameters from a single equation. Artificial neural networks (ANN) are effective in modeling and simulation of highly non-liner multivariable relationships. A well-designed and very well trained network can converge even on multiple number of variables at a time without any complex modeling and empirical calculations. In this present work ANN is applied for the prediction of percentage adsorption efficiency for the removal of Cu(II) ions from aqueous solutions by sawdust. Artificial neural network model, based on multilayered partial recurrent back-propagation algorithm has been used. The performance of the network for predicting the sorption efficiency of sawdust for copper is found to be very impressive.     

Adsorption and thermo desorption characteristics of hydrocarbons on single walled carbon nanotubes

We investigated the heterogeneous adsorption and thermal desorption behaviors of acetone, n-hexane and trichloroethylene (TCE) on single walled carbon nanotubes (SWCNTs). Adsorption isotherms for selected molecules on SWCNTs were measured using a quartz spring balance at temperatures ranging from 303.15 to 323.15 K. Thermal gravimetric desorption experiments were also conducted at different heating rates (2-10 K/min) to obtain information about the interaction strength of hydrocarbons with SWCNTs surfaces. The adsorption isotherm data were analyzed successfully with the temperature dependent Toth equation. To obtain the adsorption and desorption energy distribution functions (AED/DED) for hydrocarbons and nitrogen, the integral equation with Fowler-Guggenheim isotherm (for AED) and first order desorption rate equation (for DED) were solved using the generalized nonlinear regularization method. It was found that Henry's constants, the isosteric heats of adsorption, and the pattern of energy distribution function were highly dependent on the polarizability.     

Modeling constitutive relationship of Ti40 alloy using artificial neural network

Constitutive relationship equation reflects the highly non-linear relationship of flow stress as function of strain, strain rate and temperature. It is a necessary mathematical model that describes basic information of materials deformation and finite element simulation. In this paper, based on the experimental data obtained from Gleeble-1500 Thermal Simulator, the constitutive relationship model for Ti40 alloy has been developed using back propagation (BP) neural network. The predicted flow stress values were compared with the experimental values. It was found that the absolute relative error between predicted and experimental data is less than 8.0%, which shows that predicted flow stress by artificial neural network (ANN) model is in good agreement with experimental results. Moreover, the ANN model could describe the whole deforming process better, indicating that the present model can provide a convenient and effective way to establish the constitutive relationship for Ti40 alloy.     

Artificial neural network approach to predict the flow stress in the isothermal compression of as-cast TC21 titanium alloy

Isothermal compression of as-cast TC21 titanium alloy at the deformation temperatures ranging from 1000 to 1150 °C with an interval of 50 °C, the strain rates ranging from 0.01 to 10.0 s^?1 and the height reduction of 60% was conducted on a Gleeble-3500 thermo-mechanical simulator. Based on the experimental results, an artificial neural network (ANN) model with a back-propagation learning algorithm was developed to predict the flow stress in isothermal compression of as-cast TC21 titanium alloy. In the present ANN model, the strain, strain rate and deformation temperature were taken as inputs, and the flow stress as output. According to the predicted and experimental results, the maximum error and average error between the predicted flow stress and the experimental data were 4.60% and 1.58%, respectively. Comparison of the predicted results of flow stress based on the ANN model and those using the regression method, it was found that the relative error based on the ANN model varied from ?1.41% to 4.60% and that was in the range from ?13.38% to 10.33% using the regression method, and the average absolute relative error were 1.58% and 5.14% corresponding to the ANN model and regression method, respectively. These results have sufficiently indicated that the ANN model is more accurate and efficient in terms of predicting the flow stress of as-cast TC21 titanium alloy.     

Equilibrium studies for trimethoprim adsorption on montmorillonite KSF

In this study, the adsorption of trimethoprim (TMP) on montmorillonite KSF was studied under different conditions (pH, ionic strength, temperature). The results indicate that a pH value of 5.04 is optimum value for the adsorption of TMP on KSF. The adsorption kinetics was interpreted using pseudo-first-order kinetic model, pseudo-second-order kinetic model and intraparticle diffusion model. The pseudo-second-order model provides the best correlation with the experimental data of KSF adsorption. The adsorption data could be fitted with Freundlich, Langmuir and Dubinin-Radushkevich equation to find the characteristic parameters of each model. It was found that linear form of Langmuir isotherm seems to produce a better model than linear form of Freundlich equation. From the Langmuir and Freundlich equation, the adsorption capacity values raised as the solution temperature decreased. From DR isotherm, it was also determined that the type of adsorption can be considered as ion-exchange mechanism. Determination of the thermodynamic parameters DeltaH(0), DeltaS(0) and DeltaG(0) showed that adsorption was spontaneous and exothermic in nature. It was also added that adsorption of TMP by KSF may involve physical adsorption.     

Modelling beta transus temperature of titanium alloys using artificial neural network

An artificial neural network (ANN) model is developed to simulate the non-linear relationship between the beta transus (β_tr) temperature of titanium alloys and the alloy chemistry. The input parameters to the model consist of the concentration of nine elements, i.e. Al, Cr, Fe, Mo, Sn, Si, V, Zr and O, whereas the model output is the β_tr temperature. Good performance of the ANN model was achieved. The interactions between the alloying elements were estimated based on the obtained ANN model. The results showed good agreement with experimental data. The influence of the database scale on ANN model performance was also discussed. Estimation of β_tr temperature through thermodynamic calculation was carried out as a comparison.     

低温低压下多孔物质吸附性能的理论预测

根据ＰＯＬＡＮＹＩ位热理论,对运用某温度下的实验吸附等温线数据来推算其它温度下的吸附等温线的算法进行了探讨。分别利用ＰＲ,ＣＣＯＲ,ＭＣＳＰＴ等方程根据７８．８Ｋ温度下的吸附等温线来预测８９．９６Ｋ和７２．５Ｋ下的吸附等温线,并和实验数据相对比。结果证明ＭＣＳＰＴ、ＣＣＯＲ方程比ＰＲ方程更适于低温低压下吸附过程计算,理论计算结果与实验数据吻合较好,以ＭＣＳＰＴ方程最佳。     

Application of artificial neural network for predicting plain strain fracture toughness using tensile test results

A back‐propagation neural network was applied to predicting the K_IC values using tensile material data and investigating the effects of crack plane orientation and temperature. The 595 K_IC data of structural steels were used for training and testing the neural network model. In the trained neural network model, yield stress has relatively the most effect on K_IC value among tensile material properties and K_IC value was more sensitive to K_IC test temperature than to crack plane orientation valid in the range of material data covered in this study. The performance of the trained artificial neural network (ANN) was evaluated by comparing output of the ANN with results of a conventional least squares fit to an assumed shape. The conventional linear or nonlinear least squares fitting methods gave very poor fitting results but the results predicted by the trained neural network were considerably satisfactory. This study shows that the neural network can be a good tool to predict K_IC values according to the variation of the temperature and the crack plane orientation using tensile test results.     

Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25Cr–1Mo steel

Hot compression tests of modified 2.25Cr–1Mo steel were conducted on a Gleeble-3500 thermo-mechanical simulator at the temperatures ranging from 1173 to 1473 K with the strain rate of 0.01–10 s⁻¹ and the height reduction of 60%. Based on the experimental results, an artificial neural network (ANN) model and constitutive equations were developed to predict the hot deformation behavior of modified 2.25Cr–1Mo steel. A comparative evaluation of the constitutive equations and the ANN model was carried out. It was found that the relative errors based on the ANN model varied from −4.63% to 2.23% and those were in the range from −20.48% to 12.11% by using the constitutive equations, and the average root mean square errors were 0.62 MPa and 7.66 MPa corresponding to the ANN model and constitutive equations, respectively. These results showed that the well-trained ANN model was more accurate and efficient in predicting the hot deformation behavior of modified 2.25Cr–1Mo steel than the constitutive equations.     

用人工神经网络对PZT陶瓷进行性能分析与优化

选取了几种常用的金属氧化物掺杂剂,在均匀实验结构的基础上用人工神经网络方法对掺杂PZT陶瓷的性能进行分析和优化.实验结果表明,掺杂PZT体系的人工神经网络模型要比多重非线形回归模型准确得多,而且以人工神经网络模型为指导对材料进行优化后的性能预测也比较准确,说明人工神经网络在陶瓷这种多组分固溶体材料的性能分析中具有良好的使用前景.     

Characterizations of strontium(II) and barium(II) adsorption from aqueous solutions using dolomite powder

In this research, adsorption technique was applied for strontium and barium removal from aqueous solution using dolomite powder. The process has been investigated as a function of pH, contact time, temperature and adsorbate concentration. The experimental data was analyzed using equilibrium isotherm, kinetic and thermodynamic models. The isotherm data was well described by Langmuir isotherm model. The maximum adsorption capacity was found to be 1.172 and 3.958 mg/g for Sr(II) and Ba(II) from the Langmuir isotherm model at 293 K, respectively. The kinetic data was tested using first and pseudo-second order models. The results indicated that adsorption fitted well with the pseudo-second order kinetic model. The thermodynamic parameters (ΔG°, ΔH°, and ΔS°) were also determined using the equilibrium constant value obtained at different temperatures. The results showed that the adsorption for both ions was feasible and exothermic.     

ZSM-5沸石分子筛的高压吸附储氢特性

研究了ZSM-5沸石分子筛对氢的超临界吸附特性．结果表明，在77K／5MPa、195K／7MPa、293K／7MPa条件下，ZSM-5沸石分子筛的储氢质量分数分别为1．97％、0．65％和0．4％．用Clausius-Clapeyron方程求得的等量吸附热（3．8kJ／mol）与吸附量无关，表明该分子筛是一种表面势场均匀的吸附剂．将表面过剩吸附理论与描述Ⅰ型等温线的诸理论模型结合，分析了超临界吸附等温线，发现基于Toth方程的等温线模型在整个实验范围内与实验数据吻合较好，由该模型计算出的氢吸附相密度在77K达到55．6kg／m^3．根据回归参数讨论了超临界条件下氢在微孔沸石分子筛中的吸附机理，确认了氢在微孔沸石分子筛中的吸附为物理吸附．     

基于改进神经网络的干点软测量

针对传统的神经网络收敛判断以模型的拟合精度为指标造成训练时间过长和过拟合等缺点,提出了一种改进神经网络(M-ANN).M-ANN将样本分成训练样本和校验样本,并提出了过拟合判据参数.通过训练样本采用误差反传算法对网络进行训练,训练过程中以模型对校验样本的预测性能为指标,通过过拟合判据参数的计算自适应地在获得具有最佳预测性能模型时终止网络训练.同时,针对影响初馏塔塔顶石脑油干点的因素众多且呈高度非线性的特征,应用M-ANN建立初顶石脑油干点软测量模型,获得模型的预测相对误差平方和均值比传统神经网络模型降低了27.5%.     

Artificial neural network (ANN) modeling of dynamic adsorption of crystal violet from aqueous solution using citric-acid-modified rice (Oryza sativa) straw as adsorbent

Rice straw, an abundant, lignocellulosic agricultural residue worldwide, was thermochemically modified with citric acid to develop a biodegradable cationic adsorbent. The morphological and chemical characteristics of rice straw and acid-modified rice straw were investigated by scanning electron microscopy, surface area, and porosity analysis by the BET (Brunauer, Emmett, and Teller) nitrogen adsorption method and Fourier transform infrared spectroscopy. The modification process leads to the increase in the specific surface area and pore size of rice straw. In order to investigate the application potential of the prepared adsorbent to remove a cationic dye (Crystal violet) from its aqueous solution, a continuous adsorption study was carried out in a laboratory scale fixed-bed column packed with acid-modified rice straw. Effect of different flow rates and bed heights on the column breakthrough performance was investigated. Results show that with increasing bed height and decreasing flow rate, the breakthrough time was delayed. In order to determine the most suitable model for describing the adsorption kinetics of Crystal violet in the fixed-bed column system, the Bed Depth Service Time model as well as the Thomas model was fitted to the experimental data. An artificial neural network (ANN) based model for determining the dye concentration in the column effluent was also developed. An extensive error analysis was carried out between experimental data and data predicted by the models using the following error functions: correlation coefficient (R ²), average relative error (ARE), sum of the absolute error (SAE), and χ² statistic test. Based on the values of the error functions, the ANN model was most appropriate for describing the dynamic dye adsorption process.     

Kinetics and equilibrium studies for the adsorption of Acid Red 57 from aqueous solutions onto calcined-alunite

The adsorption of Acid Red 57 (AR57) onto calcined-alunite was examined in aqueous solution in a batch system with respect to contact time, pH and temperature. The first-order, pseudo-second-order kinetic and the intraparticle diffusion models were used to describe the kinetic data and the rate constants were evaluated. The experimental data fitted very well the pseudo-second-order kinetic model and also followed the intraparticle diffusion model up to 90 min. The Langmuir and Freundlich adsorption models were applied to describe the equilibrium isotherms and the isotherm constants were also determined. The equilibrium data are successfully fitted to the Langmuir adsorption isotherm. The Langmuir isotherm constant, K(L), was used to evaluate the changes of free energy, enthalpy and entropy of adsorption for the adsorption of AR57 onto calcined-alunite. The results indicate that calcined-alunite could be employed as low-cost material for the removal of acid dyes from textile effluents.     

Artificial neural network models for depicting mass flow rate of R22, R407C and R410A through electronic expansion valves

The utilization of electronic expansion valves (EEVs) in refrigeration and air conditioning systems is increased for energy saving and comfort environmental. However, experimental data and refrigerant mass flow models through EEVs are very limited in open literature. In this study, a new technique using artificial neural network (ANN) is applied to depict the mass flow rates of R22 and its alternatives R407C and R410A flowing through EEVs based on the error back propagation learning algorithm. Two strategies are followed; the first is to construct individual ANN models for each refrigerant, and the second is to construct a generalized ANN model for the three investigated refrigerants. The experimental results from open literature are used to construct the ANN models. The ANN models results showed a good agreement with the corresponding experimental data. For individual models, the relative deviations for R22, R407C, and R410A are within ±0.7%, ±1.1%, and ±0.006%, respectively. While for generalized model, the relative deviations are within ±2.5%. Also the generalized model was tested out of its construction range in a predictive mode and it was found to be a reliable tool to estimate the refrigerants mass flow rates.     

Adsorption characteristics of Cu(II) and Pb(II) onto expanded perlite from aqueous solution

The adsorption characteristics of Cu(II) and Pb(II) onto expanded perlite (EP) from aqueous solution were investigated with respect to the changes in pH of solution, adsorbent dosage, contact time and temperature of solution. For the adsorption of both metal ions, the Langmuir isotherm model fitted to equilibrium data better than the Freundlich isotherm model. Using the Langmuir model equation, the monolayer adsorption capacity of EP was found to be 8.62 and 13.39 mg/g for Cu(II) and Pb(II) ions, respectively. Dubinin-Radushkevich (D-R) isotherm model was also applied to the equilibrium data and the mean free energies of adsorption were found as 10.82 kJ/mol for Cu(II) and 9.12 kJ/mol for Pb(II) indicating that the adsorption of both metal ions onto EP was taken place by chemical ion-exchange. Thermodynamic functions, the change of free energy (DeltaG degrees ), enthalpy (DeltaH degrees ) and entropy (DeltaS degrees ) of adsorption were also calculated for each metal ions. These parameters showed that the adsorption of Cu(II) and Pb(II) ions onto EP was feasible, spontaneous and exothermic at 20-50 degrees C. Experimental data were also evaluated in terms of kinetic characteristics of adsorption and it was found that adsorption process for both metal ions followed well pseudo-second-order kinetics.     

Adsorption of copper ions onto microwave stabilized heavy metal sludge

Microwave stabilized heavy metal sludge was used as an adsorbent to remove the copper ions from aqueous solution. The adsorption characteristics of copper on the stabilized-sludge were studied by various models, such as Freundlich and Langmuir isotherm equation. Results show that the pH(zpc) of stabilized-sludge was at 9.2-9.5. Moreover, the adsorption of copper ions onto the stabilized-sludge surface was mainly on account of the heterogeneous surface of the stabilized-sludge. In the dynamic study, the experimental data was fitted to the intraparticle diffusion model, pseudo-first order model and pseudo-second order model. However, the experimental data was only well correlated with pseudo-second order model with the correlation coefficient>0.995. Furthermore, both Freundlich and Langmuir isotherm equations were found to represent the measured adsorption data well. From the Langmuir equation, the adsorption capacity increased from 18 to 28 mg/g as the temperature rose from 15 to 55 degrees C, since this adsorption process was an endothermic reaction. After this adsorption process, copper ions can be concentrated on and in a small bead and recovery efficiently.     

Batch study of liquid-phase adsorption of methylene blue using cedar sawdust and crushed brick

This paper presents a study on the batch adsorption of basic dye, methylene blue, from aqueous solution (40 mg L(-1)) onto cedar sawdust and crushed brick in order to explore their potential use as low-cost adsorbents for wastewater dye removal. Adsorption isotherms were determined at 20 degrees C and the experimental data obtained were modelled with the Langmuir, Freundlich, Elovich and Temkin isotherm equations. Adsorption kinetic data determined at a temperature of 20 degrees C were modelled using the pseudo-first and pseudo-second-order kinetic equations, liquid-film mass transfer and intra-particle diffusion models. By considering the experimental results and adsorption models applied in this study, it can be concluded that equilibrium data were represented well by a Langmuir isotherm equation with maximum adsorption capacities of 142.36 and 96.61 mg g(-1) for cedar sawdust and crushed brick, respectively. The second-order model best describes adsorption kinetic data. Analysis of adsorption kinetic results indicated that both film- and particle-diffusion are effective adsorption mechanisms. The Influence of temperature and pH of the solution on adsorption process were also studied. The extent of the dye removal decreased with increasing the solution temperature and optimum pH value for dye adsorption was observed at pH 7 for both adsorbents. The results indicate that cedar sawdust and crushed brick can be attractive options for dye removal from dilute industrial effluents.     

Artificial neural network modeling in competitive adsorption of phenol and resorcinol from water environment using some carbonaceous adsorbents

This paper illustrates the application of artificial neural network (ANN) for prediction of performances in competitive adsorption of phenol and resorcinol from aqueous solution by conventional and low cost carbonaceous adsorbent materials, such as activated carbon (AC), wood charcoal (WC) and rice husk ash (RHA). The three layer's feed forward neural network with back propagation algorithm in MATLAB environment was used for estimation of removal efficiencies of phenol and resorcinol in bi-solute water environment based on 29 sets of laboratory batch study results. The input parameters used for training of the neural network include amount of adsorbent (g/L), initial concentrations of phenol (mg/L) and resorcinol (mg/L), contact time (h), and pH. The removal efficiencies of phenol and resorcinol were considered as an output of the neural network. The performances of the developed ANN models were also measured using statistical parameters, such as mean error, mean square error, root mean square error, and linear regression. The comparison of the removal efficiencies of pollutants using ANN model and experimental results showed that ANN modeling in competitive adsorption of phenolic compounds reasonably corroborated with the experimental results.