Mehmet Yuceer

An artificial neural network model for the effects of chicken manure on ground water

In the areas where broiler industry is located, poultry manure from chicken farms could be a major source of ground water pollution, and this may have extensive effects particularly when the farms use nearby ground water as their fresh water supply. Therefore the prediction the extent of this pollution, either from rigorous mathematical diffusion modeling or from the perspective of experimental data evaluation bears importance. In this work, we have investigated modeling of the effects of chicken manure on ground water by artificial neural networks. An ANN model was developed to predict the total coliform in the ground water well in poultry farms. The back-propagation algorithm was employed for training and testing the network, and the Levenberg-Marquardt algorithm was utilized for optimization. The MATLAB 7.0 environment with Neural Network Toolbox was used for coding. Given the associated input parameters such as the number of chickens, type of manure pool management and depth of well, the model estimates the possible amount of total coliform in the wells to a satisfactory degree. Therefore it is expected to be of help in future for estimating the ground water pollution resulting from chicken farms.

Artificial neural network models for HFCS isomerization process

This work presents an approach to the modeling of a real industrial isomerization reactor by using artificial neural networks (ANN) pre-processed with principal component analysis (PCA). The initial model considered the output fructose concentration as the output variable, while the flow rate of substrate to the reactor as the principal input variable. Then, the ANN model was restructured and inversely trained by assuming the exit fructose concentration as the input variable and the feed flow rate as the output variable. Results indicate good performance by the application of the developed strategy to an extensive industrial data set. The results are expected to be useful in future, controlling the fructose concentration in the HFCS isomerization reactor.

Modeling of drug release behavior of pH and temperature sensitive poly(NIPAAm-co-AAc) IPN hydrogels using response surface methodology and artificial neural networks

An interpenetrated polymer network (IPN) poly(NIPAAm-co-AAc) hydrogel was synthesized by two polymerization method: emulsion and solution polymerization. The pH- and temperature-sensitive hydrogel was loaded by swelling with riboflavin drug, a B2 vitamin. The release of riboflavin as a function of time has been achieved under different pH and temperature environments. The determination of experimental conditions and the analysis of drug delivery results were achieved using response surface methodology (RSM). In this work, artificial neural networks (ANNs) in MATLAB were also used to model the release data. The predictions from the ANN model, which associated input variables, produced results showing good agreement with experimental data compared to the RSM results.

Modeling of Swelling Behaviors of Acrylamide-Based Polymeric Hydrogels by Intelligent System

Hydrogels based on acrylamide (AAm) were synthesized by free radical polymerization in an aqueous solution using N,N’-methylenebisacrylamide (MBAAm) as crosslinker. To obtain anionic hydrogels, 2-acrylamido-2-methylpropanesulfonic acid sodium salt (AMPS) and acrylic acid (AAc) were used as comonomers. The swelling behaviors of all hydrogel systems were modeled using an artificial neural network (ANN) and compared with a multivariable least squares regression (MLSR) model and phenomenal model. The predictions from the ANN model, which associated input parameters, including the amounts of crosslinker (MBA) and comonomer, and swelling values with time, produce results that show excellent correlation with experimental data. The parameters of swelling kinetics and water diffusion mechanisms of the hydrogels were calculated using the obtained experimental data. Model analysis indicated that the ANN models could accurately describe complex swelling behaviors of highly swellable hydrogels. GRAPHICAL ABSTRACT

A software for parameter estimation in dynamic models

A common problem in dynamic systems is to determine parameters in an equation used to represent experimental data. The goal is to determine the values of model parameters that provide the best fit to measured data, generally based on some type of least squares or maximum likelihood criterion. In the most general case, this requires the solution of a nonlinear and frequently non-convex optimization problem. Some of the available software lack in generality, while others do not provide ease of use. A user-interactive parameter estimation software was needed for identifying kinetic parameters. In this work we developed an integration based optimization approach to provide a solution to such problems. For easy implementation of the technique, a parameter estimation software (PARES) has been developed in MATLAB environment. When tested with extensive example problems from literature, the suggested approach is proven to provide good agreement between predicted and observed data within relatively less computing time and iterations.

Comparison of Control Strategies for Dissolved Oxygen Control in Activated Sludge Wastewater Treatment Process

Abstract Six control strategies; PID control, Model Predictive Control (MPC) with linear model, MPC with non-linear model, Nonlinear Autoregressive-Moving Average (NARMA-L2) control, Neural Network Model Predictive Control (NN-MPC) and optimal control with sequential quadratic programming (SQP) algorithm were evaluated via simulation of activated sludge wastewater treatment process. Controller performance assessment was based on rise time, overshoot, Integral Absolute Error (IAE) and Integral Square Error (ISE) performance criteria. As dissolved oxygen level in the aeration tank plays an important role in obtaining the effluent water quality, and in operating cost, it was chosen as the controlled variable. It was concluded consequently that NARMA-L2 controller and optimal control with SQP would outperform the others in achieving the specified objective.

Regression Kriging Analysis for Longitudinal Dispersion Coefficient

Prediction of longitudinal dispersion coefficient (LDC) is still a novel topic for both environmental and water sciences due to its practical importance. In this study, the appraisal of LDC is considered as a spatial modelling problem and the analyses are carried out by regression kriging. Since LDC prediction includes some geometrical (spatial) parameters, the analyses have been performed such that it takes spatial variability of data into account. The modelling procedure consists of two stages. In the first stage, spatial variables are analyzed via multi-linear regression technique and deterministic relationships are identified. In the second stage, based on the spatial auto-correlations of the residuals, the regression-based kriging procedure is applied. The capacity and accuracy level of the method has been compared with former models. As a consequence, the applications revealed that analyzing hydraulic and geometrical parameters with spatially correlated errors is a convenient approach for evaluating LDC in a hydrological system.

An integration based optimization approach for parameter estimation in dynamic models

Abstract A common problem in model verification is to determine the values of model parameters that provide the best fit to measured data, based on some type of least squares or maximum likelihood criterion. In the most general case, this requires the solution of a nonlinear and frequently nonconvex optimization problem. some of the available software lack in generality, while others do not provide ease of use. As the need for a user-interactive parameter estimation software, especially for identifying kinetic parameters, was needed; in this work we developed an integration based optimization approach to provide a solution to such problems. For easy implementation of the technique, a parameter estimation software (PARES) has been developed in MATLAB environment. When tested with extensive example problems from literature, the suggested approach is proven to provide good agreement between predicted and observed data within relatively less computing time and iterations.

A parameter identifiability and estimation study in Yesilirmak River.

Water quality models have relatively large number of parameters, which need to be estimated against observed data through a non-trivial task that is associated with substantial difficulties. This work involves a systematic model calibration and validation study for river water quality. The model considered was composed of dynamic mass balances for eleven pollution constituents, stemming from QUAL2E water quality model by considering a river segment as a series of continuous stirred-tank reactors (CSTRs). Parameter identifiability was analyzed from the perspective of sensitivity measure and collinearity index, which indicated that 8 parameters would fall within the identifiability range. The model parameters were then estimated by an integration based optimization algorithm coupled with sequential quadratic programming. Dynamic field data consisting of major pollutant concentrations were collected from sampling stations along Yesilirmak River around the city of Amasya in Turkey, and compared with model predictions. The calibrated model responses were in good agreement with the observed river water quality data, and this indicated that the suggested procedure provided an effective means for reliable estimation of model parameters and dynamic simulation for river streams.

Molecular weight control in acrylonitrile polymerization with neural network based controllers

Abstract Acrylic fiber is commercially produced by free radical polymerization, initiated by a redox system. Industrial production of polyacrylonitrile is a variant of aqueous dispersion polymerization, which takes place in homogenous phase under isothermal conditions with perfect mixing. The fact that the kinetics is a lot more complicated than that of ordinary polymerization systems makes the problem of controlling molecular weight a difficult one. On the other hand, abundant data is being gathered in industrial polymerization systems, and this information makes the neural network based controllers a good candidate for a difficult control problem. In this work, neural network based control of continuous acrylonitrile polymerization is studied, based on our previously developed new rigorous dynamic model for the polymerization of acrylonitrile. Two typical neural network controllers are investigated: model predictive control and NARMA-L2 control. These controllers are representative of the variety of common ways in which multilayer networks are used in control systems. As with most neural controllers, they are based on standard linear control architectures. The concentration of bisulfite fed to the reactor as the manipulated variable and weight average molecular weight of the polymer as an output function are used in control studies. The results present a comparison of two common neural network controllers, and indicate that the model predictive controller requires larger computational time. Furthermore, the model predictive controller involves difficulties in determining the values for the weighting factor and the prediction horizons. The NARMA-L2 controller requires minimal online computation.