Search

In this work, Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) were employed for the data reduction of a numerically simulated extraction process of sugar in an industrial RT2 extractor. The numerical model developed in OpenFOAM library was first validated using actual plant data and its stability and sensitivity to the processing variables was tested. Then, the model was used to generate data of juice and pulp sugar concentrations as affected by the main processing parameters including draft, Silin number, and capacity. The data were modelled using RSM and ANN. Both RSM and ANN were able to predict the data accurately, however, R² values obtained for ANN were slightly higher. Since the numerical model can be time consuming to be solved for all data ranges, the regression equation obtained by the RSM method or the network created according to the ANN model can be utilized as fast and ready to use tools to optimize the extractor. [ABSTRACT FROM AUTHOR]

The use of third-party logistics (3PL) providers is regarded as new strategy in logistics management. The relationships by considering 3PL are sometimes more complicated than any classical logistics supplier relationships. These relationships have taken into account as a well-known way to highlight organizations' exibilities to regard rapidly uncertain market conditions, follow core competencies, and provide long-term growth strategies. Choosing service providers has been considered as a notable research area in the last two decades. The review of the literature represents that neural networks have proposed better performance than traditional methods in this area. Therefore, in this paper, a new enhanced artificial intelligence (AI) approach is taken into consideration to assist the decision making for the logistics management which can be successfully presented in cosmetics industry for long-term prediction of the real performance data. The presented AI approach is based on modern hybrid neural networks to improve the decision making for the 3PL selection. The model can predict the overall performance of the 3PL according to least squares support vector machine and cross validation technique. In addition, the proposed AI approach is given for the 3PL selection in a real case study for the cosmetics industry. The computational results indicate that the proposed AI approach provides high performance and accuracy through the real-life situations prediction along with comparing two other two well-known AI methods. [ABSTRACT FROM AUTHOR]

This study proposes a strategy to make a quantitative correlation between the NMR log-derived free fluid porosity and seismic attributes using multiple linear regression and artificial neural network. At first the well logs tied to seismic data by creating a synthetic seismogram at each well using the sonic and density logs. Then the post-stack seismic data will be inverted to acoustic impedance by applying the created synthetic seismograms. The higher resolution of well logs than seismic data problem is dissolved by three-dimensional modeling and averaging all of the seismic and logs data in each model cell. Then the cell’s properties are processed as inputs and outputs for all operations. Stepwise regression is used to select the best attributes predicting the free fluid porosity. The multiple linear regression equation and its correlation at each step are shown. Finally, an artificial neural network of multi-layer neural network type with back propagation of errors is used for the prediction, and the better method between these two methods was selected to apply it to the whole volume of study. The proposed methodology was applied to the South Pars Gas Field in the Persian Gulf Basin. The seismic attributes were extracted from three separated seismic parts. The petrophysical logs from four wells in these seismic cubes were used for generating and evaluating the reliability of the neural network. [ABSTRACT FROM PUBLISHER]

Permeability is one of the most important parameters required for reservoir characterization. Although core analysis provides more exact information, core data do not exist for all wells in the reservoir because coring is expensive and time consuming. Therefore, another approach should be sought for permeability determination. The objective of this study was to create an artificial neural network (ANN) model in order to use well log data to predict permeability in uncored wells/intervals. The well log, core, and other data were gathered from an Iranian heterogeneous carbonate reservoir. A flow zone indicator was then predicted using an ANN approach with well logs as input variables. The reservoir was thus classified into different zones based on hydraulic flow units to overcome the extreme heterogeneity. Then, a separate ANN training procedure was followed for each flow zone with log data as input variables and permeability as output. This improved method is capable of permeability prediction in heterogeneous carbonate reservoirs in uncored wells/intervals with an average error of less than 10.9%. [ABSTRACT FROM PUBLISHER]

Response surface methodology (RSM) is a frequently used method for empirical modeling and prediction in the processing of biological media. The artificial neural network (ANN) has recently grown to be one of the most efficient methods for empirical modeling and prediction, especially for nonlinear systems. This article presents comparative studies between an ANN and RSM in the modeling and prediction of quality parameters of spray-dried pomegranate juice. In this study, the effects of the carrier type, carrier concentration, and concentration of crystalline cellulose in a pomegranate juice spray-drying process were investigated on five quality parameters—drying yield, solubility, color change, total anthocyanin content, and antioxidant activity—using RSM and ANN methods. A central composite rotatable experimental design (CCRD) and a feed-forward multilayered perceptron (MLP) ANN trained using back-propagation algorithms for three independent variables were developed to predict the five outputs. The final selected ANN model (3-10-8-5) was compared to the RSM model for its modeling and predictive abilities. The predictive abilities of both the ANN and RSM were compared using a separate dataset of 18 unseen experiments based on RMSE (root mean square error), MAE (mean absolute error), and R2 (correlation coefficient) for each output parameter. The results indicate the superiority of a properly trained ANN in capturing the nonlinear behavior of the system and the simultaneous prediction of five outputs. [ABSTRACT FROM AUTHOR]