Essential oil Extraction from Diplotaenia Cachrydifolia using Supercritical Fluid Carbon Dioxide and yields predictions with neural networks

Shakeri, Mohammad (2012) Essential oil Extraction from Diplotaenia Cachrydifolia using Supercritical Fluid Carbon Dioxide and yields predictions with neural networks. Masters thesis, University of Zabol.

[img]
Preview
Text
Essential oil Extraction from Diplotaenia Cachrydifolia using Supercritical Fluid Carbon Dioxide.pdf

Download (96kB) | Preview

Abstract

To achieve maximum efficiency in more optimization condition, experts estimate accurately the efficiency of existing methods will be convinced. In this study artificial neural network (ANNs) models is used to estimate yields essential Diplotaenia Cachrydifolia using supercritical fluid. For this purpose, the best combination of input temperature, pressure, time and volume of modifier was selected. Learning artificial neural network and estimating with the help of a mathematical structure, it is able to display arbitrary combinations of non-linear process and the link between inputs and outputs each system is capable. The lab data that was recorded during the learning network trained and expected to have predicted unknown data is used. Performance Evaluation of coefficient of determination (R2) and mean square error (MSE) to evaluate the performance of the developed models were applied to 0/9838 R2 = and MSE = 0/0088 are shown. The results showed that the model based on statistical criteria Marco Marquardt has the best performance. Comparison of estimated and measured values show good performance of the neural network model yields Diplotaenia Cachrydifolia are estimated.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Supercritical fluid Extraction, Diplotaenia cachrydifolia, Neural Network
Subjects: Q Science > QD Chemistry
Depositing User: admin admin1 admin2
Date Deposited: 15 Jun 2016 07:49
Last Modified: 15 Jun 2016 07:49
URI: http://eprints.uoz.ac.ir/id/eprint/781

Actions (login required)

View Item View Item