Please use this identifier to cite or link to this item:
Title: Prediction of the Flash Point Temperature of Pure Compounds
Other Titles: التنبؤ بدرجة حرارة نقطة الوميض للمركبات النقية
Authors: Norah A. M. Esmael 
Supervisor: Dr. Tareq A. Albahri
Keywords: Prediction Flash Point Temperature Pure Compounds
Issue Date: 2012
Publisher:  Kuwait university - college of graduate studies
Abstract: This work introduces a general quantitative structure property relationship (QSPR) for predicting the Flash Point Temperature (FPT) for 1471 pure compounds. Artificial neural networks (ANN) and multivariable linear regression (MVLR) along with the structural group contribution (SGC) approach was employed to calculate flash point temperatures. The strength of this technique is in selecting the structural groups that have the greatest effect on the pure compounds’ FPT property. Several definitions of SGC are investigated to predict the desired property based on multivariable linear regression (MVLR). Structural group contributions and occurrences in each compound are the main input parameters in the previous mentioned methods, and best represent the flash point for 1471 pure compounds. Four structural group contribution methods were proposed based on MVLR resulted in almost the same accuracy with an Average Absolute Error (AAE) ranging from 4 to 5% and a correlation coefficient (R) from 0.93 to 0.96. ANN method was also implemented to enhance the predictions of Method 2. The ANN method was the best effective alternative technique for calculating the FPT of pure compounds because it was more accurate. The predicted FPT for the 1471 data set were in good agreement with the estimated values, having an absolute average error (AAE) of 1.21% and a correlation coefficient (R) of 0.9917 using the ANN model. These results were more accurate than other methods in the literature.
Appears in Programs:0640 Chemical Engineering

Files in This Item:
File Description SizeFormat 
The Final thesis.pdf1,97 MBAdobe PDFView/Open    Request a copy
Show full item record

Page view(s)

Last Week
Last month
checked on Sep 29, 2020

Download(s) 50

checked on Sep 29, 2020

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.