Abstract
Abstract Light naphtha isomerization is a significant process in a crude oil refinery which is responsible for upgrading low-octane light naphtha to the high-octane and low-aromatic content gasoline. In this work, deactivation of an industrial chlorinated Pt/Al2O3 isomerization catalyst was studied in a laboratory scale plant. Experiments were carried out under temperatures in the range of 120–180 °C, liquid hourly space velocities (LHSV) of 0.7–2 h−1 and hydrogen to hydrocarbon molar ratios (H2/Oil) of 0.7–1.5. Moreover, the total water content of the combined feed, i. e. n-hexane and hydrogen, was 70 ppmwt. During 75 h time on stream (TOS), 42 data sets were collected and applied for training, testing and validating a hybrid-artificial neural network model (hybrid-ANN or HANN) to estimate the activity of the catalyst. Results showed that the activity decreased to 0.56 at the end of the operation mostly due to water poisoning. Furthermore, using the estimated activity, HANN could simulate the conversion and selectivity of the isomerization process with the absolute average deviations (AAD%) of 0.97 % and 0.0766 % and the mean squared errors (MSE) of 0.311 and 0.0156, respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Chemical Reactor Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
