Comparison of intelligent systems, artificial neural networks and neural fuzzy model for prediction of gas hydrate formation rate

Mohammad Javad Jalalnezhad (Department of Petroleum Engineering, Shahid Bahonar University of Kerman, Kerman)
Mohammad Ranjbar (Young Researchers Society, Shahid Bahonar University of Kerman ,Kerman)
Amir Sarafi (Department of Chemical Engineering, Shahid Bahonar University of Kerman, Kerman ,Iran 5.Department of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, Iran)
Hossein Nezamabadi-Pour (Department of Chemical Engineering, Shahid Bahonar University of Kerman, Kerman ,Iran 5.Department of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, Iran)

International Journal of Science and Engineering (IJSE)
Vol 7, No 1 (2014)

The main objective of this study was to present a novel approach for predication of gas hydrate formation rate based on the Intelligent Systems. Using a data set including about 470 data obtained from flow tests in a mini-loop apparatus, different predictive models were developed. From the results predicted by these models, it can be pointed out that the developed models can be used as powerful tools for prediction of gas hydrate formation rate with total errors of less than 4%.