An Imperialist Competitive Algorithm Artificial Neural Network Method to Predict Hydrate Formation Temperature

Formation of gas hydrates is one of the problems in the production, processing, and transportation of natural gas. Therefore, an understanding of conditions where hydrates form is necessary to overcome hydrate related issues. Although several studies have been performed on prediction of hydrate forming conditions for various gas mixtures, but the developed correlations are not accurate enough and some of these correlations are presented mainly in graphical form, thus making it difficult to use them within general computer packages for simulation and design. In this paper, we adopt imperialist competitive algorithm (ICA) that is a new socio-politically motivated global search strategy and has recently been introduced for dealing with different optimization tasks to optimize the weight of multilayer perceptron (MLP) artificial neural network for prediction of hydrate formation temperature (HFT). ICA is used to decide the initial weights of the neural network. The ICA-ANN is applied to predict hydrate formation temperature by 302 experimental data points that have been collected from literature. The performance of the ICA-ANN is compared with ANN and the results demonstrate the effectiveness of the ICA-ANN.

Keywords:

Imperialist Competitive Algorithm (ICA) , Artificial Neural Network , Multilayer Perceptron (MLP) , hydrate temperature and Prediction