Analysis of supersonic separators geometry using generalized radial basis function (GRBF) artificial neural networks

• Modeling of supersonic separator that includes many variables using neural network.
• Generalized radial basis function shows acceptable performance in design purposes.
• Optimal neural network is quicker response rather than theoretical simulations.
• Design predictions make well in various scales over wide range of conditions.
• Network with optimal parameters (spread, number of neurons) used for trend analysis.

Supersonic separators (3S) are comprised from unique combination of known physical processes, combining aero-dynamics, thermo-dynamics and fluid-dynamics to produce an innovative gas conditioning process. Condensation and separation at supersonic velocity is the key to achieve a significant reduction in both capital and operating costs. Natural gas dehydration, ethane extraction, LPG production and natural gas sweetening are some potential applications of 3S units among many others. Feed-forward artificial neural networks (ANNs) are also powerful tools for empirical modeling of various engineering processes. Generalized radial basis function (GRBF) networks which are kernel based ANNs, have the best approximation property since they represent the optimal solution of multivariate linear regularization theory. A large set of synthetic data are generated in this work via the fundamental modeling of 3S units and are used to train an optimal GRBF network. The trained network is then used to properly design two pilot and industrial scale 3S units for natural gas dehumidification processes. Furthermore, the trained network is successfully and much more rapidly used for trend analysis purposes to investigate the effect of various input parameters. The conducted research clearly demonstrates the acceptable performance of such neural networks for both design and trend analysis purposes.