A neural network model predicting combined separation efficiency of compact axial cyclonic and gravity separator

The removal of denser phase from the multiphase flow is one of fundamental and challenging task in oil and gas industry. It is because crude oil emerging from the well also contains natural gas, water and some time sand. Each of these needs to be separated out for economics reason before being transported to their destination. The available technology for multiphase separation includes gravity separators, centrifugal separators, filter vane separators and mist eliminators. However these separators are expensive in both operations and purchase. Compact or in line separators are one of suitable alternative because of their low cost, simplicity, easy handling and simple installation. The performance of such a newly designed gas liquid compact centrifugal separator is under study in the department of process and system engineering at Cranfield University UK. While several mechanistic models are available in literature for gravity separator, the neural network has not been used so far to predict the separation efficiency of the compact separator at least according to literature survey done by the author. This work describes an empirical model based on a variant of MLP neural network to predict the separation efficiency of a compact gas liquid separator. This model helps operator to effectively control the multiphase separator rig by predicting the separation efficiency at the changing operating inlet condition.