The aim of my MASc study was to design an Artificial Neural Network (ANN) trained on data set to cover a wide operating range of all parameters affecting the demulsifier dosage in a desalting process for crude oil operations. This network will be used to work as a black box model inside the controller in which all affecting parameters are inputs and the demulsifier dosage is the controller’s output. Testing this control scheme showed an effective reduction in demulsifier consumption rate compared to existing methods. The results also showed that the existing control strategy is highly conservative to prevent the salt from exceeding the limit. The generated function from the ANN was also used to optimize the amount of fresh water added to wash the salty crude oil. Further, an ANN model was developed in this research to generate an online estimate of the salt content in the produced oil.
Thesis: Modeling and Optimization of Desalting Process in Oil Industry (PDF)