Abstract
AbstractArtificial neural network (ANN) can be utilized as a tool for modeling product quality prediction of Crude Distillation Unit (CDU) that is the heart of petroleum refineries. In CDU, regardless of its origin crude oil separates into economically and commercially valuable fractions. Prediction of product quality can reduce the dependency on on-line sample analyzers and also provide early detection of malfunction of CDU operations.In an attempt for this, 7–20-1 back-propagation ANN architecture was implemented to estimate 95% naphtha cut point properties using seven CDU process parameter as 120 input data sets. The best model architecture consists of 20 neurons in one hidden layer. Proposed model obtained 1.12˚C error value for training sets while acceptable error level was 1.7 ˚C. When compared with the actual data, ANN model predicted 95% naphtha cut point product quality 96% accuracy.KeywordsArtificial neural networkCrude distillation unitQuality predictionNaphtha cut points
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
