Scholars Central

Conference abstract

Obtained more gasoil in HCR unit by using artificial neural network

Authors: Ali Shaeri

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

A feed forward and multilayer perceptron artificial neural network (ANN) with back propagation algorithm were applied for prediction of maximum rate of gasoil production in a live hydrocracker unit (HCR). To this aim, two years of operating conditions were gathered from distributed control system (DCS). The simulation of unit by petro-SIM software was done as the first step to find important operational conditions. A three-layer ANN was adopted to predict maximum gasoil production in terms of aforementioned inputs. To find the best fitted ANN structure, 3342 different structures were examined. It was found that the best structure possessed 4, 7 and 1 neurons for the first, second and third layer, respectively. Furthermore, logsig, logsig and purelin were found the best transfer function for first, second and third layer. The best model was extracted and the obtained data were applied to the live HCR unit with capacity of 40000 bbl/day. The yielded optimum data related to ANN such as reactor temperature, reactor pressure and H2/HC mole ration were selected. Applying the ANN data resulted in an increase in the amount of gasoil and save near to $.

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • JournalInternational Journal of Applied Science - Research and Review
  • SubjectComputer Science & IT
  • BylineArticles whose byline prints “Ali Shaeri”

For authors and organisers

Publish, present and keep up with your field

Find the right journal for your paper and submit your manuscript.

Photo: Pexels