• Vol 9, No 1 (2018)
  • Chemical Engineering

Modeling and Optimizing a Vacuum Gas Oil Hydrocracking Plant using an Artificial Neural Network

Sepehr Sadighi, Seyed Reza Seif Mohaddecy, Ali Abbasi


Publish at : 27 Jan 2018 - 00:00
IJtech : IJtech Vol 9, No 1 (2018)
DOI : https://doi.org/10.14716/ijtech.v9i1.44

Cite this article as:
Sadighi, S., Mohaddecy, S.R.S., Abbasi, A., 2018. Modeling and Optimizing a Vacuum Gas Oil Hydrocracking Plant using an Artificial Neural Network. International Journal of Technology. Volume 9(1), pp. 99-109
40
Downloads
Sepehr Sadighi Research Institute of Petroleum Industry (RIPI), West side of Azadi Complex
Seyed Reza Seif Mohaddecy Research Institute of Petroleum Industry (RIPI), West side of Azadi Complex
Ali Abbasi Research Institute of Petroleum Industry (RIPI), West side of Azadi Complex
Email to Corresponding Author

Abstract
image

In this research, based on actual data gathered from an industrial scale vacuum gas oil (VGO) hydrocracker and artificial neural network (ANN) method, a model is proposed to simulate yields of products including light gases, liquefied petroleum gas (LPG), light naphtha, heavy naphtha, kerosene, diesel and unconverted oil (off-test). The input layer of the ANN model consists of the catalyst, feed and recycle flow rates, and bed temperatures, while the output neurons are yields of those products. The results showed that the AAD% (average absolute deviation) of the developed ANN model for training, testing, and validating data are 0.445%, 1.131% and 0.755%, respectively. Then, by considering all operational constraints, the results confirmed that the decision variables (i.e., recycle rate and bed temperatures) generated by the optimization approach can enhance the gross profit of the hydrocracking process to more than $0.81 million annually, which is significant for the economy of the target refinery.

Artificial neural network; Hydrocracking; Modeling; Optimization; Vacuum gas oil

Conclusion

An industrial scale VGO hydrocracking unit was modeled using the ANN method. This model was designed based on a feed-forward neural network with seven neurons in the input layer and three neurons in the hidden layer. The input process variables were catalyst life, fresh and recycle feed flow rates, and the input temperature to each catalytic bed. For all VGO hydrocracking products (i.e., light gases, LPG, light and heavy naphtha, kerosene, diesel, and unconverted oil), the ANN model was trained, tested, and validated. The results showed that ANN could simulate yield of products for 69 operating points during 557 days with an AAD% of 1.2%.

To propose an application for the constructed ANN model, the gross profit function of the VGO hydrocracking plant was maximized by considering some limitations in the process. The results showed that within the permissible range for the manipulated variables (i.e., the recycle flow rate and bed temperatures), the average gross profit of the target unit could be increased to $810,000 per year. Furthermore, due to the reduction in the temperature of hydrocracking beds after optimization, it was possible to reduce the coke formation on the catalyst surface, which subsequently would increase the cycle life of the catalyst.


References

Alhajree, I., Zahedi, G.R., Manan, Z.A., Mohammad Zadeh, S., 2011. Modeling and Optimization of an Industrial Hydrocracker Plan. Journal of Petroleum Science Engineering, Volume 78, pp. 627–636

Asia-Pacific/Persian Gulf MarketScan, 2016. Volume 35(49), pp. 1–16

Bahmani, M., Sharifi, K., Shirvani, M., 2010. Product Yields Prediction of Tehran Refinery Hydrocracking Unit. Iranian Journal of Chemical Engineering, Volume 7(4), pp. 50–60

Balasubramanian, P., Pushpavanam, S., 2008. Model Discrimination in Hydrocracking of Vacuum Gas Oil using Discrete Lumped Kinetics. Fuel, Volume 87, pp. 1660–1672

Becker, P.J., Celse, B., Guillaume, D., Costa, V., Bertier, L., Guillon, E., Pirngruber, G., 2016. A Continuous Lumping Model for Hydrocracking on a Zeolite Catalysts: Model Development and Parameter Identification. Fuel, Volume 164, pp. 73–82

Bhutani, N., Ray, A.K., Rangaiah, G.P., 2006. First-principles, Data-based, and Hybrid Modeling and Optimization of an Industrial Hydrocracking Unit. Industrial & Engineering Chemistry Research, Volume 45, pp. 7807–7816

Boosari, S.H., Makouei, N., Stewart, P., 2017. Application of Bayesian Approach in the Parameter Estimation of Continuous Lumping Kinetic Model of Hydrocracking Process. Advances in Chemical Engineering and Science, Volume 7(3), pp. 257–269

Calderon, C.J., Ancheyta, J., 2016. Modeling of Slurry-phase Reactors for Hydrocracking of Heavy Oils. Energy & Fuels, Volume 30, pp. 2525–2543

Chandwani, V., Agrawal, V., Nagar, R., Singh, S., 2015. Modeling Slump of Ready Mix Concrete Using Artificial Neural Network. International Journal of Technology, Volume 6(2), pp. 207–216

Elizalde, I., Trejo, F., Munoz, J.A.D., Torres, P., Ancheyta, J., 2016. Dynamic Modeling and Simulation of a Bench-scale Reactor for the Hydrocracking of Heavy Oil by using the Continuous Kinetic Lumping Approach. Reaction Kinetics, Mechanisms and Catalysis, Volume 118, pp. 299–311

Esmaeel, S.A., Gheni, S.A., Jarullah, T.A., 2016. 5-Lumps Kinetic Modeling, Simulation and Optimization for Hydrotreating of Atmospheric Crude Oil Residue. Applied Petrochemical Research, Volume 6(2), pp. 117–133

Fachrurrazi, Husin, S., Munirwansyah, Husaini, 2017. The Subcontractor Selection Practice using ANN-Multilayer. International Journal of Technology, Volume 8(4), pp. 761–772

Faraji, D., Sadighi, S., Mazaheri, D., 2017. Modeling and Evaluating Zeolite and Amorphous Based Catalysts in Vacuum Gas Oil Hydrocracking Process. International Journal of Chemical Reactor Engineering, Volume 16(1), pp. 1–14

Istadi, I., Amin, N.A.S., 2006. A Hybrid Artificial Neural Network-genetic Algorithm (ANN-GA) Technique for Modeling and Optimization of Plasma Reactor. Industrial & Engineering Chemical          Research, Volume 45, pp. 6655–6664

Istadi, I., Amin, N.A.S., 2007. Catalytic-Dielectric Barrier Discharge Plasma Reactor for Methane and Carbon Dioxide Conversion. Bulletin of Chemical Reaction Engineering & Catalysis, Volume 2, pp. 37–44

Kusumoputro, B., Sutarya, D., Faqih, A., 2016. Performance Analysis of an Automatic Green Pellet Nuclear Fuel Quality Classification using Modified Radial Basis Function Neural Networks. International Journal of Technology, Volume 7(4), pp. 709–719

Sadighi, S., 2016. Yield Control of a Pilot Scale Vacuum Gas Oil Hydrocracker using a Soft-Sensing Approach. Journal of Chemical Engineering of Japan, Volume 49(12), pp. 979–986

Sadighi, S., Ahmad, A., Mohaddecy, S.R., 2010. 6-Lump Kinetic Model for a Commercial Vacuum Gas Oil Hydrocracker. International Journal of Chemical Reactor Engineering, Volume 7, pp. 1–25

Sadighi, S., Arshad, A., 2013. An Optimisation Approach for Increasing the Profit of a Commercial VGO Hydrocracking process. Canadian Journal of Chemical Engineering, Volume 91, pp. 1077–1091

Sadighi, S., Arshad, A., Shirvani, M., 2011. Comparison of Lumping Approaches to Predict the
Product Yields in a Dual Bed VGO Hydrocracker. International Journal of Chemical Reactor Engineering, Volume 9(A4), pp. 1–25

Sadighi, S., Mohaddecy, R.S., 2013. Predictive Modeling for Industrial Naphtha Reforming Plant Using Artificial Neural Network with Recurrent Layers. International Journal of Technology, Volume 4(2), pp. 102–111

Sadighi, S., Zahedi, S., Hayati, R., Bayat, M., 2013. Studying Catalyst Activity in an Isomerization Plant to Upgrade the Octane Number of Gasoline by using a Hybrid Artificial Neural Network Model. Energy Technology, Volume 1, pp. 743–750

Vasseghian, Y., Ahmadi, M., 2014. Artificial Intelligent Modeling and Optimizing of an Industrial Hydrocracker Plant. Journal of Chemical and Petroleum Engineering, Volume 48(2), pp. 125–137

Zuna, H.T., Hadiwardoyo, S.P., Rahadian, H., 2016. Developing a Model of Toll Road Service Quality Using an Artificial Neural Network Approach. International Journal of Technology, Volume 7(4), pp. 562–570