Precise Prediction of Interface Distribution of Materials in Multiphase Separation Facilities Using a Low-Cost and Simple Technique: ANN

Document Type : Research Article

Authors

1 Faculty of Physics, Shahrood University of Technology, Shahrood, I.R. IRAN

2 Department of Physics, Faculty of Science, University of Qom, I.R. IRAN

10.30492/ijcce.2019.36073

Abstract

The ability to precisely detect the interface of the different phases in a vessel plays an important role in chemical plants, oil, and petroleum industry. The purpose of this research is to apply the gamma-ray attenuation technique (single point source and single detector) together with MultiLayer Perceptron (MLP) neural network to detect the interface present in water-gasoil two-phase flows in pipelines and vessels, for the first time. The experimental setup is comprised of a plastic rod scintillator (BC400) coupled with two PMT tubes at two sides as a position-sensitive detector, a point gamma-ray source (137Cs), and a vessel between the source and detector. The detection system provides the required data for training and testing the network. Using this proposed method, the interface locations were determined in two-phase with mean relative error percentages less than 0.34% and 0.27% for levels of water and gasoil, respectively. The mean absolute error values were measured less than 1.16 and 1. Also, the correlation coefficients were calculated 0.999 and 1. These results presented the accuracy of the proposed method in order to determine the interface position. The used set-up is simpler than other proposed techniques and cost, radiation safety, shielding requirements, and risk production are minimized.

Keywords

Main Subjects


[1] Golnabi H., Design and Operation of a Fiber Optic Sensor for Liquid Level Detection, Opt. Lasers. Eng., 41: 801-812 (2004).
[2] Lucklum F., Jakoby B., Novel Magnetic Acoustic Resonator Sensors for Remote Liquid Phase Measurement and Mass Detection, Sens. Actuators A., 145: 41-55 (2008).
[3] Kabor T., Werthschützky R., Wafer Level Processing of Overload-Resistant Pressure Sensors, Procedia. Eng., 47: 615-618 (2012).
[4] Sakharo V.E., Kuznetsov S.A., Zaitsev B.D., Kuznetsova I.E., Joshi S.G., Liquid Level Sensor Using Ultrasonic Lamb Waves, Ultrasonics., 41: 319-322 (2003).
[6] Primrose K.M., Qiu C., Bolton G.T., Talmon A.M., Glen N., Ross A., Learmouth D., “Visualisation and Measurement of 3 Phase (Air Water Oil) Flow and 2 Phase Flow (Sand Water) with Electrical Tomography”, Proc. 6th World Congr. Ind. Process Tomog., September, (2010).
[7] Pradeep C., Ru Y., Mylvaganam S., “Interface Detection in Pipe Separators Using ECT”, Proc. IEEE Int. SAS., Feburay 22-24, San Antonio, TX, USA (2011).
[9] Gholipour Peyvandi R., Islami Rad S.Z., Taheri A., Rahmanzadeh Tootkaleh S., Askari Lehdarboni M., Study of 60Co as Gamma Source in Backscatter Gamma Densitometers, Kerntechnik., 80: 275-279 (2015).
[11] Zahoor Raja M.A., Samar R., Manzar M.A., Shah S.M., Design of Unsupervised Fractional Neural Network Model Optimized with Interior Point Algorithm for Solving Bagley–Torvik Equation, Math. Com. Sim., 132:139-158 (2017).
[12] Guiné R., Gonçalves C., Matos S., Gonçalves F., Costa D.V.T.A., Mendes M., Modeling Through Artificial Neural Networks of the Phenolic Compounds and Antioxidant Activity of Blueberries, Iran. J. Chem. Chem. Eng. (IJCCE), 37(2): 193-212 (2018).
[14] Demuth H., Beale M., Hagan M., “Neural Network Toolbox TM 6, User’s Guide, The Math Works”, Massachusetts (2008).
[15] Zaknich A., “Neural Networks for Intelligent Signal Processing”, World Scientific Pub Co. Inc., Toh Tuck Link (2011).