Neural Network Modeling for Monitoring Petroleum Pipelines

Abstract:

It is common occurrence that the transportation of petroleum products via pipelines is susceptible to failure either naturally or intentionally. The paper is a diagnostic problem having continuous inputs of pattern recognition used in predicting pipeline failures. Our problem is to design a neural network that will recognize failure events in pipelines when fed with an input pattern denoting such a scenario. A neural network paradigm is selected, and encoding of input is done to obtain the input pattern. The selected model is simulated and trained to recognize the output pattern, which in our scenario after training, goes into operational mode.The neural network is fully implemented on a Pentium II MMX computer with a Borland C++ builder.

• Periodical: International Journal of Engineering Research in Africa (Volume 26)
• Pages: 122-131
• DOI: https://doi.org/10.4028/www.scientific.net/JERA.26.122
• Online since: October 2016
• Authors: Ighodaro Osarobo*, Akaeze Chika
• Keywords: Monitoring, Neural Networks, Output Code, Pipelines, Scenario, Transportation

References

[1] Cihan Dagli, (eds)- ARTIFICIAL NEURAL NETWORKS FOR INTELLIGENT MANUFACTUING. Publisher: Chapman & Hall, London, (1994).

[2] Philip D. Wasserman, ANZA Research Inc- NEURAL COMPUTING, THEORY AND PRACTICE. Publisher: Van Nostrand Reinhold New York, (1989).

[3] Valluru B. Rao and Hayagriva V. Rao- C++ NEURAL NETWORKS AND FUZZY LOGIC. Publisher: Management Information System Press, (mip) New York, (1993).

[4] Bernieri A and D'Appuzzo M. - A NEURAL NETWORK APPROACH TO IDENTIFICATION AND FAULT DIAGNOSIS OF DYNAMIC SYSTEMS. Publisher: IEEE Transactions on Instrumentation and Measurement Vol. 93 No. 6 Page 867- 868, Dec. (1994).

DOI: 10.1109/19.368083

[5] Jagdish C.P., Garapati P. and Raneswor Barliarsiagh- ARTIFICIAL NEURAL NETWORK- BASED ON NON- LINEARITY ESTIMATION OF PRESSURE SENSORS. Publisher: IEEE Transactions on Instrumentation and Measurement Vol. 43 No. 6 Page 874- 876, Dec. 94.

[6] Lennart J. and Magnis L. - LEAK DETECTION THROUGH HYDRAULIC TRANSIENT ANALYSIS. Publisher: IDT Report Sept. 1987. Institute of Technology, Dept of Water Resources, University of Lung, Sweden.

[7] Po- Rong C., Chin W. and Gorg H.M. - A TRIANGULAR CONNECTION HOPEFIELD NEURAL NETWORK APPROACH TO ANALOG- TO- DIGITAL CONVERSION. Publisher: IEEE Transactions on Instrumentation and Measurement Vol. 43 No. 6 Page 853, Dec. 94.

DOI: 10.1109/19.368081

[8] Ward Smith, A.J. - PRESSURE LOSSES IN DUCTED FLOWS. Publisher: Butterworth & Co. Ltd, London (1971).

[9] Ayodele Adewale Moses- ENGINEERING SYSTEMS REQIUREMENT FOR THE DEVELOPMENT OF OIL SPILL CRISIS MANAGEMENT CENTRE (CMC). June 1991, final year project, Mechanical Engineering, University of Lagos.

[10] Arikpo Martin Omini- A NEURAL COMPUTING APPROACH TO PATTERN RECOGNITION (A CASE STUDY OF CLASSIFICATION OF DIGITS 0-9). June 2000, final year project, Computer science Dept., University of Lagos.

[11] Bryan Gottfried- PROGRAMMING WITH C (SCHAUM'S OUTLINE SERIES). Publisher: McGrawhill, New York, (1993).

[12] Harlin O. Thurston and William Middenporp (co-ed)- PATTERNS AND IMAGE PROCESSING. Publisher: Springer Verleg, Berlin, (1996).

[13] Lars Klander & Kris Jamsa- C/C++ PROGRAMMER'S BIBLE. Publishers: Jamsa Press, Las Vegas, USA.

[14] A.S. Hornby- ADVANCED OXFORD LEARNER'S DICTIONARY. Publishers: Oxford University Press, (1995).

[15] Alexander R. Kornilov- INTELLIGENT TECHNOLOGIES, NEW OPPORTUNITIES FOR MODERN INDUSTRIES; Technical University Report, Computer Science Dept., Moscow Institute of Electronic Technology, Vol. 3, (1997).

[16] Nigerian National Petroleum Corporation news reports April 199- Oct (2000).

[17] Pipeline & Gas Journals, Dec. 1999- Feb (2000).

[18] Encyclopedia Americana- international edition Vol. 20, 1994. Publisher: Grolier incorporated.