Gas Pipeline Corrosion Prediction Based on Modified Support Vector Machine and Unequal Interval Model

Abstract:

The corrosion is an important problem for the service safety of oil and gas pipeline. This research focuses. This paper proposed a new prediction algorithm on corrosion prediction of gathering gas pipeline, which combined modified Support Vector Machine (SVM) with unequal interval model. Firstly, grey prediction method with unequal interval model was used to pretreatment original data because there is unequal interval problem in actual collected data of pipeline. Secondly, improved Support Vector Regression (SVR) based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) has been proposed to resolve parameters selection problem for SVR. Finally, the corrosion prediction model of gas pipeline has been proposed which combined improved SVR and unequal interval grey prediction method. The experiment results show this algorithm could increase precision of the pipeline corrosion prediction compared with the traditional SVM. This research provides reliable basis for in-service pipeline life prediction and confirming inspecting cycle.

• Periodical: Applied Mechanics and Materials (Volumes 373-375)
• Pages: 1987-1994
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.373-375.1987
• Online since: August 2013
• Authors: Wei Dong Zhang, Bin Shen, Yi Bo Ai, Bin Yang
• Keywords: Corrosion Prediction, Gas Pipeline, Parameters Optimization Selection, Support Vector Machine (SVM)

References

[1] Dengfeng Zheng, Jinsheng Jiang, Mingyong Wang: Journal of Safety Science and Technology, 2012, 8(10): 76-81.

[2] Bilin Shao, Weiping Ma, Zhixia Zhang: Journal of Xi'an University of Architecture & Technology(Natural Science Edition), 2006, 38(6): 804~808.

[3] ASME-B31G. Manual for Determining the Remaining Strength of Corroded Pipelines [S]. (1991).

[4] BSI PD6493. Guidelines on Method for Assessment of the acceptability of Flaws in Fusion Welding Structures. (1991).

[5] API579. Recommended Practice for Fitness-for-Service (In Chinese). ISSUE6, (1997).

[6] Caleyo F, M Hallen J, Gonzalez J L: Oil and Gas Journal, 2003, 101(2): 50-56.

[7] Klever F J: Burst strength of corroded pipe: flow stress revisited[J]. Offshore Technology, 1992, 4(13): 417-431.

DOI: 10.4043/7029-ms

[8] Lam Hong Leea, Rajprasad Rajkumara, Lai Hung Lob, etc: Expert Systems with Applications, 2013, 40(6): 1925–(1934).

[9] N. J. Laycock, P. T. Wilson: Statistical Techniques for Analysis of Inspection Data from Corroded Plant, in attendee handouts for Technical Seminar on Pressure Vessels. Occupational Safety and Health Division. Ministry of Manpower. Singapore. 9 march.

[10] Shuai Jian: Journal of the University of Petroleum, 2003, 27(4): 91-93.

[11] Carr M J, Wenbin Wang: IEEE Transactions on Reliability, 2010, 59(2): 346-355.

[12] Steven G: Support vector machines classification and regression[J]. ISIS Technical Report-Image Speech and Inrelligent System Group, 1998, 11(3): 238-242.

[13] Peter J, Brockwell R A, Davis: Time series: theory and methods[M]. New York: Springer Verlag world Publishing Corporation, (1991).

[14] Kaidirkamanathan V, Selvarajah K, Fleming P J: IEEE Transactions on Evolutionary Computation, 2006, 10(3): 245-255.

[15] Leung Y, Wang Y P: IEEE Transactions on Systems, 2000, 3 (30): 293-304.