%0 Conference Paper
%A Hassan, F.
%A Mahmood, A.K.
%A Rimsan, M.
%A Yahya, N.
%A Alam, M.K.
%D 2021
%F scholars:14713
%I Institute of Electrical and Electronics Engineers Inc.
%K Defects; Machine learning; Petroleum prospecting; Pipeline corrosion; Pipelines; Steel corrosion, Acoustic emission signal; Detection of defects; Machine learning techniques; Non-destructive evaluation techniques; Oil-gas pipelines; Pipeline monitoring; Source localization; Structural degradation, Acoustic emission testing
%P 289-293
%R 10.1109/ICCOINS49721.2021.9497222
%T AE Source Localization for Oil Gas Pipelines using Machine Learning Technique
%U https://khub.utp.edu.my/scholars/14713/
%X Structural degradation takes place in pipelines with the passage of time. Hence. The restoration of proper functioning of these pipelines requires these defects to be identified and localized. Acoustic emission (AE) is a powerful non-destructive evaluation (NDE) technique for the detection of defects. Acoustic emission signals contain a significant amount of noise. In this paper, machine learning technique has been used to accurately classify and localize the corrosion defect. Experiments were performed on a 10'' steel pipeline to show the relationship between the location of the corrosion defect and the acoustic emission signal. The results show that by using SVR, corrosion defect can identified and localized. This method is capable of providing a reference value for the real-time pipeline monitoring being operational in status, with broad application prospects. © 2021 IEEE.
%Z cited By 1; Conference of 6th International Conference on Computer and Information Sciences, ICCOINS 2021 ; Conference Date: 13 July 2021 Through 15 July 2021; Conference Code:170762