Title :
Using Neural Networks as Pipeline Defect Classifiers
Author :
Akram, Nik Ahmad ; Shafiabady, Niusha ; Isa, Dino
Author_Institution :
Sch. of Electr. & Electron. Eng., Univ. of Nottingham, Semenyih, Malaysia
Abstract :
In this paper we discuss an approach to classify different level of defects on a pipeline. The proposed techniques implemented on a lab scale experimental rig and tested using real-time signal. The signal is acquired using Long Range Ultrasonic Transducer (LRUT) then classified using Neural Network (NN). The Neural Network was able to classify the different signal of different level of defects.
Keywords :
mechanical engineering computing; neural nets; pipelines; reliability; signal classification; ultrasonic transducers; LRUT; NN; long range ultrasonic transducer; neural networks; pipeline defect classifiers; signal acquisition; signal classification; Acoustics; Companies; Educational institutions; Inspection; Neural networks; Pipelines; Transducers;
Conference_Titel :
IT Convergence and Security (ICITCS), 2013 International Conference on
Conference_Location :
Macao
DOI :
10.1109/ICITCS.2013.6717894
