Zhang He
School of Electronic and Information Engineering, Southwest Petroleum University, Chengdu, 610500, Sichuan, China
Deng Zhen
School of Electronic and Information Engineering, Southwest Petroleum University, Chengdu, 610500, Sichuan, China
Ge Liang
School of Electronic and Information Engineering, Southwest Petroleum University, Chengdu, 610500, Sichuan, China
ABSTRACT
Pipelines provide the most economical means of carrying oil and gas. Pipeline transportation has become one of the five biggest transportation businesses which plays an important role in national economy and production. Through the laboratory simulation software ANSYS to establish the pipeline defect two-dimensional simulation model, according to the magnetic flux leakage detection signal selecting appropriate parameters of pipeline defect identification. Based on the RBF artificial neural network of pipeline defect quantitative identification, the experimental results show that this method is used to predict the pipeline defect of high accuracy and can be applied to pipeline defect quantitative prediction. And Provide theoretical basis for identifying the choice of methods and application.
PDF References Citation
How to cite this article
Zhang He, Deng Zhen and Ge Liang, 2013. Research on Pipeline Defects Identification Method based on RBF Neural Network. Information Technology Journal, 12: 4744-4747.
DOI: 10.3923/itj.2013.4744.4747
URL: https://scialert.net/abstract/?doi=itj.2013.4744.4747
DOI: 10.3923/itj.2013.4744.4747
URL: https://scialert.net/abstract/?doi=itj.2013.4744.4747
REFERENCES
- Narimani, M., S. Nazem and M. Loueipour, 2009. Robotics vision-based system for an underwater pipeline and cable tracker. Proceedings of the Conference on Europe Oceans, May 11-14, 2009, Bremen, Germany, pp: 1-6.
CrossRef - Song, X.C., X.J. Wu and Y.H. Kang, 2004. An inspection robot for boiler tube using magnetic flux leakage and ultrasonic methods. Insight-Non-Destructive Testing Condition Monitor., 46: 275-278.
CrossRef