Study on Defect Detection Based on D-S Evidential Reasoning in Natural Gas Pipeline

Abstract:

Based reasoning data fusion method, Dempster-Shafer evidence reasoning applies to natural gas pipeline detecting experiments. Through the use of multiple sensors to sample the defect information in natural gas pipeline, extracting characteristic information, using neural network to carry on the fusion recognition, and then the neural networks for normalized output value as evidence, Dempster combination rule to fuse the data further and improve reliability, the final identification of the effective decision-making a type of pipeline defect. This experiment shows the D-S evidence reasoning has a strong ability to deal with uncertain information, the result proved the correctness and effectiveness.

• Periodical: Advanced Materials Research (Volume 717)
• Pages: 315-319
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.717.315
• Online since: July 2013
• Authors: Juan Li, Hong Wei Guo
• Keywords: Data Fusion, Defect Detection in Natural Gas Pipeline, D-S Evidential Reasoning

References

[1] DUAN Xin-sheng.Ecidential theory and decision-making.Artificial intelligence[M]. China Renmin University Press.1993.(Chinese)

[2] Shafer G. A mathematical theory of evidence [M ]. Princeton: Princeton University Press.1976.

[3] NI Guo-qiang,LIANG Hao-cheng. Dempster-Shafer evidence theory based data fusion technology. Beijing University of Technology. Vol21(5):pp.603-609,2001. (Chinese).

[4] Yager R R.On the Dempster-Shafer framework and new combination rules[J].Information Sciences.pp.83-138,1987(1).

[5] SONG Shou-peng. Submarine pipeline detection of defects reconstruction and ultrasonic echo signal processing methods[D]. Shanghai jiaotong university Ph.D. Thesis,2006,p.178. (Chinese)

[6] JIANG Qi. Pipeline defect magnetic flux leakage testing quantitative technique and its application research[D]. Tianjin university doctoral dissertation,2002,12,p.120. (Chinese)

[7] YANG Wan-hai. Multi-sensor data fusion and its application. Xidian University Press. 2004.(Chinese)

[8] HE You,WANG Guo-hong,PENG Ying-ning and so on. Multi-Sensor Information Fusion and Application. Electronic Industry Press. 2000.(Chinese)

[9] SUN Rui,SUN Shang-yuan,GE Yun-feng. D-S evidence theory based on the basic probability assignment of access. Modern machinery. pp.22-23,2006.(Chinese)

[10] GONG Yuan-ming,XIAO De-yun,WANG Jun-jie. Multi-sensor data fusion technology. Metallurgical Automation.p.158 – 161,2002.(Chinese)

[11] WANG Lian-feng, LIU Wei-dong. A new method of constructing the basic probability function and application. Vol31, pp.98-100, 2009. (Chinese)

[12] GAO Juan. Introduction to intelligent information processing methods. Machinery Industry Press. p.163 – 165,2004.(Chinese)

[13] A New Approach to Evidence Combination and its Application to Targets Recognition in Image Sequence[J]. Journal of Shanghai Jiaotong University(Science). pp.143-147,2007(2).