Citation

Bi A, Luo Z, Song Y, Zhang X. China Saf. Sci. J. 2020; 30(6): 78-83.

Copyright

(Copyright © 2020, China Occupational Safety and Health Association, Publisher Gai Xue bao)

DOI

10.16265/j.cnki.issn1003-3033.2020.06.012

PMID

unavailable

Abstract

In order to explore residual strength of submarine pipelines with internal corrosion, and provide reference for maintenance so as to ensure safe operation, a FOA-GRNN calculation method of residual strength was proposed and a prediction model was constructed by using GRNN based on influencing factors like wall thickness, diameter, corrosion depth, length, width and ultimate tensile strength. Then, FOA was used to optimize the model, and negative influence of smooth factors were set artificially. Influencing factors and residual strength database were simulated and generated by finite element method, and trained and predicted through FOA-GRNN model. Finally, with experimental data of pipeline ultimate strength blasting from PETROBRAS Research Institute as an example, the prediction model was verified. The results show that average relative error of FOA-GRNN model is 16. 53% for residual strength prediction of finite element simulation data, and 7. 81% for experimental data prediction, which are reasonable and accurate. © 2020 China Safety Science Journal. All rights reserved.

Language: zh