CONTACT US: Contact info
|
Citation |
Li Y, Luo Z. China Saf. Sci. J. 2020; 30(12): 100-105. |
|
Copyright |
(Copyright © 2020, China Occupational Safety and Health Association, Publisher Gai Xue bao) |
|
DOI |
|
PMID |
unavailable |
|
Abstract |
In order to study soil corrosion situation of oil and gas pipelines and to ensure safe operation of buried pipelines, best corrosion factors were selected and high contribution factors of soil corrosion were obtained by using KPCA. Then, ICS was adopted to optimize deviation and threshold of ELM hidden layer, and with high contribution factors as input and corrosion depth as output target, ICS-ELM corrosion depth prediction model was established. Finally, taking field test of a buried oil pipeline in Shaanxi Province as an example, 8 influencing factors were selected to establish a soil corrosion index system of buried oil pipelines, and prediction and verification analysis were carried out through simulation. The results show that improved CS algorithm has faster iteration rate, and the lowest relative error, root mean square error and hill inequality coefficient of prediction results of KPCA-ICS-ELM model are 0. 209%, 0. 228% and 0. 441% respectively. It is more stable and accurate compared with other models. © 2020 China Safety Science Journal. All rights reserved. Language: zh |