External corrosion rate prediction of buried pipeline based on RBF model
In order to overcome the shortcomings of fuzziness, randomness and interaction between the soil corrosion factors of buried pipeline, as well as the low accuracy of prediction with the traditional methods, a prediction model of external corrosion rate was established with 10 influencing factors as t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Oil & Gas Storage and Transportation
2022-02-01
|
| Series: | You-qi chuyun |
| Subjects: | |
| Online Access: | http://yqcy.xml-journal.net/cn/article/doi/10.6047/j.issn.1000-8241.2022.02.014 |
| _version_ | 1797210091432181760 |
|---|---|
| author | Changjing LIANG Endong GUAN |
| author_facet | Changjing LIANG Endong GUAN |
| author_sort | Changjing LIANG |
| collection | DOAJ |
| description | In order to overcome the shortcomings of fuzziness, randomness and interaction between the soil corrosion factors of buried pipeline, as well as the low accuracy of prediction with the traditional methods, a prediction model of external corrosion rate was established with 10 influencing factors as the input, and the external corrosion rate as the output based on the field data of corrosion coupons of a buried pipeline. Thereby, the data samples were trained, verified and tested using the Radial Basis Function (RBF) neural network mode, and the key parameters affecting the corrosion were identified through Sobol sensitivity analysis. The results show that the mean square error is 0.000 99 when 10-35-1 type RBF model is iterated to step 2 273, and the correlation coefficients of the training, validation and testing stages are 0.970 7, 0.981 3 and 0.990 1 respectively. Compared with BP, MLR and SVM models, the average relative error of RBF neural network model is 2.07%, indicating that RBF neural network model has some advantages in terms of the external corrosion rate prediction of buried pipeline. The soil resistivity has the maximum effect on the external corrosion rate. Moreover, the soil resistivity, pH value, and Cl- content significantly interact with other factors, which should be paid much more attention. Generally, the established model can be effectively applied to the external corrosion rate prediction of pipeline, and the results could provide theoretical basis and reference for pipeline integrity management. |
| first_indexed | 2024-04-24T10:05:05Z |
| format | Article |
| id | doaj.art-393fb6495c694fa885052ecbda0e0801 |
| institution | Directory Open Access Journal |
| issn | 1000-8241 |
| language | zho |
| last_indexed | 2024-04-24T10:05:05Z |
| publishDate | 2022-02-01 |
| publisher | Editorial Office of Oil & Gas Storage and Transportation |
| record_format | Article |
| series | You-qi chuyun |
| spelling | doaj.art-393fb6495c694fa885052ecbda0e08012024-04-13T02:28:16ZzhoEditorial Office of Oil & Gas Storage and TransportationYou-qi chuyun1000-82412022-02-0141223324010.6047/j.issn.1000-8241.2022.02.014yqcy-41-2-233External corrosion rate prediction of buried pipeline based on RBF modelChangjing LIANG0Endong GUAN1Hebei Huabei Petroleum GangHua Survey Planning & Design Co. Ltd.Gaosheng Oil Production Plant, CNPC Liaohe Oilfield CompanyIn order to overcome the shortcomings of fuzziness, randomness and interaction between the soil corrosion factors of buried pipeline, as well as the low accuracy of prediction with the traditional methods, a prediction model of external corrosion rate was established with 10 influencing factors as the input, and the external corrosion rate as the output based on the field data of corrosion coupons of a buried pipeline. Thereby, the data samples were trained, verified and tested using the Radial Basis Function (RBF) neural network mode, and the key parameters affecting the corrosion were identified through Sobol sensitivity analysis. The results show that the mean square error is 0.000 99 when 10-35-1 type RBF model is iterated to step 2 273, and the correlation coefficients of the training, validation and testing stages are 0.970 7, 0.981 3 and 0.990 1 respectively. Compared with BP, MLR and SVM models, the average relative error of RBF neural network model is 2.07%, indicating that RBF neural network model has some advantages in terms of the external corrosion rate prediction of buried pipeline. The soil resistivity has the maximum effect on the external corrosion rate. Moreover, the soil resistivity, pH value, and Cl- content significantly interact with other factors, which should be paid much more attention. Generally, the established model can be effectively applied to the external corrosion rate prediction of pipeline, and the results could provide theoretical basis and reference for pipeline integrity management.http://yqcy.xml-journal.net/cn/article/doi/10.6047/j.issn.1000-8241.2022.02.014radial basisburied pipelineexternal corrosionsobol sensitivitysoil resistivity |
| spellingShingle | Changjing LIANG Endong GUAN External corrosion rate prediction of buried pipeline based on RBF model You-qi chuyun radial basis buried pipeline external corrosion sobol sensitivity soil resistivity |
| title | External corrosion rate prediction of buried pipeline based on RBF model |
| title_full | External corrosion rate prediction of buried pipeline based on RBF model |
| title_fullStr | External corrosion rate prediction of buried pipeline based on RBF model |
| title_full_unstemmed | External corrosion rate prediction of buried pipeline based on RBF model |
| title_short | External corrosion rate prediction of buried pipeline based on RBF model |
| title_sort | external corrosion rate prediction of buried pipeline based on rbf model |
| topic | radial basis buried pipeline external corrosion sobol sensitivity soil resistivity |
| url | http://yqcy.xml-journal.net/cn/article/doi/10.6047/j.issn.1000-8241.2022.02.014 |
| work_keys_str_mv | AT changjingliang externalcorrosionratepredictionofburiedpipelinebasedonrbfmodel AT endongguan externalcorrosionratepredictionofburiedpipelinebasedonrbfmodel |