RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM
In response to pipeline corrosion surplus intensity, a surplus intensity prediction method based on the Improved Whale Optimization Algorithm (IWOA ) -Least Square Support Vector Machine (LSSVM) combination algorithm model. Firstly the influencing factors of the surplus intensity of pipeline corrosi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Strength
2024-04-01
|
| Series: | Jixie qiangdu |
| Subjects: | |
| Online Access: | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2024.02.028 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841534135471964160 |
|---|---|
| author | ZHANG Jia Ll LinFeng WANG HaoJie ZHANG Ting |
| author_facet | ZHANG Jia Ll LinFeng WANG HaoJie ZHANG Ting |
| author_sort | ZHANG Jia |
| collection | DOAJ |
| description | In response to pipeline corrosion surplus intensity, a surplus intensity prediction method based on the Improved Whale Optimization Algorithm (IWOA ) -Least Square Support Vector Machine (LSSVM) combination algorithm model. Firstly the influencing factors of the surplus intensity of pipeline corrosion. On this basis, the theoretical introduction of the LSSVM and IWOA were analyzed was introduced to propose a combination method of the model. Taking the L245N material pipeline of a certain oil field in our country as an example, the use of some pipes to corrode the remaining strength and its influencing factors to train the combination model, and predict another part of the data. Essence studies have shown that the IWOA-LSSVM model proposed at the institute was in the process of conducting pipeline corrosion surplus intensity predictions. Its average root error is 0.323 5%, the average relative error is 2. 17%, and the fitting superiority is 0.988. The three evaluation indicators are better than the PSO-LSSVM model and the WOA-LSSVM model. Therefore, using the IWOA-LSSVM model can accurately predict the remaining intensity of pipeline corrosion, and then provide data support for the maintenance and replacement of pipelines. |
| format | Article |
| id | doaj-art-fab08a163f974da18c98e228476cff5c |
| institution | Kabale University |
| issn | 1001-9669 |
| language | zho |
| publishDate | 2024-04-01 |
| publisher | Editorial Office of Journal of Mechanical Strength |
| record_format | Article |
| series | Jixie qiangdu |
| spelling | doaj-art-fab08a163f974da18c98e228476cff5c2025-01-15T02:45:37ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692024-04-014646847563930038RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVMZHANG JiaLl LinFengWANG HaoJieZHANG TingIn response to pipeline corrosion surplus intensity, a surplus intensity prediction method based on the Improved Whale Optimization Algorithm (IWOA ) -Least Square Support Vector Machine (LSSVM) combination algorithm model. Firstly the influencing factors of the surplus intensity of pipeline corrosion. On this basis, the theoretical introduction of the LSSVM and IWOA were analyzed was introduced to propose a combination method of the model. Taking the L245N material pipeline of a certain oil field in our country as an example, the use of some pipes to corrode the remaining strength and its influencing factors to train the combination model, and predict another part of the data. Essence studies have shown that the IWOA-LSSVM model proposed at the institute was in the process of conducting pipeline corrosion surplus intensity predictions. Its average root error is 0.323 5%, the average relative error is 2. 17%, and the fitting superiority is 0.988. The three evaluation indicators are better than the PSO-LSSVM model and the WOA-LSSVM model. Therefore, using the IWOA-LSSVM model can accurately predict the remaining intensity of pipeline corrosion, and then provide data support for the maintenance and replacement of pipelines.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2024.02.028Pipe corrosionResidual strengthImproved whale optimization algorithmLeast square support vector machineL245N material |
| spellingShingle | ZHANG Jia Ll LinFeng WANG HaoJie ZHANG Ting RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM Jixie qiangdu Pipe corrosion Residual strength Improved whale optimization algorithm Least square support vector machine L245N material |
| title | RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM |
| title_full | RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM |
| title_fullStr | RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM |
| title_full_unstemmed | RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM |
| title_short | RESEARCH ON THE REMAINING INTENSITY OF PIPELINE CORROSION BASED ON IWOA-LSSVM |
| title_sort | research on the remaining intensity of pipeline corrosion based on iwoa lssvm |
| topic | Pipe corrosion Residual strength Improved whale optimization algorithm Least square support vector machine L245N material |
| url | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2024.02.028 |
| work_keys_str_mv | AT zhangjia researchontheremainingintensityofpipelinecorrosionbasedoniwoalssvm AT lllinfeng researchontheremainingintensityofpipelinecorrosionbasedoniwoalssvm AT wanghaojie researchontheremainingintensityofpipelinecorrosionbasedoniwoalssvm AT zhangting researchontheremainingintensityofpipelinecorrosionbasedoniwoalssvm |