Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models
Accurate prediction of corrosion rates is crucial for preventing infrastructure failures, reducing maintenance costs, and ensuring operational safety. Traditional models often struggle to account for the complex, non-linear interactions between environmental factors and material properties. This stu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024011083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846115926453256192 |
|---|---|
| author | Ali Hussein Khalaf Bing Lin Ahmed N. Abdalla Zhongzhi Han Ying Xiao Junlei Tang |
| author_facet | Ali Hussein Khalaf Bing Lin Ahmed N. Abdalla Zhongzhi Han Ying Xiao Junlei Tang |
| author_sort | Ali Hussein Khalaf |
| collection | DOAJ |
| description | Accurate prediction of corrosion rates is crucial for preventing infrastructure failures, reducing maintenance costs, and ensuring operational safety. Traditional models often struggle to account for the complex, non-linear interactions between environmental factors and material properties. This study presents a novel approach integrating Simulated Annealing (SA) with an Adaptive Network-based Fuzzy Inference System (ANFIS) to improve corrosion rate predictions for pipeline steels. The SA-ANFIS model features six input neurons representing temperature, H₂S pressure, CO₂ pressure, salinity, moisture content, and material type. These factors influence corrosion rates, represented by a single output neuron. The SA algorithm optimizes the ANFIS model's parameters, enhancing its ability to handle non-linear relationships. Historical corrosion data for P110SS, L80, and 2205 Duplex steel were used, incorporating environmental variables such as temperature, pH, and gas pressures. The SA-ANFIS model achieved superior accuracy, with a maximum error of 2.8424 % and an average error of 1.2536 %, outperforming the GA-ANFIS model and conventional ANFIS and SVR models. The SA-ANFIS model offers a robust, optimized tool for predicting corrosion in petroleum pipelines, significantly improving prediction accuracy under harsh conditions. |
| format | Article |
| id | doaj-art-fabbcb9c38e54699ac16f9a6b5c96ac9 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-fabbcb9c38e54699ac16f9a6b5c96ac92024-12-19T10:57:06ZengElsevierResults in Engineering2590-12302024-12-0124102853Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS modelsAli Hussein Khalaf0Bing Lin1Ahmed N. Abdalla2Zhongzhi Han3Ying Xiao4Junlei Tang5School of Chemistry and Chemical Engineering & Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, 610500, ChinaSchool of Chemistry and Chemical Engineering & Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, 610500, China; Corresponding author.Faculty of Electronic Information Engineering, Huaiyin Institute of Technology, Huai'an, Jiangsu, 223003, ChinaSchool of Materials Science and Engineering, Beijing University of Chemical Technology, Beijing, 100029, ChinaSchool of Chemistry and Chemical Engineering & Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, 610500, ChinaSchool of Chemistry and Chemical Engineering & Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, 610500, China; CNPC Shenzhen New Energy Research Institute Co., Ltd., Shenzhen, 518000, China; Corresponding author. School of Chemistry and Chemical Engineering & Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, 610500, China.Accurate prediction of corrosion rates is crucial for preventing infrastructure failures, reducing maintenance costs, and ensuring operational safety. Traditional models often struggle to account for the complex, non-linear interactions between environmental factors and material properties. This study presents a novel approach integrating Simulated Annealing (SA) with an Adaptive Network-based Fuzzy Inference System (ANFIS) to improve corrosion rate predictions for pipeline steels. The SA-ANFIS model features six input neurons representing temperature, H₂S pressure, CO₂ pressure, salinity, moisture content, and material type. These factors influence corrosion rates, represented by a single output neuron. The SA algorithm optimizes the ANFIS model's parameters, enhancing its ability to handle non-linear relationships. Historical corrosion data for P110SS, L80, and 2205 Duplex steel were used, incorporating environmental variables such as temperature, pH, and gas pressures. The SA-ANFIS model achieved superior accuracy, with a maximum error of 2.8424 % and an average error of 1.2536 %, outperforming the GA-ANFIS model and conventional ANFIS and SVR models. The SA-ANFIS model offers a robust, optimized tool for predicting corrosion in petroleum pipelines, significantly improving prediction accuracy under harsh conditions.http://www.sciencedirect.com/science/article/pii/S2590123024011083Corrosion rate predictionStainless steel alloysSimulated annealingFuzzy inference systems |
| spellingShingle | Ali Hussein Khalaf Bing Lin Ahmed N. Abdalla Zhongzhi Han Ying Xiao Junlei Tang Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models Results in Engineering Corrosion rate prediction Stainless steel alloys Simulated annealing Fuzzy inference systems |
| title | Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models |
| title_full | Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models |
| title_fullStr | Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models |
| title_full_unstemmed | Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models |
| title_short | Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models |
| title_sort | enhanced prediction of corrosion rates of pipeline steels using simulated annealing optimized anfis models |
| topic | Corrosion rate prediction Stainless steel alloys Simulated annealing Fuzzy inference systems |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024011083 |
| work_keys_str_mv | AT alihusseinkhalaf enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels AT binglin enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels AT ahmednabdalla enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels AT zhongzhihan enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels AT yingxiao enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels AT junleitang enhancedpredictionofcorrosionratesofpipelinesteelsusingsimulatedannealingoptimizedanfismodels |