{"title":"Predicting Microbiologically Influenced Concrete Corrosion in Self-cleansing Sewers using Meta-learning Techniques","authors":"Mohammad Zounemat-Kermani, Ammar Aldallal","doi":"10.5006/4457","DOIUrl":null,"url":null,"abstract":"\n Sewer networks are not only necessary as an infrastructure for human societies, but they can also help humans achieve a stable situation with the surrounding natural environment by controlling and preventing the spread of pollution in the environment. As a result, concrete sewer maintenance and analysis of their damaging elements are critical. In this regard, modeling microbiologically influenced corrosion (MIC) is a challenging phenomenon. Due to the complicated aspects related to the interaction of microorganisms and concrete degradation, this research suggests several machine-learning models as well as traditional multiple linear regression (MLR) model to predict the MIC in sewer pipelines. The models can be categorized into three sections: (i) stand-alone models (GMDH, GRNN, RBFNN, MLPNN, CHAID, and CART), (ii) integrative models (ANFIS and SVR with PSO, ABC and FA) and (iii) ensemble meta-learner Stepwise Regression model. After implementing the models, statistical measures, including RMSE, MAE, MBE, PCC, and Nash–Sutcliffe model efficiency (NSE) are considered for evaluating models' performances. The results indicate that the ensemble Meta-learner-SR model is significantly more precise than other models. They also demonstrate that using an integrative model can improve the accuracy of stand-alone models by at least up to 42 percent. The durability and lifespan of the sewer system is also estimated by the aid of the best predictive model (Meta-learner-SR) for two scenario cases of (i) gas phase and (ii) submerged conditions. It is concluded that the sewer systems have a considerably lower life span (24 years less) exposed to submerged sewage than the gas phase with 56 years of durability.","PeriodicalId":10717,"journal":{"name":"Corrosion","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Corrosion","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.5006/4457","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Sewer networks are not only necessary as an infrastructure for human societies, but they can also help humans achieve a stable situation with the surrounding natural environment by controlling and preventing the spread of pollution in the environment. As a result, concrete sewer maintenance and analysis of their damaging elements are critical. In this regard, modeling microbiologically influenced corrosion (MIC) is a challenging phenomenon. Due to the complicated aspects related to the interaction of microorganisms and concrete degradation, this research suggests several machine-learning models as well as traditional multiple linear regression (MLR) model to predict the MIC in sewer pipelines. The models can be categorized into three sections: (i) stand-alone models (GMDH, GRNN, RBFNN, MLPNN, CHAID, and CART), (ii) integrative models (ANFIS and SVR with PSO, ABC and FA) and (iii) ensemble meta-learner Stepwise Regression model. After implementing the models, statistical measures, including RMSE, MAE, MBE, PCC, and Nash–Sutcliffe model efficiency (NSE) are considered for evaluating models' performances. The results indicate that the ensemble Meta-learner-SR model is significantly more precise than other models. They also demonstrate that using an integrative model can improve the accuracy of stand-alone models by at least up to 42 percent. The durability and lifespan of the sewer system is also estimated by the aid of the best predictive model (Meta-learner-SR) for two scenario cases of (i) gas phase and (ii) submerged conditions. It is concluded that the sewer systems have a considerably lower life span (24 years less) exposed to submerged sewage than the gas phase with 56 years of durability.
期刊介绍:
CORROSION is the premier research journal featuring peer-reviewed technical articles from the world’s top researchers and provides a permanent record of progress in the science and technology of corrosion prevention and control. The scope of the journal includes the latest developments in areas of corrosion metallurgy, mechanisms, predictors, cracking (sulfide stress, stress corrosion, hydrogen-induced), passivation, and CO2 corrosion.
70+ years and over 7,100 peer-reviewed articles with advances in corrosion science and engineering have been published in CORROSION. The journal publishes seven article types – original articles, invited critical reviews, technical notes, corrosion communications fast-tracked for rapid publication, special research topic issues, research letters of yearly annual conference student poster sessions, and scientific investigations of field corrosion processes. CORROSION, the Journal of Science and Engineering, serves as an important communication platform for academics, researchers, technical libraries, and universities.
Articles considered for CORROSION should have significant permanent value and should accomplish at least one of the following objectives:
• Contribute awareness of corrosion phenomena,
• Advance understanding of fundamental process, and/or
• Further the knowledge of techniques and practices used to reduce corrosion.