Hua Si, Daoming Shen, Muhammad Nasir Amin, Siyab Ul Arifeen, Muhammad Tahir Qadir, Kaffayatullah Khan
{"title":"Producing sustainable binding materials using marble waste blended with fly ash and rice husk ash for building materials","authors":"Hua Si, Daoming Shen, Muhammad Nasir Amin, Siyab Ul Arifeen, Muhammad Tahir Qadir, Kaffayatullah Khan","doi":"10.1515/rams-2024-0049","DOIUrl":null,"url":null,"abstract":"This study explores the possibilities of a new binding material, <jats:italic>i.e.</jats:italic>, marble cement (MC) made from recycled marble. It will assess how well it performs when mixed with ash from rice husks and fly ash. This research analyzes flexural strength of marble cement mortar (FR-MCM), a mortar that incorporates MC, fly ash, and rice husk ash. A set of machine learning models capable of predicting CS and FS (flexural and compressive strengths) were developed. Gene expression programming (GEP) and multi-expression programming (MEP) are crucial in creating these types of models. Statistics, Taylor’s diagrams, <jats:italic>R</jats:italic> <jats:sup>2</jats:sup> values, and comparisons of experimental and theoretical results were used to evaluate the models. Stress testing also showed how different input features affected the model’s outputs. The accuracy of all GEP models was shown to fall within the acceptable range (<jats:italic>R</jats:italic> <jats:sup>2</jats:sup> = 0.952 for CS and <jats:italic>R</jats:italic> <jats:sup>2</jats:sup> = 0.920 for FS), and all MEP prediction models were determined to be exceptionally accurate (<jats:italic>R</jats:italic> <jats:sup>2</jats:sup> = 0.970 for CS and <jats:italic>R</jats:italic> <jats:sup>2</jats:sup> = 0.935 for FS). The statistical testing for error validation also verified that MEP models were more accurate than GEP models. According to sensitivity analysis, curing age and rice husk ash exerted the most significant influence on the prediction of CS and FS, followed by fly ash and MC.","PeriodicalId":54484,"journal":{"name":"Reviews on Advanced Materials Science","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Reviews on Advanced Materials Science","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1515/rams-2024-0049","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
This study explores the possibilities of a new binding material, i.e., marble cement (MC) made from recycled marble. It will assess how well it performs when mixed with ash from rice husks and fly ash. This research analyzes flexural strength of marble cement mortar (FR-MCM), a mortar that incorporates MC, fly ash, and rice husk ash. A set of machine learning models capable of predicting CS and FS (flexural and compressive strengths) were developed. Gene expression programming (GEP) and multi-expression programming (MEP) are crucial in creating these types of models. Statistics, Taylor’s diagrams, R2 values, and comparisons of experimental and theoretical results were used to evaluate the models. Stress testing also showed how different input features affected the model’s outputs. The accuracy of all GEP models was shown to fall within the acceptable range (R2 = 0.952 for CS and R2 = 0.920 for FS), and all MEP prediction models were determined to be exceptionally accurate (R2 = 0.970 for CS and R2 = 0.935 for FS). The statistical testing for error validation also verified that MEP models were more accurate than GEP models. According to sensitivity analysis, curing age and rice husk ash exerted the most significant influence on the prediction of CS and FS, followed by fly ash and MC.
期刊介绍:
Reviews on Advanced Materials Science is a fully peer-reviewed, open access, electronic journal that publishes significant, original and relevant works in the area of theoretical and experimental studies of advanced materials. The journal provides the readers with free, instant, and permanent access to all content worldwide; and the authors with extensive promotion of published articles, long-time preservation, language-correction services, no space constraints and immediate publication.
Reviews on Advanced Materials Science is listed inter alia by Clarivate Analytics (formerly Thomson Reuters) - Current Contents/Physical, Chemical, and Earth Sciences (CC/PC&ES), JCR and SCIE. Our standard policy requires each paper to be reviewed by at least two Referees and the peer-review process is single-blind.