{"title":"基于机器学习的塑料光纤嵌入透明混凝土抗压强度预测","authors":"Manish Pratap Singh, Anish Kumar, Sanjeev Sinha","doi":"10.1007/s42107-025-01327-6","DOIUrl":null,"url":null,"abstract":"<div><p>This study investigates the effect of plastic optical fiber integration on the compressive strength of M20 concrete. SVM-RBF, SVM-Linear, and XGBoost based machine learning prediction models were also trained and compared with conventional linear regression model. The compressive strength analysis confirms that POF inclusion reduces strength due to weak interfaces and void formation, particularly at smaller fiber spacings. However, increasing fiber spacing to 20 mm minimizes strength loss, demonstrating a more viable configuration for practical applications. The performance metrics, regression error characteristic (REC) curves, taylor diagram, and area over curve (AOC) results highlight XGBoost as the most accurate predictive model, outperforming SVM-RBF, SVM-Linear, and linear regression models. The R<sup>2</sup> values in training and testing for the XGBoost model are 0.999 and 0.997 respectively. The RMSE values in training and testing for the XGBoost model are 0.151 and 0.259 respectively. The monotonicity analysis reveals that fiber spacing and curing days positively affect compressive strength, while other mix variables remain relatively unchanged within the tested range.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2527 - 2545"},"PeriodicalIF":0.0000,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning-based prediction of compressive strength of plastic optical fiber embedded transparent concrete\",\"authors\":\"Manish Pratap Singh, Anish Kumar, Sanjeev Sinha\",\"doi\":\"10.1007/s42107-025-01327-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This study investigates the effect of plastic optical fiber integration on the compressive strength of M20 concrete. SVM-RBF, SVM-Linear, and XGBoost based machine learning prediction models were also trained and compared with conventional linear regression model. The compressive strength analysis confirms that POF inclusion reduces strength due to weak interfaces and void formation, particularly at smaller fiber spacings. However, increasing fiber spacing to 20 mm minimizes strength loss, demonstrating a more viable configuration for practical applications. The performance metrics, regression error characteristic (REC) curves, taylor diagram, and area over curve (AOC) results highlight XGBoost as the most accurate predictive model, outperforming SVM-RBF, SVM-Linear, and linear regression models. The R<sup>2</sup> values in training and testing for the XGBoost model are 0.999 and 0.997 respectively. The RMSE values in training and testing for the XGBoost model are 0.151 and 0.259 respectively. The monotonicity analysis reveals that fiber spacing and curing days positively affect compressive strength, while other mix variables remain relatively unchanged within the tested range.</p></div>\",\"PeriodicalId\":8513,\"journal\":{\"name\":\"Asian Journal of Civil Engineering\",\"volume\":\"26 6\",\"pages\":\"2527 - 2545\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Asian Journal of Civil Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s42107-025-01327-6\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asian Journal of Civil Engineering","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1007/s42107-025-01327-6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Engineering","Score":null,"Total":0}
Machine learning-based prediction of compressive strength of plastic optical fiber embedded transparent concrete
This study investigates the effect of plastic optical fiber integration on the compressive strength of M20 concrete. SVM-RBF, SVM-Linear, and XGBoost based machine learning prediction models were also trained and compared with conventional linear regression model. The compressive strength analysis confirms that POF inclusion reduces strength due to weak interfaces and void formation, particularly at smaller fiber spacings. However, increasing fiber spacing to 20 mm minimizes strength loss, demonstrating a more viable configuration for practical applications. The performance metrics, regression error characteristic (REC) curves, taylor diagram, and area over curve (AOC) results highlight XGBoost as the most accurate predictive model, outperforming SVM-RBF, SVM-Linear, and linear regression models. The R2 values in training and testing for the XGBoost model are 0.999 and 0.997 respectively. The RMSE values in training and testing for the XGBoost model are 0.151 and 0.259 respectively. The monotonicity analysis reveals that fiber spacing and curing days positively affect compressive strength, while other mix variables remain relatively unchanged within the tested range.
期刊介绍:
The Asian Journal of Civil Engineering (Building and Housing) welcomes articles and research contributions on topics such as:- Structural analysis and design - Earthquake and structural engineering - New building materials and concrete technology - Sustainable building and energy conservation - Housing and planning - Construction management - Optimal design of structuresPlease note that the journal will not accept papers in the area of hydraulic or geotechnical engineering, traffic/transportation or road making engineering, and on materials relevant to non-structural buildings, e.g. materials for road making and asphalt. Although the journal will publish authoritative papers on theoretical and experimental research works and advanced applications, it may also feature, when appropriate: a) tutorial survey type papers reviewing some fields of civil engineering; b) short communications and research notes; c) book reviews and conference announcements.