{"title":"用机器学习方法预测使用可持续天然 FRP 复合材料加固的混凝土强度","authors":"Shabbir Ali Talpur , Phromphat Thansirichaisree , Nakhorn Poovarodom , Hisham Mohamad , Mingliang Zhou , Ali Ejaz , Qudeer Hussain , Panumas Saingam","doi":"10.1016/j.jcomc.2024.100466","DOIUrl":null,"url":null,"abstract":"<div><p>Recent earthquakes have highlighted the need to strengthen existing structures with substandard designs. NFRPs provide a sustainable, cost-effective alternative for strengthening, but accurately predicting their performance remains a challenge. This study investigates the use of machine learning algorithms for predicting the compressive strength concrete specimens confined with various NFRPs. Four algorithms were employed: decision tree, random forest, neural network, and gradient boosting regressor. A diverse dataset encompassing various geometries, material properties, and confinement configurations was used to train and evaluate the models. Gradient boosting regressor (GBR) achieved the highest performance, with an average R-squared value of 0.94 and low mean absolute error (MAE) and root mean squared error (RMSE) during training and k-fold cross-validation. Neural network and random forest also demonstrated satisfactory performance, with average R-squared values of 0.88 and 0.86, respectively, during cross-validation. These results suggest that machine learning holds promise for predicting the compressive strength of concrete confined with NFRPs. GBR offers the most accurate predictions, making it a valuable tool for engineers seeking to optimize the design and performance of strengthened structures using sustainable materials.</p></div>","PeriodicalId":34525,"journal":{"name":"Composites Part C Open Access","volume":"14 ","pages":"Article 100466"},"PeriodicalIF":5.3000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666682024000379/pdfft?md5=08c6bce51afb8626a4ef3bdbd9b2895c&pid=1-s2.0-S2666682024000379-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Machine learning approach to predict the strength of concrete confined with sustainable natural FRP composites\",\"authors\":\"Shabbir Ali Talpur , Phromphat Thansirichaisree , Nakhorn Poovarodom , Hisham Mohamad , Mingliang Zhou , Ali Ejaz , Qudeer Hussain , Panumas Saingam\",\"doi\":\"10.1016/j.jcomc.2024.100466\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Recent earthquakes have highlighted the need to strengthen existing structures with substandard designs. NFRPs provide a sustainable, cost-effective alternative for strengthening, but accurately predicting their performance remains a challenge. This study investigates the use of machine learning algorithms for predicting the compressive strength concrete specimens confined with various NFRPs. Four algorithms were employed: decision tree, random forest, neural network, and gradient boosting regressor. A diverse dataset encompassing various geometries, material properties, and confinement configurations was used to train and evaluate the models. Gradient boosting regressor (GBR) achieved the highest performance, with an average R-squared value of 0.94 and low mean absolute error (MAE) and root mean squared error (RMSE) during training and k-fold cross-validation. Neural network and random forest also demonstrated satisfactory performance, with average R-squared values of 0.88 and 0.86, respectively, during cross-validation. These results suggest that machine learning holds promise for predicting the compressive strength of concrete confined with NFRPs. GBR offers the most accurate predictions, making it a valuable tool for engineers seeking to optimize the design and performance of strengthened structures using sustainable materials.</p></div>\",\"PeriodicalId\":34525,\"journal\":{\"name\":\"Composites Part C Open Access\",\"volume\":\"14 \",\"pages\":\"Article 100466\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-05-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2666682024000379/pdfft?md5=08c6bce51afb8626a4ef3bdbd9b2895c&pid=1-s2.0-S2666682024000379-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Composites Part C Open Access\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666682024000379\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, COMPOSITES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composites Part C Open Access","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666682024000379","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, COMPOSITES","Score":null,"Total":0}
引用次数: 0
摘要
最近发生的地震凸显了加固设计不合标准的现有结构的必要性。NFRP 为加固提供了一种可持续的、具有成本效益的替代方案,但准确预测其性能仍是一项挑战。本研究调查了机器学习算法在预测使用各种 NFRP 加固的混凝土试件抗压强度方面的应用。研究采用了四种算法:决策树、随机森林、神经网络和梯度提升回归器。模型的训练和评估使用了一个包含各种几何形状、材料特性和约束配置的多样化数据集。梯度提升回归器(GBR)的性能最高,平均 R 平方值为 0.94,在训练和 k 倍交叉验证期间的平均绝对误差(MAE)和均方根误差(RMSE)都很低。神经网络和随机森林的表现也令人满意,在交叉验证期间的平均 R 平方值分别为 0.88 和 0.86。这些结果表明,机器学习有望预测使用非弹性体加固混凝土的抗压强度。GBR 提供了最准确的预测,使其成为工程师优化使用可持续材料的加固结构设计和性能的重要工具。
Machine learning approach to predict the strength of concrete confined with sustainable natural FRP composites
Recent earthquakes have highlighted the need to strengthen existing structures with substandard designs. NFRPs provide a sustainable, cost-effective alternative for strengthening, but accurately predicting their performance remains a challenge. This study investigates the use of machine learning algorithms for predicting the compressive strength concrete specimens confined with various NFRPs. Four algorithms were employed: decision tree, random forest, neural network, and gradient boosting regressor. A diverse dataset encompassing various geometries, material properties, and confinement configurations was used to train and evaluate the models. Gradient boosting regressor (GBR) achieved the highest performance, with an average R-squared value of 0.94 and low mean absolute error (MAE) and root mean squared error (RMSE) during training and k-fold cross-validation. Neural network and random forest also demonstrated satisfactory performance, with average R-squared values of 0.88 and 0.86, respectively, during cross-validation. These results suggest that machine learning holds promise for predicting the compressive strength of concrete confined with NFRPs. GBR offers the most accurate predictions, making it a valuable tool for engineers seeking to optimize the design and performance of strengthened structures using sustainable materials.