{"title":"基于机器学习和多目标灰狼优化的自动化、经济和环保型沥青混合料设计","authors":"Jian Liu , Fangyu Liu , Linbing Wang","doi":"10.1016/j.jtte.2023.10.002","DOIUrl":null,"url":null,"abstract":"<div><p>The increasing impact of the greenhouse effect on ecosystems is prompting transportation agencies to seek methods for reducing CO<sub>2</sub> emissions during pavement construction and maintenance. Additionally, the laboratory mix design process, which involves selecting aggregate gradation and binder content, is time-consuming and labor-intensive. To accelerate the traditional mix design procedure, this study presented a mix design procedure that can automatically determine gradation and binder content based on machine learning (ML) and a meta-heuristic algorithm. Specifically, ML approaches were employed to model the relationship between volumetric properties (mixture bulk specific gravity (<em>G</em><sub>mb</sub>) and air void (VV)) and both mixture component properties and mixture proportion, based on a dataset collected from literature with 660 mixture designs. Integrated with the prediction of ML models and the modified multi-objective grey wolf optimization (MOGWO) algorithm, an automatic asphalt mix design was proposed to pursue three goals, including VV, cost, and CO<sub>2</sub> emission. The results indicated that least squares support vector regression (LSSVR) and eXtreme gradient boosting (XGBoost) achieved the highest prediction accuracies (correlation coefficient: 0.92 for VV and 0.96 for <em>G</em><sub>mb</sub>). The MOGWO algorithm successfully found the 26 optimal mix designs for the case of VV vs. cost vs. CO<sub>2</sub> emission. Compared to the traditional laboratory design, the optimal mixture with VV of 4% achieves a cost saving of 2.46% and a reduction of 4.03% in carbon emission. The volumetric properties of the mixtures output by the approach also align closely with values measured in a laboratory.</p></div>","PeriodicalId":47239,"journal":{"name":"Journal of Traffic and Transportation Engineering-English Edition","volume":"11 3","pages":"Pages 381-405"},"PeriodicalIF":7.4000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095756424000485/pdfft?md5=a35f28278a87d0fd99213b7d85c5a0bd&pid=1-s2.0-S2095756424000485-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Automated, economical, and environmentally-friendly asphalt mix design based on machine learning and multi-objective grey wolf optimization\",\"authors\":\"Jian Liu , Fangyu Liu , Linbing Wang\",\"doi\":\"10.1016/j.jtte.2023.10.002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The increasing impact of the greenhouse effect on ecosystems is prompting transportation agencies to seek methods for reducing CO<sub>2</sub> emissions during pavement construction and maintenance. Additionally, the laboratory mix design process, which involves selecting aggregate gradation and binder content, is time-consuming and labor-intensive. To accelerate the traditional mix design procedure, this study presented a mix design procedure that can automatically determine gradation and binder content based on machine learning (ML) and a meta-heuristic algorithm. Specifically, ML approaches were employed to model the relationship between volumetric properties (mixture bulk specific gravity (<em>G</em><sub>mb</sub>) and air void (VV)) and both mixture component properties and mixture proportion, based on a dataset collected from literature with 660 mixture designs. Integrated with the prediction of ML models and the modified multi-objective grey wolf optimization (MOGWO) algorithm, an automatic asphalt mix design was proposed to pursue three goals, including VV, cost, and CO<sub>2</sub> emission. The results indicated that least squares support vector regression (LSSVR) and eXtreme gradient boosting (XGBoost) achieved the highest prediction accuracies (correlation coefficient: 0.92 for VV and 0.96 for <em>G</em><sub>mb</sub>). The MOGWO algorithm successfully found the 26 optimal mix designs for the case of VV vs. cost vs. CO<sub>2</sub> emission. Compared to the traditional laboratory design, the optimal mixture with VV of 4% achieves a cost saving of 2.46% and a reduction of 4.03% in carbon emission. The volumetric properties of the mixtures output by the approach also align closely with values measured in a laboratory.</p></div>\",\"PeriodicalId\":47239,\"journal\":{\"name\":\"Journal of Traffic and Transportation Engineering-English Edition\",\"volume\":\"11 3\",\"pages\":\"Pages 381-405\"},\"PeriodicalIF\":7.4000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2095756424000485/pdfft?md5=a35f28278a87d0fd99213b7d85c5a0bd&pid=1-s2.0-S2095756424000485-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Traffic and Transportation Engineering-English Edition\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2095756424000485\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Traffic and Transportation Engineering-English Edition","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2095756424000485","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
摘要
温室效应对生态系统的影响与日俱增,促使交通机构在路面施工和维护过程中寻求减少二氧化碳排放的方法。此外,实验室混合料设计过程涉及骨料级配和粘结剂含量的选择,既耗时又耗力。为了加快传统的混合料设计程序,本研究提出了一种基于机器学习(ML)和元启发式算法的混合料设计程序,可自动确定级配和粘结剂含量。具体来说,基于从文献中收集的 660 种混合料设计数据集,采用了 ML 方法来模拟体积特性(混合料体积比重 (Gmb) 和空隙 (VV))与混合料组分特性和混合料配比之间的关系。结合 ML 模型预测和改进的多目标灰狼优化(MOGWO)算法,提出了一种自动沥青混合料设计方法,以实现 VV、成本和二氧化碳排放等三个目标。结果表明,最小二乘支持向量回归(LSSVR)和极端梯度提升(XGBoost)的预测精度最高(相关系数:VV 为 0.92,Gmb 为 0.96)。在 VV vs. 成本 vs. CO2 排放的情况下,MOGWO 算法成功地找到了 26 种最佳混合设计。与传统的实验室设计相比,VV 为 4% 的最佳混合料可节约成本 2.46%,减少碳排放 4.03%。该方法得出的混合物体积特性也与实验室测量值非常接近。
Automated, economical, and environmentally-friendly asphalt mix design based on machine learning and multi-objective grey wolf optimization
The increasing impact of the greenhouse effect on ecosystems is prompting transportation agencies to seek methods for reducing CO2 emissions during pavement construction and maintenance. Additionally, the laboratory mix design process, which involves selecting aggregate gradation and binder content, is time-consuming and labor-intensive. To accelerate the traditional mix design procedure, this study presented a mix design procedure that can automatically determine gradation and binder content based on machine learning (ML) and a meta-heuristic algorithm. Specifically, ML approaches were employed to model the relationship between volumetric properties (mixture bulk specific gravity (Gmb) and air void (VV)) and both mixture component properties and mixture proportion, based on a dataset collected from literature with 660 mixture designs. Integrated with the prediction of ML models and the modified multi-objective grey wolf optimization (MOGWO) algorithm, an automatic asphalt mix design was proposed to pursue three goals, including VV, cost, and CO2 emission. The results indicated that least squares support vector regression (LSSVR) and eXtreme gradient boosting (XGBoost) achieved the highest prediction accuracies (correlation coefficient: 0.92 for VV and 0.96 for Gmb). The MOGWO algorithm successfully found the 26 optimal mix designs for the case of VV vs. cost vs. CO2 emission. Compared to the traditional laboratory design, the optimal mixture with VV of 4% achieves a cost saving of 2.46% and a reduction of 4.03% in carbon emission. The volumetric properties of the mixtures output by the approach also align closely with values measured in a laboratory.
期刊介绍:
The Journal of Traffic and Transportation Engineering (English Edition) serves as a renowned academic platform facilitating the exchange and exploration of innovative ideas in the realm of transportation. Our journal aims to foster theoretical and experimental research in transportation and welcomes the submission of exceptional peer-reviewed papers on engineering, planning, management, and information technology. We are dedicated to expediting the peer review process and ensuring timely publication of top-notch research in this field.