Abstract: To explore the new ideas of asphalt mixture material composition design, the work proposes a data-driven asphalt mixture material composition design method based on the material performance database. Firstly, three machine learning prediction models, namely, BP neural network, XGBoost and Random forest, were constructed with asphalt type, air void ratio and other asphalt mixture material composition as model inputs, and dynamic modulus, dynamic stability and other mixture properties as model outputs, and a MySQL material performance database was established with the help of them. Then, using the structured SQL query statement of the database, the asphalt mixture performance is used as the query condition, and the database is reverse-matched to obtain the reference value of the material composition of asphalt mixtures, to put forward the data-driven design method of asphalt mixture material composition. Finally, the feasibility of the design method is verified by example analysis. The results show that XGBoost has the best prediction ability among the three machine learning models, and its coefficient of determination R2 is improved by 0.03—0.40 compared with BP neural network, and 0.01—0.08 compared with RF, which can be better used for predicting the performance of asphalt mixtures;and the feasibility of realizing the design of asphalt mixture composition based on reverse database matching is verified through the combination of case study and indoor experiments. The results of the study provide important references for revealing the performance correlation between asphalt mixtures and their material composition and guiding the design of asphalt mixture material composition.
1 Xiang P C, Gao L, Jia F Y. Journal of Chongqing Jiaotong University (Natural Science), 2022, 41(12), 26 (in Chinese). 向鹏成, 高璐, 贾富源. 重庆交通大学学报(自然科学版), 2022, 41(12), 26. 2 Liu L, Zhu X M, Liu Z H, et al. Materials Reports, 2023, 37(10), 66 (in Chinese). 柳力, 朱晓明, 刘朝晖, 等. 材料导报, 2023, 37(10), 66. 3 Ju P, Wang H, Ding Y N. Highways & Transportation in Inner Mongolia, 2021(5), 43 (in Chinese). 鞠鹏, 王浩, 丁寅南. 内蒙古公路与运输, 2021(5), 43. 4 Zhang J, Guo N S, Lyu X, et al. Materials Reports, 2023, 37(20), 263 (in Chinese). 张军, 郭乃胜, 吕欣, 等. 材料导报, 2023, 37(20), 263. 5 Ma T, Luan Y C, He L, et al. Journal of Traffic and Transportation Engineering, 2023, 23(2), 1 (in Chinese). 马涛, 栾英成, 何亮, 等. 交通运输工程学报, 2023, 23(2), 1. 6 Dang J T, Cheng Y, Gong L. Transport Energy Conservation & Environmental Protection, 2022, 18(3), 101 (in Chinese). 党江涛, 程愿, 弓雷. 交通节能与环保, 2022, 18(3), 101. 7 Tan L, Chen F T, Shi L M. Hunan Communication Science and Techno-logy, 2023, 49(3). 86 (in Chinese). 谭利, 尘福涛, 史立民. 湖南交通科技, 2023, 49(3), 86. 8 Luo S, Zhang X T, Wang Q Y, et al. Journal of Highway and Transportation Research and Development, 2023, 40(4), 61 (in Chinese). 罗升, 张新天, 王清晏, 等. 公路交通科技, 2023, 40(4), 61. 9 Yang X Y, Chen G Y, Zhu J T, et al. Industrial Construction, 2024, 54(9), 209 (in Chinese). 杨兴宇, 陈光耀, 朱俊潼, 等. 工业建筑, 2024, 54(9), 209. 10 Liu Z H, Liu L, Li W B, et al. China Journal of Highway and Transport, 2022, 35(7), 18 (in Chinese). 刘朝晖, 柳力, 李文博, 等. 中国公路学报, 2022, 35(7), 18. 11 Liang C, Xu X, Chen H, et al. Applied Sciences, 2021, 11(2), 835. 12 Zhao R, Gong J, Zheng Y, et al. Materials, 2022, 15(9), 3361. 13 Meng F Y, Pan X D. Journal of Jilin University(Engineering and Technology Edition), 2013, 43(S1), 535 (in Chinese). 孟繁宇, 潘晓东. 吉林大学学报(工学版), 2013, 43(S1), 535. 14 Huang W, Zhou L, Ge P, et al. Material Reports, 2021, 35(15), 15026 (in Chinese). 黄炜, 周烺, 葛培, 等. 材料导报, 2021, 35(15), 15026. 15 Zhang H, Yuan J Z, Cao X L, et al. Material Reports, 2015, 29(14), 148 (in Chinese). 张浩, 袁军座, 曹现雷, 等. 材料导报, 2015, 29(14), 148. 16 Wang Z H, Liu Y F, Wang T, et al. Computational Materials Science, 2023, 231, 112579. 17 Chang Y C, Chang K H, Wu G J. Applied Soft Computing, 2018, 73, 914. 18 Deng X Z, Ye A S, Zhong J S, et al. Energy Reports, 2022, 8, 8661. 19 Cheng W Q, Yuan D B, Xiong P, et al. Acta Scientiae Circumstantiae, 2023, 43(11), 144 (in Chinese). 程婉清, 袁定波, 熊鹏, 等. 环境科学学报, 2023, 43(11), 144. 20 Zeng B, Lyu Q R, Kou L, et al. The Chinese Journal of Geological Ha-zard and Control, 2023, 34(4), 105 (in Chinese). 曾斌, 吕权儒, 寇磊, 等. 中国地质灾害与防治学报, 2023, 34(4), 105. 21 Li Y J. Modern Information Technology, 2023, 7(11), 80 (in Chinese). 李艳杰. 现代信息科技, 2023, 7(11), 80. 22 Zou M J. Application of high modulus asphalt concrete in BRT special road. Master’s Thesis, Changsha University of Science and Technology, China, 2023 (in Chinese). 邹明均. 高模量沥青混凝土在BRT专用道路的应用研究. 硕士学位论文, 长沙理工大学, 2023.
渝公网安备50019002502923号 版权所有：《材料导报》编辑部
2025, Vol. 39 
