| 3 | 0 | 37 |
| 下载次数 | 被引频次 | 阅读次数 |
构建一种结合天牛须搜索算法（BAS）和随机森林（RF）的混合机器学习模型，预测露天矿路基回弹模量，在提高预测精度及速度的同时，为道路设计与施工提供一定的技术支持。选取塑性指数、干密度、侧限应力、偏应力、含水量和冻融循环次数作为输入变量，基于文献构建包含810组样本的数据库。通过BAS算法优化RF模型超参数，以10倍交叉验证方式评估模型性能。用均方根误差（RMSE）和相关系数（R）作为评价指标，并进行变量敏感性分析。结果表明，BAS可以实现有效的超参数调整，模型在训练集和测试集上预测精度较高。敏感性分析表明，冻融循环次数、侧限应力对回弹模量影响较大。该BAS-RF混合模型预测精度较高，具有低过拟合风险、计算速度快的特点。
Abstract：A hybrid machine learning model integrating the beetle antennae search(BAS) algorithm and random forest(RF) was developed to predict the resilient modulus of open-pit mine subgrades, with the aim of improving prediction accuracy and efficiency while providing effective technical support for road design and construction. Six input variables were selected: plasticity index, dry density, confining stress, deviator stress, water content, and number of freeze-thaw cycles. A database containing 810 samples was constructed based on published literature. The hyperparameters of the RF model were optimized using the BAS algorithm, and the model performance was evaluated through 10-fold cross-validation. The root mean square error(RMSE) and the correlation coefficient(R) were used as evaluation metrics, and a sensitivity analysis of the input variables was conducted. The results demonstrated that the BAS algorithm effectively optimized the hyperparameters, and the model exhibited high prediction accuracy on both the training and test sets. Sensitivity analysis indicated that the number of freeze-thaw cycles and confining stress had the most significant influence on the resilient modulus. The proposed BAS-RF hybrid model can effectively predict the resilient modulus, offering advantages such as low overfitting risk and high computational efficiency.
[1]燕志鹏,于泽民,顾新莲.我国碳排放价格与煤炭期货价格的传导机制研究[J].经济问题, 2022(6):67-74.
[2]王伟.碳中和目标下煤炭行业低碳发展演化博弈研究[J].煤炭工程, 2022, 54(8):186-192.
[3]张仙,李伟,陈理,等.露天开采矿区要素遥感提取研究进展及展望[J].自然资源遥感, 2023, 35(2):25-33.
[4]宋子岭,赵东洋,张宇航,等.露天煤矿绿色开采生态环境评价体系模糊评判研究[J].煤炭科学技术, 2019,47(10):58-66.
[5]宋阳,陈鑫,李金玲,等.露天开采环状推进采剥计划自动编制方法[J].矿业研究与开发, 2022, 42(5):167-172.
[6]范正祥.露天开采工艺选择的量化分析计算法研究[J].煤炭工程, 2019, 51(8):19-22.
[7]史宏江.土质对路基回弹模量的影响研究[J].内蒙古农业大学学报(自然科学版), 2011, 32(4):248-251.
[8]冉武平,李玲,陶泽峰.基于正交试验的路基回弹模量影响因素分析[J].公路工程, 2015, 40(5):40-44, 55.
[9]凌建明,陈声凯,曹长伟.路基土回弹模量影响因素分析[J].建筑材料学报, 2007, 10(4):446-451.
[10]贺国佑,刘锋民.新疆地区路基回弹模量E0研究[J].中外公路, 2008, 28(2):58-61.
[11]付伟,王云.防水保温对季冻区路基回弹模量场的影响分析[J].公路, 2016, 61(7):76-81.
[12]Park J, An G H, You Y J, et al. Evaluation of concrete freeze and thaw resistance by measuring surface rebound value and relative dynamic modulus of elasticity[J].Journal of the Korean Recycled Construction resources Institute, 2021, 9(4):419-424.
[13]Yuan K F, Zhu X B, Zhao J B. The correlation research of shanxi typical region roadbed loess CBR and rebound modulus[J]. Advanced Materials Research, 2013:838-841,1299-1301.
[14]陈真.路基填料回弹模量预估方法试验研究[J].铁道建筑技术, 2022(10):66-70.
[15]Yang S R. Influence of piston friction on resilient modulus of subgrade soil[J]. Journal of Testing and Evaluation, 2022, 50(6):3028-3035.
[16]Han Z, Vanapalli S K, Ren J P, et al. Characterizing cyclic and static moduli and strength of compacted pavement subgrade soils considering moisture variation[J]. Soils and Foundations, 2018, 58(5):1187-1199.
[17]晏创业,张玉峰.机器学习在获取检索知识中的应用[J].中国图书馆学报, 2003, 29(2):67-70.
[18]Domaratzki M, Kidane B. Deus ex machina?Demystifying rather than deifying machine learning[J].The Journal of Thoracic and Cardiovascular Surgery,2022, 163(3):1131-1137.e4.
[19]刘霏凝,石竞琛,王文杰,等.材料科学中机器学习算法的应用综述[J].化工新型材料, 2022, 50(9):42-46, 52.
[20]Liu B, Ding M, Shaham S, et al. When machine learning meets privacy:a survey and outlook[J]. ACM Computing Surveys, 2021, 54(2):1-36.
[21]Zou W L, Han Z, Ding L Q, et al. Predicting resilient modulus of compacted subgrade soils under influences of freeze-thaw cycles and moisture using gene expression programming and artificial neural network approaches[J].Transportation Geotechnics , 2021, 28:100520.
[22]Ding L Q, Han Z, Zou W L, et al. Characterizing hydromechanical behaviours of compacted subgrade soils considering effects of freeze-thaw cycles[J]. Transportation Geotechnics, 2020, 24:100392.
[23]Rahman M T. Evaluation of moisture, suction effects and durability performance of lime stabilized clayey subgrade soils[D]. Albuquerque:The University of Mexico, 2014.
基本信息:
DOI：10.20203/j.cnki.2095-8919.2026.02.002
中图分类号:TD57;TP181
引用信息:
[1]沈繁舜,时旭阳,郑成继,等.机器学习预测露天矿路基回弹模量可靠性研究[J].吉林建筑大学学报,2026,43(02):11-18.DOI:10.20203/j.cnki.2095-8919.2026.02.002.
基金信息:
国家自然科学基金项目（52104153）; 新疆维吾尔自治区重大科技专项项目（2023A01002-4）; 新疆维吾尔自治区重点研发计划项目（2023B03009-1）
2026-04-15
2026-04-15