[1]许婕婷,吴晓畅,罗漪.采用随机森林模型的高温后石灰稳定土无侧限抗压强度预测[J].华侨大学学报(自然科学版),2025,46(5):596-605.[doi:10.11830/ISSN.1000-5013.202504007]
　XU Jieting,WU Xiaochang,LUO Yi.Unconfined Compressive Strength Prediction of Lime-Stabilized Earth After High Temperature Using Random Forest Model[J].Journal of Huaqiao University(Natural Science),2025,46(5):596-605.[doi:10.11830/ISSN.1000-5013.202504007]
点击复制

采用随机森林模型的高温后石灰稳定土无侧限抗压强度预测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第5期
页码:
596-605
栏目:
出版日期:
2025-09-20

文章信息/Info

Title:
Unconfined Compressive Strength Prediction of Lime-Stabilized Earth After High Temperature Using Random Forest Model
文章编号:
1000-5013(2025)05-0596-10
作者:
许婕婷1;  吴晓畅2;  罗漪1
1. 华侨大学 土木工程学院, 福建 厦门 361021; 2. 揭阳职业技术学院 化学工程系, 广东 揭阳 522000
Author(s):
XU Jieting1;  WU Xiaochang2;  LUO Yi1
1. College of Civil Engineering, Huaqiao University, Xiamen 361021, China; 2. Department of Chemical Engineering, Jieyang Polytechnic, Jieyang 522000, China
关键词:
石灰稳定土;  随机森林模型;  高温损伤;  变量重要度;  无侧限抗压强度预测
Keywords:
lime-stabilized earth;  random forest model;  high temperature damage;  variable importance;  unconfined compressive strength prediction
分类号:
TU521.3
DOI:
10.11830/ISSN.1000-5013.202504007
文献标志码:
A
摘要:
针对石灰稳定土在高温环境下的无侧限抗压强度预测问题,提出一种基于随机森林算法的预测模型。以干土质量、砂质量、石灰质量、用水量、温度及保护层厚度为变量,开展85组无侧限抗压强度试验。结合扫描电子显微镜微观表征揭示高温损伤机理。采用学习曲线与网格搜索相结合的方法优化模型参数,并通过变量重要度评估输入指标的贡献度。结果表明:高温后期(400~700 ℃),化合物分解、结构内部局部孔径增大及表面裂缝扩展加剧了损伤;当决策树数量为703、最大深度为9时,模型拟合系数达89.1%、均方误差和平均绝对误差分别为0.124、0.240,预测性能良好;用水量、温度和石灰质量是影响高温后无侧限抗压强度的关键因素。
Abstract:
Aiming at the problem of predicting the unconfined compressive strength of lime-stabilized earth under high temperature environment, a predictive model based on the random forest algorithm was proposed. Taking the mass of dry earth, sand and lime, water consumption, temperature, as well as protective layer thickness as variables, 85 groups of unconfined compressive strength tests were conducted. Combined with the microscopic characterization by scanning electron microscopy, the mechanism of high temperature damage was revealed. Model parameters were optimized through a combination of learning curves and grid search, the contribution of input indicators was assessed using variable importance. The results show that during the later stages of high temperatures(400-700 ℃), compound decomposition, local pore enlargement within the internal structure and surface crack propagation exacerbate the damage. For the number of decision trees 703 and the maximum depth 9, the model fitting coefficient is 89.1%, with mean squared error 0.124 and mean absolute error 0.240 respectively, indicating robust predictive performance. Water consumption, temperature, and mass of lime are the key factors influencing unconfined compressive strength after high temperature.

参考文献/References:

[1] STANDARDS AUSTRALIA.2018 construction of buildings in bushfire-prone areas: AS 3959[S].Sydney:Standards Australia,2018.
[2] HOUBEN H,GUILLAUD H.Earth construction: A comprehensive guide[M].London:Intermediate Technology Publications,1994.
[3] 李丽华,刘文,白玉霞,等.椰壳纤维-石灰协同作用改良黏土性能试验研究[J].水文地质工程地质,2025,52(1):130-140.DOI:10.16030/j.cnki.issn.1000-3665.202311016.
[4] LUO Yi,XU Jieting,HUANG Yongwei,et al.Impact of relative humidity on strength and microscopic pore structure of air lime-stabilized compressed earth[J].Materials and Structures,2024,57(6):135.DOI:10.1617/s11527-024-02411-0.
[5] 沈淳珂.西安城墙改性内夯土的渗透、力学特性及耐久性研究[D].西安:西安理工大学,2024.
[6] 李慎刚,张天彪,赵文,等.石灰改良粉质黏土力学强度试验[J].沈阳工业大学学报,2024,46(6):840-847.DOI:10.7688/j.issn.1000-1646.2024.06.17.
[7] 赵晓晴,杨天风,宗钟凌,等.石灰-碱渣稳定土力学指标关联性及现场试验[J].应用基础与工程科学学报,2024,32(5):1319-1332.DOI:10.16058/j.issn.1005-0930.2024.05.009.
[8] 王硕,唐正光,华伦.基于BP神经网络的固化红土抗压强度预测[J].交通科学与工程,2024,40(2):108-115.DOI:10.16544/j.cnki.cn43-1494/u.20230412240498.
[9] TRINH Q N,LINH Q N,VAN Q T.Novel hybrid machine learning models including support vector machine with meta-heuristic algorithms in predicting unconfined compressive strength of organic soils stabilised with cement and lime[J].International Journal of Pavement Engineering,2023,24(2):2136374.DOI:10.1080/10298436.2022.2136374.
[10] TABARSA A,LATIFI N,OSOULI A,et al.Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines[J].Frontiers of Structural and Civil Engineering,2021,15(2):520-536.DOI:10.1007/s11709-021-0689-9.
[11] BAHMED I T,KHATTI J,GROVER K S.Hybrid soft computing models for predicting unconfined compressive strength of lime stabilized soil using strength property of virgin cohesive soil[J].Bulletin of Engineering Geology and the Environment,2024,83(1):46.DOI:10.1007/s10064-023-03537-1.
[12] 黄文涛,周萍,程锦翔.一种基于Adaboost和变量筛选的LSSVM工程造价估计方法[J].重庆交通大学学报(自然科学版),2016,35(3):54-57,104.DOI:10.3969/j.issn.1674-0696.2016.03.12.
[13] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.DOI:10.1023/a:1010933404324.
[14] HUANG Jiandong,DUAN Tianhong,ZHANG Yi,et al.Predicting the permeability of pervious concrete based on the beetle antennae search algorithm and random forest model[J].Advances in Civil Engineering,2020,2020(26):8863181.DOI:10.1155/2020/8863181.
[15] BIAU G.Analysis of a random forests model[J].Journal of Machine Learning Research,2012,13:1063-1095.DOI:10.1109/TASE.2012.2183739.
[16] GE Genbatu,SHI Zhongjie,ZHU Yuanjun,et al.Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms[J].Global Ecology and Conservation,2020,22:e00971.DOI:10.1016/j.gecco.2020.e00971.
[17] AO Yile,LI Hongqi,ZHU Liping,et al.The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling[J].Journal of Petroleum Science and Engineering,2019,174:776-789.DOI:10.1016/j.petrol.2018.11.067.
[18] 蔡晶,李卓奇,张然,等.共享电单车竞争下的轨道交通接驳公交服务质量评价[J].科学技术与工程,2025,25(12):5190-5199.DOI:10.12404/j.issn.1671-1815.2403854.
[19] 滕慧,李春梅,田杨君,等.基于随机森林模型的脑卒中照顾者自我护理贡献现状及影响因素研究[J].军事护理,2025,42(3):1-5.DOI:10.3969/ji.ssn.2097G1826.2025.03.001.
[20] 排日海·合力力,昝梅.干旱区绿洲城市生态环境时空格局变化及影响因子研究[J].自然资源遥感,2023,35(3):201-211.DOI:10.6046/zrzyyg.2022194.
[21] 马小宾,章锦河,周乐莹,等.长三角区域经济与旅游规模异速关系的时空识别及成因分析[J].地理研究,2023,42(11):2984-3002.DOI:10.11821/dlyj020230141.
[22] 魏星成.中国信用债券违约风险预警研究[D].呼和浩特:内蒙古财经大学,2025.
[23] AMERICAN SOCIETY FOR TESTING AND MATERIALS.2017 standard practice for classification of soils for engineering purposes(unified soil classification system): ASTM D2487-17[S].West Conshohocken:American Society for Testing and Materials,2017.
[24] AMERICAN SOCIETY FOR TESTING AND MATERIALS.2021 standard test methods for laboratory compaction characteristics of soil using standard effort(12 400 ft-lbf/ft3(600 kN-m/m3)): ASTM D698-12[S].West Conshohocken:American Society for Testing and Materials,2021.
[25] EUROPEAN COMMITTEE FOR STANDARDIZATION.2015 building lime-part 1: Definitions, specifications and conformity criteria: CEN/EN 459-1[S].Brussels:European Committee for Standardization,2015.
[26] 中华人民共和国国家卫生健康委员会,国家市场监督管理总局.食品安全国家标准 食品添加剂 氢氧化钙: GB 1886.375-2024[S].北京:中国标准出版社,2024.
[27] ROAD ENGINEERING STANDARD POLICY COMMITTEE.1990 British standard methods of test for soils for civil engineering purposes, part 7: Shear strength tests(total stress): BS 1377-7[S].London:Road Engineering Standard Policy Committee,1990.
[28] LUO Yi,ZHONG Haopeng,BAO Feiyang,et al.Insights into natural and carbonation curing of ancient Chinese rammed earth mixed with brown sugar[J].Construction and Building Materials,2022,317:125969.DOI:10.1016/j.conbuildmat.2021.125969.
[29] WANG Sen,GAINEY L,BAXTER D,et al.Thermal behaviours of clay mixtures during brick firing: A combined study of in-situ XRD, TGA and thermal dilatometry[J].Construction and Building Materials,2021,299:124319.DOI:10.1016/j.conbuildmat.2021.124319.
[30] AMERICAN SOCIETY FOR TESTING AND MATERIALS.2016 standard test method for unconfined compressive strength of cohesive soil: ASTM D2166/D2166M-16[S].West Conshohocken:American Society for Testing and Materials,2016.
[31] 曹扬晨,朱国胜,祁小云,等.基于随机森林的入侵检测分类研究[J].计算机科学,2021,48(增刊1):459-463.DOI:10.11896/jsjkx.200600161.
[32] YOUNESS M,MOHAMED E.Random forest pruning techniques: A recent review[J].Operations Research Forum,2023,4(2):43.DOI:10.1007/S43069-023-00223-6.
[33] DASH P B,NAIK B,NAYAK J,et al.Socio-economic factor analysis for sustainable and smart precision agriculture: An ensemble learning approach[J].Computer Communications,2022,182:72-87.DOI:10.1016/j.comcom.2021.11.002.
[34] 陈浮,夏依,邹铭,等.“一带一路”共建国家矿区生态修复碳汇潜力评估[J].煤炭学报,2025,50(6):2789-2801.DOI:10.13225/j.cnki.jccs.2025.0298.
[35] 孙玲莉,杨贵军,王禹童.基于Benford律的随机森林模型及其在财务风险预警的应用[J].数量经济技术经济研究,2021,38(9):159-177.DOI:10.13653/j.cnki.jqte.2021.09.009.
[36] SIHAG P,AL-JANABI A M S,ALOMARI N K,et al.Evaluation of tree regression analysis for estimation of river basin discharge[J].Modeling Earth Systems and Environment,2021,7(4):2531-2543.DOI:10.1007/s40808-020-01045-9.
[37] LIU Shi,XU Jinyu.An experimental study on the physico-mechanical properties of two post-high-temperature rocks[J].Engineering Geology,2015,18:563-570.DOI:10.1016/j.enggeo.2014.11.013.
[38] SUN Qiang,ZHANG Weiqiang,ZHANG Yuliang,et al.Variations of strength, resistivity and thermal parameters of clay after high temperature treatment[J].Acta Geophysica,2016,64(6):2076-2090.DOI:10.1515/acgeo-2016-0090.
[39] OHNO I,HARADA K,YOSHITOMI C.Temperature variation of elastic constants of quartz across the α-β transition[J].Physics and Chemistry of Minerals,2006,33(1):1-9.DOI:10.1007/s00269-005-0008-3.
[40] 郑凯恺,王继华,莫德国,等.基于GF影像的区域山水林田湖草生态系统多要素综合评价[J].环境监测管理与技术,2025,37(3):43-51.DOI:10.19501/j.cnki.1006-2009.2025.03.003.
[41] 兰中凯.改性黄土的残余强度与微观结构特性试验研究[D].西安:西安理工大学,2024.
[42] ARYANPOUR M,FALAMAKI A,VAKILI A H.Effects of elevated temperature on mineralogical/microstructural changes and mechanical responses of clay soil[J].Physics and Chemistry of the Earth,2023,132:103493.DOI:10.1016/j.pce.2023.103493.
[43] RONG Zhidan,JIAO Maopeng,ZHANG Jiaqi.Effect of modified nano-SiO2 on properties and microstructure of the high-performance cementitious composites[J].Construction and Building Materials,2023,403:133063.DOI:10.1016/j.conbuildmat.2023.133063.
[44] ZHOU Yingwu,ZHUANG Jiahao,XU Wenzhuo,et al.Study on mechanical performance and mesoscopic simulation of nano-SiO2 modified recycled aggregate concrete[J].Construction and Building Materials,2024,425:136053.DOI:10.1016/j.conbuildmat.2024.136053.

备注/Memo

备注/Memo:
收稿日期: 2025-04-05
通信作者: 罗漪(1976-),女,教授,博士,博士生导师,主要从事生土建筑(福建土楼)材料性能评价、修复性保护的研究。E-mail:Luoyi@hqu.edu.cn。
基金项目: 国家自然科学基金资助项目(52479101); 福建省对外合作项目(2023I0015)https://hdxb.hqu.edu.cn/
更新日期/Last Update: 2025-09-20