基于机器学习的磷石膏轻骨料混凝土配合比设计与力学性能研究

doi:10.16552/j.cnki.issn1001-1625.2024.1258

硅酸盐通报 ›› 2025, Vol. 44 ›› Issue (5): 1656-1665.DOI: 10.16552/j.cnki.issn1001-1625.2024.1258

基于机器学习的磷石膏轻骨料混凝土配合比设计与力学性能研究

苏瑛^1,2, 龚伟^1,2, 刘川北³, 张俊^1,2

1.西南科技大学制造过程测试技术教育部重点实验室,绵阳 621010;
2.西南科大四川天府新区创新研究院,成都 621010;
3.西南科技大学材料与化学学院,绵阳 621010

收稿日期:2024-10-22 修订日期:2024-11-19 发布日期:2025-05-20
通信作者: 龚伟,博士,教授。E-mail:jszxgw@163.com
作者简介:苏瑛(2000—),女,硕士研究生。主要从事工业固废的研究。E-mail:767442261@qq.com
基金资助:
四川省国际科技合作项目(2021YFH0089)

Mix Ratio Design and Mechanical Properties of Phosphogypsum Lightweight Aggregate Concrete Based on Machine Learning

SU Ying^1,2, GONG Wei^1,2, LIU Chuanbei³, ZHANG Jun^1,2

1. Key Laboratory of Testing Technology for Manufacturing Process, Ministry of Education, Southwest University of Science and Technology, Mianyang 621010, China;
2. Tianfu Institute of Research and Innovation, Southwest University of Science and Technology, Chengdu 621010, China;
3. School of Materials and Chemistry, Southwest University of Science and Technology, Mianyang 621010, China

Received:2024-10-22 Revised:2024-11-19 Online:2025-05-20

摘要/Abstract

摘要： 采用磷石膏轻粗骨料替代天然碎石制备轻骨料混凝土,是实现磷石膏资源综合利用的有效技术。本文结合轻骨料混凝土的配合比设计原理与BP神经网络模型,提出了一种预测小粒径磷石膏轻骨料混凝土力学性能的方法。结果表明,混凝土的抗压强度和劈裂抗拉强度随着净水灰比升高而减小,随着砂率升高而增大,随着水泥用量升高略有降低,三种影响因素的显著程度次序为净水灰比、砂率、水泥用量。适当减小净水灰比,采用高砂率和低水泥用量可以减少界面过渡区孔隙和初始微裂纹的产生,并使整体力学强度提升。构建的BP神经网络模型对小粒径磷石膏轻骨料混凝土力学强度预测的准确度较高。本研究旨在为磷石膏轻骨料混凝土配合比设计优化和力学强度预测提供借鉴。

关键词: 磷石膏轻骨料, 混凝土, 抗压强度, 劈裂抗拉强度, BP神经网络, 微观分析

Abstract: Using phosphogypsum lightweight coarse aggregate instead of natural gravel to prepare lightweight aggregate concrete is an effective technology to realize the comprehensive utilization of phosphogypsum resources. Based on the mix ratio design principle of lightweight aggregate concrete and BP neural network model, a method to predict the mechanical properties of small particle size phosphogypsum lightweight aggregate concrete was proposed. The results show that the compressive strength and splitting tensile strength of concrete decrease with the increase of net water cement ratio, increase with the increase of sand ratio, and decrease slightly with the increase of cement content. The order of significance of the three influencing factors is net water cement ratio, sand ratio and cement content. Appropriately reducing the net water cement ratio, using high sand ratio and low cement content can reduce the generation of pores and initial microcracks in the interfacial transition zone, and improve the overall mechanical strength. The constructed BP neural network model has a high accuracy in predicting the mechanical strength of small particle phosphogypsum lightweight aggregate concrete. The purpose of this study is to provide reference for mix ratio design optimization and mechanical strength prediction of phosphogypsum lightweight aggregate concrete.

Key words: phosphogypsum lightweight aggregate, concrete, compressive strength, splitting tensile strength, BP neural network, microanalysis

中图分类号:

TU528.1

苏瑛, 龚伟, 刘川北, 张俊. 基于机器学习的磷石膏轻骨料混凝土配合比设计与力学性能研究[J]. 硅酸盐通报, 2025, 44(5): 1656-1665.

SU Ying, GONG Wei, LIU Chuanbei, ZHANG Jun. Mix Ratio Design and Mechanical Properties of Phosphogypsum Lightweight Aggregate Concrete Based on Machine Learning[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2025, 44(5): 1656-1665.

参考文献

[1] MSILA X, LABUSCHAGNE F, BARNARD W, et al. Radioactive nuclides in phosphogypsum from the lowveld region of South Africa[J]. South African Journal of Science, 2016, 112(1/2): 5.
[2] 张峻, 解维闵, 董雄波, 等. 磷石膏材料化综合利用研究进展[J]. 材料导报, 2023, 37(16): 167-178.
ZHANG J, XIE W M, DONG X B, et al. Research progress on comprehensive utilization of phosphogypsum for materials: a review[J]. Materials Reports, 2023, 37(16): 167-178 (in Chinese).
[3] 周祥, 李亮, 张晓敏, 等. 硅酸盐水泥熟料和硅灰对磷建筑石膏耐水性和水化行为的影响[J]. 新型建筑材料, 2023, 50(9): 77-81.
ZHOU X, LI L, ZHANG X M, et al. Effect of silicate clinker and silica fume on water resistance and hydration behavior of phosphogypsum[J]. New Building Materials, 2023, 50(9): 77-81 (in Chinese).
[4] WANG C Q, CHEN S, HUANG D M, et al. Safe environmentally friendly reuse of red mud modified phosphogypsum composite cementitious material[J]. Construction and Building Materials, 2023, 368: 130348.
[5] DING C, SUN T, SHUI Z H, et al. Physical properties, strength, and impurities stability of phosphogypsum-based cold-bonded aggregates[J]. Construction and Building Materials, 2022, 331: 127307.
[6] 吴赤球, 吕伟, 孙涛. 一种磷石膏轻骨料制备技术[J]. 混凝土与水泥制品, 2020(2): 98-100.
WU C Q, LYU W, SUN T. A preparation technology of phosphogypsum lightweight aggregate[J]. China Concrete and Cement Products, 2020(2): 98-100 (in Chinese).
[7] OUYANG G S, SUN T, YU Z C, et al. Investigation on macroscopic properties, leachability and microstructures of surface reinforced phosphogypsum-based cold-bonded aggregates[J]. Journal of Building Engineering, 2023, 69: 106305.
[8] 陈岩. 高强轻骨料混凝土配合比设计及性能研究[D]. 长春: 吉林大学, 2007.
CHEN Y. Mix proportion design and performance study of high strength lightweight aggregate concrete[D]. Changchun: Jilin University, 2007 (in Chinese).
[9] BIEGLER-KÖNIG F, BÄRMANN F. A learning algorithm for multilayered neural networks based on linear least squares problems[J]. Neural Networks, 1993, 6(1): 127-131.
[10] 金浏, 赵瑞, 杜修力. 混凝土抗压强度尺寸效应的神经网络预测模型[J]. 北京工业大学学报, 2021, 47(3): 260-268.
JIN L, ZHAO R, DU X L. Neural network prediction model of concrete compressive strength size effect[J]. Journal of Beijing University of Technology, 2021, 47(3): 260-268 (in Chinese).
[11] 白浩杰, 刘元珍, 郭耀东, 等. 基于GA-BP神经网络的再生保温混凝土强度预测[J]. 混凝土, 2020(11): 16-19+25.
BAI H J, LIU Y Z, GUO Y D, et al. Prediction of recycled aggregate thermal insulation concrete strength based on GA-BP neural network[J]. Concrete, 2020(11): 16-19+25 (in Chinese).
[12] 赖泽涵, 宋健, 付军, 等. 基于神经网络结合遗传算法的混凝土弹模与强度性能预测[J]. 工程与建设, 2020, 34(2): 332-334.
LAI Z H, SONG J, FU J, et al. Prediction of elastic modulus and strength performance of concrete based on neural network and genetic algorithm[J]. Engineering and Construction, 2020, 34(2): 332-334 (in Chinese).
[13] DUAN Z H, KOU S C, POON C S. Prediction of compressive strength of recycled aggregate concrete using artificial neural networks[J]. Construction and Building Materials, 2013, 40: 1200-1206.
[14] 梁宁慧, 游秀菲, 曹郭俊, 等. 基于机器学习的高温后聚丙烯纤维混凝土强度预测[J]. 硅酸盐通报, 2021, 40(2): 455-464.
LIANG N H, YOU X F, CAO G J, et al. Strength prediction of mechanical properties of polypropylene fiber reinforced concrete after high temperature based on machine learning[J]. Bulletin of the Chinese Ceramic Society, 2021, 40(2): 455-464 (in Chinese).
[15] 苏磊, 柯海山. 基于深度学习的电池SOC分阶段估算[J]. 信息技术与信息化, 2023(8): 199-203.
SU L, KE H S. Phased estimation of battery SOC based on deep learning[J]. Information Technology and Informatization, 2023(8): 199-203 (in Chinese).
[16] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016 (in Chinese).
[17] 赵子祥, 陈立明, 姚琳宁, 等. 基于BP神经网络的机制砂混凝土抗压强度预测[J]. 工业控制计算机, 2024, 37(8): 57-58+60.
ZHAO Z X, CHEN L M, YAO L N, et al. Prediction of compressive strength of mechanical sand concrete based on BP neural network[J]. Industrial Control Computer, 2024, 37(8): 57-58+60 (in Chinese).
[18] 陈明. MATLAB神经网络原理与实例精解[M]. 北京: 清华大学出版社, 2013.
CHEN M. The principle and examples of MATLAB neural network[M]. Beijing: Tsinghua University Press, 2013 (in Chinese).
[19] 薛辉, 张荣花. 普通混凝土抗折强度试验研究[J]. 黑龙江八一农垦大学学报, 2013, 25(2): 17-21+29.
XUE H, ZHANG R H. Experiment study on flexural strength of ordinary concrete[J]. Journal of Heilongjiang Bayi Agricultural University, 2013, 25(2): 17-21+29 (in Chinese).
[20] 康雪儿, 黄赟, 刘刚, 等. 可溶性磷对大掺量磷石膏胶凝材料水化过程的影响[J]. 硅酸盐通报, 2024, 43(9): 3303-3312.
KANG X E, HUANG Y, LIU G, et al. Effect of soluble phosphorus on hydration process of high content phosphogypsum cementitious materials[J]. Bulletin of the Chinese Ceramic Society, 2024, 43(9): 3303-3312 (in Chinese).
[21] 刘爱平, 吴赤球, 水中和, 等. 高掺量磷石膏水硬性胶凝材料组成设计与性能调节[J]. 硅酸盐通报, 2024, 43(3): 1003-1011.
LIU A P, WU C Q, SHUI Z H, et al. Composition design and property regulation of high content phosphogypsum hydraulic cementing material[J]. Bulletin of the Chinese Ceramic Society, 2024, 43(3): 1003-1011 (in Chinese).
[22] 郑波涛, 谭旺, 郭广银, 等. 大掺量磷石膏泡沫轻质土的制备[J]. 新型建筑材料, 2023, 50(8): 79-83.
ZHENG B T, TAN W, GUO G Y, et al. Preparation of foamed lightweight soil with large amount of phosphogypsum[J]. New Building Materials, 2023, 50(8): 79-83 (in Chinese).
[23] GAO S, GUO J, ZHU Y G, et al. Study on the influence of the properties of interfacial transition zones on the performance of recycled aggregate concrete[J]. Construction and Building Materials, 2023, 408: 133592.

基于机器学习的磷石膏轻骨料混凝土配合比设计与力学性能研究

Mix Ratio Design and Mechanical Properties of Phosphogypsum Lightweight Aggregate Concrete Based on Machine Learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	章欣宇, 蒲传金, 周航, 韩森, 冉正熙, 李小双, 肖定军. 高温后花岗岩-混凝土组合体动态压缩破坏特征与能量耗散研究[J]. 硅酸盐通报, 2025, 44(5): 1646-1655.
[2]	王宁宁, 胡康飞, 包益鋆, 张文文, 卜静武, 陈徐东. 矿粉和粉煤灰掺量对可控性低强度材料(CLSM)性能的影响[J]. 硅酸盐通报, 2025, 44(5): 1726-1733.
[3]	邱明明, 杨萌, 李晓敏, 李盛斌. 水泥固化高填方黄土抗压强度特性及其影响因素[J]. 硅酸盐通报, 2025, 44(5): 1927-1938.
[4]	王超, 李强, 余金虎, 兰锦涛, 蒋志律, 杨茜. 通电加速混凝土钢筋锈蚀试验研究进展[J]. 硅酸盐通报, 2025, 44(5): 1583-1603.
[5]	刘昊信, 乔宏霞, 马法荣, 付勇, 魏定邦, 张磊. 复合盐冻融循环下机制砂混凝土的劣化规律及寿命预测[J]. 硅酸盐通报, 2025, 44(5): 1634-1645.
[6]	查文华, 蔡雨凯, 许涛, 钱育冬. 外加剂掺量对煤矸石喷射混凝土力学性能和抗渗性的影响[J]. 硅酸盐通报, 2025, 44(5): 1676-1688.
[7]	崔祎菲, 刘梦华, 张益聪, 艾威侠, 徐诺. 超高性能碱激发混凝土的性能及环境影响研究[J]. 硅酸盐通报, 2025, 44(5): 1689-1702.
[8]	梁莹, 覃伟恒, 陈宗平, 李志彬. 钢-连续纤维复合筋珊瑚混凝土单向板受弯性能研究[J]. 硅酸盐通报, 2025, 44(5): 1703-1716.
[9]	付振博, 杨曦昊, 赵伊萌, 刘云鹏, 李世纪, 李秉函, 赵淑丽, 王磊. 粉煤灰掺量对碱激发材料干燥收缩及抗压强度的影响[J]. 硅酸盐通报, 2025, 44(5): 1717-1725.
[10]	王稷良, 朱繁涛, 王振宇. 激振搅拌工艺对全固废充填材料工作性能和力学性能的影响[J]. 硅酸盐通报, 2025, 44(5): 1734-1741.
[11]	冯伟鹏, 金宇, 孔凡龙, 董志君, 蔡士名, 邵宁宁. 秸秆纤维复合碱激发钢渣基泡沫混凝土的制备[J]. 硅酸盐通报, 2025, 44(5): 1755-1766.
[12]	叶伟开, 盛国栋, 鲁刘磊, 张锦红, 张宗洋, 董发鑫, 刘明旺, 汪峻峰, 罗琦. 固体激发剂对单组份碱激发矿渣-飞灰复合胶凝材料的影响[J]. 硅酸盐通报, 2025, 44(5): 1779-1787.
[13]	闵锐, 刘馨怡, 杨甜甜, 王思莹, 刘文欢, 李辉. 循环流化床固硫灰-矿粉复合胶凝材料的性能、水化产物及其应用[J]. 硅酸盐通报, 2025, 44(5): 1813-1823.
[14]	王竞一, 杨一帆, 段国林. SiC多孔陶瓷的绿色制备及性能优化[J]. 硅酸盐通报, 2025, 44(5): 1869-1877.
[15]	魏贤华, 王得林, 李超, 钟海军, 郭龙龙. 粉煤灰基地质聚合物及含水率对固化土力学性能的影响[J]. 硅酸盐通报, 2025, 44(5): 1949-1956.