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

doi:10.16552/j.cnki.issn1001-1625.2024.1258

Abstract

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

CLC Number:

TU528.1

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.

References

[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.