Prediction of Concrete Compressive Strength by GA-BP Neural Network Based on Mortar Film Thickness

doi:10.16552/j.cnki.issn1001-1625.2025.0825

Abstract

Abstract:

To achieve more precise predictions of modern concrete compressive strength， mortar film thickness was employed as the key parameter in mix design， replacing the quantities of individual concrete constituents. Through theoretical calculations and experimental studies， the influence of mortar film thickness on concrete compressive strength was analysed. Two compressive strength prediction models were constructed： one based on traditional concrete mix proportion and another based on mortar film thickness， utilising a backpropagation optimised by a genetic algorithm （GA-BP） neural network. Results indicate that mortar film thickness is jointly determined by the total volume of cement mortar and coarse aggregate parameters. As film thickness increases， the quality of the interfacial transition zone initially improves before deteriorating， while the skeletal support function of coarse aggregates progressively weakens. This leads to an overall decline in concrete compressive strength. Compared to the traditional prediction model， the mortar film thickness-based model achieves a 19.7% improvement in accuracy， a 50.4% reduction in root mean square error， an average relative error of 2.8%， and a determination coefficient of 0.935. Regression evaluation metrics indicate this model provides more precise predictions of concrete compressive strength.

Key words: concrete, mortar film thickness, compressive strength, BP neural network, genetic algorithm

CLC Number:

TU528

YU Hanzhi, ZHOU Li’an, LIU Yu, ZHOU Wenjuan, LIANG Yunjian. Prediction of Concrete Compressive Strength by GA-BP Neural Network Based on Mortar Film Thickness[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2026, 45(2): 437-448.

Figures/Tables 14

References 28

[1]	高云，杜春苗，李栋，等. 水胶比对高强混凝土力学性能影响的实验研究［J］. 西安建筑科技大学学报（自然科学版）， 2020， 52（5）： 653-659.
	GAO Y， DU C M， LI D， et al. Experimental study on the influence of water-binder ratio on mechanical properties of high strength concrete［J］. Journal of Xi’an University of Architecture & Technology （Natural Science Edition）， 2020， 52（5）： 653-659 （in Chinese）.
[2]	BASNET G， LAMICHHANE A， PANTA A， et al. Prognosis of concrete strength： the state of art in using different machine learning algorithms［C］// Recent Advances in Civil Engineering for Sustainable Communities. Singapore： Springer Nature Singapore， 2024： 71-84.
[3]	XU J J， ZHOU L， HE G， et al. Comprehensive machine learning-based model for predicting compressive strength of ready-mix concrete［J］. Materials， 2021， 14（5）： 1068. DOI URL
[4]	VAIRAGAR S， KHILARE S P， GUNJAL A N， et al. Concrete strength prediction using machine learning［C］// Business Data Analytics. Cham： Springer Nature Switzerland， 2025： 325-339.
[5]	康天蓓，梁玉，梁意博，等. 基于多机器学习模型的再生混凝土抗盐冻性能预测［J］. 材料导报， 2025， 39（19）： 108-118.
	KANG T B， LIANG Y， LIANG Y B， et al. Prediction of salt-freeze resistance of recycled aggregate concrete based on multiple machine learning models［J］. Materials Reports， 2025， 39（19）： 108-118 （in Chinese）.
[6]	ZHANG H， TIAN Z G. Failure analysis of corroded high-strength pipeline subject to hydrogen damage based on FEM and GA-BP neural network［J］. International Journal of Hydrogen Energy， 2022， 47（7）： 4741-4758. DOI URL
[7]	GARG V， KUMAR K， CHANDRASHEKAR R， et al. A critical analysis of genetic algorithms for optimized solutions［C］// 2024 7th International Conference on Contemporary Computing and Informatics （IC3I）. Greater Noida， India. IEEE， 2024： 594-597.
[8]	DU G Q， BU L T， HOU Q， et al. Correction： prediction of the compressive strength of high-performance self-compacting concrete by an ultrasonic-rebound method based on a GA-BP neural network［J］. PLoS One， 2021， 16（9）： e0257650.
[9]	罗广彬，洪成雨，程志良，等. 基于BP和GA-BP神经网络的混凝土抗压强度预测研究［J］. 混凝土， 2023（3）： 37-41.
	LUO G B， HONG C Y， CHENG Z L， et al. Study on prediction of concrete compressive strength based on BP and GA-BP neural network［J］. Concrete， 2023（3）： 37-41 （in Chinese）.
[10]	朱文邦，郑秀梅，杨增增，等. 基于遗传算法优化BP神经网络的沙漠砂混凝土强度预测［J］. 混凝土， 2024（5）： 48-51+56.
	ZHU W B， ZHENG X M， YANG Z Z， et al. Strength prediction of desert sand concrete based on genetic algorithm optimized BP neural network［J］. Concrete， 2024（5）： 48-51+56 （in Chinese）.
[11]	NITHURSHAN M， ELAKNESWARAN Y. A systematic review and assessment of concrete strength prediction models［J］. Case Studies in Construction Materials， 2023， 18： e01830.
[12]	夏勇，陈哲，麦俊明，等. 基于膜厚度理论对水泥基材料性能的研究进展［J］. 广东建材， 2022， 38（6）： 1-5.
	XIA Y， CHEN Z， MAI J M， et al. Research progress on properties of cement-based materials based on film thickness theory［J］. Guangdong Building Materials， 2022， 38（6）： 1-5 （in Chinese）.
[13]	王啸夫，张雄，赵明，等. 砂浆层厚度的计算与测定及其对混凝土力学性能的调控规律研究［J］. 粉煤灰综合利用， 2016， 30（6）： 7-11.
	WANG X F， ZHANG X， ZHAO M， et al. The calculation and measurement of the thickness of the mortar layer and research of the regulation of mechanical properties of concrete［J］. Fly Ash Comprehensive Utilization， 2016， 30（6）： 7-11 （in Chinese）.
[14]	冯嘉健. 基于膜厚度理论的透水混凝土透水与力学性能研究［D］. 广州：广东工业大学， 2019： 80-84.
	FENG J J. Study on the permeability and mechanical properties of permeable concrete based on film thickness theory［D］. Guangzhou： Guangdong University of Technology， 2019： 80-84 （in Chinese）.
[15]	何小兵，沈武福，贾秋炳，等. 砂浆流变特性及其膜厚对自密实混凝土性能的影响［J］. 东南大学学报（自然科学版）， 2020， 50（3）： 463-470.
	HE X B， SHEN W F， JIA Q B， et al. Effects of mortar rheological characteristics and film thickness on self-compacting concrete［J］. Journal of Southeast University （Natural Science Edition）， 2020， 50（3）： 463-470 （in Chinese）.
[16]	SHEN W G， WU M M， ZHANG B L， et al. Coarse aggregate effectiveness in concrete： quantitative models study on paste thickness， mortar thickness and compressive strength［J］. Construction and Building Materials， 2021， 289： 123171. DOI URL
[17]	王海娜. 自密实混凝土的骨料比表面法配合比设计及其基本性能研究［D］. 杭州：浙江大学， 2007： 23-25.
	WANG H N. Study on the mix design and basic properties of self-compacting concrete based on the specific surface area method of aggregates［D］. Hangzhou： Zhejiang University， 2007： 23-25 （in Chinese）.
[18]	中华人民共和国住房和城乡建设部，国家市场监督管理总局. 混凝土物理力学性能试验方法标准：GB/T 50081—2019［S］. 北京：中国建筑工业出版社， 2019.
	Ministry of Housing and Urban-Rural Development of the People’s Republic of China， State Administration for Market Regulation. Standard for test methods of concrete physical and mechanical properties：［S］. Beijing： China Architecture & Building Press， 2019 （in Chinese）.
[19]	王发刚，邹平，王忠康，等. 基于GA-BP神经网络边坡稳定性预测的方法及应用［J］. 中国安全生产科学技术， 2024， 20（6）： 161-167.
	WANG F G， ZOU P， WANG Z K， et al. Method and application of slope stability prediction based on GA-BP neural network［J］. Journal of Safety Science and Technology， 2024， 20（6）： 161-167 （in Chinese）.
[20]	张国浩，王彩玲，王洪伟，等. 改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究［J］. 光谱学与光谱分析， 2025， 45（2）： 394-402.
	ZHANG G H， WANG C L， WANG H W， et al. Improved particle swarm optimization algorithm combined with BP neural network model for prediction of total phosphorus concentration in water body using transmittance spectral data［J］. Spectroscopy and Spectral Analysis， 2025， 45（2）： 394-402 （in Chinese）.
[21]	李翔宇，李新源，李明宇，等. 基于实测数据的地铁隧道长期沉降预测模型研究［J］. 西安建筑科技大学学报（自然科学版）， 2021， 53（2）： 186-193.
	LI X Y， LI X Y， LI M Y， et al. Research on prediction model of the long-term subsidence of shield tunnels based on in situ monitoring data［J］. Journal of Xi’an University of Architecture & Technology （Natural Science Edition）， 2021， 53（2）： 186-193 （in Chinese）.
[22]	苏瑛，龚伟，刘川北，等. 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. DOI
	SU Y， GONG W， LIU C B， et al. 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 （in Chinese）. DOI
[23]	陈浩，刘荣桂，闫乾勋，等. 基于GA-BP神经网络的SAP内养护机制砂混凝土抗压强度预测［J］. 混凝土， 2023（5）： 72-76.
	CHEN H， LIU R G， YAN Q X， et al. Based on GA-BP neural network prediction of compressive strength of machine-made sand concrete with SAP internal curing［J］. Concrete， 2023（5）： 72-76 （in Chinese）.
[24]	周逸轩，彭星煜，耿月华，等. 基于KPCA-GA-BP模型的页岩气集输管道的内腐蚀速率预测［J］. 腐蚀与防护， 2024， 45（4）： 63-68.
	ZHOU Y X， PENG X Y， GENG Y H， et al. Internal corrosion rate prediction of shale gas gathering pipeline based on KPCA-GA-BP model［J］. Corrosion & Protection， 2024， 45（4）： 63-68 （in Chinese）.
[25]	施惠生，孙丹丹，吴凯. 混凝土界面过渡区微观结构及其数值模拟方法的研究进展［J］. 硅酸盐学报， 2016， 44（5）： 678-685.
	SHI H S， SUN D D， WU K. Development on microstructure and numerical simulation of interfacial transition zone［J］. Journal of the Chinese Ceramic Society， 2016， 44（5）： 678-685 （in Chinese）.
[26]	杨人和，刘宝元，吴中伟. 水泥石与石灰石集料界面过渡区孔结构及其CH晶体亚微观结构的研究［J］. 硅酸盐学报， 1989， 17（4）： 302-307.
	YANG R H， LIU B Y， WU Z W. An investigation on the pore structure and Ca（OH）₂ crystal submicrostructure in the interfacial zone between cement paste and limestone aggregate［J］. Journal of the Chinese Ceramic Society， 1989， 17（4）： 302-307 （in Chinese）.
[27]	ZHANG L H， ZHANG Y S， LIU C B， et al. Study on microstructure and bond strength of interfacial transition zone between cement paste and high-performance lightweight aggregates prepared from ferrochromium slag［J］. Construction and Building Materials， 2017， 142： 31-41. DOI URL
[28]	AKÇAOĞLU T， TOKYAY M， ÇELIK T. Assessing the ITZ microcracking via scanning electron microscope and its effect on the failure behavior of concrete［J］. Cement and Concrete Research， 2005， 35（2）： 358-363. DOI URL

Gradation	Apparent density/（kg·m^-3）	Bulk density/（kg·m^-3）	Crushing value/%	Water absorption/%	Porosity/%
4.75~19.00 mm	2 790	1 780	8.5	0.8	38
4.75~26.50 mm	2 790	1 730	7.8	0.8	36

Gradation	Apparent density/（kg·m^-3）	Bulk density/（kg·m^-3）	Crushing value/%	Water absorption/%	Porosity/%
4.75~19.00 mm	2 790	1 780	8.5	0.8	38
4.75~26.50 mm	2 790	1 730	7.8	0.8	36

Gradation	Accumulative remainder/%
Gradation	9.50 mm	16.00 mm	19.00 mm	26.50 mm
4.75~19.00 mm	58.58	16.47	0	—
4.75~26.50 mm	69.59	38.67	26.58	0

Gradation	Accumulative remainder/%
Gradation	9.50 mm	16.00 mm	19.00 mm	26.50 mm
4.75~19.00 mm	58.58	16.47	0	—
4.75~26.50 mm	69.59	38.67	26.58	0

No.	Mortar multiplier	Mass/kg
No.	Mortar multiplier	Cement	Fly ash	Mineral powder	Water	Sand	Stone
M-1	0.8	2.42	1.01	0.60	1.77	7.67	11.72
M-2	0.9	2.72	1.13	0.68	2.00	8.63	11.72
M-3	1.0	3.02	1.26	0.76	2.22	9.59	11.72
M-4	1.1	3.33	1.39	0.83	2.44	10.55	11.72
M-5	1.2	3.63	1.51	0.91	2.66	11.51	11.72
M-6	1.3	3.93	1.64	0.98	2.88	12.46	11.72
M-7	1.4	4.23	1.76	1.06	3.10	13.42	11.72
M-8	1.5	4.54	1.89	1.13	3.33	14.38	11.72