基于神经网络与回归分析的多孔混凝土性能预测

doi:10.13229/j.cnki.jdxbgxb.20230239

Abstract

Abstract:

In order to predict the 28d compressive strength and permeability coefficient of porous concrete， the water-cement ratio， cementitious material dosage， bone-cement ratio and measured porosity were determined as model input parameters through correlation analysis. Furthermore， the prediction models for the two indicators are established based on the constructed dataset using artificial neural networks and regression analysis， respectively. The results showed that the statistical regression models had significant prediction errors， lacked sensitivity to multivariate responses， and their goodness-of-fit R² were all below 0.681. The artificial neural network model is more suitable for solving complex and multivariate performance prediction problems. The neural network compressive strength prediction model optimized by the genetic algorithm has a goodness-of-fit R² of more than 0.9， which reflects the accuracy and stability of the prediction model. The research results could provide reference and guidance for the optimal design of the mix ratio and performance regulation of porous concrete.

Key words: highway and railway engineering, porous concrete, compressive strength, permeable coefficient, neural network, regression analysis

CLC Number:

U414

Guang-lei QU,Zong-wei YAN,Mu-lian ZHENG,Hong LIU,Yue-ming YUAN. Performance prediction of porous concrete based on neural network and regression analysis[J].Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 269-282.

Figures/Tables 19

Table 1

Table 2

Fig.1

Table 3

Fig.2

Table 4

Fig.3

Fig.4

Fig.5

Table 5

Fig.6

Fig.7

Fig.8

Table 6

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

References 53

1	Rodin H, Rangelov M, Nassiri S, et al. Enhancing mechanical properties of pervious concrete using carbon fiber composite reinforcement [J]. Journal of Materials in Civil Engineering, 2018, 30(3): No.04018012.
2	Azad A, Saeedian A, Mousavi S F, et al. Effect of zeolite and pumice powders on the environmental and physical characteristics of green concrete filters [J]. Construction and Building Materials, 2020, 240(2020): No.117931.
3	郑木莲,邓朝显,梁行行,等. 海绵城市透水水泥混凝土路面结构力学响应分析[J]. 路基工程, 2019, 37(2): 71-77.
	Zheng Mu-lian, Deng Chao-xian, Liang Xing-xing, et al. Mechanical response analysis of permeability cement concrete pavenment structure in sponge city[J]. Subgrade Engineering, 2019, 37(2): 71-77.
4	Joshaghani A, Ramezanianpour A A, Ataei O, et al. Optimizing pervious concrete pavement mixture design by using the Taguchi method[J]. Construction and Building Materials, 2015, 101: 317-325.
5	Zhong R, Wille K. Influence of matrix and pore system characteristics on the durability of pervious concrete[J]. Construction and Building Materials, 2018, 162: 132-141.
6	Amini K, Wang X, Delatte N. Statistical modeling of hydraulic and mechanical properties of pervious concrete using nondestructive tests[J]. Journal of Materials in Civil Engineering, 2018, 30(6): No.04018077.
7	Liu J S, Ren F M, Quan H Z. Prediction model for compressive strength of porous concrete with low-grade recycled aggregate[J]. Materials, 2021, 14(14): No.3871.
8	Debnath B, Sarkar P P. Permeability prediction and pore structure feature of pervious concrete using brick as aggregate[J]. Construction and Building Materials, 2019, 213: 643-651.
9	Lian C, Zhuge Y, Beecham S. The relationship between porosity and strength for porous concrete[J]. Construction and Building Materials, 2011, 25: 4294-4298.
10	Le B A, Vu V H, Seo S Y, et al. Predicting the compressive strength and the effective porosity of pervious concrete using machine learning methods[J]. KSCE Journal of Civil Engineering, 2022, 26(11): 466-479.
11	杜青铉,张宇航,孙伟豪,等. 基于混合模型的煤矸石透水混凝土透水系数预测[J]. 材料导报, 2022, 36(): 319-323.
	Du Qing-xuan, Zhang Yu-hang, Sun Wei-hao, et al. Prediction of permeability coefficient of coal gangue permeable concrete based on mixed model[J].Materials Reports, 2022, 36(Sup.1): 319-323.
12	Azarhoosh M J, Koohmishi M. Prediction of hydraulic conductivity of porous granular media by establishment of random forest algorithm[J]. Construction and Building Materials, 2023, 366: No.130065.
13	Tian J W, Qi C C, Sun Y F, et al. Permeability prediction of porous media using a combination of computational fluid dynamics and hybrid machine learning methods[J]. Engineering with Computers, 2020, 37(4): 3455-3471.
14	Mahdi F M, Holdich R G. Using statistical and artificial neural networks to predict the permeability of loosely packed granular materials[J]. Separation Science and Technology, 2016, 52(1): 1-12.
15	Chen S, Zhao Y, Bie Y. The prediction analysis of properties of recycled aggregate permeable concrete based on back-propagation neural network[J]. Journal of Cleaner Production, 2020, 276: No.124187.
16	Baykasoğlu A, Dereli T, Tanış S. Prediction of cement strength using soft computing techniques[J]. Cement Concrete Research, 2004, 34(11): 2083-2090.
17	Akkurt S, Ozdemir S, Tayfur G, et al. The use of GA-ANNs in the modelling of compressive strength of cement mortar[J]. Cement Concrete Research, 2003, 33(7): 973-979.
18	王显利,曲广雷. 荷叶疏水剂对无砂透水混凝土性能的影响研究[J]. 新型建筑材料, 2017, 44(3): 11-15.
	Wang Xian-li, Qu Gguang-lei. Study on the effects of lotus leaf hydrophobic agent on no-fines pervious concrete performance[J]. New Building Materials, 2017, 44(3): 11-15.
19	曲广雷. 无砂内疏水透水混凝土的研制与性能研究[D]. 吉林: 北华大学林学院, 2017.
	Qu Guang-lei. Research on preparation and properties of no sand internal hydrophobic pervious concrete [D]. Jilin: College of Forestry, Beihua University, 2017.
20	郑木莲,王国清,贾献卓,等. 基于正交试验的多孔混凝土强度与空隙率影响因素分析[J]. 公路, 2015, 60(7): 230-234.
	Zheng Mu-lian, Wang Guo-qing, Jia Xian-zhuo, et al. Analysis on the influence factors of strength and porosity based on orthogonal experiment for porous concrete[J]. Highway, 2015, 60(7): 230-234.
21	闫楚良,郝云霄,刘克格. 基于遗传算法优化的BP神经网络的材料疲劳寿命预测[J]. 吉林大学学报:工学版, 2014, 44(6): 1710-1715.
	Yan Chu-liang, Hao Yun-xiao, Liu Ke-ge, et al. Fatigue life prediction of materials based on BP neural networks optimized by genetic algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(6): 1710-1715.
22	Hatanaka S, Mishima N, Maegawa A, et al. Fundamental study on properties of small particle size porous concrete[J]. Journal of Advanced Concrete Technology, 2014, 12(1): 24-33.
23	Bhutta M A R, Tsuruta K, Mirza J. Evaluation of high-performance porous concrete properties[J]. Construction and Building Materials, 2012, 31: 67-73.
24	Gupta M, Dudi L, Karkhanis R, et al. Determination of optimum parameters of porous concrete for adequate strength and permeability[C]∥Proceedings of the American—Society—of—Civil—Engineers(ASCE) India Conference on Urbanization Challenges in Emerging Economies—Resilience and Sustainability of Infrastructure, New Delhi, India, 2018: 12-14.
25	Liu H, Luo G, Wei H, et al. Strength, permeability, and freeze-thaw durability of pervious concrete with different aggregate sizes, porosities, and water-binder ratios[J]. Applied Sciences, 2018, 8(8): 12-17.
26	申明昊. 基于体积法的不同目标孔隙率下透水混凝土试验研究 [D]. 兰州: 兰州交通大学土木工程学院, 2021.
	Shen Ming-hao. Study on pervious concrete with different goal porosity based on volume method[D]. Lanzhou: School of Civil Engineering, Lanzhou Jiaotong University, 2021.
27	孙宏友. 基于正交试验法的透水混凝土配合比设计和试验研究[D]. 成都: 西南交通大学土木工程学院, 2016.
	Sun Hong-you. Experimental research and mix proportion design of porous concrete based on orthogonal test method[D]. Chendu: School of Civil Engineering, Southwest Jiaotong University, 2016.
28	王宇. 透水混凝土配合比设计及其路用性能研究[D]. 重庆: 重庆交通大学土木工程学院, 2020.
	Wang Yu. Mix design of pervious concrete and its application research on road performance[D]. Chongqing: School of Civil Engineering, Chongqing Jiaotong University, 2020.
29	马旺坤. 成型方法和配合比对透水混凝土性能的影响研究[D]. 哈尔滨: 哈尔滨工业大学土木工程学院, 2020.
	Ma Wang-kun. Research on influence of forming method and mix proportion on properties of pervious concrete [D]. Harbin: School of Civil Engineering, Harbin Institute of Technology, 2020.
30	张亚茹. 透水混凝土的基本力学性能及冻融、干湿循环试验研究[D]. 西安:西安理工大学土木建筑工程学院, 2020.
	Zhang Ya-ru. Experimental study on the basic mechanical properties pervious concrete and freeze-thaw and dry-wet cycles[D]. Xi'an: School of Civil Engineering and Architecture, Xi'an University of Technology, 2020.
31	刘相如. 透水砼透水系数及其力学与抗冻性能试验研究[D]. 烟台:烟台大学土木工程学院, 2019.
	Liu Xiang-ru. Experimental study on permeability coefficient and mechanical and frost resistance of permeable concrete[D]. Yantai: School of Civil Engineering, Yantai University, 2019.
32	张国强. 透水混凝土试验性能研究[D]. 广州:广州大学土木工程学院, 2018.
	Zhang Guo-qiang. An experimental study on the properties of the permeable concrete[D]. Guangzhou: School of Civil Engineering, Guangzhou University, 2018.
33	曲广雷,常广利,王显利,等. 透水混凝土强度与透水系数关系模型研究[J]. 混凝土与水泥制品, 2022 (2): 22-26.
	Qu Guang-lei, Chang Guang-li, Wang Xian-li, et al. Study on the relationship model between pervious concrete strength and pervious coefficient[J]. China Concrete and Cement Products, 2022(2): 22-26.
34	胡立国. 透水混凝土的抗冻性研究[D]. 大连:大连交通大学土木与安全工程学院, 2013.
	Hu Li-guo. The research about frost resistance of pervious concrete[D]. Dalian: School of Civil and Safety Engineering, Dalian Jiaotong University, 2013.
35	朱袁洁. C30透水混凝土力学性能及抗冻性能研究[D]. 镇江: 江苏科技大学土木工程与建筑学院, 2019.
	Zhu Yuan-jie. Study on mechanical properties and frost resistance of C30 pervious concrete[D]. Zhenjiang: School of Civil Engineering and Architecture, Jiangsu University of Science and Technology, 2019.
36	朱仁旺. 高透水性水泥混凝土的强度性能研究[D]. 合肥:合肥工业大学土木与水利工程学院, 2016.
	Zhu Ren-wang. Strength properties research for high-permeability cement concrete[D]. Hefei: School of Civil and Hydraulic Engineering, Hefei University of Technology, 2016.
37	林永盛. 环境友好型透水混凝土的制备与性能研究[D]. 南京: 东南大学材料科学与工程学院, 2019.
	Lin Yong-sheng. Study on preparation and properties of environmentally-friendly pervious concrete[D]. Nanjing: School of Materials Science and Engineering, Southeast University, 2019.
38	欧阳云鹏. 配合比参数对透水混凝土性能影响及其相关性研究[D]. 石家庄: 石家庄铁道大学材料科学与工程学院, 2019.
	Ouyang Yun-peng. Study on the influence and relevance of mix ratio parameters on the permeable concrete performance[D]. Shijiazhuang: School of Materials Science and Engineering, Shijiazhuang Tiedao University, 2019.
39	朱燕飞. 不同掺合料透水混凝土性能试验研究[D]. 广州: 华南农业大学水利与土木工程学院, 2019.
	Zhu Yan-fei. Experimental study on pervious concrete with different admixtures[D]. Guangzhou: College of Water Conservancy and Civil Engineering, South China Agricultural University, 2019.
40	何明. 复掺矿物掺合料透水混凝土的试验研究[D]. 鞍山: 辽宁科技大学土木工程学院, 2021.
	He Ming. Experimental research on permeable concrete mixed with mineral admixtures[D]. Anshan: School, Civil Engineering, University of Science and Technology Liaoning, 2021.
41	郭桂香. 集料骨架结构对多孔混凝土性能的影响研究[D]. 重庆: 重庆交通大学料科学与工程学院, 2016.
	Guo Gui-xiang. Study the effect of aggregate gradation on the performance of porous concrete[D]. Chongqing: School of Materials Science and Engineering, Chongqing Jiaotong University, 2016.
42	张旭东. 透水混凝土道路板配合比试验研究与组合结构形式设计[D]. 泰安: 山东农业大学水利土木工程学院, 2022.
	Zhang Xu-dong. Experimental study on mix proportion of pervious concrete pavement slab and design of composite structure form[D]. Taian: College of Water Conservancy and Civil Engineering, Shandong Agricultural University, 2022.
43	黄涛. 特定强度透水混凝土的透水性能研究[D]. 赣州: 江西理工大学建筑与测绘工程学院, 2019.
	Huang Tao. Study on permeability performance of pervious concrete under specific strength[D]. Ganzhou: School of Architectural and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, 2019.
44	Li L G, Feng J J, Zhu J, et al. Pervious concrete: effects of porosity on permeability and strength[J]. Magazine of Concrete Research, 2021, 73(2): 69-79.
45	Chandrappa A K, Biligiri K P. Effect of pore structure on fatigue of pervious concrete[J]. Road Materials and Pavement Design, 2018, 20(7): 1525-1547.
46	Joshi T, Dave U. Evaluation of strength, permeability and void ratio of pervious concrete with changing W/C ratio and aggregate size[J]. International Journal of Civil Engineering and Technology, 2016, 7(4): 276-284.
47	Ibrahim A, Mahmoud E, Yamin M, et al. Experimental study on Portland cement pervious concrete mechanical and hydrological properties[J]. Construction and Building Materials, 2014, 50: 524-529.
48	Liu H, Luo G, Wang L, et al. Laboratory evaluation of eco-friendly pervious concrete pavement material containing silica fume[J]. Applied Sciences, 2018, 9(1): 73-87.
49	Pradhan S K, Behera N. Performance assessment of pervious concrete road on strength and permeability by using silica fume[C]∥Proceedings of the International Conference on Sustainable Materials and Practices for Built Environment (SMPBE), Jaipur, India, 2021: 25-26.
50	Claudino G O, Rodrigues G G O, Rohden A B, et al. Mix design for pervious concrete based on the optimization of cement paste and granular skeleton to balance mechanical strength and permeability[J]. Construction and Building Materials, 2022, 347: No.128620.
51	Torres A, Hu J, Ramos A. The effect of the cementitious paste thickness on the performance of pervious concrete[J]. Construction and Building Materials, 2015, 95: 850-859.
52	Huang J, Luo Z, Khan M B E. Impact of aggregate type and size and mineral admixtures on the properties of pervious concrete: an experimental investigation[J]. Construction and Building Materials, 2020, 265:No. 120759.
53	Akbarpour H, Mohajeri M, Moradi M. Investigation on the synthesis conditions at the interpore distance of nanoporous anodic aluminum oxide: a comparison of experimental study, artificial neural network, and multiple linear regression[J]. Computational Materials Science, 2013, 79: 75-81.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

类别	SiO₂	Al₂O₃	Fe₂O₃	CaO	MgO	Na₂O	SO₃	LOI
水泥	21.59	4.57	5.01	64.15	1.98	0.11	2.19	0.95
硅灰	97.74	0.39	0.08	0.20	0.15	0.09	-	-

编号	水胶比	水泥	骨胶比	粗集料	水	硅灰	高效减水剂
1	0.20	450	3.19	1 435	90	-	11.25
2	0.20	405	3.30	1 485	90	45	10.13
3	0.24	495	2.93	1 450	119	-	0.98
4	0.24	445	3.01	1 490	119	50	0.98
5	0.26	480	2.91	1 395	125	-	12.00
6	0.26	432	3.29	1 425	125	48	10.80
7	0.28	420	3.33	1 400	118	-	10.50
8	0.28	378	3.45	1 450	118	42	9.45
9	0.30	390	3.85	1 505	117	-	9.75
10	0.30	351	3.97	1 550	117	39	8.76
11	0.32	460	3.08	1 420	147	-	11.5
12	0.32	414	3.20	1 470	147	46	10.35

水胶比	水泥量/（kg·m^-3）	骨胶比	实测空隙率/%	抗压强度/MPa	透水系数/（mm·s^-1）	数据来源
0.25	480.0	3.26	18.50	22.10	18.61	文献［22］
0.27	320.0	5.06	28.15	11.20	31.21	文献［23］
0.3	416.6	3.64	26.69	8.21	14.00	文献［24］
0.25	590.0	2.34	14.00	24.40	3.95	文献［25］
0.25	569.0	2.67	15.00	24.60	2.70	文献［26］
0.29	419.0	3.91	10.56	25.05	3.15	文献［27］
0.25	754.0	1.89	13.00	27.30	3.20	文献［28］
0.2	400.0	3.94	20.50	17.90	5.02	文献［29］
0.28	310.0	3.79	16.00	29.10	2.99	文献［30］
0.25	571.9	2.69	12.69	31.60	2.03	文献［31］
0.19	494.0	2.97	10.00	22.30	4.66	文献［32］
0.2	630.7	2.21	18.20	26.53	4.27	文献［33］
0.28	475.0	2.5	13.70	35.06	1.44	文献［34］
0.3	447.0	3.44	20.00	19.20	6.01	文献［35］
0.27	481.0	2.50	13.70	18.06	1.47	文献［36］
0.25	528.0	2.70	17.79	25.90	2.93	文献［37］
0.26	510.0	2.90	14.70	14.30	6.30	文献［38］
0.20	782.00	1.88	12.00	17.15	1.38	文献［39］
0.25	568.00	2.87	14.00	16.20	1.33	文献［40］
0.27	461.00	3.33	12.80	15.30	7.60	文献［41］
0.25	364.90	4.10	19.56	8.86	5.09	文献［42］
0.26	390.08	4.39	20.80	16.10	5.80	文献［43］
0.2	286.00	5.58	33.00	8.10	24.0	文献［44］
0.35	326.00	5.00	35.99	10.26	1.85	文献［45］
0.3	375.00	4.00	30.23	9.33	20.93	文献［46］
0.35	200.00	8.00	35.00	2.21	17.90	文献［47］
0.30	479.90	3.13	14.00	22.2	3.91	文献［48］
0.34	478.95	3.37	25.45	10.23	1.01	文献［49］
0.3	521.42	2.88	14.31	21.90	6.97	文献［50］
0.33	388.10	3.62	25.60	12.50	10.50	文献［51］
0.2	775.00	1.91	12.00	13.90	0.65	文献［52］

预测模型		MAE	MSE	RMSE	F值	R²
线性回归	抗压强度	6.483	71.359	8.447	156.68	0.539
线性回归	透水系数	3.328	20.691	4.548	156.87	0.540
非线性回归	抗压强度	4.871	43.125	6.567	83.084	0.681
非线性回归	透水系数	2.668	15.179	3.896	98.512	0.612

预测模型		MAE		RMSE		拟合优度R²
预测模型		训练集	测试集	训练集	测试集	训练集	测试集
BP	抗压强度	3.742	3.145	4.483	4.860	0.869	0.791
BP	透水系数	1.865	2.135	2.280	3.088	0.831	0.806
GA-BP	抗压强度	2.989	2.698	3.859	3.006	0.949	0.907
GA-BP	透水系数	1.895	1.974	2.984	2.620	0.912	0.895

Performance prediction of porous concrete based on neural network and regression analysis

RICH HTML

PDF (PC)

Abstract

Cite this article

share this article

Figures/Tables 19

References 53

Related Articles 15

Metrics

Comments

Recommended 0

[1]	Hao WANG,Bin ZHAO,Guo-hua LIU. Temporal and motion enhancement for video action recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 339-346.
[2]	Hong-yu HU,Zheng-guang ZHANG,You QU,Mu-yu CAI,Fei GAO,Zhen-hai GAO. Driver behavior recognition method based on dual-branch and deformable convolutional neural networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 93-104.
[3]	Lei SHANG,Ping YANG,Xiang-guo YANG,Jian-xin PAN,Jun YANG,Meng-ru ZHANG. Temperature control of proton exchange membrane fuel cell thermal management system based on APSO-BP-PID control strategy [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(9): 2401-2413.
[4]	Hong-wei ZHAO,Hong WU,Ke MA,Hai LI. Image classification framework based on knowledge distillation [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2307-2312.
[5]	Jin-zhou ZHANG,Shi-qing JI,Chuang TAN. Fusion algorithm of convolution neural network and bilateral filtering for seam extraction [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2313-2318.
[6]	Chao-lu TEMUR,Ya-ping ZHANG. Link anomaly detection algorithm for wireless sensor networks based on convolutional neural networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2295-2300.
[7]	Sheng-jie ZHU,Xuan WANG,Fang XU,Jia-qi PENG,Yuan-chao WANG. Multi-scale normalized detection method for airborne wide-area remote sensing images [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2329-2337.
[8]	En-liang WANG,Zhi-feng REN,Chu WANG,Jun-wei LIU,Xing-chao LIU,Ye TIAN,Meng ZOU,Zi-xiao LU,Wei-wei ZHANG,Sheng-yuan JIANG. Experiment on compressive strength of simulated lunar soil based on grey correlation analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 2015-2025.
[9]	Xiao-hui WEI,Chen-yang WANG,Qi WU,Xin-yang ZHENG,Hong-mei YU,Heng-shan YUE. Systolic array-based CNN accelerator soft error approximate fault tolerance design [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1746-1755.
[10]	Ming-hui SUN,Hao XUE,Yu-bo JIN,Wei-dong QU,Gui-he QIN. Video saliency prediction with collective spatio-temporal attention [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1767-1776.
[11]	Guang-bao LI,Dong GAO,Yong LU,Hao PING,Yuan-yuan ZHOU. Internal surface treatment of gas-liquid-solid technology based on improved neural network and Fluent [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1537-1547.
[12]	Xi-jun ZHANG,Guang-jie YU,Yong CUI,Ji-yang SHANG. Short-term traffic flow prediction based on clustering algorithm and graph neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1593-1600.
[13]	Xi-guang ZHANG,Long-fei ZHANG,Yu-xi MA,Yin-ting FAN. Design of fuzzy clustering algorithm for massive cloud data based on density peak [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1401-1406.
[14]	Chao XIA,Meng-jia WANG,Jian-yue Zhu,Zhi-gang YANG. Reduced-order modelling of a bluff body turbulent wake flow field using hierarchical convolutional neural network autoencoder [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 874-882.
[15]	Kai-xiang CHEN,He-nian ZHANG,Pei-sheng XI,Chang-dan WANG,Tao YU,Bing-xin ZHANG. Influence of carbonization humidity on mechanics and durability of carbonization block [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 445-452.