Strength Prediction of Foam Light Soil Based on GA-BP Neural Network

doi:10.12141/j.issn.1000-565X.220139

Abstract

Abstract:

Compressive strength is an important mechanical property of foamed lightweight soil. Accurately predicting and adjusting the compressive strength of lightweight foam soil is of great practical significance for improving construction efficiency. For intelligent control and optimization of foam light soil, this study designed a topology structure including 4 node input layer, 8 node hidden layer and 1 node output layer. The weight and threshold of BP neural network were improved by genetic algorithm (GA) in input layer. Using the four parameters of water-solid ratio, fly-ash ratio, fine aggregate mixing ratio and bubble rate as input parameters and 28-day compressive strength as output parameters, the two models before and after optimisation were validated and compared using mean squared error (MSE), coefficient of determination (R2) and relative error as samples. Based on this, a method for designing the mix ratio based on different performance requirements was established. The results show that compared with BP neural network, the GA-BP neural network has a larger fitness function value and smaller mean square deviation; the fit between the predicted and actual values can reach 0.946, with stronger prediction accuracy and gene-ralization ability; the global search ability of the genetic algorithm also makes up for the defect that BP neural network can easily fall into local optimum, and can better guide the fitting ratio design of the strength prediction of fly ash foam lightweight soil. The GA-BP neural network based strength growth prediction model for foam lightweight soils enables flexible adjustment of the compressive strength of foam lightweight soils, and it is of important refe-rence value for engineering construction.

Key words: foam lightweight soil, compressive strength, BP neural network, genetic algorithm, GA-BP neural network

CLC Number:

U414

ZHOU Zhong, DENG Zhuoxiang, CHEN Yun, et al. Strength Prediction of Foam Light Soil Based on GA-BP Neural Network[J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(11): 125-132.

Figures/Tables 17

Fig.1

Fig.2

Table 1

Table 2

Table 3

Table 4

Fig.3

Fig.4

Table 3

Fig.5

Fig.6

Table 5

Fig.7

Table 4

Fig.8

Fig.9

Fig.10

References 19

1	LI P， WU H， LIU Y，et al ．Preparation and optimization of ultra-light and thermal insulative aerogel foam concrete［J］．Constr Build Mater，2019，205：529-542.
2	张文华，吕毓静，刘鹏宇．EPS混凝土研究进展综述［J］．材料导报，2019，33（13）：2214-2228.
	ZHANG Wenhua， Yujing LÜ， LIU Pengyu ．Review on the research progress of EPS concrete［J］．Materials Reports，2019，33（13）：2214-2228.
3	SHERVIN A， SOHEIL K ．Multi-objective optimization of influential factors on production process of foamed concrete using Box-Behnken approach［J］．Construction and Building Materials，2018，170：101-110.
4	李婧．泡沫混凝土密度与抗压强度试验研究［J］．建筑结构，2021，51（S1）：1327-1331.
	LI Jing ．Experimental study on density and compressive strength of foamed concrete［J］．Building Structure，2021，51（S1）：1327-1331.
5	JOAQUÍN A G， JAIME F G， NANCY T C ．Properties prediction of environmentally friendly ultra-high-performance concrete using artificial neural networks［J］．European Journal of Environmental and Civil Engineering，2020，26（6）：2319-2343.
6	YADAV G S， SUDARSHAN D S， SAHITHI G，et al ．Predicting the characteristics of pond ash concrete using artificial neural networks［J］．Materials Science and Engineering，2020，872（1）：012176.
7	LIU T Y， ZHANG P， WANG J，et al ．Compressive strength prediction of PVA fiber-reinforced cementitious composites containing nano-SiO₂ using BP neural network［J］．Materials，2020，13（3）：521-524.
8	马高，刘康．基于BP神经网络CFRP约束混凝土抗压强度预测［J］．湖南大学学报（自然科学版），2021，48（9）：88-97.
	MA Gao， LIU Kang ．Prediction of compressive strength of CFRP-confined concrete columns based on BP neural network［J］．Journal of Hunan University（Natural Sciences），2021，48（9）：88-97.
9	周中，张俊杰，丁昊晖，等．基于PSO-BP神经网络的隧道绿色建造污水处理预测模型［J］．铁道科学与工程学报，2022，19（5）：1450-1458.
	ZHOU Zhong， ZHANG Junjie， DING Haohui，et al ．Prediction model of sewage treatment in tunnel green construction based on PSO-BP neural network［J］．Journal of Railway Science and Engineering： 2022，19（5）：1450-1458.
10	TU J， LIU Y， ZHOU M，et al ．Prediction and analysis of compressive strength of recycled aggregate thermal insulation concrete based on GA-BP optimization network［J］．Journal of Engineering，Design and Technology，2020．19（2）：412-422.
11	陈庆，马瑞，蒋正武，等．基于GA-BP神经网络的UHPC抗压强度预测与配合比设计［J］．建筑材料学报，2020，23（1）：176-183，191.
	CHEN Qing， MA Rui， JIANG Zhengwu，et al ．Compressive strength prediction and mix proportion desigin of UHPC based on GA-BP neural network［J］．Journal of Building Materials，2020，23（1）：176-183，191.
12	黄炜，周烺，葛培，等．基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究［J］．材料导报，2021，35（15）：15026-15030.
	HUANG Wei， ZHOU Lang， GE Pei，et al ．A Comparative study on compressive strength model of recycled brick aggregate concrete based on PSO-BP and GA-BP neural networks［J］．Materials Reports，2021，35（15）：15026-15030.
13	陈金福．高速公路新型轻质直立式路堤应用技术研究［D］．广州：广州大学，2011.
14	姜云晖．泡沫轻质土在加固深厚软土地基中的应用研究［D］．成都：西南交通大学，2016.
15	蔡历颖．泡沫轻质土在路堤工程中的应用研究［D］．福州：福建农林大学，2019.
16	王运卫．基于堆积理论的球形轻质材料路基设计方法研究［D］．哈尔滨：哈尔滨工业大学，2015.
17	姚运仕，王嘉．盐渍土对泡沫轻质土强度及耐久性的影响［J］．长安大学学报（自然科学版），2021，41（3）：33-41.
	YAO Yunshi， WANG Jia ．Effects of strength and durability of salted soil to foam lightweight Soil［J］．Journal of Chang’an University（Natural Science Edition），2021，41（3）：33-41.
18	裘友强．软土地基上泡沫轻质土路基工程特性研究［D］．西安：长安大学，2018.
19	黄小波．现浇泡沫轻质土在柳南高速改扩建高填方路基的应用研究［D］．广州：广州大学，2018.

指标	试验值	规范值	指标	试验值	规范值
细度/%	1.08	<30	终凝时间/min	228	≤600
比表面积/（m²·kg^-1）	335	≥300	3 d抗折强度/MPa	5.2	≥3.5
安定性	合格	合格	28 d抗折强度/MPa	—	≥6.5
密度/（kg·m^-3）	3 070	2 900~3 100	3 d抗压强度/MPa	24.7	≥17
初凝时间/min	178	≥45	28 d抗压强度/MPa	—	≥42.5

指标	技术要求	检测值	指标	技术要求	检测值
细度	≤18	16	Al₂O₃	≤30	24.2
烧失量	≤5	2.8	SiO₂	≤50	45.1
含水量	≤1.0	0.85	SO₃	≤3	2.1
密度	2 100~3 200	2 550	CaO	≤10	5.6
堆积密度	630~1 380	1 120	游离CaO	≤1.0	0.85

编号	水固比	粉灰比	细集料掺合比	气泡率	28 d 抗压强度/MPa	湿重度/（kN·m^-3）
1	0.61	0.50	0.70	0.65	1.74	6.19
2	0.59	0.50	0.40	0.71	1.52	5.39
3	0.57	0.50	0.25	0.62	2.12	7.05
4	0.56	0.40	0.70	0.68	1.67	6.03
5	0.54	0.40	0.55	0.59	2.80	7.53
6	0.61	0.40	0.25	0.68	1.79	5.70
7	0.59	0.30	0.85	0.59	1.99	7.50
8	0.57	0.30	0.55	0.65	1.77	6.25
9	0.56	0.30	0.25	0.71	1.26	5.98
10	0.54	0.20	0.85	0.62	2.35	6.60
11	0.61	0.20	0.55	0.71	1.57	6.37
12	0.59	0.20	0.40	0.62	1.96	6.67

编号	实际值/MPa	BP预测值/MPa	优化后GA-BP预测值/MPa	优化前抗压强度绝对误差（取绝对值）/MPa	优化后抗压强度绝对误差（取绝对值）/MPa	优化前抗压强度相对误差（取绝对值）/%	优化后抗压强度相对误差（取绝对值）/%
1	1.74	1.796	1.768	0.056	0.028	3.218	1.590
2	1.67	1.910	1.721	0.240	0.051	14.372	3.080
3	1.99	2.177	2.044	0.187	0.054	9.402	2.717
4	2.35	2.230	2.185	0.120	0.165	5.095	7.031
5	2.54	2.056	2.362	0.484	0.178	19.062	7.011
6	0.85	0.871	0.822	0.021	0.028	2.509	3.345
7	0.44	0.534	0.456	0.098	0.020	22.413	4.687
8	1.15	1.338	1.302	0.188	0.152	16.390	13.245
9	0.75	0.647	0.681	0.103	0.069	13.798	9.219
10	0.98	1.063	1.075	0.083	0.095	8.519	9.704
11	0.77	0.918	0.827	0.148	0.057	19.250	7.362
12	2.77	1.974	2.174	0.796	0.596	28.739	21.532

[1]	. Time sensitive network scheduling method based on genetic algorithm [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 1-12.
[2]	WU Bo, DING Jinpeng. Compressive and Chloride Resistance Properties of Recycled Aggregate Concrete Mixed with Hole Slag [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 120-128.
[3]	QIU Yudong, WANG Zhan, XIE Zhishen. Optimization for Steel Frames with Semirigid Connections Based on Hybrid Algorithms [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 72-77.
[4]	YU Qijun, MA Ting, ZHANG Tongsheng, et al.. Effect of Particle Size on Hydration Kinetics and Microstructure Development of Recycled Brick Powder-Cement Pastes [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(11): 63-73.
[5]	WENG Jiancheng, WANG Maolin, LIN Pengfei, et al. Cross-line Combined Bus Scheduling Optimization Method Based on Passenger Flow Characteristic Identification [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(9): 39-48.
[6]	QIN Yaqin, QIAN Zhengfu, XIE Jiming, et al. Cooperative Lane Change Decision-Making Model of Bottleneck Emergency Section in Weaving Area Based on Social Force [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(7): 66-75.
[7]	ZHENG Yajing, LI Yaohui, JIN Wenzhou. Connection Scheme Optimization of Last Trains of Urban Mass Transit Network Based on Considering the Transfer Passengers [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(5): 32-39,72.
[8]	LAN Fengchong, ZHANG Yue, CHEN Jiqing, et al. Correlation Analysis and Prediction of Pedestrian Casualty Risk in Car-Pedestrian Collision Accident [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(5): 1-10.
[9]	XIA Qinxiang, LI Kai, MA Jun, et al. Die Electrode Scheduling Problem Solution Based on Genetic Algorithm [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(3): 80-87.
[10]	LIU Xuan, WANG Zihang, ZHANG Tongrui, et al. Optimal Control Strategy for Lateral Stability of Port Heavy-Duty AGV [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(8): 113-121.
[11]	ZHANG Yirui SU Jian XU Guan. Research on Coupling Effect Experiment and Decoupling Method of 3-D Force Measuring Platform [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(5): 135-144.
[12]	LI Jing WANG Chen ZHANG Jiaxu. Vehicle Speed Estimation Based on UniTire Model [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(5): 47-55.
[13]	LUO Yutao, ZHOU Tianyang, XU Xiaotong. Time-Varying LQR Control of Four-Wheel Steer /Drive Vehicle Based on Genetic Algorithm [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(3): 114-122.
[14]	JIN Gang HE Zhihao WANG Yingjun. 5G Frequency Selection Surface Shape Optimization Method Based on Genetic Algorithm [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(11): 95-105.
[15]	LI Jiale LIU Zhenbo WANG Xuefei. Distribution Path Optimization of Electric Vehicles Considering Charging and Discharging Strategy in Smart Grid [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(10): 31-40.