收稿日期: 2022-03-18
网络出版日期: 2022-05-12
基金资助
湖南省自然科学基金资助项目(2020JJ4743)
Strength Prediction of Foam Light Soil Based on GA-BP Neural Network
Received date: 2022-03-18
Online published: 2022-05-12
Supported by
the Natural Science Foundation of Hunan Province(2020JJ4743)
泡沫轻质土的抗压强度是其重要的力学性能。精准地预测和调整泡沫轻质土的抗压强度,对于提高施工效率有重要的现实意义。为实现对泡沫轻质土抗压强度的智能控制和优化,设计了包含4节点输入层、8节点隐层、1节点输出层的拓扑结构,输入层采用遗传算法(GA)对BP神经网络的权重和阈值进行改进。以水固比、粉灰比、细集料掺合比以及气泡率4个参数作为输入参数,28天抗压强度为输出参数,以室内实验数据作为样本,使用均方差(MSE)、决定系数(R2)和相对误差等对优化前后两种模型进行验证和对比分析,并以此为基础建立了基于不同性能需求的配合比设计方法。结果表明:相比BP神经网络,GA-BP神经网络训练的适应度函数值更大、均方差更小,预测值与实际值的拟合度可达到0.946,具有更强的预测精度和泛化能力,同时遗传算法的全局搜索能力也弥补了BP神经网络容易陷入局部最优的缺陷,且能更好地指导粉煤灰泡沫轻质土强度预测配合比设计。基于GA-BP神经网络的泡沫轻质土强度增长预测模型可实现对泡沫轻质土抗压强度的灵活调整,对于工程施工具有重要的参考价值。
周中 , 邓卓湘 , 陈云 , 胡江锋 . 基于GA-BP神经网络的泡沫轻质土强度预测[J]. 华南理工大学学报(自然科学版), 2022 , 50(11) : 125 -132 . DOI: 10.12141/j.issn.1000-565X.220139
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.
| 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. |
| 2 | 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. |
| 4 | 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. |
| 8 | 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. |
| 9 | 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. |
| 11 | 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. |
| 12 | 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. |
| 17 | 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. |
/
| 〈 |
|
〉 |