基于灰色-神经网络组合模型的纤维混凝土腐蚀劣化预测模型研究

硅酸盐通报 ›› 2023, Vol. 42 ›› Issue (7): 2429-2438.

所属专题：水泥混凝土

基于灰色-神经网络组合模型的纤维混凝土腐蚀劣化预测模型研究

戎泽斌¹, 王成^1,2

1.塔里木大学水利与建筑工程学院,阿拉尔 843300;
2.塔里木大学南疆岩土工程研究中心,阿拉尔 843300

收稿日期:2023-04-20 修订日期:2023-05-20 出版日期:2023-07-15 发布日期:2023-07-25
通信作者: 王成,博士,教授。E-mail:wchgghwzy@163.com
作者简介:戎泽斌(1993—),男,助教。主要从事混凝土结构耐久性的研究。E-mail:64857846@qq.com
基金资助:
国家自然科学基金(52168035);新疆生产建设兵团区域创新引导计划(2018BB045);新疆生产建设兵团重点领域科技攻关计划(2019AB016)

Corrosion Deterioration Prediction Model of Fiber Concrete Based on Grey Neural Network Combination Model

RONG Zebin¹, WANG Cheng^1,2

1. School of Water Conservancy and Architectural Engineering, Tarim University, Alaer 843300, China;
2. South Xinjiang Geotechnical Engineering Research Center, Tarim University, Alaer 843300, China

Received:2023-04-20 Revised:2023-05-20 Online:2023-07-15 Published:2023-07-25

摘要/Abstract

摘要： 将体积掺量为0.3%的聚乙烯醇(PVA)纤维掺入C30混凝土,分别开展不同浓度溶液作用下的全浸泡-烘干试验,从而探究PVA纤维混凝土的抗劣化性能。以劣化试验数据作为原始样本值,分别建立GM(1,1)模型、BP神经网络模型和GM(1,1)-BP神经网络组合模型对样本数据进行拟合精度对比,并对35~50次循环后的相对动弹性模量数值做出预测,分析整体变化趋势。结果表明:混凝土试件在10倍基准浓度溶液下的评价指标变化最稳定,表明PVA体积掺量为0.3%的试件在高浓度溶液下的抗劣化性能较好;GM(1,1)模型对样本的整体趋势变化预测较为准确;BP神经网络模型对样本单一点的变化趋势预测较为准确,整体精度最高;而组合模型克服了两种单一模型的不足之处,预测值与测试值的变化趋势一致,预测效果最好。

关键词: 纤维混凝土, 劣化试验, GM(1,1)模型, BP神经网络模型, 组合模型

Abstract: By adding 0.3% (volume fraction) polyvinyl alcohol (PVA) fiber into C30 concrete, the full immersion-drying tests under the action of different concentration of solution were carried out respectively, so as to explore the performance of anti deterioration performance of PVA fiber concrete. Taking deterioration test data as original sample value, GM (1,1) model, BP neural network model and GM (1,1)-BP neural network combination model were established respectively to compare the fitting accuracy of sample data. The relative dynamic elastic modulus after 35~50 cycles was predicted, and the overall change trend was analyzed. The results show that the evaluation indexes of concrete specimens change most stably in 10 times of the reference concentration solution, indicating that the specimens with 0.3% (volume fraction) PVA have better anti deterioration performance in high concentration solution. GM (1,1) model can accurately predict the overall trend change of sample. BP neural network model is more accurate in predicting the change trend of single sample point, with the highest overall accuracy. The combination model overcomes the shortcomings of two single models and has the best prediction effect. The predicted value of combination model is consistent with the change trend of test value.

Key words: fiber concrete, deterioration test, GM (1,1) model, BP neural network model, combination model

中图分类号:

TU528.572

戎泽斌, 王成. 基于灰色-神经网络组合模型的纤维混凝土腐蚀劣化预测模型研究[J]. 硅酸盐通报, 2023, 42(7): 2429-2438.

RONG Zebin, WANG Cheng. Corrosion Deterioration Prediction Model of Fiber Concrete Based on Grey Neural Network Combination Model[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2023, 42(7): 2429-2438.

参考文献

[1] 杨德胜. 新时代绿色高性能混凝土发展的必要性研究[J]. 混凝土, 2019(11): 145-148.
YANG D S. Study on the necessity of developing green high-performance concrete vigorously in the new era[J]. Concrete, 2019(11): 145-148 (in Chinese).
[2] 韩宇栋, 丁小平, 岳清瑞, 等. 现代混凝土收缩开裂组合调控法评述[J]. 工业建筑, 2022, 52(7): 173-185.
HAN Y D, DING X P, YUE Q R, et al. A review on shrinkage and cracking combination control methods for modern concrete[J]. Industrial Construction, 2022, 52(7): 173-185 (in Chinese).
[3] 黄加圣, 杨鼎宜, 朱振东, 等. 聚乙烯醇纤维混凝土耐久性能试验研究[J]. 混凝土, 2019(6): 61-65.
HUANG J S, YANG D Y, ZHU Z D, et al. Experimental study on durability of polyvinyl alcohol fiber concrete[J]. Concrete, 2019(6): 61-65 (in Chinese).
[4] 王洪宇, 王成, 操静, 等. 南疆盐渍土地区聚乙烯醇纤维混凝土损伤研究[J]. 山西建筑, 2021, 47(10): 105-108.
WANG H Y, WANG C, CAO J, et al. Study on the deterioration of PVA fiber concrete in saline land area of southern Xinjiang[J]. Shanxi Architecture, 2021, 47(10): 105-108 (in Chinese).
[5] 赵杨, 孙海燕, 梅伟, 等. PVA纤维对混凝土干缩及抗侵蚀性能的影响研究[J]. 粉煤灰综合利用, 2022, 36(3): 73-78.
ZHAO Y, SUN H Y, MEI W, et al. Study on the effect of erosion resistance of mortar with PVA fiber in the different alkali concentration[J]. Fly Ash Comprehensive Utilization, 2022, 36(3): 73-78 (in Chinese).
[6] 冯树民, 刘浩, 李来成. 雨雪天气下轨道交通客流预测模型[J]. 哈尔滨工业大学学报, 2022, 54(9): 1-6.
FENG S M, LIU H, LI L C. Prediction model of rail transit passenger flow in rain and snow weather[J]. Journal of Harbin Institute of Technology, 2022, 54(9): 1-6 (in Chinese).
[7] 高矗, 孔祥振, 申向东. 基于GM(1, 1)的应力损伤轻骨料混凝土抗冻性评估[J]. 工程科学与技术, 2021, 53(4): 184-190.
GAO C, KONG X Z, SHEN X D. Freeze-thaw resistance evaluation of lightweight aggregate concrete with stress damage based on GM(1, 1)[J]. Advanced Engineering Sciences, 2021, 53(4): 184-190 (in Chinese).
[8] 赵明亮, 水中和, 周华新, 等. 中低强度等级混凝土抗压强度的BP神经网络模型预测研究[J]. 混凝土, 2021(3): 35-38.
ZHAO M L, SHUI Z H, ZHOU H X, et al. Prediction of compressive strength of medium and low strength grade concrete by BP neural network model[J]. Concrete, 2021(3): 35-38 (in Chinese).
[9] 吕燕梅, 王苏林. 基于离散灰色模型的铁路货运量预测仿真[J]. 计算机仿真, 2022, 39(5): 150-153+190.
LV Y M, WANG S L. Prediction and simulation of railway freight volume based on discrete grey model[J]. Computer Simulation, 2022, 39(5): 150-153+190 (in Chinese).
[10] 秦晓芳. BP神经网络理论下供应商选择评价模型构建[J]. 商业经济研究, 2015(27): 24-25.
QIN X F. Construction of supplier selection evaluation model based on BP neural network theory[J]. Journal of Commercial Economics, 2015(27): 24-25 (in Chinese).
[11] 罗泽民, 布优月. 基于灰色神经网络PGNN模型的建筑材料价格预测方法研究[J]. 建筑经济, 2020, 41(10): 115-120.
LUO Z M, BU Y Y. Research on price forecast method of building materials based on grey neural network PGNN model[J]. Construction Economy, 2020, 41(10): 115-120 (in Chinese).
[12] 中华人民共和国住房和城乡建设部. 普通混凝土长期性能和耐久性能试验方法标准: GB/T 50082—2009[S]. 北京: 中国建筑工业出版社, 2010.
Ministry of Housing and Urban-Rural Development of the People's Republic of China. Standard test method for long-term and durability properties of ordinary concrete: GB/T 50082—2009[S]. Beijing: China Construction Industry Press, 2010 (in Chinese).

[1]	张劲竹, 刘华新, 王家贺, 柳根金, 王学志. 混杂纤维混凝土高温后性能劣化分析与强度预测[J]. 硅酸盐通报, 2023, 42(4): 1260-1269.
[2]	王钧, 方雪琪, 焦裕榕, 崔梦麟. 玄武岩纤维混凝土板冲切试验与承载力分析[J]. 硅酸盐通报, 2023, 42(1): 100-110.
[3]	孙杰, 冯川, 吴爽, 马稳, 孙明星. 持续荷载与冻融循环耦合作用下纤维混凝土损伤性能研究[J]. 硅酸盐通报, 2022, 41(8): 2728-2738.
[4]	张建波, 陈升平, 卢应发. FRP筋异强混凝土叠浇梁挠度与延性研究[J]. 硅酸盐通报, 2022, 41(8): 2739-2747.
[5]	庄彬彬, 萧超雄, 刘强, 邓嘉辉, 汪大洋. 不同掺合料混凝土与锈蚀钢筋间粘结-滑移力学性能试验研究[J]. 硅酸盐通报, 2022, 41(8): 2767-2773.
[6]	郭寅川, 谢波, 周利超, 赵子豪, 黄炜. 动态疲劳荷载下玄武岩纤维混凝土抗渗性衰减及机理研究[J]. 硅酸盐通报, 2022, 41(3): 810-817.
[7]	王辉明, 李汝飞, 邓平贵. 基于分形理论和扩展有限元法的钢纤维混凝土损伤破坏机理[J]. 硅酸盐通报, 2022, 41(12): 4202-4213.
[8]	杨晓华, 罗滔, 刘晓剑, 叶尔木拉提. 初始缝高比对钢纤维混凝土断裂性能的影响[J]. 硅酸盐通报, 2022, 41(10): 3465-3474.
[9]	梁宁慧, 任联玺, 周侃, 胡恒, 周本炜. 聚丙烯粗纤维对泵送混凝土性能的影响及灰色关联分析[J]. 硅酸盐通报, 2022, 41(1): 88-99.
[10]	赵晓红, 沈玉, 刘娟红, 郭子栋. 硫酸盐对超深井井壁混凝土力学性能的影响及劣化机理[J]. 硅酸盐通报, 2021, 40(9): 2939-2947.
[11]	贺正波, 王辉明. 结合均匀化理论对钢纤维混凝土梁的疲劳性能分析[J]. 硅酸盐通报, 2021, 40(8): 2574-2583.
[12]	张广泰, 耿天娇, 鲁海波, 王明阳, 李雪藩. 冻融循环下沙漠砂纤维混凝土损伤模型研究[J]. 硅酸盐通报, 2021, 40(7): 2225-2231.
[13]	解国梁, 申向东, 姜伟, 张斌. 干湿循环作用下氯离子在聚丙烯纤维混凝土中传输性能研究[J]. 硅酸盐通报, 2021, 40(6): 2019-2025.
[14]	张广泰, 李瑞祥, 刘诗拓, 阿迪力·赛买提, 耿天娇. 冷热循环下纤维混凝土与高强钢筋间粘结强度损伤模型[J]. 硅酸盐通报, 2021, 40(4): 1193-1204.
[15]	刘鑫, 侯新宇, 林军, 景晶晶, 刘为平, 佘俊文, 朱浩. 实时高温下钢纤维混凝土的力学特性及其声发射响应[J]. 硅酸盐通报, 2021, 40(2): 447-454.

基于灰色-神经网络组合模型的纤维混凝土腐蚀劣化预测模型研究

Corrosion Deterioration Prediction Model of Fiber Concrete Based on Grey Neural Network Combination Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价