摘要
针对钢筋混凝土内部环境复杂,影响钢筋腐蚀程度的因素较多,而导致钢筋腐蚀程度测量精度不高的问题,利用改进天牛须算法(BAS)收敛特性快和全局搜索能力强的优势来初始BP神经网络的权值和阈值。从钢筋腐蚀机理出发,选取混凝土内部温度、湿度、CO_(2)含量、pH、氯离子含量和腐蚀电位6个影响因素作为输入变量,钢筋腐蚀程度作为输出变量,建立了IBAS-BP预测模型,并利用实测输入数据进行仿真验证。结果表明:相较于BAS-BP、PSO-BP和GA-BP模型,IBAS-BP预测模型的收敛速率快,测试集的最大相对误差为0.025,决定系数为0.9433;IBAS-BP预测模型能更精确地预测钢筋混凝土中钢筋的腐蚀程度。
In view of the complex internal environment of reinforced concrete,there were many factors that affect the corrosion of steel bars,which led to the problem that the measurement accuracy of steel corrosion was not high.It was proposed to use the advantages of fast convergence characteristics and strong global search ability of the improved long-horned whisker algorithm(BAS)to initialize the weights and thresholds of the BP neural network.Based on the corrosion mechanism of steel bars,six influencing factors of concrete internal temperature,humidity,CO_(2) content,pH,chloride ion content and corrosion potential were selected as input variables,and steel corrosion degree was selected as output variables,an IBAS-BP prediction model was established and the measured input datas were used for simulation verification.The results showed that as compared with the three models of BAS-BP,PSOBP and GA-BP,IBAS-BP prediction model had a fast convergence rate,the maximum relative error of the test set was 0.025 and the coefficient of determination was 0.9433.The IBAS-BP prediction model could more accurately predicte the corrosion degree of steel bars in reinforced concrete.
作者
黄雷
俞阿龙
HUANG Lei;YU Along(College of Electrical Engineering and Control Science,Nanjing Tech University,Nanjing 211800,China;School of Physics and Electronic Electrical Engineering,Huaiyin Normal University,Huai'an 223300,China)
出处
《腐蚀与防护》
CAS
CSCD
北大核心
2023年第6期111-117,共7页
Corrosion & Protection
作者简介
通信作者:俞阿龙(1964-),教授,博士,主要研究方向测控技术与智能系统,13016572088,yal@hytc.edu.cn。
