基于ABC-BP神经网络预测钢筋锈蚀程度  

Predict Corrosion Degree of Steel Bars in Reinforcing Concrete Based on ABC-BP Neural Network

作　　者：刘斌云[1] 王鑫[1] 万其微 LIU Bin-yun;WANG Xin;WAN Qi-wei(College of Architecture and Civil Engineering,Beijing University of Technology,Beijing 100214,China)

机构地区：[1]北京工业大学建筑工程学院

出　　处：《合成材料老化与应用》2019年第5期54-58,共5页Synthetic Materials Aging and Application

基　　金：国家自然科学基金(51378032)

摘　　要：将人工蜂群算法与BP神经网络原理相结合,设计了预测精度更高的ABC-BP神经网络,基于室内加速锈蚀实验所获得相关数据,建立了预测钢筋锈蚀程度的网络模型。利用MATLAB平台进行仿真训练,提取训练完成后的网络权值,研究了综合因素条件下混凝土内钢筋锈蚀程度与多个影响因素之间的关系。结果表明,ABC-BP神经网络较BP神经网络具有更高的预测精度,裂缝宽度对钢筋混凝土锈蚀程度影响较大,因此ABC-BP神经网络可用于预测钢筋混凝土构件锈蚀程度。The ABC-BP neural network is designed by combining Artificial Bee Colony(ABC)algorithm and BP neural network.Based on relevant conformation got from accelerating corrosion experiment,network model was established.The MATLAB platform was used for simulation of training,and the network weights after the training were extracted.The relationship between the degree of steel corrosion in concrete and multiple influencing factors was studied under the condition of comprehensive factors.The results show that the ABC-BP neural network has a higher prediction accuracy than the BP neural network,and the crack width has a greater impact on the degree of corrosion of reinforced concrete,so ABC-BP neural network can be used to predict the corrosion degree of reinforced concrete components.

关 键 词：ABC-BP MATLAB 混凝土 钢筋锈蚀 

分 类 号：TU528[建筑科学—建筑技术科学]