基于PSO-SVM的混凝土专用回弹测强曲线的研究  

Research on the Establishment of Curve for Detecting Concrete Rebound and Strength Based on PSO-SVM

作　　者：冉彦立 郄志红[1] 王铁强 

机构地区：[1]河北农业大学城乡建设学院,河北保定071001 [2]河北省水利科学研究院,石家庄050000

出　　处：《中国农村水利水电》2015年第3期135-138,共4页China Rural Water and Hydropower

摘　　要：结合试验采集的回弹值和抗压强度值数据,基于粒子群(PSO)优化支持向量机(SVM)预测模型建立了南水北调工程河北段混凝土的专用回弹测强曲线。通过与传统的幂函数回归模型及BP神经网络模型作比较,证明PSOSVM预测模型具有较高的计算精度和较快的运行速度。研究成果为南水北调工程河北段混凝土回弹检测提供了理论依据和参考标准。By using the rebound and compressive strength data of concrete experiment,the special rebound and strength curve is achieved for South-to-North Water Diversion Project in Hebei Province.The PSO-SVM prediction model has higher accuracy and faster running speed compared with the traditional exponential function and BP neural networks.The result provides a strong theoretical basis and reference standard for South-to-North Water Diversion Project in Hebei Province.

关 键 词：南水北调 混凝土 支持向量机 粒子群优化算法 回弹测强曲线 

分 类 号：TU528[建筑科学—建筑技术科学]