以粒子蜂群网络建立高性能混凝土坍落度模型  

Modelling slump model of high-performance concrete using particle bee neural network

作　　者：连立川 刘燕妮[1,2] 叶怡成 

机构地区：[1]福建工程学院土木工程学院,福建福州350118 [2]福建土木工程新技术与信息化重点实验室,福建福州350118 [3]淡江大学

出　　处：《福建工程学院学报》2015年第1期1-9,共9页Journal of Fujian University of Technology

基　　金：国家自然科学基金资助项目(51308120);福建省自然科学基金资助项目(56237845)

摘　　要：以粒子蜂群算法(particle bee algorithm,PBA)结合神经网络(artificial neural network,NN),发展出一套能预测高性能混凝土(high-performance concrete,HPC)坍落度模型的方法。以演化运算树(genetic operation tree,GOT)及倒传递网络(back-propagation network,BPN)两种已发表的方法来比较其准确度。从模型的准确度可知,粒子蜂群网络(particle bee neural network,PBNN)模型预测的准确度高于GOT,但接近BPN的准确度;从参数的影响性可知,PBNN显示水、强塑剂、粗骨材、细骨材、粉煤灰及水泥添加量对于HPC坍落度的影响性大,而高炉矿渣粉用量对HPC坍落度并不敏感,显示各项材料对于坍落度的影响仍具备高度复杂性。This study used particle bee algorithm（ PBA） combined with artificial neural network（ NN） to predict the slump model of high-performance concrete（ HPC）. This study also compared the accuracy of the results with two proposed methods： genetic operation tree（ GOT） and backpropagation network（ BPN）. The results show that particle bee neural network（ PBNN） is more accurate than GOT and closer to BPN. Besides,the addition amount of the parameters such as water,super plasticizer,coarse aggregate,fine aggregate,fly ash and cement has a high influence on the slump of HPC,while the amount of blast-furnace slag has a small influence on the slump of HPC. It shows that the impacts of those materials on the slump are still a high degree of complexity.

关 键 词：粒子蜂群算法 高性能混凝土 演化运算树 倒传递网络 粒子蜂群网络 

分 类 号：TU17[建筑科学—建筑理论]