福建工程学院学报
福建工程學院學報
복건공정학원학보
JOURNAL OF FUJIAN UNIVERSITY OF TECHNOLOGY
2015年
1期
1-9
,共9页
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
粒子蜂群算法%高性能混凝土%縯化運算樹%倒傳遞網絡%粒子蜂群網絡
입자봉군산법%고성능혼응토%연화운산수%도전체망락%입자봉군망락
particle bee algorithm%high-performance concrete%genetic operation tree%back-propa-gation network%particle bee neural network
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（ge-netic 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。
以粒子蜂群算法（particle bee algorithm，PBA）結閤神經網絡（artificial neural network，NN），髮展齣一套能預測高性能混凝土（high-performance concrete，HPC）坍落度模型的方法。以縯化運算樹（ge-netic operation tree，GOT）及倒傳遞網絡（back-propagation network，BPN）兩種已髮錶的方法來比較其準確度。從模型的準確度可知，粒子蜂群網絡（particle bee neural network，PBNN）模型預測的準確度高于 GOT，但接近 BPN 的準確度；從參數的影響性可知，PBNN 顯示水、彊塑劑、粗骨材、細骨材、粉煤灰及水泥添加量對于 HPC 坍落度的影響性大，而高爐礦渣粉用量對 HPC 坍落度併不敏感，顯示各項材料對于坍落度的影響仍具備高度複雜性。
이입자봉군산법（particle bee algorithm，PBA）결합신경망락（artificial neural network，NN），발전출일투능예측고성능혼응토（high-performance concrete，HPC）담락도모형적방법。이연화운산수（ge-netic operation tree，GOT）급도전체망락（back-propagation network，BPN）량충이발표적방법래비교기준학도。종모형적준학도가지，입자봉군망락（particle bee neural network，PBNN）모형예측적준학도고우 GOT，단접근 BPN 적준학도；종삼수적영향성가지，PBNN 현시수、강소제、조골재、세골재、분매회급수니첨가량대우 HPC 담락도적영향성대，이고로광사분용량대 HPC 담락도병불민감，현시각항재료대우담락도적영향잉구비고도복잡성。
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 back-propagation network (BPN).The results show that particle bee neural network (PBNN)is more ac-curate 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.
