摘要
为实现对不同操作条件(操作压力、料液质量浓度和温度)下的牛血清白蛋白溶液死端微滤膜通量的预测,以训练步数、绝对相对误差和相关系数作为预测的衡量指标,并对所建立的3层BP神经网络和RBF神经网络基本模型的内部参数进行了优化.优化的BP神经网络模型的拓朴结构为3-9-1,学习率为0.05,学习/训练函数为traingdx,隐层到输出层的传递函数为logsig,该网络对牛血清白蛋白(BSA)溶液膜通量预测的平均绝对相对误差为2.37%,相关系数为0.9960;优化的RBF神经网络的网络设计函数为newrbe,散布常数为400,该网络对BSA溶液膜通量预测的平均绝对相对误差为4.83%,相关系数为0.987 0.结果表明,BP神经网络优于RBF神经网络.
In order to predict the flux of BSA solutions under the different operating conditions （transmembrane pressure, feed concentration and temperature） in the dead-end microfihration, the training epochs, correlative coefficient and relative absolute error were used as three predictive criterions, and the configurations of the developed three layers BP and RBF neural network were optimized by changing the interior parameters of neural networks. The result showed that, in the experimental rang, an optimal configuration of the available BP neural network is 3-9-1, the number of hidden neurons is 9, the learning rate is 0.05, the learning function is traingdx, the transfer function is logsig. By using the BP neural network, the obtained average relative absolute error and correlative coefficient is 2.37%, 0. 9960, respectively. By using the RBF neural network, the designable function of the network for an optimal configuration of the available RBF neural network is newrbe, and its spread is 400. The obtained average relative absolute error and correlative coefficient is 4. 83% , 0. 987 0, respectively. Therefore an BP neural network is much better than a RBF neural network in the study of predicting the flux of BSA solutions in the dead-end microfiltration.
出处
《北京工业大学学报》
EI
CAS
CSCD
北大核心
2010年第2期235-239,267,共6页
Journal of Beijing University of Technology
基金
国家自然科学基金资助项目(20276003)
北京市自然科学基金资助项目(8052006)
作者简介
王湛（1966-），男，河南新安人，博士生导师．
