微粒群神经网络在常压塔汽油干点软测量建模中的应用  

Application of Particle Swarm Optimization Neural Network in Soft-sensor Modeling of Gasoline Endpoint of Crude Distillation Unit

作　　者：陈国初[1] 俞金寿[1] 

机构地区：[1]华东理工大学自动化研究所,上海200237

出　　处：《化工自动化及仪表》2005年第3期25-27,共3页Control and Instruments in Chemical Industry

基　　金：教育部博士点专项基金资助项目(20030251003)

摘　　要：首先将微粒群优化算法用于神经网络连接权值和阈值的训练,构造微粒群神经网络,然后将微粒群神经网络用于常压塔汽油干点软测量建模。通过与实际值的对比,结果表明基于微粒群神经网络的软测量模型具有良好的性能和极好的应用前景。The particle swarm optimization algorithm (PSO) is applied to train artificial neural networks (NN) and construct a neural networks based on particle swarm optimization algorithm (PSONN). The PSONN is applied to construct a practical soft-sensor modeling of gasoline endpoint of crude distillation unit. After comparing with practical industrial data, the result shows that the PSONN is feasible and effective.

关 键 词：微粒群优化算法 神经网络 常压塔 汽油干点 软测量模型 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]