【作者】 刘欣； 蒋爱平；

【Author】 LIU Xin JIANG Ai-ping (Research Institute of Automation , East China University of Science and Technology) (Shanghai 200237, China)

【机构】 华东理工大学自动化研究所；

【摘要】 本文对微粒群优化算法(PSO)这一新兴优化算法进行分析,重点研究了如何将PSO与常用软测量建模方法神经网络进行结合,构造微粒群神经网络。并将构造的微粒群神经网络用于丙烯腈收率的软测量建模。实验结果表明,将PSO应用于丙烯腈收率软测量建模,得到的模型具有较高的精度、良好的性能和很好的应用前景更多还原

【Abstract】 In this dissertation, particle swarm optimization algorithm is analyzed. It’s important in this dissertation that how PSO is applied to train artificial neural networks(NN) to construct the neural network of particle swarm optimization. Then PSONN is applied to construct a practical soft-sensor of acrylonitrile product rate . After comparing with actual industrial data, the result shows that the PSONN is feasible and effective in soft-sensor model of acrylonitrile product rate.更多还原