基于PCA-GA-RBF网络的聚丙烯熔融指数预报模型

Melt Index Prediction of Polypropylene by Neural Networks Model Based on PCA-GA-RBF

熔融指数是工业聚丙烯生产中决定聚丙烯牌号最重要的指标。但因缺乏在线分析仪,指标获得时间间隔长、滞后大,使聚丙烯质量控制困难。提出了一种基于PCA-GA-RBF的神经网络模型,基于真实数据对聚丙烯生产过程的熔融指数进行预报。其中,主元分析法(PCA)用来提取过程特征参数,剔除相关冗余信息;径向基(RBF)神经网络用来逼近非线性过程;遗传算法(GA)用来优化RBF网络的权值和网络层元数等结构参数。研究结果表明了所提出的熔融指数预报模型的可靠性和准确性。

Melt index （MI） is the most important parameter in determining the polypropylene＇s grade. Since the lack of proper on--line instruments, its measurement interval and delay are both very long. This makes the quality control quite difficult. A neural network model based on PCA--GA--RBF was proposed to infer the MI of manufactured products from real process variables, where principle component analysis （PCA） was used to select the most relevant process features and to eliminate the correlations of the input variables, radial basis function （RBF） neural networks were used to characterize the nonlinearity and accuracy, and genetic algorithms （GA） was employed to optimize the parameters and structure of the RBF neural networks. The results show that the proposed method provides promising prediction reliability and accuracy.