基于粒子群优化算法的熔融指数预报

针对丙烯聚合生产控制中聚丙烯熔融指数在线测量的控制要求,以及过程变量间相关性高的特点,提出一种实用高精度的软测量方法,以弥补传统的实验室分析严重滞后所导致的生产控制瓶颈问题。采用主元分析,提取少量主元反映多个变量的综合信息,以降低预报模型的复杂度。并在此基础上建立基于径向基函数神经网络的统计预报模型,提出利用粒子群优化算法优化神经网络的结构与参数,以减少人为因素对建模的影响,得到最优预报结果。通过对工厂实际生产过程进行详细的预报检测,并进一步与国内外相关研究报道进行比较,结果表明,所提出的预报方法具有更强的可靠性和更高的准确性。

Melt Index Prediction Based on Particle Swarm Optimization

A high-precision on-line method of predicting melt index of propylene polymerization based on principal component analysis and particle swarm optimization is proposed to overcome the high correlation characteristics and high nonlinear characteristics in the propylene polymerization process.Principal component analysis,which obtains principal components with a small number of dynamic variables reflect the entire information,is employed to reduce the complexity of prediction model.Radial basis function neural...