基于机制建模与模糊建模相结合的聚丙烯熔融指数软测量方法

Soft sensor method for polypropylene melt index based on FP-EFCM

针对聚丙烯熔融指数软测量建模问题,提出一种基于机制建模与模糊建模相结合的建模方法。从聚合反应机制出发,得到熔融指数软测量模型的机理结构框架,将其作为Takagi-Sugeno(T-S)模糊模型的后件部分,然后用加强型模糊聚类算法辨识T-S模型的前件参数。应用结果表明,将机制建模与模糊建模相结合的方法保留了模型参数的物理意义,提高了建模精度,所建软测量模型具有较好的预测性能。

To build an accurate soft-sensor model of polypropylene melt index, a new method was proposed based on first principle and enhanced fuzzy c-means （FP-EFCM）. According to polymerization mechanism, the mechanism structure framework of soft sensor model for polypropylene melt index was obtained and used as the consequent structure of the TakagiSugeno（T-S） fuzzy model. Then EFCM was used to identify the premise parameters of the T-S model. The results show that this method retains the physical meaning of the model parameters and improves the model accuracy. The soft-sensor model has good prediction performance.