基于CLGPR模型的聚丙烯生产过程质量预测

Quality Prediction of Polypropylene Production Process Based on CLGPR Model

聚丙烯聚合生产过程是一个高度非线性的过程,通常无法在线测量熔融指数,因此需要模型来估计和预测这一重要变量。本文提出了一种用于预测熔体指数的有效测量方法——组合局部高斯过程回归(CLGPR)法。通过引入的高斯过程回归模型可以很好地解决每个操作模式下过程数据的高度非线性,在工业聚丙烯生产过程中的应用,验证了所提出的测量方法的可行性和有效性。

Polypropylene polymerization process is a highly nonlinear process,and it is usually impossible to measure the melt index online.Therefore,it is necessary to estimate and predict this important variable with a model.In this paper,an effective measurement method for predicting melt index-combined local Gaussian process regression(CLGPR)method is proposed.The Gauss process regression model introduced can well solve the high nonlinearity of process data under each operation mode.The application in industrial polypropylene production process has verified the feasibility and effectiveness of the proposed measurement method.