Neural Net based Quality Modeling and Control Systems for Polymerization Processes

在这项研究中，提出了一种在线推断方案，以预测聚合物的性质，熔体指数，该性质的离线，过去的测量值和可用的在线测量的过程变量。在在线推理方案中，利用了L无限波网，这是一种从小波族中提取基函数的人工神经网络，它结合了化学工程的基本原理。多步预报器由相同的一步超前波网预报器级联而成，自适应地学习聚合物性质与工艺变量之间的函数关系。以工业高密度聚乙烯工艺的运行数据为例，说明了该方案的应用。结果表明，建立在波网基础上的推理方案可以成功地预测MI，并证明其作为一种在线监测方案的潜力，以将聚合物质量保持在最高水平。

In this study, an on-line inferential scheme is proposed in order to predict a polymer property, the Melt Index, form off-line, past measured values of this property and available on-line measured process variables. In the on-line inferential scheme, the L infinity wave-net, which is an artificial nenural network with basis functions drawn from the family of wavelets, is utilized by incorporating fundamentals of chemical engineering. The multistep predictor, formulated in a cascaded structure of identical one-step-ahead Wave-Net based predictors, is adaptively learning the functional relationship between the polymer property and process variables. The application of the scheme is illustrated using operating data for an industrial High Density Polyethylene Process. The results of the proposed scheme show that the inferential scheme built upon the Wave-Net can successfully predict the MI and prove its potential as an on-line monitoring scheme to maintain the polymer quality at the highest level.