煮糖过程的混合建模

HYBRID MODElING OF SUGAR BOILING PROCESS

基于模型的预测控制器设计最重要的一步是设计一个尽可能精确和在大范围操作条件下有效的模型。煮糖过程是一个具有严重的非线性和不稳定性过程,过程的主要非线性表现在晶体生长率。这篇论文用两种方法来描述晶体生长率模型的设计,第一种方法是传统的方法,它是通过采用非线性规划最优化方法(NLP)决定晶体生长率经验公式的参数;第二种方法是一种新颖的建模策略,它把晶体生长率作为非线性逼近器的人工神经网络(ANN)与由蔗糖晶体质量平衡所表述的先前既定的知识相结合。最初结果显示第一种类型的模型能够较好地执行局部匹配,而第二种具有更大的灵活性。

This paper offers the design of the crystal growth rate model according to two approaches In designing a model-based, predictive controller, the most important step is to develop a model as accurate as possible and The model shold be valid under a wide range of operating conditions.the nonlinearities of the main proless show on the yrowtl rate of the crystrl.The first approach is classical and consists of determining the parameters of the empirical expressions of the growth rate through the use of nonlinear programming(NLP)opfimization technique.The second is a novel modeling strategy that combines an artificial neural network(ANN) as an approximator of the growth rate with prior knowledge represented by the mass balance of sucrose crystal The initial resule show that the first type of model perfoms local fitting while the second offers a greater flexibility