PET Viscosity Prediction Using JIT-based Extreme Learning Machine

A multiobjective intelligence optimal approach in polymerizing of PET with maximum yield and the best quality is proposed. The hybrid neural network based on B-spline and diagonal recursive neural network is used to model the PET process qualities, i.e. the Intrinsic Viscosity and Molecular Weight distribution. Then a hybrid NSGAII-PSO optimal algorithm with penalty functions is applied to solve the multiobjective optimal problem in order to get the best operation conditions. The simulation result indicates that the hybrid network model and model-based multiobjective optimal algorithm are effective.

https://ieeexplore.ieee.org/iel5/5960742/5970529/05970754.pdf

Multiobjective intelligence optimal operation of PET polymerization

The polymerization process is the critical stage of polyester production, and the reaction mechanism of the polymerization process is complex and involves a large number of variables The melt intrinsic viscosity is an essential indicator of the polymer, control and prediction of melt intrinsic viscosity is particularly crucial for the synthetic fibers industry This paper introduces the Copula feature selection method, and nonlinear features of the polymerization process are selected to establish the least squares support vector machine (LSSVM) model for the viscosity prediction Since the Just-in-time learning (JITL) can account for the dynamic behavior of the process, and the Copula function can determine the nonparametric measure of the dependence between variables, a Copula-based JITL is proposed for viscosity prediction of polyester fiber polymerization process The effectiveness of the proposed approach is verified by the actual industrial data

Copula-based JITL for polyester fiber polymerization process modeling

Based on the "divide and rule" idea, hybrid neural networks (HNNs), which consisted of linear dynamic neural network and nonlinear static neural network, was used to model for complicated nonlinear systems. By using hybrid neural networks, it can reduce the degree of difficulty for training a single network, e.g. long training time and lower accuracy; and also can transfer the solution of nonlinear control strategy into solving for linear systems based on the decomposed models. An industrial polymerization process was introduced as a powerful case-study for the demonstration of potential of neural modeling. Nonlinear predicative models, based on both serial and parallel neural networks, were applied to predict the dynamic viscosity of PET. And the results indicated that both parallel and serial hybrid neural networks can model for complicated systems well

Liu-lin Cao

Papers

Viscosity Prediction for PET Process Based on Hybrid Neural Networks