Polyolefins are one of the most widely used commodity polymers with applications in films, packaging, and the automotive industry. The modeling of polymerization processes producing polyolefins, including high-density polyethylene (HDPE), polypropylene (PP), and linear low-density polyethylene (LLDPE) using Ziegler−Natta catalysts with multiple active sites, is a complex and challenging task. Most of the studies on polyolefin process modeling over the years do not consider all of the commercially important production targets when quantifying the relevant polymerization reaction kinetic parameters based on measurable plant data. Most of the published articles also do not make efficient use of simulation tools, particularly sensitivity analysis, design specifications, and data fit, that are available in commercial modeling software for polymerization processes, such as Aspen Polymers. This paper presents an effective methodology to estimate kinetic parameters that have the most significant impacts on specific production targets, and to develop the kinetics using all commercially important production targets validated over polyolefin processes producing HDPE, PP, and LLDPE using Ziegler−Natta catalysts. We demonstrate how to estimate kinetic parameters to fit production targets in a computer-aided stepby-step procedure. The percent errors between our model predictions and plant data are equivalent to or smaller than those in reported modeling studies for polyolefin processes. We report our insights and experiences from training practicing engineers to successfully apply our methodology to several dozen commercial HDPE, PP, and LLPDE processes for sustainable design, operation, and optimization at two of the world's largest petrochemical companies in the Asia-Pacific region over the past two decades. Finally, we present supplements of detailed modeling examples and an Excel modeling spreadsheet for commercial polyolefin processes.

This study presents a broad perspective of hybrid process modeling combining the scientific knowledge and data analytics in bioprocessing and chemical engineering with a science-guided machine learning (SGML) approach. We divide the approach into two major categories: ML complements science, and science complements ML. We review the literature relating to the hybrid SGML approach, and propose a systematic classification of hybrid SGML models. For applying ML to improve science-based models, we present expositions of direct serial and parallel hybrid modeling and their combinations, inverse modeling, reduced-order modeling, quantifying uncertainty in the process and even discovering governing equations of the process model. For applying scientific principles to improve ML models, we discuss the science-guided design, learning and refinement. For each subcategory, we identify its requirements, strengths, and limitations, together with their published and potential applications. We also present several examples to illustrate different hybrid SGML methodologies for modeling chemical processes.

No abstract