Quality prediction for polypropylene production process based on CLGPR model

Ge, Zhiqiang; Chen, Tao

doi:10.1016/j.conengprac.2011.01.002

Cited by 73 publications

(50 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although unfamiliar to most practicing chemists, such advanced optimization methods have already been applied in several chemical processes. Thus, Gaussian Processes has been used in prediction of quality of polypropylene [55 ], in simulation of catalytic batch etherification reaction [56], in real-time prediction of properties for industrial rubber mixing processes [57] and in screening of new additives for a Friedel-Crafts catalyst [58 ].…”

Section: Initial Input Into Doementioning

confidence: 99%

Automatic discovery and optimization of chemical processes

Houben

Lapkin

2015

Current Opinion in Chemical Engineering

View full text Add to dashboard Cite

This paper presents the first overview of recent developments in techniques and methods that enable closed-loop optimization, also sometimes called 'self optimization', as well as discovery in different areas of molecular sciences. The closed-loop experimental platforms offer tremendous new opportunities by significantly increasing productivity, as well as enabling completely new types of experiments to be performed. Such experiments involve three main enabling technology areas: automated experimental systems, analytical instruments connected to automated chemoinformatics software and optimization or decision-making algorithms. We review the most exciting developments concerning robotic experiments, 3D printed lab-ware, experimental systems with multiple analytical instruments and advanced optimization algorithms based on machine learning approaches. A range of different chemical problems is described, which show the breadth of potential applications of this emerging experimental approach.

show abstract

Section: Initial Input Into Doementioning

confidence: 99%

Automatic discovery and optimization of chemical processes

Houben

Lapkin

2015

Current Opinion in Chemical Engineering

View full text Add to dashboard Cite

show abstract

“…Jiang et al [6] devised an optimal soft sensor, named the least squares support vector machines with ant colony-immune clone particle swarm optimization (AC-ICPSO-LSSVM), to predict the MI successfully. Ge et al [7] developed a so-called combined local Gaussian process regression and it gained the best MI prediction results in contrast with several other methods, such as the Gaussian mixture model, the fuzzy-learning based model, multiple local partial least squares, artificial neural network and the support vector regression model. Park et al [8] employed partial least squares (PLS) and support vector regression to predict the MI in the high-density polyethylene process.…”

Section: Introductionmentioning

confidence: 97%

Optimal online soft sensor for product quality monitoring in propylene polymerization process

Zhong

Liu

2015

Neurocomputing

View full text Add to dashboard Cite

“…Melt index (MI) is a commonly used variable to specify different polypropylene products [1] . As online measurement of the melt index is typically unavailable in industrial polypropylene producing processes, soft sensing models are urgently required for estimation and prediction of this important quality variable [2,3] . Due to the widely utilization of the distributed control system (DCS) in modern chemical process, plenty of process data can be easily stored and used.…”

Section: Introductionmentioning

confidence: 99%

Data-based soft-sensing for melt index prediction

Fei

Liu

Liang

et al. 2014

2014 9th IEEE Conference on Industrial Electronics and Applications

View full text Add to dashboard Cite

In practical chemical plants, melt index (MI) can only be measured by off-line analysis which cost 2-4 hours. So it is important to develop online analyzers using process data especially when the mechanism is complex. A novel data based soft-sensing method is proposed for MI estimating in propylene polymerization process. This approach is constructed under justin-time modeling scheme, in which historical process datasets are searched but only the corresponding data samples relevant to the query data sample are used for local modeling, and partial least square (PLS) model is used as local model. The strategy is applied in propylene polymerization process with Spheripol technology, the results showed that feasible estimation for melt index during changeable process can be obtain by the proposed method and the root mean square error (RMSE) is much less than the PLS method.

show abstract

Quality prediction for polypropylene production process based on CLGPR model

Cited by 73 publications

References 25 publications

Automatic discovery and optimization of chemical processes

Automatic discovery and optimization of chemical processes

Optimal online soft sensor for product quality monitoring in propylene polymerization process

Data-based soft-sensing for melt index prediction

Contact Info

Product

Resources

About