Statistical data modeling based on partial least squares: Application to melt index predictions in high density polyethylene processes to achieve energy-saving operation

The accurate and reliable real‐time prediction of melt index (MI) is indispensable in quality control of the industrial propylene polymerization (PP) processes. This paper presents a real‐time soft sensor based on optimized least squares support vector machine (LSSVM) for MI prediction. First, the hybrid continuous ant colony differential evolution algorithm (HACDE) is proposed to optimize the parameters of LSSVM. Then, considering the complexity and nondeterminacy of PP plant, an online correcting strategy (OCS) is adopted to update the modeling data and to revise the model's parameters adaptively. Thus, the real‐time prediction model, HACDE‐OCS‐LSSVM, is obtained. Based on the data from a real PP plant, the models of HACDE‐LSSVM, DE‐LSSVM and LSSVM are also developed for comparison. The research results show that the proposed real‐time model achieves a good performance in the practical industrial MI prediction process. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

“…Table compares the HACDE‐OCS‐LSSVM model with other models presented in the open literatures . Note that only the research data used in Ref.…”

Section: Resultsmentioning

confidence: 99%

“…In a word, it is proved that the HACDE-OCS-LSSVM model exhibits excellent universality in MI prediction both statistically and graphically. [18,[43][44][45][46]. Note that only the research data used in Ref.…”

Section: Resultsmentioning

confidence: 99%

A real‐time model based on optimized least squares support vector machine for industrial polypropylene melt index prediction

Zhang

Liu

2016

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Recently, it has attracted numerous researchers to focus on quality prediction for MI estimation in industrial polymerization processes . To describe the dynamics of Ziegler‐Natta ethylene polymerization, Embiruçu and Marcelo presented a mathematical model to infer the MI value .…”

Section: Introductionmentioning

confidence: 99%

Quality prediction via semisupervised Bayesian regression with application to propylene polymerization

Sun

Liu

Zhang

2018

Journal of Chemometrics

View full text Add to dashboard Cite

Statistical learning techniques are widely used for quality prediction in polymerization processes during the last decades. However, compared to operation variables, quality variables of polypropylene process are usually difficult to acquire resulting from the absence of measuring units. A semisupervised Bayesian regression method is therefore presented to improve the prediction accuracy by sufficient usage of unlabeled sampling data for melt index prediction in polypropylene processes. The developed model consists of Bayesian inference to predict quality variables and neighborhood kernel density estimation for finding relationships between unlabeled data and labeled samples, which takes advantages of a probability framework with iterative maximum likelihood techniques for parameter estimation and a sparse constraint for avoiding overfitting. The quality prediction regression method is compared with published models by applying to a real dataset of industrial propylene polymerization. The experiment results demonstrate the effectiveness of the proposed semisupervised Bayesian method.

show abstract

“…It is always time-consuming to obtain a good model that can explain the extremely complex behaviours of an industrial polyolefin polymerization process. Therefore, the key to inferential estimation is to build data-driven MI modelling quickly and effectively (Ahmed et al, 2013;Barnes et al, 2007;Lee et al, 2008;Tian et al, 2013;Zhang et al, 2006). Fuzzy systems have been proved efficient tools and shown excellent ability when describing non-linear systems, because fuzzy models are capable of handling uncertainties, such as the non-linearity and ambiguity involved in a real system.…”

Section: Introductionmentioning

confidence: 99%

Application of Takagi–Sugeno fuzzy model optimized with an improved Free Search algorithm to industrial polypropylene melt index prediction

Wang

Chen

Zhang

et al. 2016

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

A new algorithm is presented for learning the Takagi-Sugeno (T-S) fuzzy model from data by improved Free Search algorithm (IFS), where the rule structure (selection of rules and number of rules), input structure (selection of inputs and number of inputs) and parameters of the T-S fuzzy model are all represented as individuals of the IFS and evolved together such that the optimization of the rule structure, the input structure and the parameters can be achieved simultaneously. The developed IFS-T-S model is used for the prediction of melt index in an industrial propylene polymerization process and the results show that the proposed IFS-T-S model has a good fitting and prediction ability.

show abstract

Statistical data modeling based on partial least squares: Application to melt index predictions in high density polyethylene processes to achieve energy-saving operation

Cited by 12 publications

References 23 publications

A real‐time model based on optimized least squares support vector machine for industrial polypropylene melt index prediction

A real‐time model based on optimized least squares support vector machine for industrial polypropylene melt index prediction

Quality prediction via semisupervised Bayesian regression with application to propylene polymerization

Application of Takagi–Sugeno fuzzy model optimized with an improved Free Search algorithm to industrial polypropylene melt index prediction

Contact Info

Product

Resources

About