Melt index prediction using optimized least squares support vector machines based on hybrid particle swarm optimization algorithm

Melt index (MI) is considered as one of the most important variables of the quality, which determines the product specifications. Thus, a reliable estimation of MI is crucial in the quality control of the practical processes in the propylene polymerization (PP). An optimal soft sensor, named the least squares support vector machines with Ant Colony-Immune Clone Particle Swarm Optimization (AC-ICPSO-LSSVM), is therefore proposed. It combines the advantages of the high accuracy of LSSVM and the fast convergence of PSO. Furthermore, the immune clone (IC) method is introduced into the PSO algorithm to make the particles of ICPSO diverse and enhance global search capability for avoiding the premature convergence and local optimization of the conventional PSO algorithm. Besides, to widen data range, improve search precision and convergence efficiency, and avoid premature convergence, Ant Colony Optimization (ACO) is introduced to find the initial particles for PSO algorithm. The resultant hybrid AC-ICPSO algorithm is then applied to optimize the parameters of LSSVM, so the optimal prediction model of melt index, AC-ICPSO-LSSVM, is obtained. As the comparative basis, the models of ICPSO-LSSVM, PSO-LSSVM, and LSSVM are also developed respectively. Based on the data from a real PP production plant, a detailed comparison of the models is carried out. These models are also compared with RBF method reported in the open literature. The research results reveal the prediction accuracy and validity of the proposed approach.

[1]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[2]  Bingxue Shi,et al.  An expandable on-chip BP learning neural network chip , 2003 .

[3]  Z. H. Che,et al.  PSO-based back-propagation artificial neural network for product and mold cost estimation of plastic injection molding , 2010, Comput. Ind. Eng..

[4]  Feng Wan,et al.  Classification of Single-Trial EEG Based on Support Vector Clustering during Finger Movement , 2009, ISNN.

[5]  C. Peng,et al.  State feedback controller design of networked control systems with interval time‐varying delay and nonlinearity , 2008 .

[6]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[7]  Umut Rifat Tuzkaya,et al.  A particle swarm optimization algorithm for the multiple-level warehouse layout design problem , 2008, Comput. Ind. Eng..

[8]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[9]  Youxian Sun,et al.  Melt index prediction by neural networks based on independent component analysis and multi-scale analysis , 2006, Neurocomputing.

[10]  Magdalene Marinaki,et al.  A hybrid genetic - Particle Swarm Optimization Algorithm for the vehicle routing problem , 2010, Expert Syst. Appl..

[11]  Guolong Chen,et al.  A PSO-based intelligent decision algorithm for VLSI floorplanning , 2010, Soft Comput..

[12]  Xinggao Liu,et al.  Melt index prediction by weighted least squares support vector machines , 2006 .

[13]  Jun Zhang,et al.  Adaptive Particle Swarm Optimization , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Hamidreza Modares,et al.  Parameter estimation of bilinear systems based on an adaptive particle swarm optimization , 2010, Eng. Appl. Artif. Intell..

[15]  Han-Xiong Li,et al.  A probabilistic SVM based decision system for pain diagnosis , 2011, Expert Syst. Appl..

[16]  Yeong-Koo Yeo,et al.  A recursive PLS-based soft sensor for prediction of the melt index during grade change operations in HDPE plant , 2009 .

[17]  Zhihua Xiong,et al.  Batch-to-batch control of fed-batch processes using control-affine feedforward neural network , 2007, Neural Computing and Applications.

[18]  Xianting Li,et al.  A mathematical model of variable displacement swash plate compressor for automotive air conditioning system , 2006 .

[19]  Yi Cao,et al.  A CASE STUDY OF PREDICTIVE CONTROL FOR THE ALSTOM GASIFIER PROBLEM , 2004 .

[20]  Shi Jian.  Melt Index Prediction by Neural Soft-Sensor Based on Multi-Scale Analysis and Principal Component Analysis , 2005 .

[21]  Xiaowei Yang,et al.  Adaptive pruning algorithm for least squares support vector machine classifier , 2010, Soft Comput..

[22]  Chonghun Han,et al.  Melt index modeling with support vector machines, partial least squares, and artificial neural networks , 2005 .

[23]  Yanbin Yuan,et al.  Unit commitment problem using enhanced particle swarm optimization algorithm , 2011, Soft Comput..

[24]  Cheng-Jian Lin,et al.  The design of neuro-fuzzy networks using particle swarm optimization and recursive singular value decomposition , 2007, Neurocomputing.

[25]  Zu-Wei Zheng,et al.  Modeling the Effect of Polymerization Rate on the Intraparticle Mass and Heat Transfer during Propylene Polymerization in a Loop Reactor , 2009 .

[26]  Halil Karahan,et al.  Prediction of hard rock TBM penetration rate using particle swarm optimization , 2011 .

[27]  János Abonyi,et al.  Semi-mechanistic Models for State-Estimation - Soft Sensor for Polymer Melt Index Prediction , 2004, ICAISC.

[28]  Kyung-shik Shin,et al.  An application of support vector machines in bankruptcy prediction model , 2005, Expert Syst. Appl..

[29]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[30]  Jie Zhang,et al.  Inferential Estimation of Polymer Melt Index Using Sequentially Trained Bootstrap Aggregated Neural Networks , 2006 .

[31]  D. J. Murraysmith,et al.  Methods for the external validation of contiuous system simulation models:a review , 1998 .

[32]  Abhay Bulsari,et al.  Scalability of neural network models makes industrial use easier , 2002 .

[33]  Huizhong Yang,et al.  Modelling and identification for non-uniformly periodically sampled-data systems , 2010 .

[34]  Sudhir S. Bafna,et al.  A design of experiments study on the factors affecting variability in the melt index measurement , 1997 .

[35]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[36]  Yeong-Koo Yeo,et al.  Prediction of the Melt Index in a High-Density Polyethylene Process , 2007 .

[37]  Enrique Luis Lima,et al.  Continuous soluble Ziegler-Natta ethylene polymerizations in reactor trains. I. Mathematical modeling , 2000 .

[38]  Xinggao Liu,et al.  Modeling mass transport of propylene polymerization on Ziegler–Natta catalyst , 2005 .