A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine

doi:10.1016/j.cjche.2016.05.030

›› 2016, Vol. 24 ›› Issue (8): 1013-1019.DOI: 10.1016/j.cjche.2016.05.030

• Process Systems Engineering and Process Safety • Previous Articles Next Articles

A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine

Miao Zhang¹, Xinggao Liu¹, Zeyin Zhang²

1 State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China;
2 Department of Mathematics, Zhejiang University, Hangzhou 310027, China

Received:2015-06-26 Revised:2015-12-20 Online:2016-09-21 Published:2016-08-28
Supported by:
Supported by the Major Program of National Natural Science Foundation of China (61590921), the Natural Science Foundation of Zhejiang Province (Y16B040003), Shanghai Aerospace Science and Technology Innovation Fund (E11501) and Aerospace Science and Technology Innovation Fund of China, Aerospace Science and Technology Corporation (E11601).

A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine

Miao Zhang¹, Xinggao Liu¹, Zeyin Zhang²

1 State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China;
2 Department of Mathematics, Zhejiang University, Hangzhou 310027, China

通讯作者: Xinggao Liu
基金资助:
Supported by the Major Program of National Natural Science Foundation of China (61590921), the Natural Science Foundation of Zhejiang Province (Y16B040003), Shanghai Aerospace Science and Technology Innovation Fund (E11501) and Aerospace Science and Technology Innovation Fund of China, Aerospace Science and Technology Corporation (E11601).

Abstract

Abstract: In propylene polymerization (PP) process, the melt index (MI) is one of the most important quality variables for determining different brands of products and different grades of product quality. Accurate prediction of MI is essential for efficient and professional monitoring and control of practical PP processes. This paper presents a novel soft sensor based on extreme learning machine (ELM) and modified gravitational search algorithm (MGSA) to estimate MI from real PP process variables, where the MGSA algorithm is developed to find the best parameters of input weights and hidden biases for ELM. As the comparative basis, the models of ELM, APSO-ELM and GSAELM are also developed respectively. Based on the data from a real PP production plant, a detailed comparison of the models is carried out. The research results show the accuracy and universality of the proposed model and it can be a powerful tool for online MI prediction.

Key words: Propylene polymerization, Melt index prediction, Extreme learning machine, Gravitational search algorithm

摘要： In propylene polymerization (PP) process, the melt index (MI) is one of the most important quality variables for determining different brands of products and different grades of product quality. Accurate prediction of MI is essential for efficient and professional monitoring and control of practical PP processes. This paper presents a novel soft sensor based on extreme learning machine (ELM) and modified gravitational search algorithm (MGSA) to estimate MI from real PP process variables, where the MGSA algorithm is developed to find the best parameters of input weights and hidden biases for ELM. As the comparative basis, the models of ELM, APSO-ELM and GSAELM are also developed respectively. Based on the data from a real PP production plant, a detailed comparison of the models is carried out. The research results show the accuracy and universality of the proposed model and it can be a powerful tool for online MI prediction.

关键词: Propylene polymerization, Melt index prediction, Extreme learning machine, Gravitational search algorithm

Miao Zhang, Xinggao Liu, Zeyin Zhang. A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine[J]. , 2016, 24(8): 1013-1019.

References

[1] S.S. Bafna, A.M. Beall, A design of experiments study on the factors affecting variability in the melt index measurement, J. Appl. Polym. Sci. 65(1997) 277-288.
[2] A. Mogilicharla, K. Mitra, S. Majumdar, Modeling of propylene polymerization with long chain branching, Chem. Eng. J. 246(2014) 175-183.
[3] T.Y. Kim, Y.K. Yeo, Development of polyethylene melt index inferential model, Korean J. Chem. Eng. 27(2010) 1669-1674.
[4] X.Z. Chen, D.P. Shi, X. Gao, Z.H. Luo, A fundamental CFD study of the gas-solid flow field in fluidized bed polymerization reactors, Powder Technol. 205(2011) 276-288.
[5] S. Lucia, T. Finkler, S. Engell, Multi-stage nonlinear model predictive control applied to a semi-batch polymerization reactor under uncertainty, J. Process Control 23(2013) 1306-1319.
[6] A. Shamiri, M.A. Hussain, F.S. Mjalli, M.S. Shafeeyan, N. Mostoufi, Experimental and modeling analysis of propylene polymerization in a pilot-scale fluidized bed reactor, Ind. Eng. Chem. Res. 53(2014) 8694-8705.
[7] P. Sarkar, S.K. Gupta, Dynamic simulation of propylene polymerization in continuous flow stirred tank reactors, Polym. Eng. Sci. 33(1993) 368-374.
[8] W. Meng, J. Li, B. Chen, H. Li, Modeling and simulation of ethylene polymerization in industrial slurry reactor series, Chin. J. Chem. Eng. 21(2013) 850-859.
[9] A. Shamiri, M.A. Hussain, F.S. Mjalli, N. Mostoufi, S. Hajimolana, Dynamics and predictive control of gas phase propylene polymerization in fluidized bed reactors, Chin. J. Chem. Eng. 21(2013) 1015-1029.
[10] W. Wang, X. Liu, Melt index prediction by least squares support vector machines with an adaptive mutation fruit fly optimization algorithm, Chemometr. Intell. Lab. Syst. 141(2015) 79-87.
[11] J. Li, X. Liu, H. Jiang, Y. Xiao, Melt index prediction by adaptively aggregated RBF neural networks trained with novel ACO algorithm, J. Appl. Polym. Sci. 125(2012) 943-951.
[12] N.M. Ramli, M. Hussain, B.M. Jan, B. Abdullah, Composition prediction of a debutanizer column using equation based artificial neural network model, Neurocomputing 131(2014) 59-76.
[13] L. Ye, H. Yang, A multi-model approach for soft sensor development based on feature extraction using weighted kernel Fisher criterion, Chin. J. Chem. Eng. 22(2014) 146-152.
[14] Z. Cong, Y. Hao, Consistency and asymptotic property of a weighted least squares method for networked control systems, Chin. J. Chem. Eng. 22(2014) 754-761.
[15] I.S. Han,C.Han, C.B. Chung, Melt index modelingwith support vector machines, partial least squares, and artificial neural networks, J. Appl. Polym. Sci. 95(2005) 967-974.
[16] J. Zhang, Q.B. Jin, Y.M. Xu, Inferential estimation of polymer melt index using sequentially trained bootstrap aggregated neural networks, Chem. Eng. Technol. 29(2006) 442-448.
[17] J. Gonzaga, L. Meleiro, C. Kiang, R. Maciel Filho, ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process, Comput. Chem. Eng. 33(2009) 43-49.
[18] J. Shi, X. Liu, Melt index prediction by weighted least squares support vector machines, J. Appl. Polym. Sci. 101(2006) 285-289.
[19] H. Jiang, Y. Xiao, J. Li, X. Liu, Prediction of the melt index based on the relevance vector machine with modified particle swarm optimization, Chem. Eng. Technol. 35(2012) 819-826.
[20] M. Zhang, X. Liu, A soft sensor based on adaptive fuzzy neural network and support vector regression for industrial melt index prediction, Chemometr. Intell. Lab. Syst. 126(2013) 83-90.
[21] F. Ahmed, L.H. Kim, Y.K. Yeo, Statistical data modeling based on partial least squares:Application to melt index predictions in high density polyethylene processes to achieve energy-saving operation, Korean J. Chem. Eng. 30(2013) 11-19.
[22] Z. Zhang, T. Wang, X. Liu, Melt index prediction by aggregated RBF neural networks trained with chaotic theory, Neurocomputing 131(2014) 368-376.
[23] G.B. Huang, Q.Y. Zhu, C.K. Siew, Extreme learning machine:Theory and applications, Neurocomputing 70(2006) 489-501.
[24] G.-B. Huang, An insight into extreme learning machines:Random neurons, random features and kernels, Cogn. Comput. 6(2014) 376-390.
[25] G.-B. Huang, H. Zhou, X. Ding, R. Zhang, Extreme learning machine for regression and multiclass classification, IEEE Trans. Syst., Man Cybern. B Cybern. 42(2012) 513-529.
[26] D. Wang, M. Alhamdoosh, Evolutionary extreme learning machine ensembles with size control, Neurocomputing 102(2013) 98-110.
[27] R.C. Deo, M. Şahin, Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia, Atmos. Res. 153(2015) 512-525.
[28] S. Li, P. Wang, L. Goel, Short-term load forecasting by wavelet transform and evolutionary extreme learning machine, Electr. Power Syst. Res. 122(2015) 96-103.
[29] Q.Y. Zhu, A.K. Qin, P.N. Suganthan, G.B. Huang, Evolutionary extreme learning machine, Pattern Recogn. 38(2005) 1759-1763.
[30] E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi, GSA:A gravitational search algorithm, Inf. Sci. 179(2009) 2232-2248.
[31] J. Kennedy, W.M. Spears, Matching algorithms to problems:An experimental test of the particle swarm and some genetic algorithms on the multimodal problem generator, IEEE, New York, 1998.
[32] K. Vaisakh, L.R. Srinivas, K. Meah, Genetic evolving ant direction particle swarm optimization algorithm for optimal power flow with non-smooth cost functions and statistical analysis, Appl. Soft Comput. 13(2013) 4579-4593.
[33] I.C. Trelea, The particle swarm optimization algorithm:Convergence analysis and parameter selection, Inf. Process. Lett. 85(2003) 317-325.
[34] E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi, BGSA:Binary gravitational search algorithm, Nat. Comput. 9(2010) 727-745.
[35] E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi, Filter modeling using gravitational search algorithm, Eng. Appl. Artif. Intell. 24(2011) 117-122.
[36] F. Ding, System identification-New theory and methods, Science Press, Beijing, 2013.
[37] F. Ding, System identification-Performances analysis for identification methods, Science Press, Beijing, 2014.
[38] S. McLoone, M.D. Brown, G. Irwin, G. Lightbody, A hybrid linear/nonlinear training algorithm for feedforward neural networks, IEEE Trans. Neural Netw. 9(1998) 669-684.
[39] D. Murray_Smith, Methods for the external validation of continuous system simulation models:A review, Math. Comp. Model. Dyn. 4(1998) 5-31.
[40] C. Jin, W. Guizeng, X. Bowen, Prediction of polypropylene melt index based on robust and adaptive RBF networks, Control Decis. 14(1999) 339-343.
[41] K.-C. Chou, H.-B. Shen, Recent advances in developing web-servers for predicting protein attributes, Nat. Sci. 1(2009) 63-92.

A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine

A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 5

Recommended Articles

Metrics

Comments

[1]	Kang Guan, Yong Gao, Qingfeng Zeng, Xingang Luan, Yi Zhang, Laifei Cheng, Jianqing Wu, Zhenya Lu. Numerical modeling of SiC by low-pressure chemical vapor deposition from methyltrichlorosilane [J]. Chinese Journal of Chemical Engineering, 2020, 28(6): 1733-1743.
[2]	Bing Wang, Feng Qian, Weimin Zhong. Wind field reconstruction for the dispersion modeling of accidental chemical spills on complex geometry [J]. Chinese Journal of Chemical Engineering, 2019, 27(11): 2712-2724.
[3]	Ahmad Shamiri, Mohamed azlan Hussain, Farouq sabri Mjalli, Navid Mostoufi, Seyedahmad Hajimolana. Dynamics and Predictive Control of Gas Phase Propylene Polymerization in Fluidized Bed Reactors [J]. Chin.J.Chem.Eng., 2013, 21(9): 1015-1029.
[4]	LIU Xinggao. Modeling and simulation of heterogeneous catalyzed propylene polymerization [J]. , 2007, 15(4): 545-553.
[5]	LUO Zhenghong, CAO Zhikai, SU Yaotang. Monte Carlo Simulation of Propylene Polymerization (Ⅰ) Effects of Impurity on Propylene Polymerization [J]. , 2006, 14(2): 194-199.