SIOC 中文
ACS
Adv search

Acta Chimica Sinica >

2013 , Vol. 71 >Issue 07: 1053 - 1058

DOI: https://doi.org/10.6023/A13020193

Article

Solubility Prediction of Gases in Polymers based on Chaotic Self-adaptive Particle Swarm Optimization Artificial Neural Networks

  • Li Mengshan ,
  • Huang Xingyuan ,
  • Liu Hesheng ,
  • Liu Bingxiang ,
  • Wu Yan ,
  • Ai Fanrong
Expand
  • a Nanchang University, College of Mechanical and Electric Engineering, Nanchang 330031;
    b JingDeZhen Ceramic Institute, School of Information Engineering, JingDeZhen 333001

Received date: 2013-02-15

  Online published: 2013-03-15

Supported by

Project supported by the National Natural Science Foundation of China (No. 20664002) and Graduate Student Innovation Fund by Nanchang University (No. cx2012011).

Fold

Abstract

Solubility is one of the most important physicochemical properties of polymer compounds, which determines the compatibility of blending system. To enhance the performance of artificial neural networks (ANN) and improve the efficiency and correlation of prediction of gas solubility in polymers, in this work, a novel ANN model based on chaos theory, self-adaptive particle swarm optimization (PSO) algorithm and back propagation (BP) algorithm is proposed, hereafter called CSAPSO-BP ANN. In the CSAPSO-BP ANN, the conventional PSO algorithm is modified by using chaos theory and self-adaptive inertia weight factor to overcome its premature convergence problem. Then the CSAPSO-BP ANN trained by hybrid algorithm which combined the modified PSO and BP algorithm has been employed to investigate carbon dioxide (CO2) solubility in polystyrene (PS), polypropylene (PP) and nitrogen (N2) solubility in PS, respectively. The CSAPSO-BP ANN model which consisted of three layers with one hidden layer, two input nodes including temperature and pressure, 8 hidden nodes which obtained by heuristics and one output node that is the solubility of gases in polymers was designed. The model combined the abilities of chaos theory, PSO algorithm and BP algorithm, accelerated the training speed of ANN and improved the prediction accuracy. Results obtained in this work indicate that the CSAPSO-BP ANN is an effective method for prediction of gas solubility in polymers in a wide range of pressure and temperature. The comparison between different neural networks was carried out in detail to reveal the proposed CSAPSO-BP ANN outperforms the traditional BP NN and PSO-BP NN. The values of average absolute deviation (AAD), standard deviation (SD) and squared correlation coefficient (R2) are 0.0058, 0.0198 and 0.9914, respectively. The statistical data demonstrate that the CSAPSO-BP ANN model is a faster, more reliable and accurate method, and has an excellent prediction capability with high-accuracy and has a good correlation between prediction values and experimental data.

Key words： solubility prediction; polymer; neural network; particle swarm optimization; chaos theory

Cite this article

Li Mengshan , Huang Xingyuan , Liu Hesheng , Liu Bingxiang , Wu Yan , Ai Fanrong . Solubility Prediction of Gases in Polymers based on Chaotic Self-adaptive Particle Swarm Optimization Artificial Neural Networks[J]. Acta Chimica Sinica, 2013 , 71(07) : 1053 -1058 . DOI: 10.6023/A13020193

References

[1] Merker, T.; Vrabec, J.; Hasse, H. Fluid Phase Equilib. 2012, 315, 77.
[2] Wang, J.; Zhu, W. L.; Zhang, H. T.; Park, C. B. Chem. Eng. Sci. 2012, 75, 390.
[3] Liu, S.; Zhang, J.; Zhang, Y.; Qin, L. Acta Chim. Sinica 2012, 70, 1511. (刘树深, 张瑾, 张亚辉, 覃礼堂, 化学学报, 2012, 70, 1511.)
[4] Yu, X. Acta Chim. Sinica 2010, 68, 2264. (禹新良, 化学学报, 2010, 68, 2264.)
[5] Nalawade, S. P.; Picchioni, F.; Janssen, L. Prog. Polym. Sci. 2006, 31, 19.
[6] Li, D. C.; Liu, T.; Zhao, L.; Yuan, W. K. Ind. Eng. Chem. Res. 2009, 48, 7117.
[7] Lei, Z. G.; Ohyabu, H.; Sato, Y.; Inomata, H.; Smith, R. L. J. Supercrit. Fluids 2007, 40, 452.
[8] Bian, X.; Du, Z.; Tang, Y. Petrochem. Technol. 2011, 40, 536. (卞小强, 杜志敏, 汤勇, 石油化工, 2011, 40, 536.)
[9] Zhang, Q.; Feng, X.; Long, H.; Suo, J.; Zhang, D.; Xu, L.; Xu, L. Acta Chim. Sinica 2012, 70, 989. (张庆友, 冯秀林, 龙海林, 索净洁, 张丹丹, 许力壮, 许禄, 化学学报, 2012, 70, 989.)
[10] Gharagheizi, F.; Eslamimanesh, A.; Mohammadi, A. H.; Richon, D. Ind. Eng. Chem. Res. 2011, 50, 221.
[11] Ma, Y.; Shi, W.; Zhao, C.; Yang, D.; Lu, Q.; Li, S.; Tu, J.; Wang, W.; Fan, Z. Acta Chim. Sinica 2011, 69, 719. (马艳, 石文鹏, 赵辰阳, 杨冬梅, 逯琪, 李速明, 涂建军, 王巍, 范仲勇, 化学学报, 2011, 69, 719.)
[12] Yu, D.; Zhou, G.; Ji, F.; Li, S.; Yang, D.; Wang, T.; Cao, L. Acta Chim. Sinica 2011, 69, 960. (虞丹尼, 周光明, 吉芳英, 黎司, 杨大成, 王图锦, 曹琳, 化学学报, 2011, 69, 960.)
[13] Bakhbakhi, Y. Math. Comput. Model. 2012, 55, 1932.
[14] Lashkarbolooki, M.; Vaferi, B.; Rahimpour, M. R. Fluid Phase Equilib. 2011, 308, 35.
[15] Eslamimanesh, A.; Gharagheizi, F.; Mohammadi, A. H.; Richon, D. Chem. Eng. Sci. 2011, 66, 3039.
[16] Yun, T.; Junsong, L. U. O. Comput. Simul. 2011, 28, 219.
[17] Ding, H.; Wu, J.; Li, X. In Advances in Swarm Intelligence. Third International Conference, Eds.: Tan, Y.; Shi, J.; Ji, Z., Springer-Verlag, Shenzhen, 2012, pp. 444～451.
[18] Ahmadi, M. A. Fluid Phase Equilib. 2012, 314, 46.
[19] Zhang, J. R.; Zhang, J.; Lok, T. M.; Lyu, M. R. Appl. Math. Comput. 2007, 185, 1026.
[20] Sun, Y.; Wang, Z.; Qi, G.; Van Wyk, B. J. Eng. Optimiz. 2011, 43, 19.
[21] Hilic, S.; Boyer, S.; Padua, A.; Grolier, J. J. Polym. Sci. B-Polym. Phys. 2001, 39, 2063.
[22] Sato, Y.; Yurugi, M.; Fujiwara, K.; Takishima, S.; Masuoka, H. Fluid Phase Equilib. 1996, 125, 129.
[23] Sato, Y.; Takikawa, T.; Takishima, S.; Masuoka, H. J. Supercrit. Fluids 2001, 19, 187.
[24] Khajeh, A.; Modarress, H.; Mohsen-Nia, M. Iran. Polym. J. 2007, 16, 759.
[25] Sato, Y.; Fujiwara, K.; Takikawa, T.; Sumarno; Takishima, S.; Masuoka, H. Fluid Phase Equilib. 1999, 162, 261.
[26] Newitt, D. M.; Weale, K. E. J. Chem. Soc. 1948, 1039, 1541.
Options
Outlines

/

〈 〉