zhpsЖурнал прикладной спектроскопииZhurnal Prikladnoii Spektroskopii0514-7506B. I. Stepanov Institute of Physics of the National Academy of Scienceszhps-955Research ArticleСтатьиClassification of rubber vulcanizing accelerators based on particle swarm optimization extreme learning machine and terahertz spectraClassification of rubber vulcanizing accelerators based on particle swarm optimization extreme learning machine and terahertz spectraYinX.YinX.

Guangxi Guilin 541004

Guangxi Guilin 541004

cpxu_ck@163.comHeW.HeW.

Guangxi Guilin 541004

Guangxi Guilin 541004

WangL.WangL.

Guangxi Guilin 541004

Guangxi Guilin 541004

MoW.MoW.

Guangxi Guilin 541004

Guangxi Guilin 541004

LiA.LiA.

Guilin 541004

Guilin 541004

School of Electronic Engineering and Automation at Guilin University of Electronic Technology; Guangxi Key Laboratory of Automatic Detecting Technology and InstrumentsSchool of Electronic Engineering and Automation at Guilin University of Electronic Technology; Guangxi Key Laboratory of Automatic Detecting Technology and InstrumentsNational Rubber and Rubber Products Quality Supervision and Inspection Center (Guangxi)National Rubber and Rubber Products Quality Supervision and Inspection Center (Guangxi)202130112021886980980Copyright © Yin X., He W., Wang L., Mo W., Li A., 20212021Yin X., He W., Wang L., Mo W., Li A.Yin X., He W., Wang L., Mo W., Li A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://zhps.ejournal.by/jour/article/view/955

In rubber tire production, three popular types of rubber vulcanizing accelerators exist that are similar in appearance (i.e., 2-Mercaptobenzothiazole, 4,4′-dithiodimorpholine, and tetramethyl thiuram monosulfide). Because the rubber vulcanizing accelerator has a great influence on the vulcanized rubber characteristics, it is necessary to classify and identify the three popular types of rubber vulcanizing accelerators to avoid using the wrong accelerator during tire production and to ensure the tire quality. The THz spectra of the accelerator samples were measured using a terahertz time-domain spectral system (THz-TDS) in a frequency range of 0.3–1.6 THz. An extreme learning machine (ELM) model was constructed to classify the three popular types of rubber vulcanizing accelerators via terahertz absorption spectra. To improve the classification accuracy of the model, a particle swarm optimization ELM model was constructed possessing a higher classification accuracy than the ELM model in the classification and identification of rubber vulcanizing accelerators. 

In rubber tire production, three popular types of rubber vulcanizing accelerators exist that are similar in appearance (i.e., 2-Mercaptobenzothiazole, 4,4′-dithiodimorpholine, and tetramethyl thiuram monosulfide). Because the rubber vulcanizing accelerator has a great influence on the vulcanized rubber characteristics, it is necessary to classify and identify the three popular types of rubber vulcanizing accelerators to avoid using the wrong accelerator during tire production and to ensure the tire quality. The THz spectra of the accelerator samples were measured using a terahertz time-domain spectral system (THz-TDS) in a frequency range of 0.3–1.6 THz. An extreme learning machine (ELM) model was constructed to classify the three popular types of rubber vulcanizing accelerators via terahertz absorption spectra. To improve the classification accuracy of the model, a particle swarm optimization ELM model was constructed possessing a higher classification accuracy than the ELM model in the classification and identification of rubber vulcanizing accelerators. 

terahertz spectrumrubber vulcanization acceleratorparticle swarm optimizationextreme learning machineclassificationterahertz spectrumrubber vulcanization acceleratorparticle swarm optimizationextreme learning machineclassification.This work was supported by the National Natural Science Foundation of China (NSFC) (grant No. 61841502), the Guangxi Natural Science Foundation (grant No. 2018GXNSFAA281341) and the Foundation from Guangxi Key Laboratory of Automatic Detecting Technology and Instruments (grant No. YQ19102). We thank Sara Maccagnano-Zacher, PhD, from Liwen Bianji (Edanz) (https://www.liwenbianji.cn) for editing the language of a draft of this manuscript.ReferencesS. H. Baek, J. H. Kang, Y. H. Hwang, K. M. Ok, K. Kwak, H. S. Chun, J. Infrared Millimeter and Terahertz Waves, 37, 486–497 (2016).S. H. Baek, J. H. Kang, Y. H. Hwang, K. M. Ok, K. Kwak, H. S. Chun, J. Infrared Millimeter and Terahertz Waves, 37, 486–497 (2016).Y. Hua, H. Zhang, IEEE Trans. Microwave Theory Tech., 58, 2064–2070 (2010).Y. Hua, H. Zhang, IEEE Trans. Microwave Theory Tech., 58, 2064–2070 (2010).Z. Chen, Z. Zhang, R. Zhu, Yang, Y. Yang, P. B. Harrington, J. Quant. Spectrosc. Radiat. Transf., 167, 1–9 (2015).Z. Chen, Z. Zhang, R. Zhu, Yang, Y. Yang, P. B. Harrington, J. Quant. Spectrosc. Radiat. Transf., 167, 1–9 (2015).M. Lu, T. Wang, Y. W. Wang, Chin. Rubber Sci. Technol. Market, 1, 32–34 (2012).M. Lu, T. Wang, Y. W. Wang, Chin. Rubber Sci. Technol. Market, 1, 32–34 (2012).F. Yan, J. Chin. Rubber/Plastics Technol. Equip., 43, No. 3, 47 (2017).F. Yan, J. Chin. Rubber/Plastics Technol. Equip., 43, No. 3, 47 (2017).J. F. Rong, Sh. L. Mao, J. F. Li, J. Phys. Test. Chem. Anal. B: Chem. Anal., 52, No. 7, 750–755 (2016).J. F. Rong, Sh. L. Mao, J. F. Li, J. Phys. Test. Chem. Anal. B: Chem. Anal., 52, No. 7, 750–755 (2016).M. Hangyo, Jpn. J. Appl. Phys., 54, 12010112 (2015).M. Hangyo, Jpn. J. Appl. Phys., 54, 12010112 (2015).O. Peters, M. Schwerdtfeger, S. Wietzke, et al., J. Polym. Test., 32, 932–936 (2013).O. Peters, M. Schwerdtfeger, S. Wietzke, et al., J. Polym. Test., 32, 932–936 (2013).Q. Mao, L. Tian, et al., J. Mod. Sci. Instrum., 5, 110–113 (2011).Q. Mao, L. Tian, et al., J. Mod. Sci. Instrum., 5, 110–113 (2011).H. B. Guang, J. Neu-Rocomputing, 70, 489–501 (2006).H. B. Guang, J. Neu-Rocomputing, 70, 489–501 (2006).X. T. Shi, J. Y. Pang, X. Zhang, et al., Chin. J. Sci. Instrum., 39, No. 12, 81–91 (2018).X. T. Shi, J. Y. Pang, X. Zhang, et al., Chin. J. Sci. Instrum., 39, No. 12, 81–91 (2018).R. C. Eberhart, J. Kennedy, Proc. 6th Int. Symposium on Micro Machine and Human Science, Nagoya, Japan, IEEE, 39–43 (1995).R. C. Eberhart, J. Kennedy, Proc. 6th Int. Symposium on Micro Machine and Human Science, Nagoya, Japan, IEEE, 39–43 (1995).Ch. P. Xu, M. Lik, Chin. J. Sci. Instrum., 38, No. 3, 765–772 (2017).Ch. P. Xu, M. Lik, Chin. J. Sci. Instrum., 38, No. 3, 765–772 (2017).T. Chen, Zh. Li, W. Mo, Chin. J. Sci. Instrum., 33, No. 11, 2480–2486 (2012).T. Chen, Zh. Li, W. Mo, Chin. J. Sci. Instrum., 33, No. 11, 2480–2486 (2012).T. D. Dorney, R. G. Baraniuk, D. M. Mittleman, J. Opt. Soc. Am. A Opt. Image SciVis, 18, No. 7, 1562–1571 (2001).T. D. Dorney, R. G. Baraniuk, D. M. Mittleman, J. Opt. Soc. Am. A Opt. Image SciVis, 18, No. 7, 1562–1571 (2001).L. Duvillaret, F. Garet, J. L. Coutaz, J. Appl. Opt., 38, No. 2, 409–415 (1999).L. Duvillaret, F. Garet, J. L. Coutaz, J. Appl. Opt., 38, No. 2, 409–415 (1999).L. Duvillaret, F. Garet, J. L. Coutaz, IEEE J. Sel. Top. Quantum Electron., 2, No. 3, 739–746 (1996).L. Duvillaret, F. Garet, J. L. Coutaz, IEEE J. Sel. Top. Quantum Electron., 2, No. 3, 739–746 (1996).H. Zhang, Z. Li, T. Chen, et al., J. Spectrochim. Acta A: Mol. Biomol. Spectrosc., 184, 335–341 (2017).H. Zhang, Z. Li, T. Chen, et al., J. Spectrochim. Acta A: Mol. Biomol. Spectrosc., 184, 335–341 (2017).

The authors declare that there are no conflicts of interest present.