Artificial intelligence based prediction models for rubber compounds
-
Zeynep Uruk
and
Alper Kiraz
Abstract
In the rubber industry, rheometric properties are critical in defining processing times and temperatures. These parameters of rubber compounds are determined by time-consuming and expensive laboratory studies performed in a rheometer. Artificial intelligence approaches, on the other hand, may be used to estimate rheometric properties in seconds without the need for any samples or laboratory experiments. In this research, artificial neural network, Gaussian process regression, and support vector regression techniques are used to predict minimum and maximum torque, 30% and 60% cure time of a rubber compound using both process parameters and raw material composition as input. The dataset comprises 1128 batches of the selected rubber compound. A detailed sensitivity analysis is performed to determine the best performing hyperparameters and the prediction performances are expressed as mean absolute percentage error (MAPE). Minimum, maximum, and average MAPE values are presented for each artificial intelligence technique. Besides this research contributes to fill the gap in rubber industry literature, the results obtained also strongly improve the existing literature results.
Funding source: Scientific and Technological Research Council of Turkey (TÜBİTAK)
Award Identifier / Grant number: 119C120
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: This research, which is performed by DRC Kauçuk and Sakarya University, is funded by Scientific and Technological Research Council of Turkey (TÜBİTAK) with project number 119C120.
-
Conflict of interest statement: The authors declare that they have no conflicts of interest regarding this article.
-
Data availability: The datasets generated and/or analyzed during the current study are available at the corresponding author and can be provided on reasonable request.
References
1. Sisanth, K. S., Thomas, M. G., Abraham, J., Thomas, S. General introduction to rubber compounding. In Progress in Rubber Nanocomposites. Woodhead Publishing: Cambridge, UK, 2017; pp. 1–39.10.1016/B978-0-08-100409-8.00001-2Search in Google Scholar
2. González Marcos, A., Castejón Lımas, M., Alba Elías, F., Martínez De Pısón Ascacıbar, F. J. Estimation of cure characteristics in rubber extrusion lines. In Proceedings of the 8th WSEAS Int. Conference on Automatic Control, Modelling and Simulation, Prague, Czech Republic March 12-14, 2006; pp. 189–194.Search in Google Scholar
3. Vijayabaskar, V., Gupta, R., Chakrabarti, P. P., Bhowmick, A. K. Prediction of properties of rubber by using artificial neural networks. J. Appl. Polym. Sci. 2006, 100, 2227–2237; https://doi.org/10.1002/app.22356.Search in Google Scholar
4. Schwartz, G. A. Prediction of rheometric properties of compounds by using artificial neural network. Rubber Chem. Technol. 2001, 74, 116–123; https://doi.org/10.5254/1.3547632.Search in Google Scholar
5. Karaağaç, B., İnal, M., Deniz, V. Artificial neural network approach for predicting optimum cure time of rubber compounds. Mater. Des. 2009, 30, 1685–1690.10.1016/j.matdes.2008.07.010Search in Google Scholar
6. Diaconescu, R. M., Barbuta, M., Harja, M. Prediction of properties of polymer concrete composite with tire rubber using neural networks. Mater. Sci. Eng. B 2013, 178, 1259–1267; https://doi.org/10.1016/j.mseb.2013.01.014.Search in Google Scholar
7. Lubura, J. D., Kojić, P., Pavličević, J., Ikonić, B., Omorjan, R., Bera, O. Prediction of rubber vulcanization using an artificial neural network. Hem. Ind. 2021, 75, 277–283; https://doi.org/10.2298/hemind210511026l.Search in Google Scholar
8. Wang, B., Ma, J. H., Wu, Y. P. Application of artificial neural network in prediction of abrasion of rubber composites. Mater. Des. 2013, 49, 802–807; https://doi.org/10.1016/j.matdes.2013.01.047.Search in Google Scholar
9. Xiang, K. L., Xiang, P. Y., Wu, Y. P. Prediction of the fatigue life of natural rubber composites by artificial neural network approaches. Mater. Des. 2014, 57, 180–185; https://doi.org/10.1016/j.matdes.2013.12.044.Search in Google Scholar
10. Sresungsuwan, N., Hansupalak, N. Prediction of mechanical properties of compatibilized styrene/natural -rubber blend by using reaction conditions: central composite design vs. artificial neural networks. J. Appl. Polym. Sci. 2013, 127, 356–365; https://doi.org/10.1002/app.37550.Search in Google Scholar
11. Haberstroh, E., Linhart, C. Batch variations and their effects on the elastomer -processing illustrated on the model of the injection moulding process. J. Polym. Eng. 2004, 24, 325–342; https://doi.org/10.1515/polyeng.2004.24.1-3.325.Search in Google Scholar
12. Jin, H., Li, J., Wang, M., Qian, B., Yang, B., Li, Z., Shi, L. Ensemble just-in-time learning-based soft sensor for Mooney viscosity prediction in an industrial rubber mixing process. Adv. Polym. Technol. 2020, 1, 1–14; https://doi.org/10.1155/2020/6575326.Search in Google Scholar
13. Song, K., Wu, F., Tong, T., Wang, X. A real-time Mooney-viscosity prediction model of the mixed rubber based on the independent component regression-Gaussian process algorithm. J. Chemometr. 2012, 26, 11–12; https://doi.org/10.1002/cem.2478.Search in Google Scholar
14. Yang, K., Jin, H., Chen, X., Dai, J., Wang, L., Zhang, D. Soft sensor development for online quality prediction of industrial batch rubber mixing process using ensemble just-in-time Gaussian process regression models. Chemometr. Intell. Lab. Syst. 2016, 155, 170–182; https://doi.org/10.1016/j.chemolab.2016.04.009.Search in Google Scholar
15. Zhang, Z., Song, K., Tong, T., Wu, F. A novel nonlinear adaptive Mooney-viscosity model based on DRPLS -GP algorithm for rubber mixing process. Chemometr. Intell. Lab. Syst. 2012, 112, 17–23; https://doi.org/10.1016/j.chemolab.2011.12.001.Search in Google Scholar
16. Foorginejad, A., Taheri, M., Mollayi, N., Shiva, M. Tire hardness modeling based on longitudinal ultrasonic velocity using the Gaussian process regression. Amirkabir J. Mech. Eng. 2019, 51, 317–318.Search in Google Scholar
17. Román, A. J., Qin, S., Rodríguez, J. C., González, L. D., Zavala, V. M., Osswald, T. A. Natural rubber blend optimization via data-driven modeling: the implementation for reverse engineering. Polymers 2022, 14, 2262; https://doi.org/10.3390/polym14112262.Search in Google Scholar PubMed PubMed Central
18. Liu, Q., Shi, W., Chen, Z. Fatigue life prediction for vibration isolation rubber based on parameter-optimized support vector machine model. Fatig. Fract. Eng. Mater. Struct. 2018, 42, 710–718; https://doi.org/10.1111/ffe.12945.Search in Google Scholar
19. Fernandez-Martinez, R., Hernandez, R., Ibarretxe, J., Jimbert, P., Iturrondobeitia, M., Guraya-Díez, T. Modeling of the mechanical properties of carbon-black reinforced rubber blends by machine learning techniques. Appl. Mech. Mater. 2014, 627, 97–100; https://doi.org/10.4028/www.scientific.net/amm.627.97.Search in Google Scholar
20. Fernandez-Martinez, R., Jimbert, P., Ibarretxe, J., Iturrondobeitia, M. Use of support vector machines, neural networks and genetic algorithms to characterize rubber blends by means of the classification of the carbon black particles used as reinforcing agent. Soft Comput. 2019, 23, 1–10; https://doi.org/10.1007/s00500-018-3262-2.Search in Google Scholar
21. Guo, B., Wang, X., Wang, Y., Su, H., Chao, S. Application of support vector regression to predict the remaining useful life of polymerized styrene butadiene rubber of cable insulation. In Prognostics and System Health Management Conference (PHM-Qingdao), 2019; pp. 1–5.10.1109/PHM-Qingdao46334.2019.8942888Search in Google Scholar
22. Jalal, M., Arabali, P., Grasley, Z., Bullard, J. W., Jalal, H. Behavior assessment, regression analysis and support vector machine modeling of waste tire rubberized concrete. J. Clean. Prod. 2020, 273, 122960; https://doi.org/10.1016/j.jclepro.2020.122960.Search in Google Scholar
23. Xie, Y., Wang, H., Ciao, Y., Li, P. Study of discharge modeling method using support vector machine for rubber mixing process. Proc. Am. Control Conf. 2003, 5, 3673–3678.Search in Google Scholar
24. Yu, Z., Wang, Y., Huang, S., Zhou, T., Chang, L. Predicting the unconfined compressive strength of rubber fiber modified cemented paste backfill using support vector machine. IOP Conf. Ser. Earth Environ. Sci. 2021, 791; https://doi.org/10.1088/1755-1315/791/1/012037.Search in Google Scholar
25. McCulloch, W., Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 1943, 5, 115–133; https://doi.org/10.1007/bf02478259.Search in Google Scholar
26. Davalo, E., Naïm, P. Des Réseaux de Neurones; Eyrolles: Paris, France, 1992.Search in Google Scholar
27. Rosenblatt, F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 1958, 65, 386–408; https://doi.org/10.1037/h0042519.Search in Google Scholar PubMed
28. Rasmussen, C. E., Williams, C. K. Gaussian Processes for Machine Learning; MIT Press Cambridge: London, England, 1, 2006.10.7551/mitpress/3206.001.0001Search in Google Scholar
29. Boser, B. E., Guyon, I. M., Vapnik, V. N. A training algorithm for optimal margin classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 1992; pp. 144–152.10.1145/130385.130401Search in Google Scholar
30. Vapnik, V. N. The Nature of Statistical Learning Theory; Springer-Verlag: New York, 1995.10.1007/978-1-4757-2440-0Search in Google Scholar
31. Sánchez, A. V. D. Advanced support vector machines and kernel methods. Neurocomputing 2003, 55, 5–20; https://doi.org/10.1016/s0925-2312(03)00373-4.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Material Properties
- The effect of filler loading and APTES treatment on the performance of PSf/SBA-15 mixed matrix membranes
- Artificial intelligence based prediction models for rubber compounds
- Synthesis and memory properties of a series of novel asymmetric soluble polyimides
- Preparation and Assembly
- Fabrication of high strength and functional GO/PVA/PAN ternary composite fibers by gel spinning
- Polycaprolactone/epoxide-functionalized silica composite microparticles for long-term controlled release of trans-chalcone
- Rapid incorporation of gold nanoparticles onto graphene oxide-polymer nanofiber membranes for photothermally-accelerated water purification
- Sustained oxygen release of hydrogen peroxide-acrylic resin inclusion complex for aquaculture
- Engineering and Processing
- Reducing component stress during encapsulation of electronics: a simulative examination of thermoplastic foam injection molding
- Influence of production process-induced surface topologies at varying roughness depths on the tribological properties of polyamide steel contact
Articles in the same Issue
- Frontmatter
- Material Properties
- The effect of filler loading and APTES treatment on the performance of PSf/SBA-15 mixed matrix membranes
- Artificial intelligence based prediction models for rubber compounds
- Synthesis and memory properties of a series of novel asymmetric soluble polyimides
- Preparation and Assembly
- Fabrication of high strength and functional GO/PVA/PAN ternary composite fibers by gel spinning
- Polycaprolactone/epoxide-functionalized silica composite microparticles for long-term controlled release of trans-chalcone
- Rapid incorporation of gold nanoparticles onto graphene oxide-polymer nanofiber membranes for photothermally-accelerated water purification
- Sustained oxygen release of hydrogen peroxide-acrylic resin inclusion complex for aquaculture
- Engineering and Processing
- Reducing component stress during encapsulation of electronics: a simulative examination of thermoplastic foam injection molding
- Influence of production process-induced surface topologies at varying roughness depths on the tribological properties of polyamide steel contact
