Prediction of Shear Thickening Ratio Based on Rheological Parameters Using Machine Learning

Öz

Shear thickening fluids (STFs) show a complex, non-Newtonian rheological behavior in which viscosity increases with shear rate. Accurately estimating the thickening ratio (TR), a summary parameter representing the rheological response, is crucial for optimizing the formulation of these fluids and their effective use in applications. In this study, a machine learning-based approach is proposed to directly predict TR. The modeling process incorporated rheologically relevant input parameters, including particle size, weight-based particle concentration, carrier-fluid concentration, molecular weight of the carrier-fluid, and test temperature. Two advanced ensemble learning algorithms, Extreme Gradient Boosting (XGBOOST) and Random Forest (RF), were used to create the prediction models. The models were trained and validated on various experimental datasets obtained from different independent sources and covering a wide range of STF compositions and experimental conditions. The results showed that XGBOOST achieved 80% and 72% accuracy for RF during the testing phase, with XGBOOST outperforming RF. Furthermore, the calculated feature importance values revealed the main parameters affecting TR. Although the influence values of the parameters on TR were close to each other, the carrier-fluid ratio (OSO) (25.91%) and the silica ratio (SO) (24.32%) stand out as the most influential parameters. This approach offers a simple and effective method for assessing the rheological behavior of STF systems, while also providing significant time and cost advantages by reducing the need for extensive experimental procedures. The developed method has the potential to be a valuable tool for decision support in the design and development of next-generation STF materials.

Anahtar Kelimeler

• Shear-thickening fluids
• thickening ratio
• machine learning
• rheology

Reolojik Parametrelere Dayalı Kalınlaşma Oranının Makine Öğrenmesi ile Tahmini

Öz

Kayma kalınlaşması gösteren sıvılar (STF’ler), viskozitenin kayma hızıyla birlikte arttığı karmaşık, Newtonsal olmayan bir reolojik davranış sergiler. Bu sıvıların formülasyonunun optimize edilmesi ve uygulamalarda etkin kullanımı açısından, reolojik tepkiyi temsil eden özet bir parametre olan kalınlaşma oranının (TR) doğru bir şekilde tahmin edilmesi büyük önem taşımaktadır. Bu çalışmada, TR’yi doğrudan tahmin edebilmek amacıyla makine öğrenmesine dayalı bir yaklaşım önerilmiştir. Modelleme sürecinde, partikül boyutu, ağırlıkça parçacık konsantrasyonu, taşıyıcı sıvı konsantrasyonu, taşıyıcı sıvının moleküler ağırlığı ve test sıcaklığı gibi reolojik açıdan etkili giriş parametreleri kullanılmıştır. Tahmin modellerinin oluşturulmasında iki gelişmiş topluluk öğrenme algoritması olan Gelişmiş Gradyan Artırma (XGBOOST) ve Rastgele Orman (RF) yöntemlerinden yararlanılmıştır. Modeller, farklı bağımsız kaynaklardan elde edilen ve geniş bir STF bileşimi ve deney koşulu aralığını kapsayan çeşitli deneysel veri setleriyle eğitilmiş ve doğrulanmıştır. Elde edilen sonuçlar, test aşamasında XGBOOST için %80 RF için %72 doğrulukla tahmin yapabildiğini ve XGBOOST’un RF’ye göre daha başarılı olduğunu göstermiştir. Ayrıca hesaplanan öznitelik önemi değerleri TR üzerinde etkili olan temel parametreleri ortaya koymuştur. TR üzerindeki parametrelerin etki değerleri birbirine yakın olduğu görünse de %25,91 ile ortam sıvısı oranı (OSO) ve %24,32 silika oranı (SO) en etkili parametreler olarak ön plana çıkmaktadır. Bu yaklaşım, STF sistemlerinin reolojik davranışını sade ve etkili bir şekilde değerlendirebilecek bir yöntem sunmakta; aynı zamanda kapsamlı deneysel süreçlere duyulan ihtiyacı azaltarak zaman ve maliyet açısından önemli avantajlar sağlamaktadır. Geliştirilen yöntem, yeni nesil STF malzemelerinin tasarım ve geliştirme süreçlerinde karar destek mekanizması olarak kullanılabilecek değerli bir araç potansiyeli taşımaktadır.

Anahtar Kelimeler

• Kayma altında kalınlaşan sıvılar
• kalınlaşma oranı
• makine öğrenmesi
• reoloji

Kaynakça

1. [1] Serra, G. F., Oliveira, L., Gürgen, S., de Sousa, R. A., & Fernandes, F. A. (2024). Shear thickening fluid (STF) in engineering applications and the potential of cork in STF-based composites. Advances in Colloid and Interface Science, 327, 103157. https://doi.org/10.1016/j.cis.2024.103157
2. [2] Fernandes, T. R., Alves de Sousa, R. J., & Fernandes, F. A. (2025). Multilayered cork-STF composite structures enhanced with laser texturing for impact mitigation. The International Journal of Advanced Manufacturing Technology, 136(1), 97-107. https://doi.org/10.1007/s00170-024-13815-1
3. [3] Wang, L., Du, Z., Fu, W., & Wang, P. (2021). Study of mechanical property of shear thickening fluid (STF) for soft body-armor. Materials Research Express, 8(4), 045021. DOI 10.1088/2053-1591/abf76a
4. [4] Park, Y., Baluch, A. H., Kim, Y., & Kim, C. G. (2013). High velocity impact characteristics of shear thickening fluid impregnated Kevlar fabric. International Journal of Aeronautical and Space Sciences, 14(2), 140-145.
5. [5] Wang, Y., Li, S. K., & Feng, X. Y. (2015). The ballistic performance of multi-layer Kevlar fabrics impregnated with shear thickening fluids. Applied Mechanics and Materials, 782, 153-157. https://doi.org/10.4028/www.scientific.net/AMM.782.153
6. [6] Khodadadi, A., Liaghat, G., Vahid, S., Sabet, A. R., & Hadavinia, H. (2019). Ballistic performance of Kevlar fabric impregnated with nanosilica/PEG shear thickening fluid. Composites Part B: Engineering, 162, 643-652. https://doi.org/10.1016/j.compositesb.2018.12.121
7. [7] Zelelew, T. M., Ali, A. N., Kidanemariam, G., Kebede, G. A., & Koricho, E. G. (2025). Effects of shear thickening fluids to enhance the impact resistance of soft body armor composites: a review. Smart Materials and Structures. DOI 10.1088/1361-665X/adbdb2
8. [8] Ercümen, K. M., & Aydin, M. (2024). Ballistic impact performance of aramid fabrics impregnated with single‐phase shear thickening fluids STFs and SiC additive multi‐phase shear thickening fluids. Polymer Composites, 45(18), 16850-16865. https://doi.org/10.1002/pc.28936

9. [9] Hasanzadeh, M., Mottaghitalab, V., Rezaei, M., & Babaei, H. (2017). Numerical and experimental investigations into the response of STF-treated fabric composites undergoing ballistic impact. Thin-Walled Structures, 119, 700-706. https://doi.org/10.1016/j.tws.2017.07.020
10. [10] Ercümen, K.M., Aydin, M. Experimental Investigation of Ballistic Impact Performance of Composite Structures Prepared by Shear Thickening Fluid Impregnation Into Aramid, Uhmwpe, and Hybrid Fabrics. Exp Tech (2025). https://doi.org/10.1007/s40799-025-00809-1
11. [11] Fahool, M., & Sabet, A. R. (2016). Parametric study of energy absorption mechanism in Twaron fabric impregnated with a shear thickening fluid. International Journal of Impact Engineering, 90, 61-71. https://doi.org/10.1016/j.ijimpeng.2015.11.016
12. [12] Aşkan, A., & Aydın, M. (2025). The role of impact energy and silica concentration on dynamic impact and quasi-static puncture resistance of fabrics treated with shear-thickening fluids. Composite Structures, 352, 118689. https://doi.org/10.1016/j.compstruct.2024.118689
13. [13] Wang, S., Zhang, W., Gao, J., Gao, D., & He, C. (2024). Characteristics of shear thickening fluid and its application in engineering: a state-of-the-art review. The International Journal of Advanced Manufacturing Technology, 133(5), 1973-2000. https://doi.org/10.1007/s00170-024-13816-0
14. [14] Zarei, M., & Aalaie, J. (2020). Application of shear thickening fluids in material development. Journal of Materials Research and Technology, 9(5), 10411-10433. https://doi.org/10.1016/j.jmrt.2020.07.049
15. [15] Astaraki, S., Zamani, E., Moghadam, M., Pol, M. H., & Hasannezhad, H. (2024). Investigating the effect of temperature, angular frequency, and strain on the rheological properties of shear thickening fluid (STF) with different weight fractions of fumed silica. Colloid and Polymer Science, 302(1), 1-11. https://doi.org/10.1007/s00396-023-05173-3
16. [16] Husain, M., Aftab, R. A., Zaidi, S., & Rizvi, S. J. A. (2025). Shear thickening fluid: A multifaceted rheological modeling integrating phenomenology and machine learning approach. Journal of Molecular Liquids, 425, 127223. https://doi.org/10.1016/j.molliq.2025.127223
17. [17] Gürgen, S., Sofuoğlu, M. A., & Kuşhan, M. C. (2020). Rheological modeling of multi-phase shear thickening fluid using an intelligent methodology. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 42, 1-7. https://doi.org/10.1007/s40430-020-02681-z
18. [18] Galindo-Rosales, F. J., Rubio-Hernández, F. J., & Sevilla, A. (2011). An apparent viscosity function for shear thickening fluids. Journal of Non-Newtonian Fluid Mechanics, 166(5-6), 321-325. https://doi.org/10.1016/j.jnnfm.2011.01.001
19. [19] Chamola, R., Das, S., Ahlawat, D. S., Mishra, Y. K., & Goyat, M. S. (2024). Recent developments in shear thickening fluid-impregnated synthetic and natural fiber-reinforced composites for ballistic applications: a review. Journal of Materials Science, 59(3), 747-793. https://doi.org/10.1007/s10853-023-09201-z
20. [20] Liu, H., Fu, K., Cui, X., Zhu, H., & Yang, B. (2023). Shear thickening fluid and its application in impact protection: a review. Polymers, 15(10), 2238. https://doi.org/10.3390/polym15102238
21. [21] Bajya, M., Majumdar, A., Butola, B. S., Verma, S. K., & Bhattacharjee, D. (2020). Design strategy for optimising weight and ballistic performance of soft body armour reinforced with shear thickening fluid. Composites Part B: Engineering, 183, 107721. https://doi.org/10.1016/j.compositesb.2019.107721
22. [22] Manukonda, B. H., Chatterjee, V. A., Verma, S. K., Bhattacharjee, D., Biswas, I., & Neogi, S. (2020). Rheology based design of shear thickening fluid for soft body armor applications. Periodica Polytechnica Chemical Engineering, 64(1), 75-84. https://doi.org/10.3311/PPch.13626
23. [23] Das, J., Butola, B. S., & Majumdar, A. (2025). Development of stab resistant armor for different energy levels using shear thickening fluid reinforced multi‐layered p‐aramid fabrics. Polymer Composites, 46(2), 1843-1856. https://doi.org/10.1002/pc.29077
24. [24] Chang, C. P., Shih, C. H., You, J. L., Youh, M. J., Liu, Y. M., & Ger, M. D. (2021). Preparation and ballistic performance of a multi-layer armor system composed of kevlar/polyurea composites and shear thickening fluid (Stf)-filled paper honeycomb panels. Polymers, 13(18), 3080. https://doi.org/10.3390/polym13183080
25. [25] Yeh, S. K., Lin, J. J., Zhuang, H. Y., Chen, Y. C., Chang, H. C., Zheng, J. Y., ... & Rwei, S. P. (2019). Light shear thickening fluid (STF)/Kevlar composites with improved ballistic impact strength. Journal of Polymer Research, 26(6), 155. https://doi.org/10.1007/s10965-019-1811-8
26. [26] Tian, T., Peng, G., Li, W., Ding, J., & Nakano, M. (2015). Experimental and modelling study of the effect of temperature on shear thickening fluids. Korea-Australia rheology journal, 27(1), 17-24. https://doi.org/10.1007/s13367-015-0003-2
27. [27] Liu, X. Q., Bao, R. Y., Wu, X. J., Yang, W., Xie, B. H., & Yang, M. B. (2015). Temperature induced gelation transition of a fumed silica/PEG shear thickening fluid. Rsc Advances, 5(24), 18367-18374. https://doi.org/10.1039/C4RA16261G
28. [28] Gürgen, S., & Kuşhan, M. C. (2017). The ballistic performance of aramid based fabrics impregnated with multi-phase shear thickening fluids. Polymer Testing, 64, 296-306. https://doi.org/10.1016/j.polymertesting.2017.11.003
29. [29] Baharvandi, H. R., Saeedi Heydari, M., Kordani, N., Alebooyeh, M., Alizadeh, M., & Khaksari, P. (2017). Characterization of the rheological and mechanical properties of shear thickening fluid-coated Twaron® composite. The Journal of The Textile Institute, 108(3), 397-407. https://doi.org/10.1080/00405000.2016.1168091
30. [30] Liu, L., Yang, Z., Zhao, Z., Liu, X., & Chen, W. (2020). The influences of rheological property on the impact performance of kevlar fabrics impregnated with SiO2/PEG shear thickening fluid. Thin-Walled Structures, 151, 106717. https://doi.org/10.1016/j.tws.2020.106717
31. [31] Baharvandi, H. R., Alebooyeh, M., Alizadeh, M., Khaksari, P., & Kordani, N. (2016). Effect of silica weight fraction on rheological and quasi-static puncture characteristics of shear thickening fluid-treated Twaron® composite. Journal of Industrial Textiles, 46(2), 473-494. https://doi.org/10.1177/1528083715589750
32. [32] Yanen, C. (2021). Hibrit nanopartikül takviyeli kayma altında katılaşan sıvıların balistik uygulamalarında kullanımının araştırılması [Investigation of the use of hybrid nanoparticle-reinforced shear thickening fluids in ballistic applications] (Doctoral dissertation). Elazığ University, Department of Mechanical Engineering.
33. [33] Li, D., Wang, R., Liu, X., Zhang, S., Fang, S., & Yan, R. (2020). Effect of dispersing media and temperature on inter-yarn frictional properties of Kevlar fabrics impregnated with shear thickening fluid. Composite Structures, 249, 112557. https://doi.org/10.1016/j.compstruct.2020.112557
34. [34] Mawkhlieng, U., & Majumdar, A. (2019). Deconstructing the role of shear thickening fluid in enhancing the impact resistance of high-performance fabrics. Composites Part B: Engineering, 175, 107167. https://doi.org/10.1016/j.compositesb.2019.107167
35. [35] Grover, G., Verma, S. K., Thakur, A., Biswas, I., & Bhatacharjee, D. (2020). The effect of particle size and concentration on the ballistic resistance of different shear thickening fluids. Materials Today: Proceedings, 28, 1472-1476. https://doi.org/10.1016/j.matpr.2020.04.823
36. [36] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794). https://doi.org/10.1145/2939672.2939785.
37. [37] Qiu, Y., Zhou, J., Khandelwal, M., Yang, H., Yang, P., & Li, C. (2022). Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Engineering with Computers, 38(Suppl 5), 4145-4162. https://doi.org/10.1007/s00366-021-01393-9
38. [38] Aslay, S. E. (2024). Yapım İşlerinde İhale Parametreleri Kullanılarak Makine Öğrenmesi ile Sözleşme Bedeli Tahmini. Karaelmas Fen ve Mühendislik Dergisi, 14(3), 64-73. https://doi.org/10.7212/karaelmasfen.1484595
39. [39] Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
40. [40] Adusumilli, S., Bhatt, D., Wang, H., Bhattacharya, P., & Devabhaktuni, V. (2013). A low-cost INS/GPS integration methodology based on random forest regression. Expert Systems with Applications, 40(11), 4653-4659. https://doi.org/10.1016/j.eswa.2013.02.002
41. [41] Upreti, K., Verma, M., Agrawal, M., Garg, J., Kaushik, R., Agrawal, C., ... & Narayanasamy, R. (2022). Prediction of mechanical strength by using an artificial neural network and random forest algorithm. Journal of Nanomaterials, 2022(1), 7791582. https://doi.org/10.1155/2022/7791582
42. [42] Aslan, S., & Yıldız, T. (2022). Makine öğrenmesinde rastgele oran ve sıralı küme örneklemesi yöntemlerinin doğrusal regresyon modellerine etkisi. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 24(70), 29-36. https://doi.org/10.21205/deufmd.2022247004
43. [43] Kilinc, H. C., Haznedar, B., Ozkan, F., & Katipoğlu, O. M. (2024). An evolutionary hybrid method based on particle swarm optimization algorithm and extreme gradient boosting for short-term streamflow forecasting. Acta Geophysica, 72(5), 3661-3681. https://doi.org/10.1007/s11600-024-01307-5
44. [44] Aslay, S. E. (2025). Building Energy Prediction Model with AI-Based PSO-ANN Approach Integrating Architectural and HVAC Processes. Building and Environment, 113305. https://doi.org/10.1016/j.buildenv.2025.113305
45. [45] Thodda, G., Madhavan, V. R., & Thangavelu, L. (2023). Predictive modelling and optimization of performance and emissions of acetylene fuelled CI engine using ANN and RSM. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 45(2), 3544-3562. https://doi.org/10.1080/15567036.2020.1829191
46. [46] Brown, M. G., Peterson, M. G., Tezaur, I. K., Peterson, K. J., & Bull, D. L. (2025). Random forest regression feature importance for climate impact pathway detection. Journal of Computational and Applied Mathematics, 464, 116479. https://doi.org/10.1016/j.cam.2024.116479
47. [47] Aslay, S. E. (2024). Estimating contract value using structural parameters: a machine learning approach with data preprocessing. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 15(3), 755-765. https://doi.org/10.24012/dumf.1515160