Predictive modelling and rheological investigation of titanium oxide–enhanced silica-based shear-thickening fluids
Source abstract
Abstract
A silica-based (SiO 2 ) shear-thickening fluid (STF) reinforced with titanium dioxide (TiO 2 ) nanoparticles was systematically examined across a broad range of temperature, shear rate, and applied stress. The TiO 2 /SiO 2 system showed a distinct, stress-dependent, nonlinear shear-thickening behavior, with an optimal nanoparticle concentration that maximized viscosity increase. The synergistic interaction between SiO 2 and TiO 2 nanoparticles promoted the formation of dense hydroclaster structures, significantly enhancing resistance to flow at high shear rates and improving rheological stability across different thermal conditions. To accurately model and predict highly nonlinear viscosity behavior, advanced machine learning (ML) models, including Support Vector Regression (SVR), Random Forest (RF), XGBoost, and CatBoost, were developed and fine-tuned using Bayesian Optimization (BO). CatBoost outperformed others, achieving a coefficient of determination (R 2 ) of 0.9991 and 0.9906 for training and testing datasets, respectively, along with a test root mean squared error (RMSE) of 7.2553 and a mean absolute error (MAE) of 4.0291. Additional validation confirmed the model’s generalization, with an R 2 of 0.9842. Moreover, Shapley additive explanation (SHAP) analysis was used to improve interpretability, revealing shear rate and shear stress as the most influential factors in viscosity changes. Meanwhile, temperature and TiO 2 concentration contributed positively within an optimal range. The close match between experimental results and ML predictions demonstrates the robustness of the proposed data-driven approach. This research highlights the potential of ML-based methods for the intelligent design and optimization of high-performance STFs for advanced impact mitigation, energy absorption, and vibration control applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rheology and Fluid Dynamics Studies · Drilling and Well Engineering · Enhanced Oil Recovery Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Southeast University
References (52)
Show source-provided references
1. 10.1088/1361-665X/aa5a2c10.1088/1361-665X/aa5a2c ↗
2. 10.1038/nature1118710.1038/nature11187 ↗
3. 10.1088/0034-4885/77/4/04660210.1088/0034-4885/77/4/046602 ↗
4. 10.1016/j.ymssp.2024.11118210.1016/j.ymssp.2024.111182 ↗
5. 10.1016/j.jsv.2010.06.02710.1016/j.jsv.2010.06.027 ↗
6. 10.1177/004051751351239510.1177/0040517513512395 ↗
7. 10.1142/S179329201450100810.1142/S1793292014501008 ↗
8. 10.1088/1674-0068/23/03/342-34610.1088/1674-0068/23/03/342-346 ↗
9. 10.1007/s13367-016-0020-910.1007/s13367-016-0020-9 ↗
10. 10.1080/00405000.2016.116809110.1080/00405000.2016.1168091 ↗
11. Fischer C Plummer CJG Michaud V et al. Pre-and post-transition behavior of shear-thickening fluids in oscillating shear. https://doi.org/10.1007/s00397-007-0202-y10.1007/s00397-007-0202-y ↗
12. 10.2140/jomms.2026.21.7110.2140/jomms.2026.21.71 ↗
13. Khan S Xu Z-D Yang Y et al. Influence of hexagonal boron nitride on the rheological behaviour of concentrated silica shear-thickening fluids 2026. https://doi.org/10.21203/rs.3.rs-8264684/v110.21203/rs.3.rs-8264684/v1 ↗
14. 10.1122/1.189580010.1122/1.1895800 ↗
15. 10.1007/s10570-017-1440-510.1007/s10570-017-1440-5 ↗
16. 10.1002/marc.20060029410.1002/marc.200600294 ↗
17. 10.1063/1.324847610.1063/1.3248476 ↗
18. 10.1016/j.jcis.2013.09.02010.1016/j.jcis.2013.09.020 ↗
19. 10.1007/s10853-015-9151-510.1007/s10853-015-9151-5 ↗
20. 10.1016/j.polymer.2010.11.05010.1016/j.polymer.2010.11.050 ↗
21. Khan S, Xu ZD, Khan A, et al. Rheological characterization and optimized predictive modeling of hexagonal boron nitride-enhanced silica-based shear-thickening fluids. J Thermoplast Compos Mater. 2026; (First published online March 11, 2026): 08927057261434862. https://doi.org/10.1177/08927057261434862
22. 10.1016/j.surfin.2025.10812210.1016/j.surfin.2025.108122 ↗
23. 10.1093/ijlct/ctab00310.1093/ijlct/ctab003 ↗
24. 10.23955/rkl.v16i2.2073910.23955/rkl.v16i2.20739 ↗
25. 10.1016/j.icheatmasstransfer.2020.10478310.1016/j.icheatmasstransfer.2020.104783 ↗
26. 10.1155/2018/697813010.1155/2018/6978130 ↗
27. 10.1007/s13367-015-0003-210.1007/s13367-015-0003-2 ↗
28. 10.1016/j.molliq.2020.11522010.1016/j.molliq.2020.115220 ↗
29. 10.1016/j.molliq.2025.12722310.1016/j.molliq.2025.127223 ↗
30. Kadir Münir ERCÜMEN. Prediction of shear thickening ratio based on rheological parameters using machine learning. Erzincan University Journal of Science and Technology, 2025.
31. 10.1016/j.cej.2023.14245410.1016/j.cej.2023.142454 ↗
32. 10.1016/j.triboint.2023.10875910.1016/j.triboint.2023.108759 ↗
33. 10.1016/j.cej.2023.14606910.1016/j.cej.2023.146069 ↗
34. 10.1016/j.enconman.2023.11738710.1016/j.enconman.2023.117387 ↗
35. 10.1016/j.molliq.2023.12225110.1016/j.molliq.2023.122251 ↗
36. 10.1016/j.colsurfa.2024.13402610.1016/j.colsurfa.2024.134026 ↗
37. 10.1007/978-1-4757-3264-110.1007/978-1-4757-3264-1 ↗
38. 10.1023/A:102262741141110.1023/A:1022627411411 ↗
39. 10.1016/j.mtcomm.2025.11225610.1016/j.mtcomm.2025.112256 ↗
40. 10.1007/s00366-021-01398-410.1007/s00366-021-01398-4 ↗
41. 10.1515/rams-2024-005010.1515/rams-2024-0050 ↗
42. Chen T Guestrin C. XGBoost. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. San Francisco CA USA. 13-17 August 2016: ACM 2016 pp. 785–794. https://doi.org/10.1145/2939672.293978510.1145/2939672.2939785 ↗
43. 10.1007/s00521-022-07896-w10.1007/s00521-022-07896-w ↗
44. 10.1016/j.cscm.2025.e0471510.1016/j.cscm.2025.e04715 ↗
45. CatBoost — yandex technologies. https://yandex.com/dev/catboost/. Accessed: Nov. 11 2025.
46. 10.1186/s40537-020-00369-810.1186/s40537-020-00369-8 ↗
47. Feurer M, Hutter F. Hyperparameter optimization. Hyperparameter Optimization. 2019; 18: 3–33. First Online: 18 May 2019. https://doi.org/10.1007/978-3-030-05318-5_1
48. Bergstra J, Bardenet R, Bengio Y, et al. {Bergstra, James and Bardenet, R’{e}mi and Bengio, Yoshua and K’{e}gl, Bal’{a}zs}. Algorithms for hyper-parameter optimization. Adv Neural Inf Process Syst. 2011; 24. https://doi.org/10.5555/2986459.2986743
49. 10.3389/feart.2023.111210510.3389/feart.2023.1112105 ↗
50. Wu J, Chen XY, Zhang H, et al. Hyperparameter optimization for machine learning models based on bayesian optimization. Journal of Electronic Science and Technology 2019; 17(1): 26–40. https://doi.org/10.11989/JEST.1674-862X.80904120
51. Ekanayake IU, Meddage DPP, Rathnayake U. A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Stud Constr Mater 2022; 16: e01059. https://doi.org/10.1016/j.cscm.2022.e01059
52. ScottLundberg M., Su-In L. 2017. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 4768–4777.