journal article·2026-02-13Open access

A small-sample multiaxial fatigue life prediction method for titanium alloys based on a parameter fusion model

Jiao Li, Qi Li, Feng Wang, Mingshan Lou, Liuxiangzi Yang

Materials Research Express· Volume 13· Issue 3

Abstract

Abstract A physics data fusion driven strategy for estimating the multiaxial fatigue life of titanium alloys is proposed. Using TC4 titanium alloy as the research subject, multiaxial fatigue experiments are performed and a physical framework is created by adopting von-Mises equivalent strain as the damage indicator. A Backpropagation (BP) neural network is then developed in which phase difference, normal strain amplitude, shear strain amplitude, normal stress amplitude, shear stress amplitude, and von-Mises equivalent strain serve as inputs, while the life predicted by the physical framework serves as the output. The connection weights between the hidden layer and the output layer of the neural network are subsequently refined through measured fatigue life data to form a parameter fusion model. By using the measured fatigue life as the reference, the predictive performance of the physical framework, the neural network, and the parameter fusion scheme is evaluated. The results reveal that the parameter fusion architecture achieves a substantial improvement in predictive accuracy compared with the single physical framework or the BP neural network, with every predicted life value remaining inside the twofold scatter zone of the experimental results. This approach integrates the foundational understanding of physical behavior with the adaptive learning abilities of data centered models, provides a promising route for reliable multiaxial fatigue life estimation of titanium alloys under limited sample conditions, and contributes theoretical value for fatigue resistant design of titanium alloy structural elements.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Fatigue and fracture mechanics · Titanium Alloys Microstructure and Properties · High Temperature Alloys and Creep

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (28)

Show source-provided references
1. Additive manufacturing of titanium alloys: processability, properties, and applications10.1002/adem.202301122 ↗
2. Classification and applications of titanium and its alloys: a review10.1016/j.jacomc.2024.100019 ↗
3. Fatigue failure mechanism of Ti60 titanium alloy in HCF and VHCF regime at different temperatures10.1016/j.engfailanal.2023.107393 ↗
4. High-temperature failure mechanism and defect sensitivity of TC17 titanium alloy in high cycle fatigue10.1016/j.jmst.2022.01.010 ↗
5. A new method for predicting workpiece fatigue life based on segmentation features of titanium alloy surface morphology10.1007/s10845-024-02538-5 ↗
6. Fusing image and physical data for fatigue life prediction of nickel-based single crystal superalloys10.1016/j.engfailanal.2024.108343 ↗
7. A new multiaxial fatigue life prediction model for aircraft aluminum alloy10.1016/j.ijfatigue.2020.105993 ↗
8. High cycle fatigue life prediction on TC4 titanium alloy after overload treatment10.1016/j.ijfatigue.2022.107095 ↗
9. Multiaxial fatigue life prediction for titanium alloy TC4 under proportional and nonproportional loading10.1016/j.ijfatigue.2013.08.028 ↗
10. Probabilistic framework for multiaxial LCF assessment under material variability10.1016/j.ijfatigue.2017.06.019 ↗
11. Load path sensitivity and multiaxial fatigue life prediction of metals under non-proportional loadings10.1016/j.ijfatigue.2022.107281 ↗
12. A theory for the effect of mean stress on fatigue of metals under combined torsion and axial load or bending10.1115/1.4008327 ↗
13. A critical plane approach to multiaxial fatigue damage including out-of-phase loading10.1111/j.1460-2695.1988.tb01169.x ↗
14. Data-driven machine learning approach for predicting dwell fatigue life in two classes of Titanium alloys10.1016/j.engfracmech.2024.110214 ↗
15. Low cycle fatigue life prediction of titanium alloy using genetic algorithm-optimized BP artificial neural network10.1016/j.ijfatigue.2023.107609 ↗
16. Machine learning-based fatigue life prediction of lamellar titanium alloys: a microstructural perspective10.1016/j.engfracmech.2024.110106 ↗
17. A multi-algorithm integration machine learning approach for high cycle fatigue prediction of a titanium alloy in aero-engine10.1016/j.engfracmech.2023.109485 ↗
18. A generalization ability enhanced image recognition based multiaxial fatigue life prediction method for complex loading conditions10.1016/j.engfracmech.2023.109802 ↗
19. A novel method of multiaxial fatigue life prediction based on deep learning10.1016/j.ijfatigue.2021.106356 ↗
20. A fatigue life prediction framework of laser-directed energy deposition Ti-6A1-4V based on physics-informed neural network10.1108/IJSI-10-2024-0170 ↗
21. Data-driven and continuum damage mechanics-based approach for predicting fatigue life in additive manufacturing10.19636/j.cnki.cjsm42-1250/o3.2024.010 ↗
22. Study on impact fatigue test and life prediction method of TC18 titanium alloy10.1016/j.ijfatigue.2022.107391 ↗
23. Low-cycle fatigue parameters and fatigue life estimation of high-strength steels with artificial neural networks10.1111/ffe.13847 ↗
24. Some analytical expressions to measure the accuracy of the ‘equivalent von Mises stress’ in vibration multiaxial fatigue10.1016/j.jsv.2014.04.047 ↗
25. Fatigue life and experimental study of high-temperature bellows based on the improved Manson-Coffin equation10.1016/j.ijpvp.2024.105216 ↗
26. New neural network-based algorithm for predicting fatigue life of aluminum alloys in terms of machining parameters10.1016/j.engfailanal.2023.107128 ↗
27. Fatigue of carbon cord-rubber composites: effect of frequency, R ratio and lifetime prediction using constant life models10.1016/j.ijfatigue.2020.105558 ↗
28. Improving fatigue life prediction of natural rubber using a physics-informed neural network model10.1111/ffe.14533 ↗