journal article·2025-05-01Open access

A method of fatigue life prediction for rubber materials based on convolutional neural network

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

Materials Research Express· Volume 12· Issue 5

Abstract

Abstract Studies show that mechanical load, ambient temperature, and material hardness significantly influence the fatigue life of rubber materials. The current physical models based on crack initiation methods face challenges in comprehensively addressing the combined effects of these factors on the fatigue life of rubber materials. Meanwhile, data-driven models such as back-propagation neural networks (BPNN) or support vector machines (SVM) are often constrained by limited dataset sizes and uncertainties in model parameters, leading to low prediction accuracy for fatigue life. Aiming at resolving these limitations, a novel fatigue life prediction approach for rubber materials utilizing convolutional neural networks (CNN) was introduced. Dumbbell-shaped rubber specimens, vulcanized from rubber materials, were subjected to uniaxial tensile fatigue tests under varying temperatures, hardness levels, and load conditions. Using the obtained fatigue test data, a CNN model was developed, incorporating environmental temperature, material hardness, and peak engineering strain as input features, with the corresponding measured fatigue life of rubber materials as the output. The prediction performance of the CNN model was then evaluated against physical models, BPNN, and SVM models. Comparative analysis using the measured fatigue life as a reference revealed that the CNN model achieved superior predictive accuracy. The predicted fatigue lives consistently fell within the 1.5 times dispersion range of the experimental values.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Engineering Diagnostics and Reliability · Advanced machining processes and optimization · Transport Systems and Technology

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

References (29)

Show source-provided references
1. Static and dynamic properties of eggshell filled rubber materials composites for potential application in automotive vibration isolation and damping10.1016/j.jclepro.2022.131656 ↗
2. Accelerated fatigue bench test method for rubber vibration isolators based on load spectrum compilation10.1177/09544070241256426 ↗
3. A unified probabilistic fatigue life prediction model for rubber materials components considering strain ratio effect10.1111/ffe.13941 ↗
4. Viscoelastic properties of rubber materials with fatigue damage10.1016/j.ijfatigue.2021.106344 ↗
5. Probabilistic fatigue life prediction model of rubber materials components based on the expanded sample data10.1016/j.ijfatigue.2022.107034 ↗
6. Residual fatigue life prediction of rubber materials components under variable amplitude loads10.1016/j.ijfatigue.2022.107199 ↗
7. Fatigue crack growth analysis of different adhesive systems: effects of mode mixity and load level10.1111/ffe.13145 ↗
8. FE and probabilistic analysis for rubber life estimation considering cracking energy density as a fatigue predictor10.1177/09673911231202377 ↗
9. Prediction of actual fatigue test temperature and isothermal fatigue life curves for non-crystallising rubber under fully relaxing uni-axial loading conditions10.1016/j.ijfatigue.2021.106622 ↗
10. Research progress on fatigue life of rubber materials10.3390/polym14214592 ↗
11. Multiscale stress deconcentrating amplifies fatigue resistance of rubber10.1038/s41586-023-06782-2 ↗
12. Recent advances on fatigue of rubber after the literature survey by Mars and Fatemi in 2002 and 200410.1016/j.ijfatigue.2018.01.007 ↗
13. A pattern recognition artificial neural network method for random fatigue loading life prediction10.1016/j.ijfatigue.2017.02.003 ↗
14. Low cycle fatigue and creep–fatigue interaction behavior of 316L (N) stainless steel and life prediction by artificial neural network approach10.1016/S0142-1123(03)00064-1 ↗
15. Modeling and simulation of low-cycle fatigue life of steel reinforcing bars using artificial neural network10.1016/j.jfranklin.2010.04.005 ↗
16. Fatigue strength prediction of Cobalt alloys using material composition and monotonic properties: ML-based approach10.1088/2053-1591/adc5c8 ↗
17. Prediction of the fatigue life of rubber materials composites by artificial neural network approaches10.1016/j.matdes.2013.12.044 ↗
18. Intelligent prediction of fatigue life of rubber materials considering strain ratio effect10.1111/ffe.13952 ↗
19. A first proposal for fatigue life prediction of carbon black filled natural rubber at different temperatures with an artificial neural network10.1111/str.70001 ↗
20. Prediction of rubber fatigue life using an assimilation-based learning approach and incremental crack propagation model10.1111/ffe.14495 ↗
21. Prediction of high-temperature mechanical properties of filled rubber based on the deep learning algorithm10.1002/pc.29302 ↗
22. Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit10.1016/j.measurement.2021.109166 ↗
23. Fatigue life prediction of rubber materials components using an artificial neural network10.1111/ffe.13690 ↗
24. A non-contact real-time strain measurement and control system for multiaxial cyclic/fatigue tests of polymer materials by digital image correlation method10.1016/j.polymertesting.2005.06.013 ↗
25. A method to develop a unified fatigue life prediction model for filled rubber materialss under uniaxial loads10.1111/ffe.12081 ↗
26. Fatigue life prediction for elastomeric structures10.5254/1.3548175 ↗
27. Experimental and analytical study on uniaxial compressive fatigue behavior of self-compacting rubber lightweight aggregate concrete10.1016/j.conbuildmat.2019.117623 ↗
28. Correlations between crack initiation and crack propagation lives of notched specimens under constant and variable amplitude loading10.1111/ffe.13549 ↗
29. Fatigue of carbon cord-rubber composites: effect of frequency, R ratio and life prediction using constant life models10.1016/j.ijfatigue.2020.105558 ↗