Artificial intelligence modeling of ultrasonic fatigue test to predict the temperature increase
Source abstract
Abstract
The temperature behavior in very high cycle fatigue (VHCF) testing as well as the influence of the intermittent loading is not completely understood. In many cases the high frequency causes the specimens to heat up and may interfere in the material's fatigue performance. In order to address this issue, this study proposed an experimental test with different stress levels and intermittent driving (pulse-pause) with the aid of non-destructive testing (NDT) using a thermography camera. Specimens were coated with black spray to improve the emissivity to 0.93 and conducted to fully reversed condition (R = −1) up to 107 cycles. A large amount of raw data of pulse, pause, stress amplitude, number of cycles and temperature were recorded. These raw data were used to develop tree-based machine learning models called extreme gradient boosting (XGBoost), capable of predicting the temperature throughout the VHCF tests. The result presented a high performance model with determination coefficients (R2) above 0.98, proving the model to be an important ally for ultrasonic fatigue tests. Additionally, Shapley additive explanation (SHAP) method was adopted to assist in the interpretation of the model results.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Fatigue and fracture mechanics · Thermography and Photoacoustic Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Bathias · 2005
2. The effect of frequency on the gigacycle fatigue properties of a Ti-6Al-4V alloy10.1111/j.1460-2695.2008.01257.x ↗
3. Analysis of temperature and fracture surface of AISI4140 steel in very high cycle fatigue regime10.1016/j.tafmec.2015.07.007 ↗
4. A Brief Review of the Application and Problems in Ultrasonic Fatigue Testing
5. The present situation and future problems in ultrasonic fatigue testing – Mainly reviewed on environmental effects and materials’ screening10.1016/j.ijfatigue.2005.04.019 ↗
6. Does loading frequency affect fatigue behavior of metallic materials?
7. The influential factors on very high cycle fatigue testing results10.1051/matecconf/201816520002 ↗
8. A review about the effects of structural and operational factors on the gigacycle fatigue of steels10.1111/ffe.12779 ↗
9. Maldague · 2001
10. Chen T, Guestrin C, XGBoost: A scalable tree boosting system. In: Proc ACM SIGKDD Int Conf Knowl Discov Data Min 201; 785–94.10.1145/2939672.2939785 ↗
11. Li P. Robust Logitboost and adaptive base class (ABC) Logitboost. In: Proceedings of the Twenty-Sixth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI’10); 2010. p. 302–11.
12. Pedregosa et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res 2011; 12: 2825–30.
13. Accelerating the Discovery of Materials for Clean Energy in the Era of Smart Automation10.1038/s41578-018-0005-z ↗
14. Fulfilling the Promise of the Materials Genome Initiative with High-Throughput Experimental Methodologies10.1063/1.4977487 ↗
15. Machine-Learning-Assisted Discovery of Polymers with High Thermal Conductivity Using a Molecular Design Algorithm10.1038/s41524-019-0203-2 ↗
16. Big Data Creates New Opportunities for Materials Research: A Review on Methods and Applications of Machine Learning for Materials Design
17. A machine-learning fatigue life prediction approach of additively manufactured metals10.1016/j.engfracmech.2020.107508 ↗
18. Machine learning-based predictions of fatigue life and fatigue limit for steels10.1016/j.jmst.2021.02.021 ↗
19. Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning10.3390/met10101349 ↗
20. Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters10.1186/2193-9772-3-8 ↗
21. An online tool for predicting fatigue strength of steel alloys based on ensemble data mining10.1016/j.ijfatigue.2018.04.017 ↗
22. Machine-learning-based investigation into the effect of defect/inclusion on fatigue behavior in steels10.1016/j.ijfatigue.2021.106597 ↗
23. Pore-affected fatigue life scattering and prediction of additively manufactured Inconel 718: An investigation based on miniature specimen testing and machine learning approach10.1016/j.msea.2020.140693 ↗
24. Machine learning based very-high-cycle fatigue life prediction of Ti-6Al-4V alloy fabricated by selective laser melting10.1016/j.ijfatigue.2022.106764 ↗
25. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach10.1016/j.engstruct.2020.110927 ↗
26. Explaining prediction models and individual predictions with feature contributions10.1007/s10115-013-0679-x ↗
27. Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls
28. Shimadzu Excellence in Science. Catalog C225-E036: Very High Cycle Fatigue Testing System USF – 2000A.
29. Kazymyrovych · 2009 · 22
30. Manson, WP, referred by [1]. For a detailed analysis see Manson, WP, Piezoeletric Crystals and their Application in Ultrasonics. New York: Van Nostrand:161.
31. Fault Diagnosis Method for Hydraulic Directional Valves Integrating PCA and XGBoost10.3390/pr7090589 ↗
32. Wade · 2020 · 310
33. Hyperparameter optimization for machine learning models based on Bayesian optimization
34. Prediction and analysis of train arrival delay based on XGBoost and Bayesian optimization10.1016/j.asoc.2021.107538 ↗
35. Random search for hyper-parameter optimization
36. Echo State network based soft sensor for Monitoring and Fault Detection of Industrial
37. Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization
38. Algorithms for Hyper-Parameter Optimization. Advances in Neural Information Processing Systems 24
39. Lundberg, Scott M., and Su-In Lee. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 201.
40. SHAP (Shapley Additive explanations), https://christophm.github.io/interpretable-ml-book/shap.html.