{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T10:50:40Z","timestamp":1784371840911,"version":"3.55.0"},"reference-count":42,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Science &amp; Technology Development Fund of Tianjin Education Commission for Higher Education","award":["2021KJ098"],"award-info":[{"award-number":["2021KJ098"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Materials"],"abstract":"<jats:p>This study established a machine learning framework to enhance the accuracy of very-high-cycle fatigue (VHCF) life prediction in selective laser melted Inconel 718 alloy by systematically comparing the use of generative adversarial networks (GANs) and variational auto-encoders (VAEs) for data augmentation. We quantified the influence of critical defect parameters (dimensions and stress amplitudes) extracted from fracture analyses on fatigue life and compared the performance of GANs versus VAEs in generating synthetic training data for three regression models (ANN, Random Forest, and SVR). The experimental fatigue data were augmented using both generative models, followed by hyperparameter optimization and rigorous validation against independent test sets. The results demonstrated that the GAN-generated data significantly improved the prediction metrics, with GAN-enhanced models achieving superior R2 scores (0.91\u20130.97 vs. 0.86 \u00b1 0.87) and lower MAEs (1.13\u20131.62% vs. 2.00\u20132.64%) compared to the VAE-based approaches. This work not only establishes GANs as a breakthrough tool for AM fatigue prediction but also provides a transferable methodology for data-driven modeling of defect-dominated failure mechanisms in advanced materials.<\/jats:p>","DOI":"10.3390\/ma18112604","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T03:57:18Z","timestamp":1748923038000},"page":"2604","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["High-Cycle Fatigue Life Prediction of Additive Manufacturing Inconel 718 Alloy via Machine Learning"],"prefix":"10.3390","volume":"18","author":[{"given":"Zongxian","family":"Song","sequence":"first","affiliation":[{"name":"School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinling","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Zhu","sequence":"additional","affiliation":[{"name":"Wheel Rail Center, Tianjin Research Institute for Advanced Equipment, Tsinghua University, Tianjin 300300, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiyan","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Materials Science and Engineering, Tianjin University, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3869-8734","authenticated-orcid":false,"given":"Yangyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingya","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angran","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.jmrt.2021.08.050","article-title":"Research status of laser additive manufacturing for metal: A review","volume":"15","author":"Gong","year":"2021","journal-title":"J. Mater. Res. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1016\/j.jmapro.2022.10.060","article-title":"An overview of modern metal additive manufacturing technology","volume":"84","author":"Armstrong","year":"2022","journal-title":"J. Manuf. Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106110","DOI":"10.1016\/j.ijrmhm.2023.106110","article-title":"Additive manufacturing of titanium alloys via selective laser melting: Fabrication, microstructure, post-processing, performance and prospect","volume":"111","author":"Lu","year":"2023","journal-title":"Int. J. Refract. Met. Hard Mater."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/j.jmapro.2023.10.024","article-title":"Revolutionizing manufacturing: A comprehensive overview of additive manufacturing processes, materials, developments, and challenges","volume":"107","author":"Kanishka","year":"2023","journal-title":"J. Manuf. Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1016\/j.jmrt.2023.07.196","article-title":"Crack initiation mechanisms and life prediction of GH4169 superalloy in the high cycle and very high cycle fatigue regime. cycle and very high cycle fatigue regime","volume":"26","author":"Qin","year":"2023","journal-title":"J. Mater. Res. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106920","DOI":"10.1016\/j.ijfatigue.2022.106920","article-title":"Correlations of fatigue strength of additively manufactured metals with hardness and defect size","volume":"162","author":"Derrick","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"100724","DOI":"10.1016\/j.pmatsci.2020.100724","article-title":"Defects in additive manufactured metals and their effect on fatigue performance: A state-of-the-art review","volume":"117","author":"Sanaei","year":"2021","journal-title":"Prog. Mater. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.ijfatigue.2008.09.001","article-title":"Very high cycle fatigue properties of bainitic high carbon-chromium steel","volume":"31","author":"Mayer","year":"2009","journal-title":"Int. J. Fatigue"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1016\/j.ijfatigue.2009.02.038","article-title":"Very high cycle fatigue properties of bainitic high carbon\u2013chromium steel under variable amplitude conditions","volume":"31","author":"Mayer","year":"2009","journal-title":"Int. J. Fatigue"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.actamat.2018.07.036","article-title":"Fatigue life and mechanistic modeling of interior micro-defect induced cracking in high cycle and very high cycle regimes","volume":"157","author":"Zhu","year":"2018","journal-title":"Acta Mater."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1016\/S0142-1123(02)00037-3","article-title":"Effect of inclusion on subsurface crack initiation and gigacycle fatigue strength","volume":"24","author":"Wang","year":"2002","journal-title":"Int. J. Fatigue"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/0142-1123(89)90054-6","article-title":"Quantitative evaluation of effects of non-metallic inclusions on fatigue strength of high strength steels. I: Basic fatigue mechanism and evaluation of correlation between the fatigue fracture stress and the size and location of non-metallic inclusions","volume":"11","author":"Murakami","year":"1989","journal-title":"Int. J. Fatigue"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"107917","DOI":"10.1016\/j.ijfatigue.2023.107917","article-title":"A data-physics integrated approach to life prediction in very high cycle fatigue regime","volume":"176","author":"Fan","year":"2023","journal-title":"Int. J. Fatigue"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107185","DOI":"10.1016\/j.ijmecsci.2022.107185","article-title":"The potency of defects on fatigue of additively manufactured metals","volume":"221","author":"Peng","year":"2022","journal-title":"Int. J. Mech. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"140693","DOI":"10.1016\/j.msea.2020.140693","article-title":"Pore-affected fatigue life scattering and prediction of additively manufactured Inconel 718: An investigation based on miniature specimen testing and machine learning approach","volume":"802","author":"Luo","year":"2021","journal-title":"Mater. Sci. Eng. A"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"109630","DOI":"10.1016\/j.engfracmech.2023.109630","article-title":"Data-driven approach to very high cycle fatigue life prediction","volume":"292","author":"Liu","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103860","DOI":"10.1016\/j.compind.2023.103860","article-title":"A transformed-feature-space data augmentation method for defect segmentation","volume":"147","author":"Niu","year":"2023","journal-title":"Comput. Ind."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109132","DOI":"10.1016\/j.ress.2023.109132","article-title":"An improved density peaks clustering algorithm based on k nearest neighbors and turning point for evaluating the severity of railway accidents","volume":"233","author":"Shi","year":"2023","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107850","DOI":"10.1016\/j.engfracmech.2021.107850","article-title":"Data-driven fatigue life prediction in additive manufactured titanium alloy: A damage mechanics based machine learning framework","volume":"252","author":"Zhan","year":"2021","journal-title":"Eng. Fract. Mech."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.1109\/TPAMI.2018.2868350","article-title":"Representation Learning by Rotating Your Faces","volume":"41","author":"Tran","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., and Tao, D. (2019, January 15). MirrorGAN: Learning Text-To-Image Generation by Redescription. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s12206-020-1202-4","article-title":"Remaining useful life prediction of planet bearings based on conditional deep recurrent generative adversarial network and action discovery","volume":"35","author":"Yu","year":"2021","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109559","DOI":"10.1016\/j.engfracmech.2023.109559","article-title":"Machine learning method for estimating the defect-related mechanical properties of additive manufactured alloys","volume":"291","author":"Wang","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"104779","DOI":"10.1016\/j.ijpvp.2022.104779","article-title":"Application of tabular data synthesis using generative adversarial networks on machine learning-based multiaxial fatigue life prediction","volume":"199","author":"He","year":"2022","journal-title":"Int. J. Press. Vessel. Pip."},{"key":"ref_25","first-page":"2672","article-title":"Generative adversarial nets","volume":"Volume 2","author":"Goodfellow","year":"2014","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"7335","DOI":"10.5194\/acp-19-7335-2019","article-title":"Temporal variations and trend of ground-level ozone based on long-term measurements in Windsor, Canada","volume":"19","author":"Xu","year":"2019","journal-title":"Atmos. Chem. Phys."},{"key":"ref_27","unstructured":"Patki, R.N., and Veeramachaneni, K. (2022, May 21). The Synthetic Data Vault, 2016. Available online: https:\/\/ieeexplore.ieee.org\/document\/7796926."},{"key":"ref_28","unstructured":"Choi, E., Biswal, S., Malin, B., Duke, J., Stewart, W., and Sun, J. (2017). Generating Multi-Label Discrete Patient Records Using Generative Adversarial Networks. arXiv."},{"key":"ref_29","unstructured":"Xu, L., and Veeramachaneni, K. (2018). Synthesising Tabular Data Using Generative Adversarial Networks. arXiv."},{"key":"ref_30","unstructured":"Kingma, D.P. (2022). Max Welling. Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_31","first-page":"9","article-title":"Ultra-high circumferential fatigue properties of Inconel718 nickel-based high-temperature alloy","volume":"40","author":"Yan","year":"2016","journal-title":"Mech. Eng. Mater."},{"key":"ref_32","first-page":"45","article-title":"High-temperature low-week fatigue damage mechanism of Inconel718 nickel-based high-temperature alloy","volume":"43","author":"Wang","year":"2019","journal-title":"Mech. Eng. Mater."},{"key":"ref_33","first-page":"25","article-title":"High-temperature low-frequency fatigue properties of Inconel718 nickel-based high-temperature alloy","volume":"40","author":"Yao","year":"2016","journal-title":"Mech. Eng. Mater."},{"key":"ref_34","unstructured":"Song, Z. (2021). Study on Ultra-High Circumferential Fatigue Fracture Mechanism of Inconel 718 Nickel-Based High Temperature Alloy Based on SLM Forming, Taiyuan University of Science and Technology."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"109709","DOI":"10.1016\/j.engfracmech.2023.109709","article-title":"A machine learning based approach with an augmented dataset for fatigue life prediction of additively manufactured Ti-6Al-4V samples","volume":"293","author":"Homola","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/S0893-6080(00)00077-0","article-title":"Optimal control by least squares support vector machines","volume":"14","author":"Suykens","year":"2001","journal-title":"Neural Netw."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107147","DOI":"10.1016\/j.ijfatigue.2022.107147","article-title":"Fatigue-life prediction of additively manufactured metals by continuous damage mechanics (CDM)-informed machine learning with sensitive features","volume":"164","author":"Wang","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_38","first-page":"519","article-title":"Prediction of fatigue life of powder metallurgy superalloy disk via machine learning","volume":"43","author":"Zhang","year":"2022","journal-title":"Foundry Technol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1016\/j.oregeorev.2015.01.001","article-title":"Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines","volume":"71","year":"2015","journal-title":"Ore Geol. Rev."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"106236","DOI":"10.1016\/j.ijfatigue.2021.106236","article-title":"A deep learning based life prediction method for components under creep, fatigue and creep-fatigue conditions","volume":"148","author":"Zhang","year":"2021","journal-title":"Int. J. Fatigue"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.engstruct.2018.05.122","article-title":"Remaining fatigue life assessment of in-service road bridge decks based upon artificial neural networks","volume":"171","author":"Fathalla","year":"2018","journal-title":"Eng. Struct."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4989","DOI":"10.1016\/j.eswa.2014.02.025","article-title":"Approximating support vector machine with artificial neural network for fast prediction","volume":"41","author":"Kang","year":"2014","journal-title":"Expert Syst. Appl."}],"container-title":["Materials"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1944\/18\/11\/2604\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:46:21Z","timestamp":1760031981000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1944\/18\/11\/2604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":42,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["ma18112604"],"URL":"https:\/\/doi.org\/10.3390\/ma18112604","relation":{},"ISSN":["1996-1944"],"issn-type":[{"value":"1996-1944","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,3]]}}}