Fatigue life prediction based on a deep learning method for Ti-6Al-4V fabricated by laser powder bed fusion up to very-high-cycle fatigue regime

Jia, Yumeng; Fu, Rui; Ling, Chao; Zheng, Shuilin; Zheng, Liang; Zhong, Zheng; Hong, Youshi

doi:10.1016/j.ijfatigue.2023.107645

Cited by 25 publications

(2 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Bao et al [ 13 ] adopted a machine learning method to explore the influence of defect parameters on the fatigue life of selective laser-melted Ti-6Al-4 V alloy, achieving high coefficients of determination. Most recently, Jia et al [ 14 ] examined the fatigue behavior of titanium alloys fabricated by laser powder bed fusion, particularly in very-high-cycle fatigue regimes. They developed a deep-belief neural network for predicting the fatigue life of such alloys.…”

Section: Overview and Analysis Of Existing Approaches And Estimation ...mentioning

confidence: 99%

Estimation of Cyclic Stress–Strain Curves of Steels Based on Monotonic Properties Using Artificial Neural Networks

2023

View full text Add to dashboard Cite

This paper introduces a novel method for estimating the cyclic stress–strain curves of steels based on their monotonic properties and plastic strain amplitudes, utilizing artificial neural networks (ANNs). ANNs were trained on a substantial number of experimental data for steels, collected from relevant literature, and divided into subgroups according to alloying elements content (unalloyed, low-alloy, and high-alloy steels). Only monotonic properties that were proven to be relevant for the estimation of points on the stress–strain curve were used. The performance of the developed ANNs was assessed using an independent set of data, and the results were compared to experimental values, values obtained by existing empirical estimation methods, and by previously developed ANNs. The results showed that the new approach which combines relevant monotonic properties and plastic strain amplitudes as inputs to ANNs for cyclic stress–strain curve estimation is better than the previously used approach where ANNs estimate the parameters of the Ramberg–Osgood material model separately. This shows that a more favorable approach to the estimation of cyclic stress–strain behavior would be to directly estimate corresponding material curves using monotonic properties. Additionally, this may also reduce inaccuracies resulting from simplified representations of the actual material behavior inherent in the material model.

show abstract

Section: Overview and Analysis Of Existing Approaches And Estimation ...mentioning

confidence: 99%

Estimation of Cyclic Stress–Strain Curves of Steels Based on Monotonic Properties Using Artificial Neural Networks

2023

View full text Add to dashboard Cite

show abstract

“…The predominant titanium alloy in the AM industry, Ti-6Al-4V (Ti64), is manufactured in powder form by multiple producers in numerous grades and with a wide range of particle sizes. Ti64 processed by PBF-LB demonstrates high fatigue resistance [16] and, when presented in the scaffold form, exhibits a Young's modulus comparable to that of human bone [17]. Ti64 is the leading metallic material commercially employed for the custom and serial production of implants using AM technologies [18].…”

Section: Introductionmentioning

confidence: 99%

Mechanical Properties of Ti Grade 2 Manufactured Using Laser Beam Powder Bed Fusion (PBF-LB) with Checkerboard Laser Scanning and In Situ Oxygen Strengthening

Wysocki,

Chmielewska-Wysocka,

Maj

et al. 2024

Crystals

View full text Add to dashboard Cite

Additive manufacturing (AM) technologies have advanced from rapid prototyping to becoming viable manufacturing solutions, offering users both design flexibility and mechanical properties that meet ISO/ASTM standards. Powder bed fusion using a laser beam (PBF-LB), a popular additive manufacturing process (aka 3D printing), is used for the cost-effective production of high-quality products for the medical, aviation, and automotive industries. Despite the growing variety of metallic powder materials available for the PBF-LB process, there is still a need for new materials and procedures to optimize the processing parameters before implementing them into the production stage. In this study, we explored the use of a checkerboard scanning strategy to create samples of various sizes (ranging from 130 mm3 to 8000 mm3 using parameters developed for a small 125 mm3 piece). During the PBF-LB process, all samples were fabricated using Ti grade 2 and were in situ alloyed with a precisely controlled amount of oxygen (0.1–0.4% vol.) to enhance their mechanical properties using a solid solution strengthening mechanism. The samples were fabricated in three sets: I. Different sizes and orientations, II. Different scanning strategies, and III. Rods for high-cycle fatigue (HCF). For the tensile tests, micro samples were cut using WEDM, while for the HCF tests, samples were machined to eliminate the influence of surface roughness on their mechanical performance. The amount of oxygen in the fabricated samples was at least 50% higher than in raw Ti grade 2 powder. The O2-enriched Ti produced in the PBF-LB process exhibited a tensile strength ranging from 399 ± 25 MPa to 752 ± 14 MPa, with outcomes varying based on the size of the object and the laser scanning strategy employed. The fatigue strength of PBF-LB fabricated Ti was 386 MPa, whereas the reference Ti grade 2 rod samples exhibited a fatigue strength of 312 MPa. Our study revealed that PBF-LB parameters optimized for small samples could be adapted to fabricate larger samples using checkerboard (“island”) scanning strategies. However, some additional process parameter changes are needed to reduce porosity.

show abstract

Intelligent laser-based metal additive manufacturing: A review on machine learning for process optimization and property prediction

Moradi,

Tajalli,

Mosallanejad

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Fatigue life prediction based on a deep learning method for Ti-6Al-4V fabricated by laser powder bed fusion up to very-high-cycle fatigue regime

Cited by 25 publications

References 61 publications

Estimation of Cyclic Stress–Strain Curves of Steels Based on Monotonic Properties Using Artificial Neural Networks

Estimation of Cyclic Stress–Strain Curves of Steels Based on Monotonic Properties Using Artificial Neural Networks

Mechanical Properties of Ti Grade 2 Manufactured Using Laser Beam Powder Bed Fusion (PBF-LB) with Checkerboard Laser Scanning and In Situ Oxygen Strengthening

Intelligent laser-based metal additive manufacturing: A review on machine learning for process optimization and property prediction

Contact Info

Product

Resources

About