Page 45 - IJAMD-1-1

International Journal of AI
for Material and Design ML for quality improvement in L-PBF

achieved competitive accuracy, there remains uncertainty Conflict of interest
regarding the model’s performance when transferred
to different platforms or devices. To mitigate this issue, The authors declare that they have no competing interests.
standardizing data acquisition and processing formats are Author contributions
crucial for facilitating the sharing of 3D printing data within
the AM community, thereby improving ML training. Conceptualization: All authors
19
Furthermore, fostering the development of ML models Writing – original draft: Jiayi Zhang, Ce Yin, Yiyang Xu
with greater transferability and universality is important, Writing – review & editing: All authors
enabling adaptation to various manufacturing conditions
and materials. This approach allows manufacturers to Ethics approval and consent to participate
apply these models more widely and not confined to Not applicable.
specific contexts.
In the in situ monitoring scenario, the accomplishment Consent for publication
of simple classification and regression tasks involving Not applicable.
predicting the existence of defects and quality levels using
ML algorithms has achieved high accuracy. However, Availability of data
there is a notable scarcity of studies exploring multi-defect Not applicable.
classification or more precise quality prediction. Meanwhile,
the application of more advanced ML methods remains References
underexplored, which could further improve the accuracy 1. Bhavar V, Kattire P, Patil V, Khot S, Gujar K, Singh R.
or complete complex tasks. 77,78 Concerning parameter A review on powder bed fusion technology of metal additive
optimization, to gain a more comprehensive understanding manufacturing. In: Additive Manufacturing Handbook.
of the relationship between process parameters and product United States, CRC Press 2017, p251-253.
quality, a multi-scale modeling approach can be introduced doi: 10.1201/9781315119106-15
based on current research findings. By integrating the
impacts of various process parameters, this approach offers 2. Buchanan C, Gardner L. Metal 3D Printing in construction:
a deeper insight into the printing process, enabling finer A review of methods, research, applications, opportunities
optimization for efficient and high-precision production. 79 and challenges. Eng Struct. 2019;180:332-348.
doi: 10.1016/j.engstruct.2018.11.045
5. Conclusion
3. Sing SL. Perspectives on additive manufacturing enabled
This article explores the applications of ML in L-PBF for beta-titanium alloys for biomedical applications. Int J
quality improvement. It presents a thorough and easily Bioprint. 2022;8(1):478.
comprehensible introduction to ML. Different methods doi: 10.18063/ijb.v8i1.478
and works related to process optimization and in situ 4. Frazier WE. Metal additive manufacturing: A review.
monitoring for quality improvement are highlighted. J Mater Eng Perform. 2014;23:1917-1928.
Current obstacles in the ML application for quality
improvement in L-PBF are discussed, drawing insights doi: 10.1007/s11665-014-0958-z
from reviewed works. Adopting ML methods in process 5. Guo N, Leu MC. Additive manufacturing: Technology,
optimization and in situ monitoring has demonstrated applications and research needs. Front Mech Eng.
great potential for achieving more precise and efficient 2013;8:215-243.
quality control, thereby improving the quality of the doi: 10.1007/s11465-013-0248-8
manufactured parts. In addition, this integration lays a
foundation for closed-loop control systems. 6. Gu D, Shen Y. Effects of dispersion technique and
component ratio on densification and microstructure of
Acknowledgments multi-component cu-based metal powder in direct laser
sintering. J Mater Process Technol. 2007;182(1-3):564-573.
The authors acknowledge the support of the National doi: 10.1016/j.jmatprotec.2006.09.026
University of Singapore for providing the research resources.
7. Yap CY, Chua CK, Dong ZL, et al. Review of selective laser
Funding melting: Materials and applications. Appl Physics Rev.
2015;2(4):041101.
This study is supported by the Singapore Ministry of
Education Academic Research Fund Tier 1 (Award No.: doi: 10.1063/1.4935926
22-3721-A0001 and 22-4901-A0001). 8. Li R, Liu J, Shi Y, Du M, Xie Z. 316L stainless steel with

Volume 1 Issue 1 (2024) 39 https://doi.org/10.36922/ijamd.2301