Additive Manufacturing Section Image Features for Magnetic Processing Characteristics Prediction

Abstract:

Metal additive manufacturing encompasses multiple techniques, among which Selective Laser Melting (SLM) is extensively employed for fabricating highly complex, precise, and uniquely shaped metal parts. However, obtaining accurate product characteristics often requires complex experimentation, which can potentially damage the products. Thus, there is a need to develop an automated method for predicting product characteristics. To forecast these attributes, details related to metal additive manufacturing products were documented, including process parameters and textural features. These features were extracted from product’s longitudinal sectional images and layer-by-layer images, using the gray-level co-occurrence matrix (GLCM). Subsequently, machine learning (ML) models such as Support Vector Regression (SVR), XGBoost, and LightGBM were employed to predict product properties and compare their performance. The experimental results indicated stronger correlations between process parameters and textural features in longitudinal section images compared to layer-by-layer ones. Moreover, the models demonstrated high predictive accuracy, particularly XGBoost and LightGBM, with R² score approaching 0.9 for all properties. These findings highlight the superiority and feasibility of the proposed approach. Furthermore, this method shows potential for accurately predicting a variety of product properties, fulfilling the needs of multiple application scenarios.

• Periodical: Key Engineering Materials (Volume 1016)
• Pages: 99-104
• DOI: https://doi.org/10.4028/p-1yH6uE
• Online since: June 2025
• Authors: Lien Kai Chang, Tsung Wei Chang, Jhih Cheng Huang, De Qian Liu, Mi Ching Tsai, Ming Huwi Horng*
• Keywords: Feature Selection, Gray-Level Co-Occurrence Matrix, Image Processing, Machine Learning, Metal Additive Manufacturing, Property Prediction

References

[1] Felice, I. O., Shen, J., Barragan, A. F. C., Moura, I. A. B., Li, B., Wang, B., Khodaverdi, H., Mohri, M., Schell, N., Ghafoori, E., Santos, T. G., & Oliveira, J. P. (2023). Wire and arc additive manufacturing of Fe-based shape memory alloys: Microstructure, mechanical and functional behavior. *Materials & Design, 231, 112004.

DOI: 10.1016/j.matdes.2023.112004

[2] Marques, D. A., Oliveira, J. P., & Baptista, A. C. (2023). A Short Review on the Corrosion Behaviour of Wire and Arc Additive Manufactured Materials. Metals, 13(4), 641.

DOI: 10.3390/met13040641

[3] Hamilton, R.F., Bimber, B. A., & Palmer, T. A. (2018). Correlating microstructure and superelasticity of directed energy deposition additive manufactured Ni-rich NiTi alloys. Journal of Alloys and Compounds, 739, 712-722.

DOI: 10.1016/j.jallcom.2017.12.270

[4] Wang, C., Tan, X. P., Du, Z., Chandra, S., Sun, Z., Lim, C. W. J., Tor, S. B., Lim, C. S., & Wong, C. H. (2019). Additive manufacturing of NiTi shape memory alloys using pre-mixed powders. Journal of Materials Processing Technology, 271, 152-161.

DOI: 10.1016/j.jmatprotec.2019.03.025

[5] Li, B., Wang, L., Wang, B., Li, D., Oliveira, J. P., Cui, R., Yu, J., Luo, L., Chen, R., Su, Y., Guo, J., & Fu, H. (2022). Electron beam freeform fabrication of NiTi shape memory alloys: Crystallography, martensitic transformation, and functional response. Materials Science and Engineering: A, 843, 143135.

DOI: 10.1016/j.msea.2022.143135

[6] Chang, L.-K., Chen, R.-S., Tsai, M.C, Lee, R.-M, Lin, C.-C., Chang T. -W., Horng, M.-H. (2024). Machine learning applied to property prediction of metal additive manufacturing products with texture features extraction. The International Journal of Advanced Manufacturing Technology. Vol. 32, 83-98.

DOI: 10.1007/s00170-024-13165-y

[7] Su, X., Yan, X., & Tsai, C. L. (2012). Linear regression. Wiley Interdisciplinary Reviews: Computational Statistics, 4(3), 275-294.

[8] Awad, M., Khanna, R., Awad, M., & Khanna, R. (2015). Support vector regression. Efficient learning machines: Theories, Concepts, and Applications for Engineers and System Designers, 67-80.

DOI: 10.1007/978-1-4302-5990-9_4

[9] Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.  785-794.

DOI: 10.1145/2939672.2939785

[10] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, 30 (NIPS 2017).

[11] Karna, S. K., & Sahai, R. (2012). An overview on Taguchi method. International Journal of Engineering and Mathematical Sciences, 1(1), 1-7.