Characterisation and prediction of mechanical properties in laser powder bed fusion-printed parts: a comparative analysis using machine learning DOI Creative Commons
Naol Dessalegn Dejene, Hirpa G. Lemu

Materials Technology, Год журнала: 2024, Номер 39(1)

Опубликована: Окт. 25, 2024

This study investigates the effects of process parameters including scanning strategy, build orientation, and hatching distance on mechanical properties AlSi10Mg parts produced by Laser Powder Bed Fusion (L-PBF). The experiment varied these within defined ranges used statistical analysis to evaluate their impact tensile strength ductility. Results showed that strategy had greatest influence, followed distance, while orientation affected anisotropic properties. Microstructural clear correlation between conditions strength, thereby showing underlying mechanisms govern material behavior. Moreover, Machine learning models, Random Forest Regression (RFR), Support Vector (SVR), Artificial Neural Networks (ANNs), were applied predict ductility characteristics. RFR SVR outperformed ANNs, high predictive accuracy with limited datasets. These findings emphasize importance optimizing L-PBF minimize anisotropy achieve consistent in parts.

Язык: Английский

Effects of Scanning Strategies, Part Orientation, and Hatching Distance on the Porosity and Hardness of AlSi10Mg Parts Produced by Laser Powder Bed Fusion DOI Creative Commons
Naol Dessalegn Dejene, Wakshum Mekonnen Tucho, Hirpa G. Lemu

и другие.

Journal of Manufacturing and Materials Processing, Год журнала: 2025, Номер 9(3), С. 78 - 78

Опубликована: Фев. 27, 2025

Laser powder bed fusion (L-PBF) shows potential in metal additive manufacturing for producing complex components. However, achieving ideal hardness and minimizing porosity poses a significant challenge. This study explores the impact of part orientation, scanning methods, hatching distance on AlSi10Mg alloy produced through L-PBF. Utilizing Box–Behnken design experiments (DOE), cubic samples were systematically produced. Hardness was quantitatively assessed using Vickers tests, while measurements involved 2D image analysis polished electron microscopy (SEM) samples, percentages analyzed ImageJ software. The results demonstrate that both strategy significantly influence porosity. spiral pattern notably enhances reduces In contrast, bidirectional lower more pronounced formations. An inverse correlation between grain size distribution observed, with finer sizes leading to higher values, indicating refinement improves mechanical properties. Additionally, negative relationship established, emphasizing importance enhance material hardness. These findings contribute overall understanding L-PBF process, providing valuable insights optimizing properties ensuring integrity high-performance parts.

Язык: Английский

Процитировано

0
Data-Driven Based Prediction and Optimization of Balling Levels in Laser Powder Bed Fusion Additive Manufacturing DOI Open Access

He Qiu,

Guozhang Jiang, Xin Lin

и другие.

Materials, Год журнала: 2025, Номер 18(9), С. 1949 - 1949

Опубликована: Апрель 25, 2025

Laser powder bed fusion has been demonstrated as a promising additive manufacturing technology due to its unique advantages, such weight reduction, the ability produce arbitrarily complex geometries and single-step manufacturing. However, production quality may deteriorate poor surface of deposited layers caused by occurrence balling phenomenon, which hampers widespread application. In this work, data-driven framework is proposed optimize process parameters laser achieve satisfactory levels. The effects key on levels are also investigated. Specifically, an image segmentation-based method introduced quantitatively evaluate interlayer surfaces as-built specimens under various parameter combinations. Considering limited amount experimental data, different machine learning models, including polynomial regression, support vector backpropagation neural networks, developed predict within predefined space. predicted values from best-performing model then used fitness individuals in improved genetic algorithm search for globally optimal parameters. final validation experiments confirm that parts fabricated using optimized exhibit minimal levels, demonstrating effectiveness feasibility level prediction optimization. This study provides valuable insights practical guidance enhancing produced process.

Язык: Английский

Процитировано

0
Characterisation and prediction of mechanical properties in laser powder bed fusion-printed parts: a comparative analysis using machine learning DOI Creative Commons
Naol Dessalegn Dejene, Hirpa G. Lemu

Materials Technology, Год журнала: 2024, Номер 39(1)

Опубликована: Окт. 25, 2024

This study investigates the effects of process parameters including scanning strategy, build orientation, and hatching distance on mechanical properties AlSi10Mg parts produced by Laser Powder Bed Fusion (L-PBF). The experiment varied these within defined ranges used statistical analysis to evaluate their impact tensile strength ductility. Results showed that strategy had greatest influence, followed distance, while orientation affected anisotropic properties. Microstructural clear correlation between conditions strength, thereby showing underlying mechanisms govern material behavior. Moreover, Machine learning models, Random Forest Regression (RFR), Support Vector (SVR), Artificial Neural Networks (ANNs), were applied predict ductility characteristics. RFR SVR outperformed ANNs, high predictive accuracy with limited datasets. These findings emphasize importance optimizing L-PBF minimize anisotropy achieve consistent in parts.

Язык: Английский

Процитировано

3