기계학습을 활용한 3차원 적층제조용 알루미늄 합금 개발
Development of Aluminum Alloys for Additive Manufacturing Using Machine Learning
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The present study introduces a machine learning approach for designing new aluminum alloys tailored for directed energy deposition additive manufacturing, achieving an optimal balance between hardness and conductivity. Utilizing a comprehensive database of powder compositions, process parameters, and material properties, predictive models—including an artificial neural network and a gradient boosting regression model, were developed. Additionally, a variational autoencoder was employed to model input data distributions and generate novel process data for aluminum-based powders. The similarity between the generated data and the experimental data was evaluated using K-nearest neighbor classification and t-distributed stochastic neighbor embedding, with accuracy and the F1-score as metrics. The results demonstrated a close alignment, with nearly 90% accuracy, in numerical metrics and data distribution patterns. This work highlights the potential of machine learning to extend beyond multi-property prediction, enabling the generation of innovative process data for material design.
Abstract
The present study introduces a machine learning approach for designing new aluminum alloys tailored for directed energy deposition additive manufacturing, achieving an optimal balance between hardness and conductivity. Utilizing a comprehensive database of powder compositions, process parameters, and material properties, predictive models—including an artificial neural network and a gradient boosting regression model, were developed. Additionally, a variational autoencoder was employed to model input data distributions and generate novel process data for aluminum-based powders. The similarity between the generated data and the experimental data was evaluated using K-nearest neighbor classification and t-distributed stochastic neighbor embedding, with accuracy and the F1-score as metrics. The results demonstrated a close alignment, with nearly 90% accuracy, in numerical metrics and data distribution patterns. This work highlights the potential of machine learning to extend beyond multi-property prediction, enabling the generation of innovative process data for material design.