Scholarlink

<p>This research investigates the effects of various 3D-printing parameters on surface finish, material density, and tensile strength by applying machine learning techniques. As additive manufacturing continues to evolve, optimizing process parameters has become essential for achieving high-quality prints with consistent mechanical properties. This study systematically examined the influence of parameters such as layer height, infill percentage, and print speed, which impact print quality and material integrity. Multiple predictive models were employed, including linear regression, K-neighbors regressor, random forest regressor, and XGB regressor, to assess each parameter’s contribution to the overall print outcomes. The models were trained and validated on a dataset of samples with varying parameter configurations. Performance was evaluated using metrics such as mean squared error (MSE) and root mean squared error (RMSE). The evaluation revealed that the XGB regressor model outperformed the others, achieving an MSE of 0.799 and an RMSE of 0.826, indicating a solid predictive capability and suitability for parameter optimization in 3D printing. To further interpret the results, visualized the relationships between actual and predicted values, which provided a clearer understanding of how each parameter, individually and in combination, affects surface finish, density, and tensile strength. The findings underscore that layer height and print speed are primary factors influencing surface finish and material density, while infill percentage has a more pronounced impact on tensile strength. In addition, the study explores the potential trade-offs in parameter settings, such as balancing print speed with material integrity, which is critical for different applications in sectors such as prototyping, medical, and aerospace. This study offers valuable insights for optimizing 3D-printing parameters using machine learning models, contributing to enhanced reliability, improved product quality, and paving the way for automated and precision-driven additive manufacturing advancements.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A machine learning approach to refining surface quality and material durability in additive manufacturing

  • 期刊论文

  • 发表日期：

    2025年3月27日

查看全文
  • Siva Surya Mulugundam,
  • S. K. Gugulothu,
  • M. Varshith

摘要

This research investigates the effects of various 3D-printing parameters on surface finish, material density, and tensile strength by applying machine learning techniques. As additive manufacturing continues to evolve, optimizing process parameters has become essential for achieving high-quality prints with consistent mechanical properties. This study systematically examined the influence of parameters such as layer height, infill percentage, and print speed, which impact print quality and material integrity. Multiple predictive models were employed, including linear regression, K-neighbors regressor, random forest regressor, and XGB regressor, to assess each parameter’s contribution to the overall print outcomes. The models were trained and validated on a dataset of samples with varying parameter configurations. Performance was evaluated using metrics such as mean squared error (MSE) and root mean squared error (RMSE). The evaluation revealed that the XGB regressor model outperformed the others, achieving an MSE of 0.799 and an RMSE of 0.826, indicating a solid predictive capability and suitability for parameter optimization in 3D printing. To further interpret the results, visualized the relationships between actual and predicted values, which provided a clearer understanding of how each parameter, individually and in combination, affects surface finish, density, and tensile strength. The findings underscore that layer height and print speed are primary factors influencing surface finish and material density, while infill percentage has a more pronounced impact on tensile strength. In addition, the study explores the potential trade-offs in parameter settings, such as balancing print speed with material integrity, which is critical for different applications in sectors such as prototyping, medical, and aerospace. This study offers valuable insights for optimizing 3D-printing parameters using machine learning models, contributing to enhanced reliability, improved product quality, and paving the way for automated and precision-driven additive manufacturing advancements.