Scholarlink

<p>The key factors affecting the mechanical performance of FDM 3D printing output, an additive molding technology using polymeric materials, are the output conditions and the applied materials. Quantitative analysis of the effects of printing conditions and applied materials on the mechanical performance of printed parts requires a lot of effort, which can improve the mechanical performance of printed parts. In this study, a new approach that can secure reliability along with existing analysis methods was explored. A tensile test dataset and image dataset were prepared to analyze the mechanical properties of the output, and machine learning algorithms were applied to develop a prediction model for the mechanical properties of the output. The custom machine learning model developed by PCA, LSTM, and CNN-based machine learning algorithms showed mechanical property prediction results close to the actual experimental results. From this, this study presented a machine learning algorithm for mechanical property analysis of FDM 3D printing output and reliability improvement in engineering fields that can be developed in the future. The results of this study are of great significance in the field of 3D printing, which requires a commercialized mechanical performance analysis methodology based on high accuracy and consistency.</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

Development of machine learning models for material classification and prediction of mechanical properties of FDM 3D printing outputs

  • 期刊论文

  • 发表日期：

    2025年1月31日

查看全文
  • Su-Hyun Kim,
  • Ji-Hye Park,
  • Ji-Young Park,
  • Seung-Gwon Kim,
  • Young-Jun Lee,
  • Joo-Hyung Kim

摘要

The key factors affecting the mechanical performance of FDM 3D printing output, an additive molding technology using polymeric materials, are the output conditions and the applied materials. Quantitative analysis of the effects of printing conditions and applied materials on the mechanical performance of printed parts requires a lot of effort, which can improve the mechanical performance of printed parts. In this study, a new approach that can secure reliability along with existing analysis methods was explored. A tensile test dataset and image dataset were prepared to analyze the mechanical properties of the output, and machine learning algorithms were applied to develop a prediction model for the mechanical properties of the output. The custom machine learning model developed by PCA, LSTM, and CNN-based machine learning algorithms showed mechanical property prediction results close to the actual experimental results. From this, this study presented a machine learning algorithm for mechanical property analysis of FDM 3D printing output and reliability improvement in engineering fields that can be developed in the future. The results of this study are of great significance in the field of 3D printing, which requires a commercialized mechanical performance analysis methodology based on high accuracy and consistency.