Scholarlink

<p>The problem of predicting the breaking force of composite samples for tensile, compressive, and shear deformations is considered. The strength behavior patterns of thin-walled samples depending on fiber orientation and sample geometric characteristics are investigated. Cluster analysis methods and Kohonen self-organizing maps are used to reduce the dimensionality of the data and identify dependences. The predictive powers of machine learning models are comparatively analyzed.</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

Prediction of Carbon−Epoxide Composite Characteristics Based on Machine Learning Models

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • V. I. Pimenov,
  • I. A. Nebaev,
  • I. V. Pimenov

摘要

The problem of predicting the breaking force of composite samples for tensile, compressive, and shear deformations is considered. The strength behavior patterns of thin-walled samples depending on fiber orientation and sample geometric characteristics are investigated. Cluster analysis methods and Kohonen self-organizing maps are used to reduce the dimensionality of the data and identify dependences. The predictive powers of machine learning models are comparatively analyzed.