Scholarlink

<p>Traditional microhardness characterization of fine-blanked components is constrained by the discrete nature of physical indentation, limiting resolution of continuous mechanical gradients. This study investigates microstructural texture as an interpretable representation of local microhardness. Texture is quantified using Gabor filters, inspired by the human visual system, which decompose micrographs into orientation- and scale-specific components that capture physically meaningful structural patterns. These features are analyzed using Principal Component Analysis (PCA) and related to microhardness through a linear Principal Component Regression (PCR) framework. The linear structure of the model enables regression weights to be mapped back to specific image-space features, allowing direct interpretation of which microstructural patterns correspond to hardening and softening behavior. Results show that microstructural texture encodes both deformation state and material condition, enabling a transparent link between optical morphology and mechanical response. This provides a physically grounded approach for interpreting micrographs as spatially resolved indicators of microhardness beyond traditional indentation methods.</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

Interpretable mapping between microstructural texture and microhardness in fine-blanked steel

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月14日

查看全文
  • Zeya Yang,
  • Guijiang Du,
  • Haotian Liu,
  • Di Zhao,
  • Ziyan Luo

摘要

Traditional microhardness characterization of fine-blanked components is constrained by the discrete nature of physical indentation, limiting resolution of continuous mechanical gradients. This study investigates microstructural texture as an interpretable representation of local microhardness. Texture is quantified using Gabor filters, inspired by the human visual system, which decompose micrographs into orientation- and scale-specific components that capture physically meaningful structural patterns. These features are analyzed using Principal Component Analysis (PCA) and related to microhardness through a linear Principal Component Regression (PCR) framework. The linear structure of the model enables regression weights to be mapped back to specific image-space features, allowing direct interpretation of which microstructural patterns correspond to hardening and softening behavior. Results show that microstructural texture encodes both deformation state and material condition, enabling a transparent link between optical morphology and mechanical response. This provides a physically grounded approach for interpreting micrographs as spatially resolved indicators of microhardness beyond traditional indentation methods.