Sign in Subscribe
Artificial intelligence

Artificial Intelligence Algorithms for Microstructure Analysis

Strategic Insights

— 1 min read

Researchers at the Faculty of Metals Engineering and Industrial Computer Science have investigated the potential of artificial intelligence in analyzing microstructure images. The study aimed to develop an application that recognizes specific features, such as "dark color" and "worm shape," in vermicular cast iron microstructure. The researchers encountered challenges in defining these features, as they varied depending on the image conditions and size of the graphite separation. To overcome this, they employed the local feature paradigm, which involves defining a set of features that more precisely define the microcomponent's shape, color, and surroundings.

Key Takeaways:

  • The study focused on developing an application that recognizes specific features in vermicular cast iron microstructure, such as "dark color" and "worm shape."
  • Researchers encountered challenges in defining these features, as they varied depending on the image conditions and size of the graphite separation.
  • The local feature paradigm was employed to define a set of features that more precisely define the microcomponent's shape, color, and surroundings.
  • Distinctive image features, such as edges, spots, and ridges, need to be distinguished to detect places of interest.
  • The study used selected artificial intelligence algorithms for the assessment of the microstructure of vermicular cast iron.

Statistics:

  • 173-182: Page numbers for the journal article "Analysis of the Possibility of Using Selected Artificial Intelligence Algorithms for the Assessment of the Microstructure of Vermicular Cast Iron" in the Archives of Foundry Engineering.
  • 2025: Year of publication for the journal article.
  • 25: Volume number for the journal article in the Archives of Foundry Engineering.
  • 2: Issue number for the journal article in the Archives of Foundry Engineering.
  • 10.24425/afe.2025.153807: DOI for the journal article "Analysis of the Possibility of Using Selected Artificial Intelligence Algorithms for the Assessment of the Microstructure of Vermicular Cast Iron" (available at https://doi-org.sdpl.idm.oclc.org).

Sources:

  • "Analysis of the Possibility of Using Selected Artificial Intelligence Algorithms for the Assessment of the Microstructure of Vermicular Cast Iron." Archives of Foundry Engineering. 2025, vol. 25(No 2):173-182.
  • https://doi.org/10.24425/afe.2025.153807 (free version available online)
  • Faculty of Metals Engineering and Industrial Computer Science, AGH University of Krakow, Poland.

Read more