journal article·2025-08-27Open access

Surface Corrosion Detection for Ferrous-metal Parts: Application of Artificial Intelligence, Python and Microscopic Images

Roman WDOWIK, Artur BEŁZO, Regita BENDIKIENE

Materials Science· Volume 31· Issue 3

Abstract

This paper presents an innovative technique for ferrous-metal surface damage identification, especially corrosion, supported by generative artificial intelligence (AI). It demonstrates how to automate damage identification and recognize corrosion. High-quality microscopic images were recorded, taking into account selected ferrous-metals parts. The Python code lines were generated using ChatGPTTM according to prompts developed by the authors, and this approach was applied to corrosion analysis. The results were discussed from the perspective of possible industrial applications. Moreover, there were discussed the limitations resulting from generated results which sometimes do not meet a damage inspector's expectation. Compared to traditional corrosion detection methods such as visual inspection and non-destructive testing methods, the AI-based methods offer a faster and more cost-effective solution that can process large volumes of images in real time and produce consistent results. Further research directions are also proposed, including the analysis of other damage types and improvements to model accuracy.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Industrial Vision Systems and Defect Detection · Non-Destructive Testing Techniques · Surface Roughness and Optical Measurements

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References

Reference metadata was not supplied for this record.