Deep Learning-Enhanced Wear Analysis of Fe-Cr Composite Coatings for Automotive Brake Applications under Euro 7 Requirements
Year: 2025
Type: article
Abstract: The increasing transition to electric vehicles and the implementation of Euro 7 standards have intensified the focus on brake-derived particulate emissions. This study investigates the application of Fe-Cr-based composite coatings on gray cast iron substrates for brake-disc applications, alongside the development of an automated wear pattern recognition methodology. High-velocity oxygen fuel-sprayed coatings were evaluated via ball-on-disk tests using Si₃N₄ and WC counterfaces. The coatings exhibited enhanced hardness (6.52–7.51 GPa) and significantly reduced wear (Composite B: 7.37 × 10⁻⁶ m³/N·m). Tribochemical reactions differed by counterface material. A deep ensemble convolutional neural network, trained on 500 SEM images, achieved 96.0% test accuracy. This integrated materials–AI approach provides a scalable methodology for tribological analysis and material design.
Source: 대한금속재료학회지
Authors: Tae-Jun Park, Gye-Won Lee, Jong-Il Kim, Sahn Nahm, Yoon-Suk Oh
Institutions: Korea University, Korea University
Language: English
Subfield: Automotive Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4416833619