What question did this study set out to answer?

This study aims to predict the outcomes of the Welded Bead Bending Test using a CNN classification of microscopy images.

June 10, 2026Open Access

CNN-Based Classification of Structural Steel Microstructures for the Prediction of the Outcome of the Welded Bead Bending Test

Puntos clave

This study aims to predict the outcomes of the Welded Bead Bending Test using a CNN classification of microscopy images.
Evaluated five CNN architectures for predicting WBBT outcomes from images of steel samples.
Utilized a dataset of 800 light optical microscopy images from 40 different steel samples.
Implemented two validation strategies: patch-level and sample-level splitting to prevent data leakage.
I-ResNet-34 model achieved a patch-level accuracy of 79.58% ± 6.82% and 100% specificity under sample-level splitting.
Leave-one-sample-out cross-validation yielded an accuracy of 79.36% and a specificity of 86.26%.
Sample-level results showed approximately 86% accuracy and 91% specificity.

Resumen

The Welded Bead Bending Test (WBBT), used in Germany to assess the crack-arrest capacity of structural steels, is conducted in accordance with ZTV-ING Part 4 or Deutsche Bahn Standard 918 002-02 and specified in Stahl-Eisen-Prüfblatt 1390. Three possible test outcomes are distinguished: passed if a bending angle of α≥60∘ is reached without fracture but with visible cracks in the base material, not passed if fracture occurs beforehand, and invalid if no crack propagates into the base material despite bending to α≥60∘. This study proposes a novel data-driven approach for predicting WBBT outcomes using a Convolutional Neural Network (CNN) applied to patch-wise classification of Light Optical Microscopy images (LOMs) taken from WBB-tested samples. A dataset comprising 800 LOMs from 40 steel samples originating from various manufacturers was acquired in collaboration with Chemnitzer Werkstoff- und Oberflächentechnik GmbH. Five CNN architectures are evaluated in terms of Accuracy, Recall and Specificity: MicroNet-pretrained DenseNet-121 and EfficientNet-B0, ResNet-34 pretrained on both ImageNet (I-ResNet-34) and MicroNet (M-ResNet-34), and a light CNN trained from scratch. The models were subjected to training in accordance with three different methods, which varied by patch size and number of LOMs utilised for training. Two validation strategies, patch-level and sample-level splitting, were employed to analyse potential data leakage effects. The I-ResNet-34 model demonstrates the best performance in this comparison, achieving a patch-level Accuracy of 79.58% ± 6.82% and an image- and sample-level Specificity of 100% under sample-level splitting. This performance is confirmed via leave-one-sample-out cross-validation, yielding a comparable patch-level Accuracy of 79.36% and a Specificity of 86.26%. The corresponding WBBT sample-level results under this validation scheme are approximately 86% Accuracy and 91% Specificity.

Leer artículo completoexternamente

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo