Deep Learning based Dimple Segmentation for Quantitative Fractography
This work addresses the challenge of determining fracture causes in metals for material property prediction and development of fracture-resistant materials, though it appears incremental as it builds on existing neural network methods for a specific domain.
The paper tackles the problem of dimple detection and segmentation in Titanium alloy fractographs using a novel fully convolutional neural network with self-attention, achieving the best performance compared to previous approaches.
In this work, we try to address the challenging problem of dimple detection and segmentation in Titanium alloys using machine learning methods, especially neural networks. The images i.e. fractographs are obtained using a Scanning Election Microscope (SEM). To determine the cause of fracture in metals we address the problem of segmentation of dimples in fractographs i.e. the fracture surface of metals using supervised machine learning methods. Determining the cause of fracture would help us in material property, mechanical property prediction and development of new fracture-resistant materials. This method would also help in correlating the topography of the fracture surface with the mechanical properties of the material. Our proposed novel model achieves the best performance as compared to other previous approaches. To the best of our knowledge, this is one the first work in fractography using fully convolutional neural networks with self-attention for supervised learning of dimple fractography, though it can be easily extended to account for brittle characteristics as well.