The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.Steel is still one of the most important and extensively used classes of materials because of its excellent mechanical properties while keeping costs low which gives a huge variety of applications 1,2 . The mechanical properties of steel are mainly determined by its microstructure 3 shown in Fig. 1, so that the performance of the material highly depends on the distribution, shape and size of phases in the microstructure 4 . Thus, correct classification of these microstructures is crucial 5 . The microstructure of steels has different appearances, influenced by a vast number of parameters such as alloying elements, rolling setup, cooling rates, heat treatment and further post-treatments 6 . Depending on how the steel is produced due to these parameters, the microstructure consists of different constituents such as ferrite, cementite, austenite, pearlite, bainite and martensite 7 shown in Fig. 1.This motivation leads us to use Deep Learning methods which are recently grabbing the attention of scientists due to their strong ability to learn high-level features from raw input data. Recently, these methods have been applied very successfully to computer vision problems 8,9 . They are based on artificial neural networks such as Convolutional Neural Networks (CNNs) 9 . They can be trained for recognition and semantic pixel-wise segmentation tasks. Unlike traditional methods in which feature extraction and classification are learnt separately, in Deep Learning methods, these parts are learnt jointly. The trained models have shown successful mappings from raw unprocessed input to semantic meaningful outp...
Comparison of segregations formed in unmodified and Sr-modified Al-Si alloys studied by atom probe tomography and transmission electron microscopy, 2014, Journal of Alloys and Compounds, (611)
AbstractThe mechanical properties of Al-7 wt.% Si can be enhanced by structural modifications of its eutectic phase. Addition of low concentrations of certain elements, in this case 150 wt-ppm Sr, is enough to cause a transition from a coarse plate-like Si structure to a finer coralline one. To fully understand the operating mechanism of this modification, the composition of the eutectic Si phase in unmodified and Sr-modified alloys was analysed and compared by Atom Probe Tomography and (Scanning) Transmission Electron Microscopy. The unmodified alloy showed nanometre sized Al-segregations decorating defects, while the Sr-modified sample presented three types of Al-Sr segregations: (1) rod-like segregations that promote smoothening of the Al-Si boundaries in the eutectic phase, (2) particle-like segregations comparable to the ones seen in the unmodified alloy, and (3) planar segregations favouring the formation of twin boundaries. Al and Sr solubilities in Si after solidification were determined to be 430 ± 160 at-ppm and 40 ± 10 at-ppm, respectively. Sr predominantly segregates to the Si phase confirming its importance in the modification of the eutectic growth.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.