TY - CONF A1 - Zia, Ghezal Ahmad Jan A1 - Torres, Benjami Moreno A1 - Skrotzki, Birgit A1 - Bayerlein, Bernd T1 - Quantitative Precipitate Analysis of an Age-Hardenable Aluminium Alloy Using a Deep Learning Approach N2 - Mechanical properties of metals and their alloys are strongly governed by their microstructure. The nanometer-sized precipitates in hardenable wrought aluminium alloys, which can be controlled by heat treatment, act as obstacles to dislocation movement within the material and are critical to the mechanical performance of the component, in this case a radial compressor wheel of a ships’ engine. TEM-based image analysis is essential for the study to investigate the microstructural changes (precipitation coarsening) that occur as a result of ageing at elevated temperatures. T2 - MSE 2022 CY - Darmstadt, Germany DA - 27.09.2022 KW - Aluminium Alloy KW - Deep Learning KW - TEM Image PY - 2022 UR - https://dgm.de/mse/2022/ AN - OPUS4-55949 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Schmies, Lennart A1 - Hemmleb, Matthias A1 - Bettge, Dirk T1 - Relevant input data for crack feature segmentation with deep learning on SEM imagery and topography data JF - Engineering Failure Analysis N2 - Fractography plays a critical role in failure analysis of engineering components and has a considerable importance for safety investigations. Usually, the interpretation of fracture surfaces is done by experts with the help of literature and experimental data, that requires a lot of experience. The use of deep learning (DL) with neural networks in failure analysis becomes more and more relevant with the rapidly developing possibilities. Especially, the modern network architectures can assist fractographers in determining various fracture features on SEM images of the fracture surfaces. The basis for the best possible evaluation is the understanding of the influence of the input data used for training deep neural networks (DNN). Therefore, this study discusses the influence of the selection of the input data used for the prediction quality of these networks in order to take this into account for future data acquisition. Specimens of various metallic materials were subjected to fatigue cracking experiment under laboratory conditions. The fractured surfaces were then imaged using various modes or detectors (such as SE, BSE and topography) in SEM, and those captured images were used to create a training data set. The relevance of the individual data for the quality of the prediction is determined by a specific combination of the different detector data. For the training, the well-established architecture of a UNet-ResNet34 with a fixed set of hyperparameters is used. It has been found in this present study that the combination of all input data significantly increases the prediction accuracy, whereby even the combination of SE and BSE data provides considerable advantages over the exclusive use of SE images. KW - Fractography KW - Machine Learning KW - Deep Learning KW - KI PY - 2023 DO - https://doi.org/10.1016/j.engfailanal.2023.107814 VL - 156 SP - 1 EP - 8 PB - Elsevier AN - OPUS4-58918 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -