@misc{StendalBambachEisentrautetal., author = {Stendal, Johan Andreas and Bambach, Markus and Eisentraut, Mark and Sizova, Irina and Weiß, Sabine}, title = {Applying Machine Learning to the Phenomenological Flow Stress Modeling of TNM-B1}, series = {Metals}, volume = {9}, journal = {Metals}, number = {2}, issn = {2075-4701}, doi = {10.3390/met9020220}, pages = {18}, abstract = {Data-driven or machine learning approaches are increasingly being used in material science and research. Specifically, machine learning has been implemented in the fields of materials discovery, prediction of phase diagrams and material modelling. In this work, the application of machine learning to the traditional phenomenological flow stress modelling of the titanium aluminide (TiAl) alloy TNM-B1 (Ti-43.5Al-4Nb-1Mo-0.1B) is investigated. Three model types were developed, analyzed and compared; a physics-based phenomenological model (PM) originally developed for steel by Cingara and McQueen, a purely data-driven machine learning model (MLM), and a hybrid model (HM), which uses characteristic points predicted by a learning algorithm as input for the phenomenological model. The same amount of data was used to both fit the PM and train the MLM and HM. The models were analyzed and compared based on the accuracy of their predictions, development and computing time, and their ability to predict on interpolated and extrapolated inputs. The results revealed that for the same amount of experimental data, the MLM was more accurate than the PM. In addition, the MLM was better able to capture the characteristic peak stress in the TNM-B1 the flow curves, and could be developed and computed faster. Furthermore, the MLM was able to make realistic predictions for inputs outside the experimental data used for training. The HM showed comparable accuracy to the PM for the experimental conditions. However, the HM was able to produce a better fit for input conditions outside the training data.}, language = {en} } @misc{EisentrautBolzSizovaetal., author = {Eisentraut, Mark and Bolz, Sebastian and Sizova, Irina and Bambach, Markus and Weiß, Sabine}, title = {Development of a heat treatment strategy for the γ-TiAl based alloy TNM-B1 to increase the hot workability}, series = {SN Applied Sciences}, volume = {1}, journal = {SN Applied Sciences}, number = {11}, issn = {2523-3963}, doi = {10.1007/s42452-019-1563-4}, pages = {8}, language = {en} } @misc{StendalEisentrautSizovaetal., author = {Stendal, Johan Andreas and Eisentraut, Mark and Sizova, Irina and Bolz, Sebastian and Bambach, Markus and Weiß, Sabine}, title = {Effect of heat treatment on the workability of hot isostatically pressed TNM-B1}, series = {AIP Conference Proceedings}, volume = {2113}, journal = {AIP Conference Proceedings}, number = {1}, isbn = {978-0-7354-1847-9}, doi = {10.1063/1.5112544}, language = {en} } @misc{EisentrautStendalBolzetal., author = {Eisentraut, Mark and Stendal, Johan Andreas and Bolz, Sebastian and Bambach, Markus and Weiß, Sabine}, title = {Applying a softening adapted acceleration to the hot deformation of TNM-B1}, series = {MRS Fall Meeting 2020}, journal = {MRS Fall Meeting 2020}, abstract = {Hot isostatically forged TiAl turbine blades made of TNM-B1 are commercially used in aircraft engines, as they offer significantly lower weight than the traditional nickel-based blades while exhibiting similar strength. Like other TiAl alloys, TNM-B1 displays high peak stress followed by a strong softening behavior (i.e. stress reduction) during hot deformation. This softening can be used to accelerate the deformation process by reducing the processing time and in turn the costs for TNM-B1 parts. In order to avoid increased damage during the accelerated process, a pre-heat treatment (HT) for the hot isostatically pressed material (HIP) is required. To simulate the accelerated forming process, hot compression tests were performed with a DIL805A/D/T dilatometer from TA Instruments (New Castle, Delaware, USA) with different strain rates (0.0013, 0.005, 0.01 and 0.05) and temperatures (T=1150, 1175 and 1200°C). Deformation of the heat-treated state revealed lower flow stress (in both, peak stresses and steady state stresses) and fewer voids compared to the HIP state (Fig. 1.a). The compression test data were used to develop material and temperature specific strain rate profiles based on a material model. Subsequently, hot compression tests were performed with different strain rate profiles (starting strain rates 0.0013 and 0.0052) for the HIP and the HT state. The results were evaluated with regard to their microstructure, deformation, and damage behavior. A reduction of the processing time for all tested strain rates profiles by factors 2-3 could be achieved compared to constant strain rates. Furthermore, the results indicated that the deformation with strain rate profiles (compared to constant strain rates) did not significantly change the resulting microstructure or damage tolerance of the HT state.}, language = {en} } @misc{StendalEisentrautSizovaetal., author = {Stendal, Johan Andreas and Eisentraut, Mark and Sizova, Irina and Bolz, Sebastian and Weiß, Sabine and Bambach, Markus}, title = {Accelerated hot deformation and heat treatment of the TiAl alloy TNM-B1 for enhanced hot workability and controlled damage}, series = {Journal of Materials Processing Technology}, volume = {Vol. 291}, journal = {Journal of Materials Processing Technology}, issn = {0924-0136}, doi = {10.1016/j.jmatprotec.2020.116999}, pages = {12}, language = {en} } @misc{SizovaSviridovBambachetal., author = {Sizova, Irina and Sviridov, Alexander and Bambach, Markus and Eisentraut, Mark and Hemes, Susanne and Hecht, Ulrike and Marquardt, Axel and Leyens, Christoph}, title = {A study on hot-working as alternative post-processing method for titanium aluminides built by laser powder bed fusion and electron beam melting}, series = {Journal of Materials Processing Technology}, volume = {291}, journal = {Journal of Materials Processing Technology}, issn = {0924-0136}, doi = {10.1016/j.jmatprotec.2020.117024}, pages = {14}, language = {en} }