Designing alloys for additive manufacturing (AM) presents significant opportunities. Still, the
chemical composition and processing conditions required for printability (ie., their suitability for
fabrication via AM) are challenging to explore using solely experimental means. In this work, we
develop a high-throughput (HTP) computational framework to guide the search for highly printable
alloys and appropriate processing parameters. The framework uses material properties from stateof-
the-art databases, processing parameters, and simulated melt pool profiles to predict processinduced
defects, such as lack-of-fusion, keyholing, and balling. We accelerate the printability assessment
using a deep learning surrogate for a thermal model, enabling a 1,000-fold acceleration in
assessing the printability of a given alloy at no loss in accuracy when compared with conventional
physics-based thermal models. We verify and validate the framework by constructing printability
maps for the CoCrFeMnNi Cantor alloy system and comparing our predictions to an exhaustive
’in-house’ database. The framework enables the systematic investigation of the printability of a
wide range of alloys in the broader Co-Cr-Fe-Mn-Ni HEA system. We identified the most promising
alloys that were suitable for high-temperature applications and had the narrowest solidification
ranges, and that was the least susceptible to balling, hot-cracking, and the formation of macroscopic
printing defects. A new metric for the global printability of an alloy is constructed and is further
used for the ranking of candidate alloys. The proposed framework is expected to be integrated
into ICME approaches to accelerate the discovery and optimization of novel high-performance,
printable alloys.
more »
« less
Deep learning approach for chemistry and processing history prediction from materials microstructure
Abstract Finding the chemical composition and processing history from a microstructure morphology for heterogeneous materials is desired in many applications. While the simulation methods based on physical concepts such as the phase-field method can predict the spatio-temporal evolution of the materials’ microstructure, they are not efficient techniques for predicting processing and chemistry if a specific morphology is desired. In this study, we propose a framework based on a deep learning approach that enables us to predict the chemistry and processing history just by reading the morphological distribution of one element. As a case study, we used a dataset from spinodal decomposition simulation of Fe–Cr–Co alloy created by the phase-field method. The mixed dataset, which includes both images, i.e., the morphology of Fe distribution, and continuous data, i.e., the Fe minimum and maximum concentration in the microstructures, are used as input data, and the spinodal temperature and initial chemical composition are utilized as the output data to train the proposed deep neural network. The proposed convolutional layers were compared with pretrained EfficientNet convolutional layers as transfer learning in microstructure feature extraction. The results show that the trained shallow network is effective for chemistry prediction. However, accurate prediction of processing temperature requires more complex feature extraction from the morphology of the microstructure. We benchmarked the model predictive accuracy for real alloy systems with a Fe–Cr–Co transmission electron microscopy micrograph. The predicted chemistry and heat treatment temperature were in good agreement with the ground truth.
more »
« less
- Award ID(s):
- 2142935
- PAR ID:
- 10383355
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 12
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A Data-Driven Framework to Select a Cost-Efficient Subset of Parameters to Qualify Sourced MaterialsThe quality of powder processed for manufacturing can be certified by hundreds of different variables. Assessing the impact of all these different metrics on the performance of additively manufactured engineered products is an invaluable, but time intensive specification process. In this work, a comprehensive, generalizable, data-driven framework was implemented to select the optimal powder processing and microstructure variables that are required to predict the target property variables. The framework was demonstrated on a high-dimensional dataset collected from selective laser melted, additively manufactured, Inconel 718. One hundred and twenty-nine powder quality variables including particle morphology, rheology, chemical composition, and build composition, were assessed for their impact on eight microstructural features and sixteen mechanical properties. The importance of each powder and microstructure variable was determined by using statistical analysis and machine learning models. The trained models predicted target mechanical properties with an R2 value of 0.9 or higher. The results indicate that the desired mechanical properties can be achieved by controlling only a few critical powder properties and without the need for collecting microstructure data. This framework significantly reduces the time and cost of qualifying source materials for production by determining an optimal subset of experiments needed to predict that a given source material will lead to a desired outcome. This general framework can be easily applied to other material systems.more » « less
-
Structure-Property Relationships of Differently Heat-Treated Binder Jet Printed Co-Cr-Mo BiomaterialThis investigation systematically examines the influence of sintering temperature and aging treatment on the density, microstructure evolution, phase formation, and mechanical properties of a binder jet printed Co-Cr-Mo biomedical alloy. Sintering at 1380 °C for 2 h yielded a near-fully dense part (99.1%) with favorable mechanical properties (up to 325 HV0.1 hardness and up to 693 MPa ultimate tensile strength). The grain size remained unchanged after aging at 800 °C for 24 h (89 ± 21 µm). Aging resulted in increased microhardness and tensile strength due to phase formation (Cr23C6, CrMo, and ε phase), but a significant decrease in ductility. Consequently, the sintered and aged specimen exhibited higher hardness (522 HV0.1), yield strength (641 MPa), and ultimate tensile strength (854 MPa) compared to cast Co-Cr-Mo alloy. Biocompatibility testing with fibroblasts showed a cell viability of 95 ± 2%, indicating that binder jet printing did not affect the biocompatibility of the Co-Cr-Mo alloy. Exemplary printed parts including hip-joint, partial denture, and small-scale knee joint were successfully demonstrated. This study highlights the comparable properties of binder jet Co-Cr-Mo alloy to the cast alloy, affirming its potential for biomedical applications.more » « less
-
Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.more » « less
-
more » « less
The potential defects during the additive manufacturing (AM) process greatly deteriorate the mechanical properties of the fabricated structures and, as a result, increase the risks of part fatigue failure and even disasters. As laser additive manufacturing is such a complex process, many different physical phenomena such as electromagnetic radiation, optical and acoustic emission, and plasma generation will occur. Unlike vision and acoustic methods, the spectroscopy based smart optical monitoring system (SOMS) provides atomic level information revealing mechanical and chemical condition of the product. By monitoring plasma, multiple information such as line intensity, standard deviation, plasma temperature, or electron density, and by using different signal processing algorithms such as vector machine training or wavelet transforming, AM defects have been detected and classified. Utilizing two fiber optic components, a bifurcated fiber and a split fiber, the experimental results were performed to improve SOMS signal-to-noise ratio. Defects, including subsurface pores and sudden changes of process parameters including shielding gas shut-off and foreign substance, were identified by the spectroscopy based SOMS. For chemical composition characterization, a degree of dilution in terms of chemical element variation is identified by a spectral peak intensity ratio through the SOMS. It turned out that the information on the Cr/Fe ratio of deposit at a certain layer is vital to design the mechanical property in the IN625 deposition on the mild steel case. The SOMS has also demonstrated that the chemistry ratio can be determined from the calibration curve method based on the known alloy samples and that the ratio of the maximum intensities of multiple species provides more information about the quality of the alloy.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1038/s41598-022-08484-7
