An official website of the United States government
Ionic liquids are currently being considered as potential electrolyte candidates for next-generation batteries and energy storage devices due to their high thermal and chemical stability. However, high viscosity and low conductivity at lower temperatures have severely hampered their commercial applications. To overcome these challenges, it is necessary to develop structure–property models for ionic liquid transport properties to guide the ionic liquid design. This work expands our previous effort in developing a machine learning model on imidazolium-based ionic liquids to now include ten different cation families, representing structural and chemical diversity. The model dataset contains 2869 ionic conductivity values over a temperature range of 238–472 K collected from the NIST ILThermo database and literature values for 397 unique ionic liquids. The database covers 214 unique cations and 68 unique anions. Three machine learning models, namely multiple linear regression, random forest, and extreme gradient boosting are applied to correlate the ionic liquid conductivity data with cation and anion features. Shapely additive analysis is performed to glean insights into cation and anion features with significant impact on ionic conductivity. Finally, the extreme gradient boosting model is used to predict the ionic conductivity of ionic liquids from all the possible combinations of unique cations and anions to identify ionic liquids crossing the ionic conductivity threshold of 2.0 S m −1 .
more »
« less
Machine-Learning-Based Thermal Conductivity Prediction for Additively Manufactured Alloys
Thermal conductivity (TC) is greatly influenced by the working temperature, microstructures, thermal processing (heat treatment) history and the composition of alloys. Due to computational costs and lengthy experimental procedures, obtaining the thermal conductivity for novel alloys, particularly parts made with additive manufacturing, is difficult and it is almost impossible to optimize the compositional space for an absolute targeted value of thermal conductivity. To address these difficulties, a machine learning method is explored to predict the TC of additive manufactured alloys. To accomplish this, an extensive thermal conductivity dataset for additively manufactured alloys was generated for several AM alloy families (nickel, copper, iron, cobalt-based) over various temperatures (300–1273 K). This unique dataset was used in training and validating machine learning models. Among the five different regression machine learning models trained with the dataset, extreme gradient boosting performs the best as compared with other models with an R2 score of 0.99. Furthermore, the accuracy of this model was tested using Inconel 718 and GRCop-42 fabricated with laser powder bed fusion-based additive manufacture, which have never been observed by the extreme gradient boosting model, and a good match between the experimental results and machine learning prediction was observed. The average mean error in predicting the thermal conductivity of Inconel 718 and GRCop-42 at different temperatures was 3.9% and 2.08%, respectively. This paper demonstrates that the thermal conductivity of novel AM alloys could be predicted quickly based on the dataset and the ML model.
more »
« less
- Award ID(s):
- 1946231
- PAR ID:
- 10496371
- Publisher / Repository:
- https://www.mdpi.com/2504-4494/7/5/160
- Date Published:
- Journal Name:
- Journal of Manufacturing and Materials Processing
- Volume:
- 7
- Issue:
- 5
- ISSN:
- 2504-4494
- Page Range / eLocation ID:
- 160
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This study investigates the stability of Inconel–Cu Multimetallic Layered Composites (MMLCs) in nuclear reactor applications using Molecular Dynamics simulations. The focus is on understanding the underlying mechanisms governing the properties of MMLCs for advanced nuclear reactors, specifically, the mechanochemistry of the interface between Inconel and copper alloys. The selection of Inconel–Cu MMLCs is primarily due to copper’s superior thermal conductivity, enhancing heat management within reactors by preventing hotspots and ensuring uniform temperature distribution. This research examines Incoloy 800H and two Inconel variants (718 and 625), assessing their stability at 1000 K after exposure to 10 keV collision cascades up to 0.12 dpa. Notable findings include defect clustering on the {1 2 0} family of planes of Inconel and Cu, with Stacking Faults and Lomer–Cottrell locks on the Inconel side.more » « less
-
Nickel-based alloys, Alloys 625 and 718, are widely used in the aerospace industry due to their excellent corrosion resistance and high strength at elevated temperatures. Recently, these alloys have been utilized to manufacture rocket engine components using additive manufacturing (AM) technologies such as laser powder bed fusion (LPBF) and powder-blown laser-based directed energy deposition (DED). These technologies offer faster and more cost-effective production while enabling the fabrication of near-net-shape parts that are subsequently joined by welding. However, solidification cracking susceptibility varies significantly between AM and conventionally processed materials, and limited weldability characterization has been conducted on AM-fabricated materials. This study assesses the weld solidification cracking susceptibility of Alloys 625 and 718 produced by wrought (mill-rolled), LPBF, and DED using transverse varestraint testing, Scheil-Gulliver simulations, the Crack Susceptibility Index (CSI), and the Flow Resistance Index (FRI). Transverse varestraint testing revealed that AM parts exhibited higher susceptibility due to the presence of larger and elongated grains in the fusion zone, affecting the weld solidification cracking response. In Alloy 625, the LPBF condition exhibited the highest maximum crack distance (MCD) of 2.35 ± 0.16 mm, compared to 1.56 ± 0.06 mm for wrought and 1.72 ± 0.10 mm for DED. Similarly, in Alloy 718, the DED condition showed the highest MCD of 2.93 ± 0.41 mm, while the wrought condition had an MCD of 2.01 ± 0.12 mm, and the LPBF condition reached 3.01 ± 0.33 mm at 5 % strain, without a clearly defined saturation strain. Although wrought materials demonstrated greater resistance to solidification cracking, solidification simulations did not correlate with the experimental testing, as they do not account for microstructural and mechanical factors, relying solely on chemistry.more » « less
-
Refractory complex concentrated alloys (RCCAs) have drawn increasing attention recently owing to their balanced mechanical properties, including excellent creep resistance, ductility, and oxidation resistance. The mechanical and thermal properties of RCCAs are directly linked with the elastic constants. However, it is time consuming and expensive to obtain the elastic constants of RCCAs with conventional trial-and-error experiments. The elastic constants of RCCAs are predicted using a combination of density functional theory simulation data and machine learning (ML) algorithms in this study. The elastic constants of several RCCAs are predicted using the random forest regressor, gradient boosting regressor (GBR), and XGBoost regression models. Based on performance metrics R-squared, mean average error and root mean square error, the GBR model was found to be most promising in predicting the elastic constant of RCCAs among the three ML models. Additionally, GBR model accuracy was verified using the other four RHEAs dataset which was never seen by the GBR model, and reasonable agreements between ML prediction and available results were found. The present findings show that the GBR model can be used to predict the elastic constant of new RHEAs more accurately without performing any expensive computational and experimental work.more » « less
-
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
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/jmmp7050160
