An official website of the United States government
MAX phase foams could have various applications where tailored functional and mechanical properties are required. In this study, Ti2AlC and Ti3SiC2 MAX phase foams with controlled porosity and pore size were produced and characterized. The foams were produced from MAX phase powders by powder metallurgy method using crystalline carbohydrate as a space holder. Foams with overall porosity up to approximately 71 vol% and pore size from 250 μm to 1000 μm were successfully produced; micro-porosity and macro-porosity was characterized. Poisson's ratio and elastic moduli of the foams were measured by resonant ultrasound spectroscopy (RUS) and analyzed as a function of porosity and pore size. Different models were used to fit the experimental data and interpret the effect of pore size and amount of porosity and on elastic properties. It was found that the amount and type of porosity has a larger influence on the elastic properties than the pore size.
more »
« less
A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy
Abstract We used deep-learning-based models to automatically obtain elastic moduli from resonant ultrasound spectroscopy (RUS) spectra, which conventionally require user intervention of published analysis codes. By strategically converting theoretical RUS spectra into their modulated fingerprints and using them as a dataset to train neural network models, we obtained models that successfully predicted both elastic moduli from theoretical test spectra of an isotropic material and from a measured steel RUS spectrum with up to 9.6% missing resonances. We further trained modulated fingerprint-based models to resolve RUS spectra from yttrium–aluminum-garnet (YAG) ceramic samples with three elastic moduli. The resulting models were capable of retrieving all three elastic moduli from spectra with a maximum of 26% missing frequencies. In summary, our modulated fingerprint method is an efficient tool to transform raw spectroscopy data and train neural network models with high accuracy and resistance to spectra distortion.
more »
« less
- Award ID(s):
- 2144792
- PAR ID:
- 10406374
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 13
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Surface-enhanced Raman spectroscopy (SERS) is an attractive method for bio-chemical sensing due to its potential for single molecule sensitivity and the prospect of DNA composition analysis. In this manuscript we leverage metal specific chemical enhancement effect to detect differences in SERS spectra of 200-base length single-stranded DNA (ssDNA) molecules adsorbed on gold or silver nanorod substrates, and then develop and train a linear regression as well as neural network models to predict the composition of ssDNA. Our results indicate that employing substrates of different metals that host a given adsorbed molecule leads to distinct SERS spectra, allowing to probe metal-molecule interactions under distinct chemical enhancement regimes. Leveraging this difference and combining spectra from different metals as an input for PCA (Principal Component Analysis) and NN (Neural Network) models, allows to significantly lower the detection errors compared to manual feature-choosing analysis as well as compared to the case where data from single metal is used. Furthermore, we show that NN model provides superior performance in the presence of complex noise and data dispersion factors that affect SERS signals collected from metal substrates fabricated on different days.more » « less
-
Recently, molecular fingerprints extracted from three-dimensional (3D) structures using advanced mathematics, such as algebraic topology, differential geometry, and graph theory have been paired with efficient machine learning, especially deep learning algorithms to outperform other methods in drug discovery applications and competitions. This raises the question of whether classical 2D fingerprints are still valuable in computer-aided drug discovery. This work considers 23 datasets associated with four typical problems, namely protein–ligand binding, toxicity, solubility and partition coefficient to assess the performance of eight 2D fingerprints. Advanced machine learning algorithms including random forest, gradient boosted decision tree, single-task deep neural network and multitask deep neural network are employed to construct efficient 2D-fingerprint based models. Additionally, appropriate consensus models are built to further enhance the performance of 2D-fingerprint-based methods. It is demonstrated that 2D-fingerprint-based models perform as well as the state-of-the-art 3D structure-based models for the predictions of toxicity, solubility, partition coefficient and protein–ligand binding affinity based on only ligand information. However, 3D structure-based models outperform 2D fingerprint-based methods in complex-based protein–ligand binding affinity predictions.more » « less
-
Abstract Dynamic perturbations reveal unconventional nonlinear behavior in rocks, as evidenced by field and laboratory studies. During the passage of seismic waves, rocks exhibit a decrease in elastic moduli, slowly recovering after. Yet, comprehensive physical models describing these moduli alterations remain sparse and insufficiently validated against observations. Here, we demonstrate the applicability of two physical damage models—the internal variable model (IVM) and the continuum damage model (CDM)—to provide quantitative descriptions of nonlinear co‐seismic elastic wave propagation observations. While the IVM uses one internal variable to describe the evolution of elastic material moduli, the CDM damage variable is a mathematical representation of microscopic defects. We recast the IVM and CDM models as nonlinear hyperbolic partial differential equations and implement 1D and 2D numerical simulations using an arbitrary high‐order discontinuous Galerkin method. We verify the modeling results with co‐propagating acousto‐elastic experimental measurements. Subsequently, we infer the parameters for these nonlinear models from laboratory experiments using probabilistic Bayesian inversion and 2D simulations. By adopting the Adaptive Metropolis Markov chain Monte Carlo method, we quantify the uncertainties of inferred parameters for both physical models, investigating their interplay in 70,000 simulations. We find that the damage variables can trade off with the stress‐strain nonlinearity in discernible ways. We discuss physical interpretations of both damage models and that our CDM quantitatively captures an observed damage increase with perturbation frequency. Our results contribute to a more holistic understanding of co‐seismic damage and post‐seismic recovery after earthquakes bridging the worlds of theoretical analysis and laboratory findings.more » « less
-
Abstract We present a machine learning framework to train and validate neural networks to predict the anisotropic elastic response of a monoclinic organic molecular crystal known as ‐HMX in the geometrical nonlinear regime. A filtered molecular dynamic (MD) simulations database is used to train neural networks with a Sobolev norm that uses the stress measure and a reference configuration to deduce the elastic stored free energy functional. To improve the accuracy of the elasticity tangent predictions originating from the learned stored free energy, a transfer learning technique is used to introduce additional tangential constraints from the data while necessary conditions (e.g., strong ellipticity, crystallographic symmetry) for the correctness of the model are either introduced as additional physical constraints or incorporated in the validation tests. Assessment of the neural networks is based on (1) the accuracy with which they reproduce the bottom‐line constitutive responses predicted by MD, (2) the robustness of the models measured by detailed examination of their stability and uniqueness, and (3) the admissibility of the predicted responses with respect to mechanics principles in the finite‐deformation regime. We compare the training efficiency of the neural networks under different Sobolev constraints and assess the accuracy and robustness of the models against MD benchmarks for ‐HMX.more » « less
