Nikolai A Zarkevich | Search NASA

NASA NTRS2022

MLtool: Universal Supervised Machine Learning Tool to Model Tabulated Data

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine learning↗

NASA NTRS2022

MLtool Python Code

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine Learning↗

NASA NTRSDate not supplied

Materials and technologies for interstellar flights and intra-galactic spread of life

Small automated spaceships are capable to deliver seeds, frozen ova and gametes to other planetary systems. A spaceship can be equipped with a freezer containing reproductive cells, an artificial uterus, a robotic nursery and school, and a collection of instruments and equipment. The whole spaceship will be frozen during a long interstellar flight. Approaching another star, a spaceship will generate electricity from light, warm up, slow down and land on a suitable planet (if any), give birth to a human, provide care and education. After schooling, the human will vacate the spaceship and either build more space for living (using local materials) or die. A vacant spaceship will supply more people, one at a time. Hopefully, they will collectively create a sustainable colony on a remote planet. Our Milky Way galaxy has hundreds billion stars (i.e., more stars than humans on Earth). Mass production of spacecrafts for intragalactic spread of life will make each spaceship cheaper, will improve employment and purposeful production on Earth, and will spread human life beyond the Solar System. If any spaceship will miss its target stellar system, it will fly to the next one, retaining ability to bring life to another planet. Which materials and technologies are needed for the interstellar life propagation? Materials age during a long interstellar flight, which can last from 10^4 to 10^10 years. We evaluate the computational methods (such as C2NEB, available from https://lib.dr.iastate.edu/ameslab_software/1) that are suitable for addressing materials aging at low temperatures and high radiation levels during the appropriately long-time scales.

Technologies↗

NASA NTRSDate not supplied

Composition-property correlations in NiTi-based shape memory alloys from the first principles

Development of shape memory alloys (SMA) has been traditionally accomplished by means of extensive empirical efforts, with a very limited support from phenomenological models and related tools. We present a theoretical framework based on the Hamiltonian formalism, which connects important thermodynamic properties directly to the relative energies (the eigenvalues of the Hamiltonian), computed from the first principles using density functional theory. The estimates based on this formalism allow to establish correlations between composition and physical properties, such as relative energies, phase transition temperatures, hysteresis, thermal expansion, and other thermodynamic information. Importantly, estimates and correlations not only provide a fast answer, but also elucidate underpinning of thermodynamic features in terms of the electronic structure. Using this framework, we consider phase transformations and correlations between the selected properties and composition in the NiTi-based ternary and multicomponent shape memory alloys. Our theoretical guidance facilitates design and development of future alloys.

shape memory alloys↗

NASA NTRSDate not supplied

Controlling properties by chemistry in doped shape memory alloys

Shape memory alloys find increasing use in airspace applications. Using theoretical and computational methods, we investigate correlations between the selected properties and composition in doped NiTi-based shape memory alloys. Among the properties we consider relative energies, phase transition temperature, and hysteresis. We compare predictions to experimental data. Our theoretical guidance facilitates design of future alloys. We acknowledge support from the NASA Transformative Aeronautics Concepts Program, Transformational Tools & Technologies (TTT) Project.

NiTi↗

NASA NTRSDate not supplied

Controlling properties by chemistry in doped shape memory alloys

Shape memory alloys find increasing use in airspace applications. Using theoretical and computational methods, we investigate correlations between the selected properties and composition in doped NiTi-based shape memory alloys. Among the properties we consider relative energies, phase transition temperature, and hysteresis. We compare predictions to experimental data. Our theoretical guidance facilitates design of future alloys.

Nikolai A Zarkevich↗

NASA NTRSDate not supplied

Extraction and Analysis of the Properties of Shape Memory Alloys

Shape Memory Alloys (SMA) are materials of high industrial importance, increasingly used for the aerospace applications. Use of SMA allows to simplify flight systems and reduce the total weight. Through the literature-based data mining, we extracted the computed SMA properties from the high-impact journals. We plotted the selected pairs of properties, found and parametrized correlations.

Jason Ernesto Diaz↗

NASA NTRSDate not supplied

Guided Design of Alloys, Strengthened via Precipitation

Using theoretical and computational guidance, we are designing stronger middle and high-entropy alloys and superalloys for the airspace applications. We focus on improving mechanical properties of materials at cryogenic and elevated temperatures. Here we discuss basic science and fundamental theory that are being used for guided design of next-generation alloys. As examples, we consider the medium-entropy NiCoCr alloy and precipitated superalloys with a local phase transformation strengthening. This research is funded by NASA’s Aeronautics Research Mission Directorate (ARMD) via Transformational Tools and Technologies (TTT) Project.

Alloys↗

NASA NTRSDate not supplied

Guided Design of Alloys

Using multiscale materials modeling, we are designing stronger alloys for the airspace applications. We focus on improving mechanical properties of materials at operating temperature. We employ basic science and fundamental theory for guided design of the next-generation alloys. Among the examples, we consider precipitated superalloys with a local phase transformation strengthening. We acknowledge funding by NASA’s Aeronautics Research Mission Directorate (ARMD) via Transformational Tools and Technologies (TTT) Project.

multiscale↗

NASA NTRSDate not supplied

High-precision predictions of properties of chemically disordered crystals

Multiple scattering theory (MST) combined with density functional theory (DFT) allows to predict properties of chemically disordered materials from the first principles. However, such predictions often suffer from the systematic errors, which depend on crystal geometry. Each computed property of a particular crystal structure typically has a relatively small random error and a larger systematic error. Cancellation of systematic errors allows more accurate predictions. We propose a computational methodology based on the subtraction of the systematic errors in MST. To exemplify it, we apply it to the precipitated alloys. Considering precipitation strengthening in Ni superalloys, we compute the relative enthalpies of the competing Ni3(Al,Ti)1 crystal structures with a chemical disorder on the Al+Ti sublattice. Such predicted composition-structure-property dependencies are useful for the guided design of the next-generation alloys with improved strength. Our predictions are validated by comparison with the results of other DFT methods (having a higher computational cost) and with experiment. We acknowledge funding of the guided design of stronger superalloys for airspace by NASA Aeronautics Research Mission Directorate (ARMD) via Transformational Tools and Technologies (TTT) Project.

Computational↗

NASA NTRSDate not supplied

Guided Design of Alloys: Part 2

Using multiscale materials modeling, we are designing stronger alloys for the airspace applications. We focus on improving mechanical properties of materials at operating temperature. We employ basic science and fundamental theory for guided design of the next-generation alloys. Among the examples, we consider precipitated superalloys with a local phase transformation strengthening. We acknowledge funding by NASA’s Aeronautics Research Mission Directorate (ARMD) via Transformational Tools and Technologies (TTT) Project.

Multiscale↗

NASA NTRSDate not supplied

Energy landscape in Ni-Co-Cr and related alloys

Among multi-principal element alloys, the NiCoCr middle-entropy alloy has an outstanding combination of strength and ductility at both low and elevated temperatures. Equiatomic NiCoCr is a single-phase alloy with the face centered cubic (fcc) crystal structure. A low stacking fault energy in the fcc matrix is a cause of a relatively low creep in this alloy. The hexagonal close-packed (hcp) structure differs from the fcc by a stacking of atomic layers. The energy difference between the hcp and fcc structures is known to correlate with the stacking fault energy in the fcc phase. We compute formation and relative structural energies versus composition in the Ni-Co-Cr ternary and related quaternary systems, discuss possibilities of compositional adjustments, and compare theoretical predictions with experiment. We acknowledge funding by NASA’s Aeronautics Research Mission Directorate (ARMD) via Transformational Tools and Technologies (TTT) Project.

NiCoCr↗