Limits...
A predictive machine learning approach for microstructure optimization and materials design.

Liu R, Kumar A, Chen Z, Agrawal A, Sundararaghavan V, Choudhary A - Sci Rep (2015)

Bottom Line: These challenges render traditional search-based optimization methods incompetent in terms of both searching efficiency and result optimality.A systematic framework consisting of random data generation, feature selection and classification algorithms is developed.Experiments with five design problems that involve identification of microstructures that satisfy both linear and nonlinear property constraints show that our framework outperforms traditional optimization methods with the average running time reduced by as much as 80% and with optimality that would not be achieved otherwise.

View Article: PubMed Central - PubMed

Affiliation: EECS Department, Northwestern University, Evanston IL, USA.

ABSTRACT
This paper addresses an important materials engineering question: How can one identify the complete space (or as much of it as possible) of microstructures that are theoretically predicted to yield the desired combination of properties demanded by a selected application? We present a problem involving design of magnetoelastic Fe-Ga alloy microstructure for enhanced elastic, plastic and magnetostrictive properties. While theoretical models for computing properties given the microstructure are known for this alloy, inversion of these relationships to obtain microstructures that lead to desired properties is challenging, primarily due to the high dimensionality of microstructure space, multi-objective design requirement and non-uniqueness of solutions. These challenges render traditional search-based optimization methods incompetent in terms of both searching efficiency and result optimality. In this paper, a route to address these challenges using a machine learning methodology is proposed. A systematic framework consisting of random data generation, feature selection and classification algorithms is developed. Experiments with five design problems that involve identification of microstructures that satisfy both linear and nonlinear property constraints show that our framework outperforms traditional optimization methods with the average running time reduced by as much as 80% and with optimality that would not be achieved otherwise.

No MeSH data available.


Related in: MedlinePlus

The single crystal properties for elastic modulus, magnetostrictive strains and the yield sgth obtained from our analyses are visualized on the ODF mesh in Rodrigues space.Both the surface contours and internal slices of the ODF are shown. The single crystals with maximum and minimum properties and their locations can be seen directly from these plots.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4477370&req=5

f4: The single crystal properties for elastic modulus, magnetostrictive strains and the yield sgth obtained from our analyses are visualized on the ODF mesh in Rodrigues space.Both the surface contours and internal slices of the ODF are shown. The single crystals with maximum and minimum properties and their locations can be seen directly from these plots.

Mentions: The single crystal properties for elastic modulus, magnetostrictive strains and the yield strength obtained from the above analyses can be visualized on the ODF mesh in Rodrigues space. The plots shown in Fig. 4(left) depict the surface contours with internal slices of the ODF shown alongside in Fig. 4(right). The single crystals with maximum and minimum properties and their locations can be seen directly from these plots. For example, the single crystals with maximum magnetostrictive strains are all located along the z–axis of the Rodrigues space as seen in Fig. 4(a) (right). This corresponds to the z–axis fiber in which the crystal direction of easy magnetization ([001]) is aligned along the measurement axis (sample z–axis).


A predictive machine learning approach for microstructure optimization and materials design.

Liu R, Kumar A, Chen Z, Agrawal A, Sundararaghavan V, Choudhary A - Sci Rep (2015)

The single crystal properties for elastic modulus, magnetostrictive strains and the yield sgth obtained from our analyses are visualized on the ODF mesh in Rodrigues space.Both the surface contours and internal slices of the ODF are shown. The single crystals with maximum and minimum properties and their locations can be seen directly from these plots.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4477370&req=5

f4: The single crystal properties for elastic modulus, magnetostrictive strains and the yield sgth obtained from our analyses are visualized on the ODF mesh in Rodrigues space.Both the surface contours and internal slices of the ODF are shown. The single crystals with maximum and minimum properties and their locations can be seen directly from these plots.
Mentions: The single crystal properties for elastic modulus, magnetostrictive strains and the yield strength obtained from the above analyses can be visualized on the ODF mesh in Rodrigues space. The plots shown in Fig. 4(left) depict the surface contours with internal slices of the ODF shown alongside in Fig. 4(right). The single crystals with maximum and minimum properties and their locations can be seen directly from these plots. For example, the single crystals with maximum magnetostrictive strains are all located along the z–axis of the Rodrigues space as seen in Fig. 4(a) (right). This corresponds to the z–axis fiber in which the crystal direction of easy magnetization ([001]) is aligned along the measurement axis (sample z–axis).

Bottom Line: These challenges render traditional search-based optimization methods incompetent in terms of both searching efficiency and result optimality.A systematic framework consisting of random data generation, feature selection and classification algorithms is developed.Experiments with five design problems that involve identification of microstructures that satisfy both linear and nonlinear property constraints show that our framework outperforms traditional optimization methods with the average running time reduced by as much as 80% and with optimality that would not be achieved otherwise.

View Article: PubMed Central - PubMed

Affiliation: EECS Department, Northwestern University, Evanston IL, USA.

ABSTRACT
This paper addresses an important materials engineering question: How can one identify the complete space (or as much of it as possible) of microstructures that are theoretically predicted to yield the desired combination of properties demanded by a selected application? We present a problem involving design of magnetoelastic Fe-Ga alloy microstructure for enhanced elastic, plastic and magnetostrictive properties. While theoretical models for computing properties given the microstructure are known for this alloy, inversion of these relationships to obtain microstructures that lead to desired properties is challenging, primarily due to the high dimensionality of microstructure space, multi-objective design requirement and non-uniqueness of solutions. These challenges render traditional search-based optimization methods incompetent in terms of both searching efficiency and result optimality. In this paper, a route to address these challenges using a machine learning methodology is proposed. A systematic framework consisting of random data generation, feature selection and classification algorithms is developed. Experiments with five design problems that involve identification of microstructures that satisfy both linear and nonlinear property constraints show that our framework outperforms traditional optimization methods with the average running time reduced by as much as 80% and with optimality that would not be achieved otherwise.

No MeSH data available.


Related in: MedlinePlus