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

Microstructural model validation.(a) Comparison of textures (Euler angle space, ϕ2 = 45°) predicted by our model with experiments on BCC iron reported in21. (b) Comparison of results of current model with published results in20. The plot shows tensile test curves of as-cast polycrystalline Galfenol (alloy composition Fe82.17Ga16.83 with 0.5–1% Boron) at room temperature.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

f3: Microstructural model validation.(a) Comparison of textures (Euler angle space, ϕ2 = 45°) predicted by our model with experiments on BCC iron reported in21. (b) Comparison of results of current model with published results in20. The plot shows tensile test curves of as-cast polycrystalline Galfenol (alloy composition Fe82.17Ga16.83 with 0.5–1% Boron) at room temperature.

Mentions: The crystal plasticity model described in Method section and also in10 is used to calculate the yield strength at all nodal points in the fundamental region. The model adequately captures the macroscopic tensile mode stress-strain response at room temperature reported in20 as shown in Fig. 3(b). To further validate the microstructural model, we compared the crystallographic textures seen in BCC iron rolling processes and textures predicted by our model. Fig. 3(a) shows that the model captures both α and γ texture that arise from rolling of BCC metals (experimental result from21). The strength (Y(r)) at orientation r is found as the offset z–stress resulting from an applied z–strain of 0.2% under the following velocity gradient18:


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)

Microstructural model validation.(a) Comparison of textures (Euler angle space, ϕ2 = 45°) predicted by our model with experiments on BCC iron reported in21. (b) Comparison of results of current model with published results in20. The plot shows tensile test curves of as-cast polycrystalline Galfenol (alloy composition Fe82.17Ga16.83 with 0.5–1% Boron) at room temperature.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

f3: Microstructural model validation.(a) Comparison of textures (Euler angle space, ϕ2 = 45°) predicted by our model with experiments on BCC iron reported in21. (b) Comparison of results of current model with published results in20. The plot shows tensile test curves of as-cast polycrystalline Galfenol (alloy composition Fe82.17Ga16.83 with 0.5–1% Boron) at room temperature.
Mentions: The crystal plasticity model described in Method section and also in10 is used to calculate the yield strength at all nodal points in the fundamental region. The model adequately captures the macroscopic tensile mode stress-strain response at room temperature reported in20 as shown in Fig. 3(b). To further validate the microstructural model, we compared the crystallographic textures seen in BCC iron rolling processes and textures predicted by our model. Fig. 3(a) shows that the model captures both α and γ texture that arise from rolling of BCC metals (experimental result from21). The strength (Y(r)) at orientation r is found as the offset z–stress resulting from an applied z–strain of 0.2% under the following velocity gradient18:

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