An evolutionary approach to microstructure optimisation of stereolithographic models

Mahdavi, Siavash Haroun; Hanna, Sean

doi:10.1109/cec.2003.1299647

Cited by 6 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These were measured (Fig. 5;Haroun Mahdavi & Hanna, 2003) and factored into the optimization of examples presented to the machine for learning by modifying the stiffness of each element as calculated in the finite element model by a function of its angle.…”

Section: Manufacturingmentioning

confidence: 99%

“…The present work adopts a similar approach. Previous work by Haroun Mahdavi and Hanna (2003) has also used GA for topology, but it has been found that GD is more efficient for shape optimization. This method, extended here, uses a single topology previously found by a nested GA/GD process for each unit of the overall structure, but is concerned specifically with the process of geometry optimization.…”

Section: S Hannamentioning

confidence: 99%

See 1 more Smart Citation

Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Hanna

2007

AIEDAM

View full text Add to dashboard Cite

While structural optimisation is usually handled by iterative methods requiring repeated samples of a physics-based model, this process can be computationally demanding. Given a set of previously optimised structures of the same topology, this paper uses inductive learning to replace this optimisation process entirely by deriving a function that directly maps any given load to an optimal geometry. A support vector machine is trained to determine the optimal geometry of individual modules of a space frame structure given a specified load condition. Structures produced by learning are compared against those found by a standard gradient descent optimisation, both as individual modules and then as a composite structure. The primary motivation for this is speed, and results show the process is highly efficient for cases in which similar optimisations must be performed repeatedly. The function learned by the algorithm can approximate the result of optimisation very closely after sufficient training, and has also been found effective at generalising the underlying optima to produce structures that perform better than those found by standard iterative methods.

show abstract

Section: Manufacturingmentioning

confidence: 99%

Section: S Hannamentioning

confidence: 99%

Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Hanna

2007

AIEDAM

View full text Add to dashboard Cite

show abstract

“…Such algorithms are very good at finding solutions to problems that have bumpy or discontinuous search spaces, and so are ideal for searching through a population of topologies, which are defined discretely. The details of the GA ensure that the solutions evolved are as unrestricted as possible while also allowing a simplification of structure (please see Haroun Mahdavi and Hanna 2003 for further details).…”

Section: The Genetic Algorithmmentioning

confidence: 99%

Proceedings of the 24th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) and the 2004 Conference of the AIA Technology in Architectural Practice Knowledge Community

2004

ACADIA Proceedings

View full text Add to dashboard Cite

“…Therefore, most 3D CAD software companies adopt approximation schemes, such as homogenization or beam elementbased approaches, in their lattice design tools. For example, Autodesk Within is a popular commercial software for lattice structure design that uses the beam/shell element-based method [58]. Their website can be found in [3].…”

Section: Introductionmentioning

confidence: 99%

Component-wise reduced order model lattice-type structure design

McBane,

Choi

2020

Preprint

View full text Add to dashboard Cite

Lattice-type structures can provide a combination of stiffness with light weight that is desirable in a variety of applications. Design optimization of these structures must rely on approximations of the governing physics to render solution of a mathematical model feasible. In this paper, we propose a topology optimization (TO) formulation that approximates the governing physics using component-wise reduced order modeling as introduced in [46] and [33], which can reduce solution time by multiple orders of magnitude over a full-order finite element model while providing a relative error in the solution of <1%. In addition, the offline training data set from such component-wise models is reusable, allowing its application to many design problems for only the cost of a single offline training phase, and the component-wise method is nearly embarrassingly parallel. We also show how the parameterization chosen in our optimization allows a simplification of the component-wise reduced order model (CWROM) not noted in previous literature, for further speedup of the optimization process. The sensitivity of the compliance with respect to the particular parameterization is derived solely in the component level. In numerical examples, we demonstrate a 1000x speedup over a full-order FEM model with relative error of <1% and show minimum compliance designs for two different cantilever beam examples, one smaller and one larger. Finally, error bounds for displacement field, compliance, and compliance sensitivity of the CWROM are derived.

show abstract

An evolutionary approach to microstructure optimisation of stereolithographic models

Cited by 6 publications

References 3 publications

Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Proceedings of the 24th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) and the 2004 Conference of the AIA Technology in Architectural Practice Knowledge Community

Component-wise reduced order model lattice-type structure design

Contact Info

Product

Resources

About