Determining an approximate finite element mesh density using neural network techniques

Dyck, D.N.; Lowther, D.A.; McFee, S.

doi:10.1109/20.124047

Cited by 40 publications

(13 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, rather than just learning about geometry, a neural network can be trained to understand the effects of materials and excitations, as well as geometry, on the structure of a magnetic field, i.e., it can be trained to predict the field structure [3] in much the same way as a design engineer might. This, then, can provide much more information to a mesh generator.…”

Section: Knowledge Representation Paradigms and Computationmentioning

confidence: 99%

Accelerating the computer-based simulation and design of electromagnetic devices by applying knowledge

Lowther

2002

IEEE Trans. Magn.

Self Cite

View full text Add to dashboard Cite

The paper provides a survey of existing knowledge representation paradigms in the context of electromagnetic device design. The use of a variety of knowledge-based paradigms in decreasing the time taken to achieve a desired maximum error in the solution, as well as in the optimization of a design, is discussed, and a typical example of the improvements in one process (adaptive solution in finite elements) is given.

show abstract

Section: Knowledge Representation Paradigms and Computationmentioning

confidence: 99%

Accelerating the computer-based simulation and design of electromagnetic devices by applying knowledge

Lowther

2002

IEEE Trans. Magn.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to address the problem of triangulating geometries which present similarities, the use of backpropagation artificial neural networks (ANNs) has been proposed for predicting the mesh density vector of certain electromagnetic field problems [3]- [5]. The derived mesh density vector may then be used to create the mesh, which maintains the mesh density properties of the prediction.…”

Section: B Recent Developments In Mesh Generation Using Annmentioning

confidence: 99%

A finite-element mesh generator based on growing neural networks

Triantafyllidis

Labridis

2002

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

A mesh generator for the production of high-quality finite-element meshes is being proposed. The mesh generator uses an artificial neural network, which grows during the training process in order to adapt itself to a prespecified probability distribution. The initial mesh is a constrained Delaunay triangulation of the domain to be triangulated. Two new algorithms to accelerate the location of the best matching unit are introduced. The mesh generator has been found able to produce meshes of high quality in a number of classic cases examined and is highly suited for problems where the mesh density vector can be calculated in advance.

show abstract

“…The use of arti"cial neural networks (ANNs) has been proposed in the last years for predicting the mesh density of speci"c electromagnetic problems [3,4]. For this purpose a prototype mesh is generated for a magnetic device, which includes all the features expected to be found in future devices to be meshed.…”

Section: Introductionmentioning

confidence: 99%

An automatic mesh generator for handling small features in open boundary power transmission line problems using artificial neural networks

Triantafyllidis

Labridis

2000

Commun. Numer. Meth. Engng.

View full text Add to dashboard Cite

An arti"cial neural network (ANN) has been trained to automatically predict the mesh density vector of open-boundary faulted power transmission line problems under the presence of small features, such as conductors. In order to produce the data for the training database of the ANN a technique for recursively subdividing the solving area is proposed. A Delaunay-based mesh generator is used to produce the "nal mesh. Several test cases show that the proposed automatic mesh generator signi"cantly reduces solving time.

show abstract

Determining an approximate finite element mesh density using neural network techniques

Cited by 40 publications

References 1 publication

Accelerating the computer-based simulation and design of electromagnetic devices by applying knowledge

Accelerating the computer-based simulation and design of electromagnetic devices by applying knowledge

A finite-element mesh generator based on growing neural networks

An automatic mesh generator for handling small features in open boundary power transmission line problems using artificial neural networks

Contact Info

Product

Resources

About