A knowledge base for finite element mesh design

Dolšak, Bojan; Jezernik, Anton; Bratko, Ivan

doi:10.1016/0954-1810(94)90003-5

Cited by 10 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A literal such as neighbor (a3,X) is called nondeterminate because the "input" argument a3 does not necessarily determine the "output" argument X (if a3 has several neigh-bors, X can be any one of them). In spite of this, a "determinate" version of background knowledge description also was used in our earlier experiments (Dol Ysak & Muggleton, 1992;Dol Ysak et al, 1994) with the ILP program GOLEM (Muggleton & Feng, 1990), which is restricted to determinate literals only. CLAUDIEN allows nondeterminate literals.…”

Section: Topological Relations Between the Edgesmentioning

confidence: 99%

Knowledge base for finite-element mesh design learned by inductive logic programming

Dolšak

Bratko

Jezernik

1998

AIEDAM

Self Cite

View full text Add to dashboard Cite

This paper addresses an important application of machine learning (ML) in design. One of the major bottlenecks in the process of engineering analysis by using the finite-element method—a design of the finite-element mesh—was a subject of improvement. Defining an appropriate geometric mesh model that ensures low approximation errors and avoids unnecessary computational overhead is a very difficult and time-consuming task based mainly on the user's experience. A knowledge base for finite-element mesh design has been constructed using the ML techniques. Ten mesh models have been used as a source of training examples. The mesh dataset was probably the first real-world relational dataset and became one of the most widely used training set for experimenting with inductive logic programming (ILP) systems. After several experiments with different ML systems in the last few years, the ILP system CLAUDIEN was chosen to construct the rules for determining the appropriate mesh resolution values. The ILP has been found to be an effective approach to the problem of mesh design. An evaluation of the resulting knowledge base shows that the mesh design patterns are captured well by the induced rules and represent a solid basis for practical application. The aim of this paper is not only to present the real-life ML application to design, but also to describe and discuss a relation of the work being done to the topic of this special issue: the proposed “dimensions” of ML in design.

show abstract

Section: Topological Relations Between the Edgesmentioning

confidence: 99%

Knowledge base for finite-element mesh design learned by inductive logic programming

Dolšak

Bratko

Jezernik

1998

AIEDAM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Here we describe the application of ILP to this problem following Dol~ak et al [12,13], also presented in [6]. An earlier experiment is described in [14].…”

Section: Finite-element Mesh Designmentioning

confidence: 99%

“…There is no known general method that would enable automatic determination of optimal, or reasonably good meshes. ILP techniques have been successfully applied by Dolgak et al [12,14,13] towards the automation of mesh design.…”

Section: Introductionmentioning

confidence: 99%

Applications of inductive logic programming

Bratko¹,

King²

1994

SIGART Bull.

Self Cite

View full text Add to dashboard Cite

Some applications of Inductive Logic Programming (ILP) are presented. Those applications are chosen that specifically benefit from relationaidescriptions generated by ILP programs, and from ILP's ability to accommodate background knowledge. Applications included are: drug design, predicting the secondary structure of proteins, and design of finite-element meshes. Some other applications are briefly described. The practical advantages and disadvantages of ILP learning are discussed.

show abstract

“…Each paradigm has its advantages and limitations and so any future FEA package/design tool that wishes to achieve the ideals of a perfect FE implementation [10] should try to take into account the feasibility of incorporating such methods based on their limitations rather than their advantages [32]. [15], [16], [22], [24], [28], [33], [39], [40], [49], [50], [54], [[57], [59], [77], [82]} Quicker convergence of solutions based on "learnt" Mesh patterns { [1], [3], [15], [16], [18], [38], [42], [58], [71] A cognitive mapping for the FEM is now presented, which entails detailing the nature of how each AI technique has been and could be applied to FEMG in particular. This is done so as to develop a framework for incorporating AI within the FEA process (see Section IIIB).…”

Section: A Classification Of Ai Methods Applied To Finite Elementmentioning

confidence: 99%

“…Software implementations of the method, can sometimes be needlessly verbose and technical, so much so that even experts find difficulty in the modelling of relatively straightforward problems ( [10], [12], [30], [52], [68]). Using previous knowledge and interrelationships between model parameters, to overcome such problems does not mean that such a technique is always adaptable to new design scenarios ( [15], [16], [27], [46], [51]). …”

Section: Introductionmentioning

confidence: 99%

The management of intelligence-assisted finite element analysis technology

Sharif

Innovation in Technology Management. The Key to Global Leadership. PICMET '97

View full text Add to dashboard Cite

-Artificial Intelligence (AI) approaches to Finite Element Analysis (FEA), have had tentative degrees of success over the last few years and some authors have argued that effective FEA can help in the manufacture reliability and safety aspects of engineered artefacts. The author of this paper reviews how such AI techniques have been applied and in this light, the author then uses a Fuzzy Cognitive Mapping (FCM), to develop a framework for the management of intelligence-assisted FEA.

show abstract

A knowledge base for finite element mesh design

Cited by 10 publications

References 2 publications

Knowledge base for finite-element mesh design learned by inductive logic programming

Knowledge base for finite-element mesh design learned by inductive logic programming

Applications of inductive logic programming

The management of intelligence-assisted finite element analysis technology

Contact Info

Product

Resources

About