Learning to Set Up Numerical Optimizations of Engineering Designs

Schwabacher, Mark; Ellman, Thomas; Hirsh, Haym

doi:10.1007/978-1-4757-4911-3_4

Cited by 10 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the system notes that a designer is either potentially in error or the system identifies a potential alternative solution, this is brought to the designer's attention. Scwabacher et al (1998) use a machine learning approach to support a designer in setting up an optimiser, along with predicting design goals. On a similar note, Ong and Keane (2002) provide a support method that advises a designer on suitable optimisers to use for a given design problem.…”

Section: Design Model Structurementioning

confidence: 99%

Challenges to Bayesian decision support using morphological matrices for design: empirical evidence

Matthews

2010

Res Eng Design

View full text Add to dashboard Cite

Section: Design Model Structurementioning

confidence: 99%

Challenges to Bayesian decision support using morphological matrices for design: empirical evidence

Matthews

2010

Res Eng Design

View full text Add to dashboard Cite

“…But, in these, the knowledge is not persistent beyond the current design experience, and no new knowledge may be created that can influence future design tasks. Schwabacher et al developed a decision-tree inductive learning based optimization tool, where characteristics of the designed product and the optimization process are learnt [10]. Ellman et al developed a tool allowing the user to formulate, test, reformulate and visualize a tree of optimization strategies constructed by the user that may be applied onto test problems in order to identify relevant optimization strategies for particular design domains [11].…”

Section: Related Prior Workmentioning

confidence: 99%

Learning Symbolic Formulations in Design Optimization

Sarkar

Dong

Gero

2008

Design Computing and Cognition '08

View full text Add to dashboard Cite

This paper presents a learning and inference mechanism for unsupervised learning of semantic concepts from purely syntactical examples of design optimization formulation data. Symbolic design formulation is a tough problem from computational and cognitive perspectives, requiring domain and mathematical expertise. By conceptualizing the learning problem as a statistical pattern extraction problem, the algorithm uses previous design experiences to learn design concepts. It then extracts this learnt knowledge for use with new problems. The algorithm is knowledge-lean, needing only the mathematical syntax of the problem as input, and generalizes quickly over a very small training data set. We demonstrate and evaluate the method on a class of hydraulic cylinder design problems.

show abstract

“…Inductive learning has been found useful to improve the speed and quality of this loop by reusing knowledge of previous designs or iterations. Murdoch and Ball (1996) have used a Kohonen feature map to cluster bridge designs in an evaluation space, and Schwabacher et al (1998) have used a symbolic learning algorithm, C4.5 (Quinlan, 1993), to select appropriate starting prototypes and search space formulations for a parametric optimization of yacht hull and aircraft designs. Both allow a rapid reevaluation of previous work that improves the optimization when run again to new specifications or fitness criteria.…”

Section: Related Researchmentioning

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

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

Learning to Set Up Numerical Optimizations of Engineering Designs

Cited by 10 publications

References 9 publications

Challenges to Bayesian decision support using morphological matrices for design: empirical evidence

Challenges to Bayesian decision support using morphological matrices for design: empirical evidence

Learning Symbolic Formulations in Design Optimization

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

Contact Info

Product

Resources

About