A transformation system for interactive reformulation of design optimization strategies

2010

AIEDAM

An artificial intelligence (AI) algorithm to automate symbolic design reformulation is an enduring challenge in design automation. Existing research shows that design tools either require high levels of knowledge engineering or large databases of training cases. To address these limitations, we present a singular value decomposition (SVD) and unsupervised clustering-based method that performs design reformulation by acquiring semantic knowledge from the syntax of design representations. The development of the method was analogically inspired by applications of SVD in statistical natural language processing and digital image processing. We demonstrate our method on an analytically formulated hydraulic cylinder design problem and an aeroengine design problem formulated using a nonanalytic design structure matrix form. Our results show that the method automates various design reformulation tasks on problems of varying sizes from different design domains, stated in analytic and nonanalytic representational forms. The behavior of the method presents observations that cannot be explained by pure symbolic AI approaches, including uncovering patterns of implicit knowledge that are not readily encoded as logical rules, and automating tasks that require the associative transformation of sets of inputs to experiences. As an explanation, we relate the structure and performance of our algorithm with findings in cognitive neuroscience, and present a set of theoretical postulates addressing an alternate perspective on how symbols may interact with each other in experiences to reify semantic knowledge in design representations.

Section: Problem Reformulation Tasks: Hydraulic Cylinder Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning symbolic formulations in design: Syntax, semantics, and knowledge reification

2010

AIEDAM

“…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]. Nath and Gero developed a machine learning tool that acquires strategies as mappings between past design contexts and design decisions that led to useful results [2].…”

Section: Related Prior Workmentioning

confidence: 99%

“…Each engineering and design domain tends to develop "favorites" and "best practices" -preferred formulations and preferred algorithms for solving these models. Over time, the discipline, as a whole, discovers what works well and what does not for a particular family of problems [1] [11]. What works is usually based on many factors -the design-based and mathematical characteristics of the problem being modeled, pragmatic engineering and design considerations, or, very often, a designers' developed understanding of a formulation or algorithm developing into a preferred choice.…”

Section: Cognitive Hypothesis As Basis Of the Learning And Inference mentioning

confidence: 99%

Learning Symbolic Formulations in Design Optimization

Design Computing and Cognition '08

2008

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.

“…We applied the method to this problem, varying the number of dimensions from 2 to 4 (k =2, 3,4) in order to study the variations in the number of correct cases returned and the number of missed cases not returned by the method.…”

Section: Figure 13: the Aircraft Concept Sizing Problemmentioning

confidence: 99%

Design Optimization Problem Reformulation Using Singular Value Decomposition

Journal of Mechanical Design

2009

This paper presents a design optimization problem reformulation method based on Singular Value Decomposition (SVD), dimensionality reduction, and unsupervised clustering. The method calculates linear approximations of the associative patterns of symbol co-occurrences in a design problem representation to infer induced interaction/coupling strengths between variables and constraints. Unsupervised clustering of these approximations is used to identify useful reformulations. These two components of the method automate a range of reformulation tasks that have traditionally required different solution algorithms. We explain the method using an analytic model-based decomposition problem, and apply the method to an analytic hydraulic cylinder design problem as an example of heuristic design "case" identification, and to non-analytic problems expressed in FDT and DSM forms as examples of design decomposition. An Aircraft Concept Sizing (ACS) problem is used to empirically validate the method's performance. The results show that the method can be used to infer multiple well-formed reformulations starting from a single problem representation in a knowledge-lean and training lean manner.