Learning prototype-selection rules for case-based iterative design

Abstract

The first step f o r most case-based design systems as to select an initial prototype f r o m a database of previous designs. T h e retrieved prototype is then modified t o tailor it t o the given goals. For any particular design goal the selection of a starting point f o r the design process can have a dramatic effect both on the quality of the eventual design and on the overall design time. W e present a technique for automatically constructing effective prototype-selection rules. Our technique applies a standard inductive-learning algorithm, C4.5, t o a set of training data describing which particular prototype would have been the best choice f o r each goal encountered in a previous design session. W e have tested our technique in the domain of racing-yacht-hull design, comparing our inductively learned selection rules t o several competing prototypeselection methods.Our results show that the inductive prototype-selection method leads to better final designs when the design process is guided by a noisy evaluation function, and that the inductively learned rules will often be more efficient than competing methods. 1: IntroductionMany automated design systems begin by retrieving an initial prototype from a library of previous designs, using the given design goal as an index to guide the retrieval process [14]. The retrieved prototype is then modified by a set of design modification operators to tailor the selected design to the given goals. In many cases the quality of competing designs can be assessed using domain-specific evaluation functions, and in such cases the design-modification process is often This research has benefited from numerous discussions with members of the Rutgers CAP project. We thank Andrew Gelsey for helping with the cross-validation code, John Keane for helping with RUVPP, and Andrew Gelsey and Tim Weinrich for comments on a previous draft of this paper. This research was supported under ARPA-funded NASA grant NAG 2-645.accomplished by an optimization method such as hillclimbing search [12, 21. Such a design system can be seen as a case-based reasoning system [4], in which the prototype-selection method is the indezing process, and the optimization method is the adaptation process.In the context of such case-based design systems, the choice of an initial prototype can affect both the quality of the final design and the computational cost of obtaining that design, for three reasons. First, prototype selection may impact quality when the prototypes lie in disjoint search spaces. In particular, if the system's design modification operators cannot convert any prototype into any other prototype, the choice of initial prototype will restrict the set of possible designs that can be obtained by any search process. A poor choice of initial prototype may therefore lead to a suboptimal final design. Second, prototype selection may impact quality when the design process is guided by a nonlinear evaluation function with unknown global properties. Since there is no known method that is guaranteed to ...

Intelligent gradient-based search of incompletely defined design spaces

“…We have found that using rule-based gradients results in good optimization performance in several other design domains. These domains include the design of racing yachts (Ellman et al, 1993;Schwabacher et al, 1994Schwabacher et al, , 1996, the design of exhaust nozzles for supersonic jets (Gelsey et al, 1996a), the design of inlets for hypersonic jets (Gelsey et al, 1995;Shukla et al, 1996Shukla et al, , 1997, and the design of inlets for supersonic missiles (Zha et al, 1996(Zha et al, , 1997. All of these domains use simulators that are more expensive than our airframe simulator.…”

Multilevel Simulation and Numerical Optimization of Complex Engineering Designs

“…A great deal of work has been done in the area of numerical optimization algorithms Gill et al 1981, Vanderplaats 1984, Peressini et al 1988, Mor e and Wright 1993, Papalambros and Wilde 1988 , though not much has been published about the particular di culties of attempting to optimize functions de ned by large real-world" numerical simulators. A number of research e orts have combined AI techniques with numerical optimization , Schwabacher et al 1994, Tong et al 1992, Powell 1990, Bouchard et al 1988, Bouchard 1992, Agogino and Almgren 1987, Williams and Cagan 1994, Hoeltzel and Chieng 1987, Cerbone 1992 have not addressed the issue of performing optimization at multiple levels.…”

Inductive learning for engineering design optimization

“…We w ere surprised by h o w poorly the other methods performed. We did further experiments also presented in Schwabacher et al, 1994 which suggest that C4.5 was able to outperform the other methods because it is better able to deal with noise in the simulator.…”

“…Table 1 compares the performance of C4.5 with that of several alternative methods. Schwabacher et al, 1994 provides more details of the experiments and explanations of the competing methods. C4.5 outperformed the other methods both on error rate the percentage of the testing goals for which i t c hose the right prototype and course-time increase the loss in design quality resulting from incorrect choices.…”

“…A particular course-time goal thus requires the speci cation of two e n vironment parameters: 1 the race course, represented as a set of distance; heading pairs; and 2 the wind speed, represented as a scalar number, in knots. Our design system represents a yacht geometry by a set of design parameters, and evaluates course time using a Velocity-Prediction Program" called RUVPP, " Schwabacher et al, 1994 a somewhat simpli ed version of AHVPP" from AeroHydro, Inc., which i s a marketed product used in yacht design Letcher, 1991 . Y acht designs are modi ed by operators that manipulate design parameters.…”