Incorporating adaptability-related knowledge into support vector machine for case-based design adaptation

Abstract

In case-based design systems, the adaptation operation based on similar cases is a difficult and complex step, and the more adaptable cases usually could make larger contribution for adaptation generation than less ones. Under this ideology, this paper addresses a new case adaptation method which uses support vector machine (SVM) incorporating adaptability-related knowledge provided by the retrieved cases, called adaptability-involving SVM (ASVM). The knowledge of adaptability includes the adaptability characteristic of old cases returned by the adaptability analysis and the guideline that the training data from adaptable case should be given higher weight to build SVM model. So the content of this work presented here consists of two parts. The first one is to explore the adaptable property of old cases by utilizing decision tree technology. The second one is to study the construction of ASVM adaptation model in terms of retrieved cases. We first employ the differences between test and retrieved cases to assemble the adaptation pattern data for ASVM model training. Then the higher adaptability coefficients are given to the training data from more adaptable cases than those from less adaptable cases. We adopt ASVM in actual power transformer design to illustrate its feasibility, and carry out comparison researches with different numbers of retrieved cases in the different data sets to validate its superiority, through comparing the adaptation error results with those provided by other classical methods. Empirical results show that ASVM is feasible and validated for case adaptation.