CBR algorithm provides a better knowledgetransfer and explanation than rule-based inference. Itsolves new problems by adapting solutions that wereused to solve old problems. Based on CBR algorithm,a methodology applied in modular fixture design andfocus on workpiece locating is proposed in this study.A similar solution can be retrieved from pastexperiences. Evaluation is applied for this retrievedcase by checking degrees of freedom (DOF) todetermine whether it is satisfactory for a new problemand some components would be replaced if it is not.According to this methodology, a computer-aidedmodular fixture design system can be established infuture. In the system, three sub-bases would beincluded. Data base stores many function structuresthat are assembled by modular components to completesome functions. Knowledge base stores thequalitative knowledge that is required in consideringthe location of the workpieces. Case base storesprevious successful design cases that can be applied todevelop a new solution. MOP-based memorytechnique is applied to organize these complex data,knowledge and case base. A demonstrated example isfinally provided in this study to illustrate how thismethodology works.This methodology principally focuses oninference process of case evaluation and modification.This is the most important and difficult issue on CBR algorithm. In the evaluation of workpiece locating,geometry recognition play a critical role. Featurerecognition is beyond this study and then too detaildiscussion about that would not be given here. Forthis reason, the methodology can handle simplegeometry workpiece only presently.