This paper proposes a methodology of maintaining Case Based Reasoning (CBR) systems by using fuzzy decision tree induction - a machine learning technique. The methodology is mainly based on the idea that a large case library can be transformed to a small case library together with a group of adaptation rules, which are generated by fuzzy decision trees. Firstly, an approach to learning feature weights automatically is used to evaluate the importance of different features in a given case-base. Secondly, clustering of cases will be carried out to identify different concepts in the case-base using the acquired feature knowledge. Thirdly, adaptation rules will be mined for each concept using fuzzy decision trees. Finally, a selection strategy based on the concepts of ε-coverage and ε-reachability is used to select representative cases. The effectiveness of the method is demonstrated experimentally using two sets of testing data.