Condition evaluation of mechatronic equipment is always a hot research point in fault diagnosis fields, and it can provide a decision-making for condition based maintenance. In this paper, a novel intelligent condition evaluation method based on SVM and GA is proposed, and it combines the feature selection method and condition classification method to evaluate the operational condition of mechatronic equipment. In order to validate the intelligent condition evaluation method proposed in this paper, the rolling element bearing fault dataset is introduced. Experiment results show that the optimal feature subset can be selected with very good classification accuracy rate and the dimension of the optimal feature subset significantly decreases.