Abstract: Based on the favorable classification performance of support vector data description(SVDD)，aiming at the problem of fault samples' acquisition in rotating machinery fault diagnosis, this paper proposed a fuzzy support vector data description classifier based on positive and negative samples,which can be used to deal with the outlier sensitivity problem in traditional multi-class classification problems. hhis method considers the effect of negative samples to classification results,as well as the positive samples in the traditional SVDD algorithm. Experimental results show that the proposed method can reduce the effect of outliers and yield higher classification rate than other existing methods.

Key words: Support vector data description, Weighting, Classifier, Support vector machine