The working process and fault mechanism of condensers were analyzed.Moreover

the typical fault set

symptom set and typical fault feature vectors were established.A fault diagnosis model was built on the basis of fuzzy support vector machine(SVM)method.Furthermore

specific sample calculations were carried out to demonstrate the effectness of this method.Compared with the neural network model

the SVM method is superior in terms of calculation results

generalization ability and efficiency

under the condition of small quantity samples.When a relatively small number of diagnosis samples are involved

this SVM method will provide a new approach for creating an intelligent system with highly practical value in condensers condition monitoring and fault diagnosis.