为了解决支持向量机(SVM)必须采用标识样本进行训练和支持向量选择困难两个弊端,提出了一种基于模糊C均值(FCM)和支持向量机的半监督支持向量机分类算法S3VM)。为了验证模型的有效性,将该算法应用于供电企业安全性评价。与BP神经网络的分类结果比较表明,该模型在样本较少的条件下,具有较高的分类正确率和很好的推广能力。 In order to solve the drawbacks of support vector machine (SVM), such as training of identification samples and difficulty of selection of support vectors, a semi-supervised SVM classification algorithm based on fuzzy C-means (FCM) and support vector machine (SVM) is proposed. In order to verify the validity of the model, the algorithm is applied to the safety assessment of power supply enterprises. Compared with the BP neural network classification results show that the model in the sample less conditions, with a high classification accuracy and good promotion ability.