使用模糊C均值聚类（FCM）的方法对状态进行分类，其优点首先是可以根据实际情况自动确定聚类中心，减少人工干涉的因素，其次，对状态特征参数不是进行硬分类，而是通过隶属度的表征方式对其聚类，更加符合现实状态类别之间不具备明显界限的实际问题。(The use of fuzzy C mean clustering (FCM) method to classify the state, its advantage is first can automatically determine the cluster center according to the actual situation, to reduce the interference of artificial factors, secondly, the state parameters are not hard classification, but through the characterization of Party membership of the cluster, more practical problems have not obvious the boundaries between reality state categories.)