建立未确知RBF神经网络.特点是:综合了未确知系统与神经网络的优点,充分利用已知样本所提供的先验信息,给出了期望输出隶属度的计算方法,网络输出合理且具有良好的可解释性.将未确知RBF神经网络应用于故障诊断领域,取得了很好的效果. The characteristics of unascertained RBF neural network are established, which combines the advantages of unascertained system and neural network, makes full use of prior information provided by known samples, and gives the calculation method of expected output membership degree. The network output is reasonable Which has good interpretability.Using the unascertained RBF neural network in the field of fault diagnosis has achieved good results.