中文摘要：

提出了用Volterra频域核作为故障特征对弱非线性定常动态网络进行故障诊断的方法，利用计算方法求出网络响应在各种常见故障状态下的Volterra级数解的各阶频域核，并输入给BP神经网络，利用BPNN的分类功能建立故障字典，用对实测的故障网络的各阶频域核进行测试样本分类来实现故障诊断。给出了各阶频域核的统一递推算式，讨论了Volterra频域核的测量，并给出了故障诊断实例。

英文摘要：

A fault location method for nonlinear dynamic network by taking the cores of Volterra series in frequency domain as the fault characters is proposed. The frequency cores of Volterra series in frequency domain are calculated for the response of usual fault states and fed into BPNN as the fault features. By using the function of classification of BPNN, the fault dictionary is built. The fault location is completed by BPNN classifying the Volterra frequency cores tested from the nonlinear network. The unified recursive computing formulae for frequency cores and the core testing method are presented. At last, an example of this method is given.