An artificial neural network with the hidden layer consisting of wavelets was presented for the identification on target profiles of step frequency MMW radar. The good localization characteristics of wavelet functions in both time and frequency space allowed hierarchical multi-resolution learning of input-output data mapping. The mathematic frame of the neural network and error back propagation algorithm were introduced. The procedure of the identification which uses wavelet neural network was described in detail. Then the presented approach was applied to the target profile identification of step frequency MMW radar. The results indicate that the method is valuable for target profile identification.