通过将自适应小波神经网络 (AWNN)中的小波基函数直接替换为 Gauss径向基函数 ,提出了一种适于对目标一维距离像信号直接进行分类的径向基函数神经网络(RBFNN)。对用于信号分类的 RBFNN网络结构的确定、RBFNN的训练以及最终判决规则的确定等问题 ,进行了深入的讨论。对 6个目标不同信噪比下的分类结果表明 ,提出的 RBFNN对距离像信号具有很强的分类能力 ,对于开发更加实用化的目标识别算法显示了很大的潜力 A radial basis function neural network (RBFNN) suitable for directly classifying target one-dimensional distance image signals is proposed by directly replacing the wavelet basis functions in the adaptive wavelet neural network (AWNN) with Gauss radial basis functions. . The structure of RBFNN for signal classification, the determination of RBFNN training and the determination of final judgment rules are discussed in depth. The classification results under different signal-to-noise ratios of six targets show that the proposed RBFNN has strong classification ability for range-like signals and shows great potential for developing a more practical target recognition algorithm