Abstract: An RBF adaptive equalizer based on immune algorithm is proposed for nonlinear channels with severe inter symbol interference (ISI). The equalizer is constructed with decision feedback structure, and an immune algorithm is used to determine the structure and parameters of RBF nonlinear hidden layer. The immune algorithm has global searching ability, and it improves the algorithm efficiency and overcomes the immature problem by introducing the diversity control and immune memory mechanism. Simulation results demonstrate that the proposed RBF equalizer based on immune algorithm has good performance with strong ability to restrain nonlinear distortion.