The Study On The Fuzzy Neural Network Blind Equalization Algorithm

In digital communication systems, the inter-symbol interference (ISI) caused by non-ideal character of channel is the main factor which affects communication quality. In order to reduce the ISI, a equalizer has to be used in the receiver. The conventional equalizer resorts to a training sequence to overcome inter-symbol interference. But this method would influence communication efficiency. As a self-adaptive equalization technology, blind equalization utilizes the prior information of transmitted signals to equalize the channel character without referring to a training sequence to maintain normal work.The major contribution of this paper is summarized as follow:1. This paper formulizes the foundational principles anddevelopment of the CMA, the blind equalization algorithm based on neural network and analyses their advantages and disadvantages.2. In order to overcome the tradeoff between convergence rate and maladjustment, this paper proposes a new algorithm. In the algorithm, fuzzy neural network is constructed as a controller and the information is distilled from MSE to control the step-size of CMA. The simulation result shows that CMA has better convergence performance after the application of neural network controller.3. This paper proposes another algorithm in which fuzzy neural network is structured as a class implement, which classifies the output signal in the space of output signal. The simulation result shows that the convergence performance of the new algorithm is better than that of the blind equalization algorithm based on feed-forward neural network.