The Research of GA Optimization Neural Network Weights Blind Equalization Algorithm Based on Binary Coding

摘要

Two-stage optimization project was proposed by applying genetic algorithm to neural network blind equalization.At first.the initialization weight was optimized using the characteristic of genetic algorithm.which is strong global search capability.And then,optimal weight was gained in virtue of the merit of BP algorithm.which is fast local search speed.Simulation shows that.compared with traditionaI blind equalization based on BP neural network,the convergence speed of proposed algorithm is quickened.state residual error is decreased and BER is reduced.