Multilayer Blind Equalization Algorithm Of Neural Network For QAM Signal

With the development of communication technology, the communication environment has become more and more complex, the linear channel environment no longer exists, and the neural network blind equalization algorithm has good effect on improving the communication quality. So the neural network blind equilibrium algorithm has also attracted a lot of attention. This paper focuses on the blind equalization algorithm of multilayer neural networks based on QAM(Quadrature Amplitude Modulation, a modulation method that performs amplitude modulation on two orthogonal carriers) signals. The iteration step factor with fixed parameters has slightly limitations on the convergence speed and MSE(Mean Square Error, is the average of the sum of the squares of the deviations of the data from the true value, that is, the average of the sums of the squares of the errors) in communication. In order to solve this problem, this paper proposes to transform the fixed-parameter iteration step factor into a variable iteration step factor that is associated with the MSE. In order to solve this problem, we take to change the iteration step factor of fixed parameters into a varying iteration step factor which is related to the mean square error, think of it as a variable parameter, so that the iteration step factor and the mean square error show a positive correlation, which can improve the convergence speed and the final convergence accuracy in the convergence process. Through algorithm analysis and computer simulation, it is shown that the convergence speed and convergence accuracy of the improved algorithm are improved.