论文部分内容阅读
采用粒子群算法与自然梯度法相结合进行非线性混叠信号盲分离。用高阶奇数多项式拟合非线性混合函数,建立非线性信号盲分离模型。同时根据粒子群算法的特点,作了改进,引入了“迁徙操作”和局部深度搜索方法。对多项式的参数用粒子群算法来求估计,然后用自然梯度法对线性去混合矩阵进行迭代。仿真结果表明,粒子群算法可以快速、有效地求得非线性混叠信号盲分离的优化解。
Particle swarm optimization algorithm is combined with natural gradient method to separate blind aliasing signals. A high-order odd polynomial is used to fit a nonlinear mixing function to establish a blind separation model of nonlinear signals. At the same time, according to the characteristics of Particle Swarm Optimization, some improvements have been made, and the “migration operation” and the local depth search method have been introduced. The parameters of the polynomial are estimated using a particle swarm optimization algorithm, and then the linear de-mixing matrix is iterated by the natural gradient method. The simulation results show that the PSO algorithm can obtain the optimal solution of blind separation of nonlinear aliasing signals quickly and effectively.