论文部分内容阅读
当激光混沌信号受各种噪声强度的干扰时,关于高精度重构源信号的问题,本文提出了一种基于相位空间重构混沌流信号的盲源分离算法。该算法首先对分离信号的相位空间进行时间延迟重构,然后将分离矩阵作为待优化参数,通过在相空间中构建目标函数,将盲源分离问题转换为优化问题,应用粒子群优化算法求解最优分离矩阵,然后将观测数据乘以最优分离矩阵来重构源信号。实验结果表明,该算法不仅具有快速收敛的特点,其精度明显优于各种噪声强度下现有的独立分量分析方法。
When the laser chaos signal is disturbed by various noise intensities, a blind source separation algorithm based on phase space reconstruction of chaotic signal is proposed in this paper. The algorithm firstly reconstructs the phase space of the separated signal by time delay and then takes the separation matrix as the parameter to be optimized. By constructing the objective function in the phase space, the blind source separation problem is transformed into an optimization problem, and the particle swarm optimization algorithm is used to solve the problem The matrix is then separated and the observed data is multiplied by the optimal separation matrix to reconstruct the source signal. The experimental results show that the proposed algorithm not only has the characteristics of fast convergence, but also has better accuracy than the existing independent component analysis methods under various noise intensities.