过程信号的前馈-反馈型自适应盲分离算法

利用神经网络的自学习能力实现信号的盲分离已被证明是实现信号分离的一种有效方法，不同的神经网络模型对分离算法的效能将产生极大的影响。针对化工生产过程的复杂性和在线监测控制的要求，在其他学者研究的基础上，基于前馈－反馈型神经网络模型，提出了一种自适应盲分离算法用于过程信号的分离。计算机仿真实验的结果表明了算法的有效性。

Feed-forward and Feedback Self-adaptive Blind Signal Separation of Process Signal

Make use of the self learning ability of neural network to realize blind signal separation has been proved as a efficient method for signal separation. Different neural network model can produce distinct algorithm efficiency. For the need of the real time process control, based on the feed forward and feedback neural network model, this paper develops a self adaptive blind source separation algorithm and applies it to the separation of process signal. The performance of the proposed algorithm is illustrated by computer simulation experiments.