论文部分内容阅读
基于复杂非线性系统相空间重构理论,提出了混沌背景中微弱信号检测的神经网络方法,利用神经网络强大的学习和非线性处理能力,建立了混沌背景噪声的一步预测模型,从预测误差中检测淹没在混沌背景噪声中的微弱目标信号(包括周期信号和瞬态信号),研究了混沌背景中存在白噪声时该方法的检测能力,指出了目标信号为瞬态信号和周期信号时检测原理的异同点,最后以Lorenz系统作为混沌背景噪声进行了仿真实验,实验表明该方法能有效地将混沌背景中极其微弱的信号检测出来.
Based on the theory of phase space reconstruction in complex nonlinear systems, a neural network method of weak signal detection in chaotic background is proposed. By using the powerful learning and nonlinear processing capabilities of neural networks, a one-step prediction model of chaotic background noise is established. From the prediction error The weak target signal (including periodic signal and transient signal) submerged in chaotic background noise is detected. The detection ability of the proposed method is investigated when there is white noise in the chaotic background. The detection principle of the target signal is transient signal and periodic signal Finally, the Lorenz system is used as the chaotic background noise to simulate the experiment. Experiments show that this method can effectively detect the extremely weak signals in the chaotic background.