基于TSVD-SCN的光纤入侵信号识别算法研究

采用随机配置网络(SCN,Stochastic configurat ion network)对光纤振动信号进行识别,常由于光 纤预警系统的背景噪声问题使得网络的隐含层输出接近奇异,直接影响了SCN对光纤数据的 识别准确率。 因此本文提出了一种基于截断奇异值分解(Truncated singular value decomposition,TS VD)的SCN 方法(TSVD-SCN) 对光纤入侵信号进行识别。TSVD-SCN通过对网络的隐含层输出进行SVD分解并设置阈值去 除其中较小的 奇异值,以减少隐含层输出矩阵的条件数,提升网络识别率。本文利用占空比,平均幅差函 数,FFT求能 量占比的方法进行特征提取,采用基于TSVD-SCN算法对不同入侵振动特征矢量进行分类识 别。实验证明, 本文所提算法模型精度比SCN的模型精度更高,可以准确识别光纤入侵信号类型,对SCN网 络在实际应用中对分类精度的提高有着重要意义。

A recognition algorithm of optical fiber intrusion signals based on TSVD-SCN neural network

Because of the background noise problem of optical fiber early warning system,the hidden layer output of the network is close to singularity,and the recognition accurac y is low when Stochastic configuration Network (SCN) is used to identify the optical fiber vib ration signal.Therefore,a SCN method (TSVD-SCN) based on the Truncated singular value decomposition (TSVD-SCN) is proposed in this paper to identify the optical fiber intrusion si gnals.TSVD-SCN performs SVD decomposition on the hidden layer output of the network and sets th resholds to remove the smaller singular value,reducing the condition number of the output matrix o f the hidden layer, and improving the network recognition rate.This paper utilizes the function of d uty cycle,average magnitude difference function and the frequency domain energy ratio are used to extract the different intrusion features of multiplex signal,respectively.The classificatio n of the feature vectors for different intrusion vibrations is realized by using the TSVD-SCN al gorithm. Experimental results show that the proposed algorithm has higher accuracy than t hat of SCN model, and can accurately identify the type of optical fiber intrusion signal.It is si gnificant to improve the classification accuracy of SCN network in frequency domain.