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.