提出了一种多迸制频移键控(M娲K)信号调制分类及解调方法，选取截获接收机输出的MFSK信

号的时频脊线作为分类特征，利用无监督聚类算法求取最佳聚类数M．利用时频脊线的Ham：小波变换

估计码元宽度，并且利用对应最佳聚类数的聚类中心确定抽判门限，通过对时频脊线抽样判决，实现了

MFSK信号的解调．理论分析和对实际信号的处理结果证明了此算法的可行性．-new algorithm is proposed for elassillcation and demodulation of MFSK signals．The ridge of time—

frequency representation of MFSK signals is analyzed．Modulation elassi_fieation is realized by using the unsupervised

clustering algorithm to determine the optimal nulnllt2r of clusters．In order to demodulate MFSK signals，the Haar

wavelet transform is used to estimate the code—width and the centers of optimal clusters are used to determine

thresholds．Theoretical analysis and practical signal processing results justify the robusticity and the efficiency of the

new classification and demodulation Mgorithm．