In order to separate mechanical vibration sources form sensor signals rapidly and effectively, a novel method was proposed, which was based on maximization of negentropy for semi-blind sources separation of mechanical vibrations. The reference signals that carry some information of sources were constructed. The mean square error between reference signals and separated sources was incorporated into contrast function as the constraints. The interested mechanical vibration source was obtained by solving the constrained optimization problem. The proposed method was compared with the conventional BSS method, and the experiment results showed that the proposed method is very effective. It is possible to apply the new method to vibration signals analysis and mechanical fault diagnosis．
［1］ 李舜酩. 机械振动信号盲源分离的时域方法 ［J］. 应用力学学报, 2005, 22(04)：579-585． LI Shunming. Blind source separation of mechanical vibration signal in time domain ［J］.Chinese Journal of Applied Mechanics, 2005,22(04):579-585． ［2］ 叶红仙, 杨世锡, 杨将新. 多振源卷积混合的时域盲源分离算法 ［J］. 机械工程学报, 2009, 45(1)：189-194． YE Hongxian, YANG Shixi, YANG Jiangxin. Temporal blind source separation algorithm for convolution mixtures with multi sources ［J］. Journal of Mechanical Engineering, 2009, 45(1): 189-194． ［3］ 孙晖, 朱善安. 调制故障源信号盲分离的经验模态分解法 ［J］. 浙江大学学报：工学版, 2006, 40(2) ：258-261． SUN Hui, ZHUN Shanan. Empirical mode decomposition for blind separation of modulation fault source signals ［J］. Journal of Zhejiang University：Engineering Science, 2006, 40(2): 258-261． ［4］ YPMA A. Learning methods for machine vibration analysis and health monitoring ［D］. Delft: Delft University of Technology, 2001. ［5］ LIU X, RANDALL R B, ANTONI J. Blind separation of internal combustion engine vibration signals by a deflation method ［J］. Mechanical Systems and Signal Processing, 2008, 22(5): 1082-1091． ［6］ GELLE G, COLAS M, SERVIERE C. Blind source separation: a tool for rotating machine monitoring by vibrations analysis ［J］. Journal of Sound and Vibration, 2001, 248(5): 865-885． ［7］ 胥永刚, 张发启, 何正嘉. 独立分量分析及其在故障诊断中的应用［J］. 振动与冲击, 2004, 23(2)：104-108． XU Yonggang, ZHANG Faqi, HE Zhengjia. Independent component analysis and its applications to fault diagnosis ［J］. Journal of Vibration and Shock,2004, 23(2):104-108． ［8］ ANTONI J. Blind separation of vibration components: principles and demonstrations ［J］. Mechanical Systems and Signal Processing, 2005, 19(6): 1166-1180． ［9］ WEI L, RAJAPAKSE J C. Approach and applications of constrained ICA ［J］. IEEE Transactions on Neural Networks, 2005, 16(1): 203-212． ［10］ LU W, RAJAPAKSE J C. Ica with reference ［J］. Neurocomputing, 2006, 69(16/18): 2244-2257． ［11］ HYVARINEN A, KARHUNEN J, OJA E. Independent component analysis ［M］. New York: Wiley, 2001. ［12］ HYVARINEN A. Fast and robust fixedpoint algorithms for independent component analysis ［J］. IEEE Transactions on Neural Networks, 1999, 10(3): 626-634．
