基于盲源分离的旋转机械干扰消除技术研究

实际工厂环境中，用于状态监测与故障诊断的信号检测传感器，其所采集的机器信号(振动或声音)中，不可避免地混杂有来自于相邻设备以及周围环境的干扰，这对于机器健康状态的准确监测是很不利的。这里研究利用盲源分离技术分离(去除)这些无用的外来干扰，以提高故障诊断的准确性。盲源分离是一个很独特的盲信号分析与处理工具，在机械设备监测与诊断领域有着很好的应用前景。仿真实验以及现实世界的声源信号分离实验结果，证实了盲源分离方法在机械设备干扰去除方面的有效性。

Study on the Technique for Interference Removal Based on Blind Sources Separation

In an actual factory, there exist inevitably a lot of interference from neighbor machines and noises from surroundings in measurements by the sensors used in condition monitoring and fault diagnosis, which is disadvantageous for accurately diagnostic implementation of a machine. Blind sources separation, a special tool for analyzing and processing signals blindly, which is promising in condition monitoring and fault diagnosis of machinery, is used in flaking off these useless interference. The validity of BSS, in interference removal, is verfied by some simulations and the result of separating mechanically acoustical signal from real world.