信号稀疏分解理论在轴承故障检测中的应用

将信号稀疏分解理论引入到轴承故障检测问题中,提出新的轴承故障检测方法。通过字典学习的方式可有效实现轴承正常状态振动信号稀疏表示的超完备字典。利用该字典只适用于轴承正常状态信号稀疏分解的特点,将待分析信号在该字典上展开,通过比较信号稀疏表示误差与所设定阈值的关系来判断轴承对应的状态,从而实现轴承的故障检测。实验结果表明:当误差阈值设置合理时,该方法可有效地判断出轴承是否发生故障。

Application of signal sparse decomposition theory in bearing fault detection

A new bearing fault detection method based on the signal sparse decomposition theory is developed in this paper. Firstly, a over-complete dictionary on which the bearing vibration signals in normal state can be represented sparsely is trained by dictionary learning method. According to the fact that this dictionary just can sparsely represent the signals in normal state, the bearing vibration signal in unknown state will be decomposed on this dictionary. The bearing state can be determined by comparing the representation error of the signal on the dictionary with the given error threshold, and then the bearing fault detection will be achieved. Experimental tests validate the effectiveness of the proposed method in bearing fault detection when setting an appropriate error threshold.