改进自适应共振稀疏分解轴承故障诊断方法

Improved adaptive resonance sparse decomposition bearing fault diagnosis method

针对早期滚动轴承微弱故障在强噪声工业环境影响下其故障信息提取困难这一点,提出一种改进自适应共振稀疏分析分解故障诊断方法。首先采用变分模态分解方法对原始信号降噪处理;根据相关峭度准则对包含故障信息较多的分解信号重构;再对重构信号进行GTO优化算法的共振稀疏分解,将包含故障信息的低共振分量Hilbert包络谱分析,提取其故障频率信息。通过实验和仿真结果证明了该故障诊断方法的有效性和准确性。

Aiming at the difficulty of extracting fault information from weak faults of early rolling bearings under the strong noise industrial environment,an improved adaptive resonance sparse analysis decomposition fault diagnosis method is proposed.Firstly,the variational mode decomposition method is used to reduce the noise of the original signal.Then,according to the relevant steepness criterion,the decomposition signal containing more fault information is reconstructed.The resonance sparse decomposition of the re-constructed signal based on the artificial gorilla troop optimization algorithm,and the low resonance component Hilbert envelope spec-trum containing fault information was analyzed to extract the fault frequency information.Experimental and simulation results prove the effectiveness and accuracy of the fault diagnosis method.