Vibration Source Signal Separation of Rotating Machinery Equipment and Robot Bearings Based on Low Rank Constraint

With the development of industrial robots and other mechanical equipment to a higher degree automation, systems have become increasingly complex. This represents huge challenge for condition monitoring. The separation vibration source signals plays an important role in monitoring fault diagnosis. key method signal is prior knowledge, such as statistical features signal, number sources, so forth. However, effective knowledge difficult obtain engineering applications. study found that low rank common feature rotating machinery signals. To address problem difficulty obtaining source, multi-low-rank constrained was proposed. Its advantages effectiveness been verified through simulations experimental tests. Compared with blind independent component analysis (BSS-ICA) ensemble empirical mode decomposition (EEMD) methods, it obtained better clustering results signal-to-signal ratio (SSR) values.