Approximate entropy and its preliminary applications in the analysis of mechanical vibration signals

Approximate Entropy (ApEn) is a newly introduced statistic that can be: used to quantify the complexity (or irregularity) of time series. Successful applications have been achieved in the biological data analysis, such as heart rate, blood pressure and ECG signals. The purpose of this work is to evaluate the approximate entropy as a descriptor and/or classifier of vibration signals. The results show that the ApEn is able to quantify the complexity of signals, distinguish different running conditions, and provide an effective technology for condition monitoring and fault diagnosis of mechanical equipment.