Approximate Entropy as a diagnostic tool for machine health monitoring

This paper presents a new approach to machine health monitoring based on the Approximate Entropy (ApEn), which is a statistical measure that quantifies the regularity of a time series, such as vibration signals measured from an electrical motor or a rolling bearing. As the working condition of a machine system deteriorates due to the initiation and/or progression of structural defects, the number of frequency components contained in the vibration signal will increase, resulting in a decrease in its regularity and an increase in its corresponding ApEn value. After introducing the theoretical framework, numerical simulation of an analytic signal is presented that establishes a quantitative relationship between the severity of signal degradation and the ApEn values. The results of the simulation are then verified experimentally, through vibration measurement on a realistic bearing test bed. The study has shown that ApEn can effectively characterise the severity of structural defect, with good computational efficiency and high robustness.