Real-Time Anomaly Detection using Average Level-Crossing Rate

Vibration data collected from piezoelectric sensors serve as a means for detecting faults in machines that have rotating parts. The sensor output that is sampled at the Nyquist rate is stored for analysis of faults in the traditional condition monitoring system. The massive amount of data makes the analysis very difficult. Very complex procedures are adopted for anomaly detection in standard methods. The proposed system works on the analog output of the sensor and does not require conventional steps like sampling, feature extraction, classification, or computation of the spectrum. It is a simple system that performs real-time detection of anomalies in the bearing of a machine using vibration signals. Faults in the machines usually create an increase in the frequency of the vibration data. The amplitude of the signal also changes in some situations. The increase in amplitude or frequency leads to a corresponding increase in the level-crossing rate, which is a parameter indicating the rate of change of a signal. Based on the percentage increase in the average value of the level-crossing rate (ALCR), a suitable warning signal can be issued. It does not require the data from a faulty machine to set the thresholds. The proposed algorithm has been tested with standard data sets. There is a clear distinction between the ALCR values of normal and faulty machines, which has been used to release accurate indications about the fault. If the noise conditions do not vary much, the pre-processing of the input signal is not needed. The vibration signals acquired with faulty bearings have ALCR values, ranging from 3.48 times to 10.71 times the average value of ALCR obtained with normal bearing. Hence the proposed system offers bearing fault detection with100% accuracy