Fault Diagnosis of Rotating Machinery Using the Mahalanobis Distance

摘要

A diagnostic system for the predictive maintenance of production facilities is highlyrecommended due to the need for higher reliability and accuracy to detect incipient faults. Thispaper presents the results of a study on the application of vibration signals to diagnose faults inrotating machinery using the Mahalanobis Distance. The root mean square (RMS), crest factorand kurtosis are statistical parameters of the Mahalanobis distance and were used, along withspectrum analysis, to diagnose these faults.