Analyze and Fault Diagnosis by Multi-scale PCA

Abstract

This paper introduces a new methodology for fault diagnosis of rotating machinery in complex industrial process. In this fault diagnosis system, multi-scale principal component analysis (MSPCA) is used. The main contribution of this paper is the use of the MSPCA technique in the fault diagnosis based on vibration analysis in rotating machinery. Their maintenance as well as their diagnosis then became an economic state. It is important to early detect the faults likely to appear in those motors and to implement a preventive maintenance.