Induction motor fault detection and diagnosis using a current state space pattern recognition

In the last few decades the continuous monitoring of complex dynamic systems has become an increasingly important issue across diverse engineering areas. This paper presents a pattern recognition based system that uses visual-based efficient invariants features for continuous monitoring of induction motors. The procedures presented here are based on the image identification of the 3-D current state space patterns that allow the identification of distinct fault types and, furthermore, their corresponding severity. This automatic fault detection system deals with time-variant electric currents and is based on the identification of three-phase stator currents specified patterns. Several simulation and experimental results are also presented in order to verify the effectiveness of the proposed methodology.

Research highlights
► Induction motor stator current analysis converted into pattern recognition problem.
► Induction motor stator current vector transformed into a binary image contour.
► Induction motor fault condition denoted by a specific pattern.
► Induction motor fault severity index established from obtained pattern.