Condition monitoring strategy based on an optimized selection of high-dimensional set of hybrid features to diagnose and detect multiple and combined faults in an induction motor

•Diagnosis methodology to detect multiple and combined faults in an induction motor.•Estimation of a potential high-dimensional set of hybrid features.•PCA-GA optimization allows highlight the most effective fault-related features.•The detection of faults that simultaneous occur is successfully overcome.•High-performance and reliable results allowed by multi-domain analysis techniques.