Mechanical faults detection in induction machine using recursive PCA with weighted distance

An original method for multi-fault detection in synchronous machine is proposed in this paper. This method aims to answer two questions: how to detect a fault when only the normal functioning is known? How to differentiate two different faults from one fault with two severities? The proposed method relies on the use of a recursive Principal Components Analysis (PCA), which is updated each time a new fault is detected. The detection is based on a weighted distance criteria that takes into account the contribution of the different components. A geometrical criteria is also proposed to differentiate new faults from existing ones. The method has been successfully tested on a simulation database of motor currents with different levels of unbalance and eccentricity. It is then tested on real data from a 5.5 kW synchronous machine with three different levels of unbalance.

[1]  Walmir M. Caminhas,et al.  Fault detection in dynamic systems by a Fuzzy/Bayesian network formulation , 2014, Appl. Soft Comput..

[2]  Olivier Darnis,et al.  Statistic-based spectral indicator for bearing fault detection in permanent-magnet synchronous machines using the stator current , 2014 .

[3]  Jose A. Antonino-Daviu,et al.  Comparison of different wavelet families for broken bar detection in induction motors , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[4]  Humberto Henao,et al.  Analytical approach of the stator current frequency harmonics computation for detection of induction machine rotor faults , 2003, 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED 2003..

[5]  N. Tandon,et al.  A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings , 1999 .

[6]  Baptiste Trajin,et al.  Hilbert versus Concordia transform for three-phase machine stator current time-frequency monitoring , 2009 .

[7]  Antoine Picot,et al.  Bearing fault diagnosis based on the analysis of recursive PCA projections , 2018, 2018 IEEE International Conference on Industrial Technology (ICIT).

[8]  Hui Li,et al.  Condition Monitoring for Bearing Using Envelope Spectrum of EEMD , 2009, 2009 International Conference on Measuring Technology and Mechatronics Automation.

[9]  Miguel Delgado Prieto,et al.  Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis , 2016, IEEE Access.

[10]  Thomas W. Rauber,et al.  Heterogeneous Feature Models and Feature Selection Applied to Bearing Fault Diagnosis , 2015, IEEE Transactions on Industrial Electronics.

[11]  Elias G. Strangas,et al.  On the Accuracy of Fault Detection and Separation in Permanent Magnet Synchronous Machines Using MCSA/MVSA and LDA , 2016, IEEE Transactions on Energy Conversion.

[12]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[13]  H. Abdi,et al.  Principal component analysis , 2010 .

[14]  Gianluca Ippoliti,et al.  Electric Motor Fault Detection and Diagnosis by Kernel Density Estimation and Kullback–Leibler Divergence Based on Stator Current Measurements , 2015, IEEE Transactions on Industrial Electronics.

[15]  Giansalvo Cirrincione,et al.  Dedicated hierarchy of neural networks applied to bearings degradation assessment , 2013, 2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED).